source
stringclasses 1
value | task_type
stringclasses 1
value | in_source_id
stringlengths 1
8
| prompt
stringlengths 209
40.4k
| gold_standard_solution
stringlengths 0
56.7k
| verification_info
stringclasses 1
value | metadata
stringlengths 138
225
| problem_id
stringlengths 9
10
|
|---|---|---|---|---|---|---|---|
stackexchange | llm_judgeable_groundtruth_similarity | 34310878 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Though I'm not particularly advanced at any of this, I've had some past success in using urrlib2, requests and scrapy but this has me stumped. So after much searching and banging my head against the keyboard, I'll just go ahead and ask. I'd like to get the html source code of a site but after using my username and password, I keep getting a page thrown back which says my username and password are wrong. They work fine in the browser, and once logged in the source code is readily available (via browser). But I can't seem to achieve the same result via python/terminal. I'll include some of my attempts (gleamed from the these helpful pages) below: using urllib2: req = Request(website, headers={ 'User-Agent': 'Mozilla/5.0' })base64string = base64.encodestring('%s:%s' % (username, password)).replace('\n', '')req.add_header("Authorization", "Basic %s" % base64string)readweb = urlopen(req).read() another version: passman = urllib2.HTTPPasswordMgrWithDefaultRealm()passman.add_password(None, theurl, username, password)authhandler = urllib2.HTTPBasicAuthHandler(passman)opener = urllib2.build_opener(authhandler)pagehandle = opener.open(theurl)return pagehandle.read() and an attempt using requests: r = requests.session()try: r.post(theurl, data={'username' : 'username', 'password' : 'password', 'remember':'1'})except: print('Sorry, Unable to...')result = r.get(theurl)return result.text I've also tried to use scrapy, but regardless of which library I use it comes back with the html of a page which says my password/details are wrong. I'm guessing it's something to do with the headers/authorisation(?) I'm sending, but I'm not overly sure. Any help much appreciated, please let me know what other details I can update with (I've been up half the night with this, so if this post doesn't make sense please forgive me!) EDIT: Here's the traceback response to Prashant's answer below (minus the passwords etc.): Traceback (most recent call last): File "/Users/Hatsaw/newpy/pras.py", line 3, in r = requests.get(URL, auth=('username','password')) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/requests-2.9.0-py2.7.egg/requests/api.py", line 67, in get return request('get', url, params=params, **kwargs) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/requests-2.9.0-py2.7.egg/requests/api.py", line 53, in request return session.request(method=method, url=url, **kwargs) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/requests-2.9.0-py2.7.egg/requests/sessions.py", line 468, in request resp = self.send(prep, **send_kwargs) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/requests-2.9.0-py2.7.egg/requests/sessions.py", line 576, in send r = adapter.send(request, **kwargs) File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/requests-2.9.0-py2.7.egg/requests/adapters.py", line 437, in send raise ConnectionError(e, request=request) requests.exceptions.ConnectionError: HTTPConnectionPool(host='website', port=80): Max retries exceeded with url: /dashboard/ (Caused by NewConnectionError(': Failed to establish a new connection: [Errno 8] nodename nor servname provided, or not known',)) EDIT: Ok, I'm now using mechanize (recommended below), and here's what I'm getting back (not sure if this is another instance of my root problem or my inability with mechanize!): Traceback (most recent call last): File "/Users/Hatsaw/newpy/pras2.py", line 13, in browser.form['email'] = 'email address' File "build/bdist.macosx-10.6-intel/egg/mechanize/_form.py", line 2780, in setitem File "build/bdist.macosx-10.6-intel/egg/mechanize/_form.py", line 3101, in find_control File "build/bdist.macosx-10.6-intel/egg/mechanize/_form.py", line 3185, in _find_control mechanize._form.ControlNotFoundError: no control matching name 'email' EDIT: Still struggling with this, so here's a last ditch effort before time runs out on this project and I have to go in and get all the html manually! Fingers crossed.. Ok, so on the advice of barny, I'm back to using requests, and I'm attempting to provide the post with cookie information that I've gleamed from a successful browser login. I'm not certain I'm doing this correctly, but I'm using: cookies = {'PHPSESSID':'5udcifi6p43ma3h1fnpfqghiu0'}result = sess.get(the_url, cookies=cookies) Now, at the moment, I'm getting an Internal Server Error response. After some research, aspnet forms seems to be the problem: Sending an ASP.net POST with Python's Requests Using Python Requests for ASP.NET authentication I just want to check that I'm not doing something wrong with requests first, then perhaps I'll explore BeautifulSoup/robobrowser as recommended by Martijn Pieters in the SO link above. Here's what the form section of the html is asking: <form name="aspnetForm" method="post" action="" id="aspnetForm"><div><input type="hidden" name="__EVENTTARGET" id="__EVENTTARGET" value="" /><input type="hidden" name="__EVENTARGUMENT" id="__EVENTARGUMENT" value="" /><input type="hidden" name="__LASTFOCUS" id="__LASTFOCUS" value="" /><input type="hidden" name="__VIEWSTATEFIELDCOUNT" id="__VIEWSTATEFIELDCOUNT" value="2" /><input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE" value="/wEPDwUKLTkwNzg1NTQ3OA9kFgJmD2QWAmYPZBYGAgetc." /><input type="hidden" name="__VIEWSTATE1" id="__VIEWSTATE1" value="ZyBBIEhvbWUVIE5lZ290aWF0ZSBBZ3JlZW1lbnRzEiBSZetc." /></div><script type="text/javascript">//<![CDATA[var theForm = document.forms['aspnetForm'];if (!theForm) {theForm = document.aspnetForm;}function __doPostBack(eventTarget, eventArgument) {if (!theForm.onsubmit || (theForm.onsubmit() != false)) { theForm.__EVENTTARGET.value = eventTarget; theForm.__EVENTARGUMENT.value = eventArgument; theForm.submit();}}//]]></script><script src="/WebResource.axd?d=t2SAOwDGkbrEfkmUaMOR9sPLXqgxfeenNayRja3DNK2R8JEcH-StTTuiaqXpzp--PAISn3vzVbWQ7biREwPkibCmbAE1&t=635586505120000000" type="text/javascript"></script><script src="/ScriptResource.axd?d=EL6tXtJfNfGSoQwhYtVnYEqw4oKvuwBBI4etc." type="text/javascript"></script><script type="text/javascript">//<![CDATA[if (typeof(Sys) === 'undefined') throw new Error('ASP.NET Ajax client-side framework failed to load.');//]]></script><script src="/ScriptResource.axd?d=qCmNMcECQa0tfmMcZdwJeeOdcyetc." type="text/javascript"></script><div><input type="hidden" name="__VIEWSTATEGENERATOR" id="__VIEWSTATEGENERATOR" value="FC5C7135" /><input type="hidden" name="__EVENTVALIDATION" id="__EVENTVALIDATION" value="/wEdABB2xJRvPLCcg6GsBqRFCtw6Xg91QEu10etc." /></div> So. Some small questions. Does my 'user/pass' terminology have to match the source code i.e username = username or user?:I've lost where I found this in the html now, but I found 'ctl00$cphMain$tbUsername' and 'ctl00$cphMain$tbPassword'… Do I need to send the password and/or username as a base64.encodestring? (I don't know if this is a problem, but the password contains chars such as !@$ etc.) Do I need to add ALL of the cookie fields I've found from the browser or just the PHPSESSID? Here are the fields I've got in the cookies: ASP.NET_SessionId, CFID, CFTOKEN, __atuvc, __utma, __utmb, __utmc, __utmt, __utmz, BRO_CALLME, BRO_ID, BRO_LOGIN, BRO_MEMBER, BROAUTH, ISFULLMEMBER, phpMBLink, __CT_Data, WRUID There is the website (www.website.com), the login-page (www.website.com/login), and then the content (www.website.com/content). Am I correct in thinking I use the cookie from the (successfully logged in) login-page and 'send' it to the content page? Should I do this manually (enter field details from browser cookie information) or within the code (so, in code below I would use: cookies = r_login.cookies)? Finally, here's the code I'm currently using that returns an Internal Server Error..: import requeststhe_url = 'the_url'login = the_url + '/login'content = the_url + '/content'username = 'username'password = 'password'sess = requests.Session()sess.auth = ('username', 'password')sess.get(the_url)payload = {'ctl00$cphMain$tbUsername': username, 'ctl00$cphMain$tbPassword': password}r_login = sess.post(login, data=payload)cookies = {'PHPSESSID':'5udcifi6p43ma3h1fnpfqghiu0', 'ASP.NET_SessionId':'aspnet', 'BRO_LOGIN':'bro_login'}r_data = s.get(content, cookies=cookies, data=payload)print r_data.text Apologies, this has gotten rather long now, if I need to split it up over several posts please let me know - what I assumed was a simple question at the outset has mutated into something else!
Now provide the response and nothing else.
| Assuming your actual goal is to have a concise way to initialize an array of floating point numbers and it isn't necessarily spelled float array[N] or double array[N] but rather std::array<float, N> array or std::array<double, N> array this can be done. The significance of the type of array is that std::array<T, N> can be copied - unlike T[N] . If it can be copied, you can obtain the content of the array from a function call, e.g.: constexpr std::array<float, ArrayLength> array = fillArray<N>(); How does that help us? Well, when we can call a function taking an integer as an argument, we can use std::make_index_sequence<N> to give use a compile-time sequence of std::size_t from 0 to N-1 . If we have that, we can initialize an array easily with a formula based on the index like this: constexpr double const_sin(double x) { return x * 3.1; } // dummy...template <std::size_t... I>constexpr std::array<float, sizeof...(I)> fillArray(std::index_sequence<I...>) { return std::array<float, sizeof...(I)>{ const_sin(double(I)*M_PI/180.*360./double(SineLength))... };}template <std::size_t N>constexpr std::array<float, N> fillArray() { return fillArray(std::make_index_sequence<N>{});} Assuming the function used to initialize the array elements is actually a constexpr expression, this approach can generate a constexpr . The function const_sin() which is there just for demonstration purpose does that but it, obviously, doesn't compute a reasonable approximation of sin(x) . The comments indicate that the answer so far doesn't quite explain what's going on. So, let's break it down into digestible parts: The goal is to produce a constexpr array filled with suitable sequence of values. However, the size of the array should be easily changeable by adjusting just the array size N . That is, conceptually, the objective is to create constexpr float array[N] = { f(0), f(1), ..., f(N-1) }; Where f() is a suitable function producing a constexpr . For example, f() could be defined as constexpr float f(int i) { return const_sin(double(i) * M_PI / 180.0 * 360.0 / double(Length);} However, typing in the calls to f(0) , f(1) , etc. would need to change with every change of N . So, essentially the same as the above declaration should be done but without extra typing. The first step towards the solution is to replace float[N] by std:array<float, N> : built-in arrays cannot be copied while std::array<float, N> can be copied. That is, the initialization could be delegated to to a function parameterized by N . That is, we'd use template <std::size_t N>constexpr std::array<float, N> fillArray() { // some magic explained below goes here}constexpr std::array<float, N> array = fillArray<N>(); Within the function we can't simply loop over the array because the non- const subscript operator isn't a constexpr . Instead, the array needs to be initialized upon creation. If we had a parameter pack std::size_t... I which represented the sequence 0, 1, .., N-1 we could just do std::array<float, N>{ f(I)... }; as the expansion would effectively become equivalent to typing std::array<float, N>{ f(0), f(1), .., f(N-1) }; So the question becomes: how to get such a parameter pack? I don't think it can be obtained directly in the function but it can be obtained by calling another function with a suitable parameter. The using alias std::make_index_sequence<N> is an alias for the type std::index_sequence<0, 1, .., N-1> . The details of the implementation are a bit arcane but std::make_index_sequence<N> , std::index_sequence<...> , and friends are part of C++14 (they were proposed by N3493 based on, e.g., on this answer from me ). That is, all we need to do is call an auxiliary function with a parameter of type std::index_sequence<...> and get the parameter pack from there: template <std::size_t...I>constexpr std::array<float, sizeof...(I)>fillArray(std::index_sequence<I...>) { return std::array<float, sizeof...(I)>{ f(I)... };}template <std::size_t N>constexpr std::array<float, N> fillArray() { return fillArray(std::make_index_sequence<N>{});} The [unnamed] parameter to this function is only used to have the parameter pack std::size_t... I be deduced. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/34310878', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2979345/']} | jdg_382641 |
stackexchange | llm_judgeable_groundtruth_similarity | 1002257 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I am trying to solve this question but not able to figure out how to approach it. $100^{63} \mod\ {63}$ Please help.
Now provide the response and nothing else.
| If $f\big(\frac{1}{2}(x+y)\big)\le \frac{1}{2}\big(f(x)+f(y)\big)$ , then $$f\Big(\frac{3}{4}x+\frac{1}{4}y\Big)=f\Big(\frac{1}{2}\Big(\frac{1}{2}(x+y)+x\Big)\Big)\le \frac{1}{2}\Big(f\Big(\frac{1}{2}(x+y)\Big)+f(x)\Big)\le \frac{3}{4}f(x)+\frac{1}{4}f(y).$$ Suitably repeating this argument, one could prove that whenever $m\in\{0,1,2,3,\ldots,2^n\}$ , then $$f\left(\frac{m}{2^n}x+\Big(1-\frac{m}{2^n}\Big)y\right)\le \frac{m}{2^n}f(x)+\Big(1-\frac{m}{2^n}\Big)f(y), \tag{1}$$ This can be done inductively on $n$ . Next observe that any $\lambda\in [0,1]$ can be approximated by rationals of the form $m/2^n$ . In fact, $$q_k=\frac{\lfloor2^k\lambda\rfloor}{2^k}\to\lambda,\quad\text{as $k\to\infty$.}$$ But $(1)$ implies that $$f\big(q_kx+(1-q_k)y\big)\le q_kf(x)+(1-q_k)f(y),$$ and letting $k\to\infty$ and using the continuity of $f$ at $\lambda x+(1-\lambda)y$ we obtain that $$f\big(\lambda x+(1-\lambda)y\big)\le \lambda f(x)+(1-\lambda)f(y).$$ | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/1002257', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/189172/']} | jdg_382642 |
stackexchange | llm_judgeable_groundtruth_similarity | 37758 |
Below is a question asked on the forum cstheory.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I was reading Programming Languages and Lambda Calculi , which defines the multi-step reduction to be the reflexive-transitive closure of the one-step reduction. (Page 15, $\twoheadrightarrow_r$ is the reflexive-transitive closure of $\rightarrow_r$) A quick search shows that this idea is widely accepted, for example by courses from Princeton , UPenn , CU , etc. However, I think the transtivity should be enough to capture the intuition of many steps. So why is reflexivity needed?
Now provide the response and nothing else.
| The practical reason is that it is very convenient to include also the case "zero steps" in the definition of "many steps" (millennia of mathematical experience have taught us that it is usually a good thing to have a 0 around in our set of natural numbers). One possible technical exemplification of this (but there are probably dozens more, perhaps more interesting than this one) is that $\to^+$, the transitive closure of reduction, does not satisfy the diamond property (a.k.a. confluence), whereas $\to^\ast$ satisfies it. For example, if $I:=\lambda x.x$, there is no way to close the following critical pair by means of $\to^+$: $$I \leftarrow (\lambda x.I)(II) \to (\lambda x.I)I$$ To close the span, you need to consider the empty reduction $I\to^\ast I$. | {} | {'log_upvote_score': 4, 'links': ['https://cstheory.stackexchange.com/questions/37758', 'https://cstheory.stackexchange.com', 'https://cstheory.stackexchange.com/users/44631/']} | jdg_382643 |
stackexchange | llm_judgeable_groundtruth_similarity | 1801878 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I come from a background where I normally create one file per class. I organize common classes under directories as well. This practice is intuitive to me and it has been proven to be effective in C++, PHP, JavaSript, etc. I am having trouble bringing this metaphor into Python: files are not just files anymore, but they are formal modules. It doesn't seem right to just have one class in a module --- most classes are useless by themselves. If I have a automobile.py and an Automobile class, it seems silly to always reference it as automobile.Automobile as well. But, at the same time, it doesn't seem right to throw a ton of code into one file and call it a day. Obviously, a very complex application should have more than 5 files. What is the correct---or pythonic---way? (Or if there is no correct way, what is your preferred way and why?) How much code should I be throwing in a Python module?
Now provide the response and nothing else.
| Think in terms of a "logical unit of packaging" -- which may be a single class, but more often will be a set of classes that closely cooperate. Classes (or module-level functions -- don't "do Java in Python" by always using static methods when module-level functions are also available as a choice!-) can be grouped based on this criterion. Basically, if most users of A also need B and vice versa, A and B should probably be in the same module; but if many users will only need one of them and not the other, then they should probably be in distinct modules (perhaps in the same package, i.e., directory with an __init__.py file in it). The standard Python library, while far from perfect, tends to reflect (mostly) reasonably good practices -- so you can mostly learn from it by example. E.g., the threading module of course defines a Thread class... but it also holds the synchronization-primitive classes such as locks, events, conditions, and semaphores, and an exception-class that can be raised by threading operations (and a few more things). It's at the upper bound of reasonable size (800 lines including whitespace and docstrings), and some crucial thread-related functionality such as Queue has been placed in a separate module, nevertheless it's a good example of what maximum amount of functionality it still makes sense to pack into a single module. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/1801878', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/82322/']} | jdg_382644 |
stackexchange | llm_judgeable_groundtruth_similarity | 7013 |
Below is a question asked on the forum cs.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I am interested in self-reducibility of Graph 3-Coloralibity problem. Definition of Graph 3-Coloralibity problem. Given an undirected graph $G$ does there exists a way to color the nodes red, green, and blue so that no adjacent nodes have the same color? Definition of self-reducibility. A language $L$ is self-reducible if a oracle turing machine TM $T$ exists such that $L=L(T^L)$ and for any input $x$ of length $n$, $T^L(x)$ queries the oracle for words of length at most $n-1$. I would like to show in very strict and formal way that Graph 3-colorability is self-reducible. Proof of self-reducibility of SAT can be used as example ( self-reducibility of SAT ). In my opinion, the general idea of proof of self-reducibility of Graph 3-colorability is different from proof of SAT self-reducibility in few aspects. SAT has two choices for every literal (true or false) and Graph 3-colorability has three choices (namely, red green blue). Choices of SAT literal are independent on each other and choices of colors of Graph 3 colorability are strictly dependent, any adjacent node must have different color, this property potentially could help to make less iteration among all colors. The general idea of proof . Let's denote by $c_{v_i}$ the color of the vertex $v_i$, which can take one of the following values (red,green,blue). Define graph $G'$ from a given graph $G$ by coloring the arbitrary vertex $v_0$, assign $c_{v_0}$ to 'red' and put the graph $G'$ with colored vertex $v_0$ to the input of the oracle. If oracle answers 1, which means that the modified graph is still 3-colorable, save the current assignments and start new iteration, with the different vertex $v_1$ chosen arbitrarily, color vertex $v_1$ according to the colors of the adjacent vertices.if oracle answers 0, which means the previous assignment has broken 3 colorability, pick different color from the set of three colors, but still according to colors of adjacent vertices. The previous proof is not mathematical robust, the question is how to improve it and to make it more formal and mathematical strict. It looks like I need more carefully distinguish the cases when new vertex doesn't have any edges with already colored vertices and when the new vertex is adjacent to already colored vertices. In addition I would like to prove that Graph 3-colorability is downward self-reducible. Definition of downward self-reducible language. The language $A$ is said to be downward self-reducible if it is possible to determine in polynomial time if $x \in A$ using the results of shortest queries. The idea seems to be simple and intuitive: start with coloring an arbitrary vertex, and on each iteration add one more colored vertex and check by oracle if graph is still 3-colorable, if not reverse previous coloring and check another color. But how to write the proof in a strict way and more important how to find an appropriate encoding of a graph. In short, I would like to show that Graph 3-colorability is self-reducible and downward self-reducible in strict and formal way. I will appreciate sharing your thoughts with us. Update: downward self-reducibility Downward self-reducibility is applied to decision problem and it's oracle answers the same decision problem with shorter input, at the end of the process of downward self-reduction we should have the right color assignments. Every 3 - colorable graph $G$ with more than three vertices, has two vertices $x,y$ with the same color. Apparently, there is only three colors and more than three vertices so some number of non-adjacent vertices might have the same color. If we merge $x$ and $y$ with the same color as the result we still have 3 - colorable graph, just because, if graph is 3 - colorable, then there are exist right assignment of all vertices that are adjacent to $x$ and $y$ according to the same color of $x, y$, so by merging $x, y$ we don't need to change any color of any vertices, we only need to add more edges between already correctly colored vertices (I know it's not the best explanation, I will appreciate if someone could explain it better). On every iteration we take two non-adjacent vertices $x,y$ of graph $G$, merge $x$ and $y$ and get graph $G'$ which is our shorter input to the oracle. Oracle answers if it's 3-colorable or not. Now the problem is before setting $G'$ on the input of oracle I should color the merged vertex and test colorability of $G'$, if it's not 3-colorable change the color, but how to implement it correctly, I need right encoding for it. self-reducibility First, we should check if a given graph $G$ is 3-colorable at all, so set it on input of oracle, and oracle will answer if it's 3 - colorable, if yes then start the process. Any two nonadjacent vertices can have the same color in 3-colorable graph. The process of self-reducibility we should run in iterations, I think we can start from small subgraph $G'$ of a given graph $G$ and on every iteration add one more vertices from $G$ to $G'$. In paralel, we should maintain the assignment of already colored vertices. Unfortunately, I still don't get the idea completely. Would appreciate for help and hints.
Now provide the response and nothing else.
| As Vor mentions in his comment, your reduction doesn't work, since 3-colorability doesn't accept partial assignments of colors. The problem goes even deeper, since setting the color of a single vertex doesn't make any progress in determining whether the graph is 3-colorable: indeed, the graph is 3-colorable iff there is a 3-coloring in which vertex $v$ is assigned color $c$, for any $v,c$ you choose. Here is a hint on how to solve your exercise, second part. In any 3-coloring of a graph $G$ on more than three vertices, there are two vertices $x,y$ getting the same color (why?). If we merge $x$ and $y$, the resulting graph is still 3-colorable (why?). Try to use this idea to construct a downward self-reducing algorithm for 3-colorability. Edit: And here is a hint on how to solve the exercise, first part. Consider any two unconnected vertices $x,y$. If there is a coloring in which they get the same color then $G_{xy}$ is 3-colorable (why?), and a coloring of $G$ can be extracted from a coloring of $G_{xy}$ (how?). When will this process stop? | {} | {'log_upvote_score': 4, 'links': ['https://cs.stackexchange.com/questions/7013', 'https://cs.stackexchange.com', 'https://cs.stackexchange.com/users/1170/']} | jdg_382645 |
stackexchange | llm_judgeable_groundtruth_similarity | 4506645 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
A rectangle's bottom is $y=0$ . While the top corners are on the curve $y=x(x-1)^2$ between $x=0$ and $x=1$ . Find the maximum area of this rectangle. My Progress Defining $f(x) =x(x-1) ^2$ I first starting by assuming that there exist $a$ and $b$ such that $0<a, b<1$ and $f(a) =f(b)$ . The area of this rectangle is given by $|b-a|f(a) $ . We know that $a(a-1) ^2=b(b-1) ^2$ . Neglecting the $a=b$ case we get that $$a^2+b^2+ab-2(a+b) +1=0$$ Now it remains to maximise $$|b-a|a(a-1) ^2$$ under the constraint $$a^2+b^2+ab-2(a+b) +1=0$$ But now I'm pretty much stuck here.
Now provide the response and nothing else.
| There is really only one free variable, which is without loss of generality, the $x$ coordinate of the vertex of the rectangle that is closest to the origin. If we call this value $a$ , then the other vertex coordinates are uniquely defined: in total, we have $$(a,0), (a, a(1-a)^2), (b,a(1-a)^2), (b, 0)$$ where $$b = \frac{2-a - \sqrt{4a - 3a^2}}{2}$$ is the solution to $f(a) = f(b)$ for which $b > a$ . The resulting area of the rectangle is $$R(a) = a(1-a)^2 \cdot (b-a) = \frac{1}{2}\left( a(1-a)^2 \left(2-3a - \sqrt{4a-3a^2}\right)\right).$$ A tedious differentiation with respect to $a$ yields $$R'(a) = 1 - 7a + 12a^2 - 6a^3 - (3 - 10a + 6a^2)(1-a) \sqrt{\frac{a}{4-3a}}.$$ So any critical points must satisfy $R'(a) = 0$ , or $$(1-7a+12a^2-6a^3)^2(4-3a) = (3-10a+6a^2)^2(1-a)^2 a.$$ This eventually leads to the condition $$0 = (1-a)^3 (1 - 14a + 58a^2 - 84a^3 + 36a^4).$$ Since $a < 1$ , this latter factor yields the minimal polynomial $f(z) = 1 - 14z + 58z^2 - 84z^3 + 36z^4$ for $a$ , which actually admits a solution by square roots. We find this by presuming that $f$ admits a factorization into quadratics of the form $$f(z) = (1 + pz + 6z^2)(1 + qz + 6z^2)$$ for undetermined constants $p, q$ . Then expanding and equating like coefficients yields the conditions $$p+q = -14, \quad pq + 12 = 58.$$ This gives $(p,q) = -7 \pm \sqrt{3}$ in any order, hence the roots of $f$ are $$z \in \left\{ \frac{-p \pm \sqrt{p^2 - 24}}{12}, \quad \frac{-q \pm \sqrt{q^2 - 24}}{12} \right\}.$$ Numeric evaluation of the four roots shows that only one satisfies $0 < a < b < 1$ , namely $$a = \frac{7 + \sqrt{3} - \sqrt{14(2+\sqrt{3})}}{12} = \frac{7 + \sqrt{3} - \sqrt{7} - \sqrt{21}}{12} \approx 0.12531031679570389137.$$ The corresponding maximum area is then $$R(a) = \frac{7 \sqrt{7} - 10}{108 \sqrt{3}} \approx 0.045547906756179342935.$$ By no means do I claim that this is the most elegant or simplest solution; it is simply what I was able to compute on a first try at this question. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/4506645', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/970256/']} | jdg_382646 |
stackexchange | llm_judgeable_groundtruth_similarity | 11030805 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am using JAXB to create Java objects from XSD file. I am creating immutable wrappers to conceal objects generated by JAXB (earlier I was updating JAXB objects to implement immutable interface and return interface to client. But realised it is bad to change auto generated classes, hence using wrappers) Currently I am returning these immutable wrappers to client app. Is there any option so that auto generated classes will be immutable and it will avoid extra work of creating immutable wrappers. Any other approach is encouraged. Thanks
Now provide the response and nothing else.
| as of JSR-133 (Java 1.5 dependency) you can use reflection to set uninitialized final variables. so you can init to null in the private constructor and use JAXB + immutable cleanly without any XMLAdapter. example from https://test.kuali.org/svn/rice/sandbox/immutable-jaxb/ , got this from a comment on Blaise's blog http://blog.bdoughan.com/2010/12/jaxb-and-immutable-objects.html#comment-form_584069422380571931 package blog.immutable;import javax.xml.bind.annotation.XmlAccessType;import javax.xml.bind.annotation.XmlAccessorType;import javax.xml.bind.annotation.XmlAttribute;import javax.xml.bind.annotation.XmlElement;import javax.xml.bind.annotation.XmlRootElement;@XmlRootElement(name="customer")@XmlAccessorType(XmlAccessType.NONE)public final class Customer { @XmlAttribute private final String name; @XmlElement private final Address address; @SuppressWarnings("unused") private Customer() { this(null, null); } public Customer(String name, Address address) { this.name = name; this.address = address; } public String getName() { return name; } public Address getAddress() { return address; }} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/11030805', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1298354/']} | jdg_382647 |
stackexchange | llm_judgeable_groundtruth_similarity | 89725 |
Below is a question asked on the forum mathematica.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a set of random numbers distributed on a annular disk. I want to find points on the inner and outer edge along a particular angle. One possibility is to use ConvexHull . For example n = 1000;pts = {#[[1]] Cos[#[[2]]], #[[1]] Sin[#[[2]]]} & /@ Transpose[{RandomReal[{4, 6}, n], RandomReal[{0, 2 Pi}, n]}];q = -3 Pi/4; (*Direction*)dq = Pi/10; (*Span*)Needs["ComputationalGeometry`"]dq0=0.01; (*use slightly bigger angle to select*)pts4=Select[pts, q-dq-dq0 < ArcTan@@# < q+dq+dq0 &];out=pts4[[ConvexHull[pts4]]];R=Mean[Norm/@pts4];edge1=Select[out, q-dq < ArcTan@@# < q+dq && Norm[#] < R &];edge2=Select[out, q-dq < ArcTan@@# < q+dq && Norm[#] > R &];Grid[{{Graphics[{LightBlue,Disk[{0,0},6,{q-dq,q+dq}], PointSize[Large],Orange, Point[pts4], PointSize[Small], Black, Point[pts], Dashed, Red, Circle[{0,0},4], Circle[{0,0},6]}, ImageSize->300],Graphics[{LightBlue,Disk[{0,0},6,{q-dq,q+dq}], PointSize[Large], Green, Point[edge1], Blue, Point[edge2], PointSize[Small], Black, Point[pts], Dashed, Red, Circle[{0,0},4], Circle[{0,0},6]}, ImageSize->300]}}] But it doesn't cover all edge points. Another way Another possibility is, as suggested by Batracos, is to use the radial distance as filtering condition. Since the points are not uniformly distributed, there may or may not be a point within a radial range along a particular direction. As you can see from the figure that the inner edge is much deeper in the middle of the blue region than the border. Clarification : "Point at the edge" By point at the edge I mean the points which construct the boundary. For example consider this segment I need to find points constructing the blue and red lines. ConvexHull gives only points on the green line, which is very small in number. I would prefer a tunable parameter which can determine the roughness of the edges (which is the slice width here). Increasing the roughness/slice width will include more points in this case. Here I used the the slicing to find the edges dat = {RandomReal[{-10, 10}], RandomReal[{-2, 2}]} & /@ Range[500];Needs["ComputationalGeometry`"]pts1 = dat[[ConvexHull[dat]]];dqq = 0.5;(*slice width*)slice = Most@Range[-10, 10, dqq];edge1 = edge2 = {};Do[ps = Sort[ Select[dat, qq < #[[1]] < qq + dqq &], #1[[2]] < #2[[2]] &]; If[Length[ps] > 0, AppendTo[edge1, First[ps]]; AppendTo[edge2, Last[ps]];],{qq, slice}]Graphics[{PointSize[Large], Blue, Line[edge1], Red, Line[edge2], Green, Dashed, Line[pts1], PointSize[Small], Black, Point[dat]},ImageSize -> 300]
Now provide the response and nothing else.
| I'm not sure which points you really want, so this is a stab in the dark: You could "walk around" the inner resp. outer circle, and pick the closest point in pts to every point on each circle. (code for the animation at the bottom of the answer.) Mathematica's Nearest function makes this relatively quick: n = 1000;pts = {#[[1]] Cos[#[[2]]], #[[1]] Sin[#[[2]]]} & /@ Transpose[{RandomReal[{4, 6}, n], RandomReal[{0, 2 Pi}, n]}];nf = Nearest[pts -> Automatic];{rMin, rMax} = MinMax[Norm /@ pts];ptsOnCircle = Array[{Cos[#], Sin[#]} &, 1000, {0., 360 °}]; Now nf[{x,y}] returns the index of the closest point to {x,y} , rMin and rMax are the radii of the innermost/outermost points and ptsOnCircle are points on a unit circle. This function then finds the closest point in pts for each point on a circle, deletes duplicates and creates a "closed" list (i.e. the end point is the start point again): ptIndices[r_] := Module[{indices = (nf /@ (r*ptsOnCircle))[[All, 1]]}, indices = DeleteDuplicates[indices]; Append[indices, First[indices]]] Now e.g. pts[[ptIndices[rMin]]] gives the closest points to every point on a circle with radius rMin Graphics[ { Point[pts], Blue, {Thick, Line[pts[[ptIndices[rMin]]]]}, {Dashed, Opacity[0.6], Circle[{0, 0}, rMin]}, Red, {Thick, Line[pts[[ptIndices[rMax]]]]}, {Dashed, Opacity[0.6], Circle[{0, 0}, rMax]} }, ImageSize -> 600] To control the "jerkiness" of the lines, you can use a transform the "squashes" the points to a thinner ring: transformRadius[pt_] := pt/Norm[pt]*(Norm[pt]*.1 + 1)Graphics[Point[transformRadius /@ pts]] (since the result of ptIndices is a list of indices , this doesn't move the result points, it just modifies the distances used in the calculation.) nf = Nearest[transformRadius /@ pts -> Automatic];{rMin, rMax} = MinMax[Norm /@ transformRadius /@ pts];ptsOnCircle = Array[{Cos[#], Sin[#]} &, 1000, {0., 360 °}];ptIndices[r_] := Module[{indices = (nf /@ (r*ptsOnCircle))[[All, 1]]}, indices = DeleteDuplicates[indices]; Append[indices, First[indices]]]Graphics[ { Point[pts], Blue, {Thick, Line[pts[[ptIndices[rMin]]]]}, Red, {Thick, Line[pts[[ptIndices[rMax]]]]} }, ImageSize -> 600] Since the points were "squashed" closer together for the calculation, the resulting border line is "jerkier": Here's the code for the animation at the beginning: Monitor[frames = Table[Graphics[ { {AbsolutePointSize[1/300], Gray, Point[pts]}, MapThread[ Function[{r, col}, Module[{nearest, poly}, nearest = nf[ptsOnCircle[[i]]*r][[1]]; poly = Append[TakeWhile[ptIndices[r], # != nearest &], nearest]; { col, {Line[pts[[poly]]]}, {Dashed, Opacity[0.6], Circle[{0, 0}, r]}, {Thick, Line[{ptsOnCircle[[i]]*r, pts[[nearest]]}]} }]], {{rMin, rMax}, {Red, Blue}}] }, ImageSize -> 300], {i, 1, Length[ptsOnCircle], 5}];, i]ListAnimate[frames] | {} | {'log_upvote_score': 4, 'links': ['https://mathematica.stackexchange.com/questions/89725', 'https://mathematica.stackexchange.com', 'https://mathematica.stackexchange.com/users/8070/']} | jdg_382648 |
stackexchange | llm_judgeable_groundtruth_similarity | 4067192 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a sequence $a_n = \frac {3+n^2}{1-n}$ I assume this sequence is contained in the function $f$ such that $a_n=f(n)$ Now I take the derivative of $f(n)$ , which gives me $\frac{-(n+1)(n-3)}{(1-n)^2}$ I find that $(1-n)^2$ is positive for all $n>1$ I also find that, for $n>3$ , the numerator will always be negative. So $\frac{negative}{positive} = negative$ Since $f'(n)$ is negative for all $n>3$ , it means the function $f(n)$ is eventually decreasing. Which should also imply that the sequence $a_n=\frac {3+n^2}{1-n}$ is eventually decreasing, meaning it is a monotonic sequence. However, the textbook answer says this sequence is not monotone. What am I doing wrong?
Now provide the response and nothing else.
| Use the formula $(a-b)^3 = a^3 - b^3 - 3ab(a-b)$ . Let $a = \sqrt[3]{\sqrt{5} + 2}$ and $b = \sqrt[3]{\sqrt{5} - 2}$ . Plug in the values of $a$ , $b$ . We can get (some calaulation steps are omitted) $$(\sqrt[3]{\sqrt{5} + 2} - \sqrt[3]{\sqrt{5} - 2}) = 4 - 3 \cdot(\sqrt[3]{\sqrt{5} + 2} - \sqrt[3]{\sqrt{5} - 2})$$ which means $$(a-b)^3 = 4 - 3 \cdot (a-b)$$ Then let $x = a-b$ . The rest it to find the root of polynomial $x^3 = 4 - 3x$ , which has only one real root. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/4067192', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/833217/']} | jdg_382649 |
stackexchange | llm_judgeable_groundtruth_similarity | 22436618 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am starting with Postgre Regular Expressions, working on PostgreSQL 8.3 version. I have a table of records as following: record-----------a ababc 123abc 132abc123ABC abc1234567 56786789 I was going through a simple tutorial: www.oreillynet.com .Everything seemed clear to me until I came to the following query: SELECT record FROM myrecords WHERE record ~ '[^0-9]'; The tutorail says: this expression returns strings that don't include digits. But it returned following output to me: output------aababc123abc132abc123ABCabc123 Can anyone explain me this behaviour, please? I am then struggling with another expression on that site trying to exclude strings that include digits AND lower-case letters in the same string.
Now provide the response and nothing else.
| This command: SELECT record FROM myrecords WHERE record ~ '[^0-9]'; means that in the record field there should be at least one non-digit character (this is the meaning of the regex). If one looks for the records which would include digits and lower-case letter, then I would expect a regex like: SELECT record FROM myrecords WHERE record ~ '[0-9a-z]'; which would return all the records having at least one character which is a digit or lowercase letter. If you want to get the records which have no digits, then you would have to use the following regex: SELECT record FROM myrecords WHERE record ~ '^[^0-9]+$'; Here, the ^ character outside of square brackets means the beginning of the field, the $ character means the end of the field, and we require that all characters in between are non-digits. + indicates that there should be at least one such characters. If we would also allow empty strings, then the regex would look like ^[^0-9]*$ . | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/22436618', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3425548/']} | jdg_382650 |
stackexchange | llm_judgeable_groundtruth_similarity | 95921 |
Below is a question asked on the forum biology.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I was reading a paper in the journal Molecular Basis of Disease , which stated: The ORFs are arranged as replicase, and protease and major S, E, M,and N proteins which follows a typical 5’—3’ order of appearance, areconsidered are as considered as major drug/vaccine targets. (Naqvi, et al., 2020) I'd like to know what the " ' " means; if it means inch, or something else like minute. I am doing research so I don't know what units are being used. Source Naqvi, A. A. T. et al., 2020. Insights into SARS-CoV-2 genome, structure, evolution, pathogenesis and therapies: Structural genomics approach. Biochimica et Biophysica Acta (BBA) - Molecular Basis of Disease, Volume 1866, p. 165878.
Now provide the response and nothing else.
| I assume you are referring to the "typical 5’—3’ order of appearance". The correct way to pronounce these is with the word "prime", that is, "Five prime to three prime". These are not units but refer to the directionality of RNA/DNA and the numbers five and three refer to specific carbon atoms arranged in the sugar molecules that make up the RNA/DNA backbone. RNA/DNA are typically "read" (and always written) from the 5' to the 3' end of the molecule by molecular machinery in the cell, so that's usually the order we read the sequences as well. "5' to 3'" in molecular biology effectively means "beginning to end". | {} | {'log_upvote_score': 4, 'links': ['https://biology.stackexchange.com/questions/95921', 'https://biology.stackexchange.com', 'https://biology.stackexchange.com/users/46675/']} | jdg_382651 |
stackexchange | llm_judgeable_groundtruth_similarity | 27084849 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am trying to build a directive with angular. Here is the plunker I wanted to split it into 3 directives: Top, grand-parent directive. - many DAYS Middle, created with ng-repeat - one DAY Bottom, created with ng-repeat - many TIME BLOCKS angular.directive('dateTimeBlocks', [function dateTimeBlocksDirective () {}]) .directive('dayBlock', [function dayDirective () {}]).directive('timeBlock', [function timeBlockDirective () {}]) I wanted to create middle and bottom directives withisolated scopes and only pass the data that I want to modify inside. But it seems to unable to compile "Multiple directives [dateBlock, dateBlock] asking for template on: ..." Any input would be greatly appreciated.
Now provide the response and nothing else.
| This line causes that error: <date-block data-date-block="datePeriod"></date-block> The reason is a combination of factors. First, AngularJS always normalizes directive declarations, so data-date-block (or x-date-block , data:date:block etc.) is actually treated as date-block . Therefore, the above line is equivalent to: <date-block date-block="datePeriod"></date-block> Now, the dateBlock directive is declared with restrict: 'AE' , so it can be applied as either an element or attribute. Therefore, the above line resulting in AngularJS applying the dateBlock directive to the element twice . That per se doesn't cause the error, but dateBlock declares a template and AngularJS doesn't allow an element to have 2 templates (it doesn't make sense anyway, which template should AngularJS choose?), so it throws an error. There are several ways to fix it. Restrict the directive to E so that AngularJS doesn't treat data-date-block as a directive. Rename the isolated scope property dateBlock to something else. Use the attribute form of the directive and use <div> for the element form. Like this: <div data-date-block="datePeriod"></div> | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/27084849', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1095951/']} | jdg_382652 |
stackexchange | llm_judgeable_groundtruth_similarity | 27754606 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Does the Map class in Dart have a way to ignore case if the key is a string? Eg. var map = new Map<String, int>(/*MyComparerThatIgnoresCase*/);map["MyKey"] = 42;var shouldBe42 = map["mykey"]; In C# the Dictionary constructor takes a comparer like the comment above. What is the canonical way to do this in Dart?
Now provide the response and nothing else.
| Maps in Dart have an internal method that compares keys for equality. So far as I know, you can't change this for the default Map class. However, you can use the very similar core LinkedHashMap class, which not only allows, but requires that you specify a key equality method. You can check out more about LinkedHashMaps at https://api.dartlang.org/apidocs/channels/stable/dartdoc-viewer/dart:collection.LinkedHashMap LinkedHashMap<String, String> map = new LinkedHashMap( (a, b) => a.toLowerCase() == b.toLowerCase(), (key) => key.toLowerCase().hashCode);map['Foo'] = 'bar';print(map['foo']); //bar | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/27754606', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2761797/']} | jdg_382653 |
stackexchange | llm_judgeable_groundtruth_similarity | 640724 |
Below is a question asked on the forum electronics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I am trying to read a MIDI signal. I have used a logic analyzer to look at the signal: The upper picure is the note-on signal that should read 0x90 0x3C 0x7F. The lower picture is the note-off signal that should read 0x80 0x3C 0x0 . In binary I get 100100000011110001111111 note on 60 100000000011110000111100 note off 60 EDIT: The note number is 0x3C (60) in decimal and 00111100 in binary. I have no idea how this corresponds to the signals pictured. Can someone help?
Now provide the response and nothing else.
| You are just reading the bits in wrong order. You should enable UART frame decoding. MIDI uses standard UART framing of 8 data bits, no parity, and 1 stop bit. at bit rate of 31250. UART also sends least significant bit first and most significant bit last. The line idles high, start bit is low and stop bit is high. Therefore, 0x90 0x60 0x7F is Note On on Channel 0, note 0x60, velocity 127. In binary it looks like: S00001001P S00000110P S11111110P I used S for low start bit and P for high stop bit. There can be arbitrary amount of idle high time between stop bit and the next start bit. Your logic capture may also have too low sampling rate so see the bits accurately, it looks slightly inaccurate (or the note number is not really 0x60). The Note Off is: S00000001P S00000110P S00000000P Edit: The note number is not 0x60. It's 0x3C or 60 in decimal. The transactions are as follows: S00001001P S00111100P S11111110P S00000001P S00111100P S00000000P | {} | {'log_upvote_score': 5, 'links': ['https://electronics.stackexchange.com/questions/640724', 'https://electronics.stackexchange.com', 'https://electronics.stackexchange.com/users/86242/']} | jdg_382654 |
stackexchange | llm_judgeable_groundtruth_similarity | 640518 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Given (in C++) char * byte_sequence;size_t byte_sequence_length;char * buffer;size_t N; Assuming byte_sequence and byte_sequence_length are initialized to some arbitrary length sequence of bytes (and its length), and buffer is initialized to point to N * byte_sequence_length bytes, what would be the easiest way to replicate the byte_sequence into buffer N times? Is there anything in STL/BOOST that already does something like this? For example, if the sequence were "abcd", and N was 3, then buffer would end up containing "abcdabcdabcd".
Now provide the response and nothing else.
| I would probably just go with this: for (int i=0; i < N; ++i) memcpy(buffer + i * byte_sequence_length, byte_sequence, byte_sequence_length); This assumes you are dealing with binary data and are keeping track of the length, not using '\0' termination. If you want these to be c-strings you'll have to allocate an extra byte and add in the '\0' a the end. Given a c-string and an integer, you'd want to do it like this: char *RepeatN(char *source, size_t n){ assert(n >= 0 && source != NULL); size_t length = strlen(source) - 1; char *buffer = new char[length*n + 1]; for (int i=0; i < n; ++i) memcpy(buffer + i * length, source, length); buffer[n * length] = '\0';} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/640518', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4928/']} | jdg_382655 |
stackexchange | llm_judgeable_groundtruth_similarity | 62319 |
Below is a question asked on the forum unix.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
man pgrep says the following about -f option: -f The pattern is normally only matched against the process name. When -f is set, the full command line is used. What does it mean to say the full command line is used?
Now provide the response and nothing else.
| It means that without -f , pgrep only searches for the provided regexp in the command names, while with -f it searches it in their arguments (where the first argument ( argv[0] ) is not necessarily the same as the command name). $ sleep 2000 &[1] 15768$ pgrep 2000$ pgrep -f 200015768 And if we cause argv[0] to be different from the command name (on Linux as seen in /proc/$pid/stat ) as when using zsh 's ARGV0 : $ ARGV0=foo sleep 2000 &[2] 15881$ ps -fp $!UID PID PPID C STIME TTY TIME CMDchazelas 15881 13126 0 19:55 pts/1 00:00:00 foo 2000$ ps -o comm= $!sleep$ awk '{print $2}' /proc/$!/stat(sleep)$ pgrep foo$ pgrep sleep15881$ pgrep -f sleep$ pgrep -f foo15881 There's a lot of potential confusion regarding process name on Unix and Linux. There are 3 attributes of a process that could claim being the process name: The base name of the executable that was passed to the last execve(2) system call that the process made. On Linux, that is used to initialise the process name, as reported by ps or found in /proc/$pid/stat . However, it should be noted that on Linux, it can be changed using prctl(PR_SET_NAME...) . any path to the executable that is currently mmap ed for execution in the process and preferably the path as it was invoked (for scripts, that would be the path provided in the shebang line for instance). On Linux, you can get it with a readlink or /proc/$pid/exe . That one, you can't change without calling another execve (though you could in theory load a new executable in memory and execute its code without calling execve , see for instance some attempts at a user land execve ). The first argument passed along the execve system call. By convention, that argument is meant to tell the application its name to let it know how to behave accordingly so is often what is meant by the process name. On Linux, it can be found in /proc/$pid/cmdline , but a process can also change it by modifying the memory pointed to by argv[0] . It should also be noted that there's a lot of variation among the difference Unices. | {} | {'log_upvote_score': 5, 'links': ['https://unix.stackexchange.com/questions/62319', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/28032/']} | jdg_382656 |
stackexchange | llm_judgeable_groundtruth_similarity | 148556 |
Below is a question asked on the forum softwareengineering.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I am starting to write a webservice, and I've built with nodeJS and a RESTfulish approach. From what I gather: The advantage is that you don't have to duplicate code. The disadvantages are that you: will update the public API frequently, but should be solved with versioning can't really make service specific caching and optimizations What is considered best practice? Do sites such as Stack Exchange, Github, Twitter, etc use their own APIs for their clients?
Now provide the response and nothing else.
| You should absolutely use your own API. This concept is widely known as dogfooding and it has many benefits beyond avoiding code duplciation. Consistent behaviour between your site/product and what API consumers will write (ie. their expectations of your API) Another form of testing. You can and will find bugs in the API before your customers do, making their resolutions cost less. Although I would argue against one of your points: you should not be updating the API frequently. Spend the time to architect and proof out an API that will stay around for a while. Fortunately, dogfooding in this way will enforce that. Where you would have just broken customer code before, you'll now be breaking your own code. When you must , yes versioning is a solution, but it should be avoided. | {} | {'log_upvote_score': 5, 'links': ['https://softwareengineering.stackexchange.com/questions/148556', 'https://softwareengineering.stackexchange.com', 'https://softwareengineering.stackexchange.com/users/-1/']} | jdg_382657 |
stackexchange | llm_judgeable_groundtruth_similarity | 10237615 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
How to get the dimensions given a multidimensional array? Edit: it could be of 1, 2, or 3 dimensions but each sub-array has the same length. i.e. for var a = [[1,1,1], [1,1,1]] would be [2,3]
Now provide the response and nothing else.
| const dimensions = [ arr.length, arr[0].length ]; This works, if you know length of the inner arrays never change. If the dimension of the inner arrays aren't static ( jagged array ), you could combine Array.reduce and Math.max to calculate the largest dimension: const dimensions = [ arr.length, arr.reduce((x, y) => Math.max(x, y.length), 0)]; | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/10237615', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/-1/']} | jdg_382658 |
stackexchange | llm_judgeable_groundtruth_similarity | 1071261 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Let me first confirm you that this question is not a duplicate of either this , this or this or any other similar looking problem. Here in the current problem I'm asking to disprove me(most probably I'm wrong). As you can see in this problem as answered by Nicolas that if a map is from $A \to B$ and is bijective then the cardinality of $A$ and $B$ is same. Logarithmic map is from $\mathbb{R^+} \to \mathbb{R}$ and it is a bijective map and therefore it implies that the cardinality of $\mathbb{R^+}$ and $\mathbb{R}$ is same. My logic We can rewrite $\mathbb{R}=\mathbb{R^-} \cup \{0\} \cup \mathbb{R^+}$ Now we can see that $\mathbb{R}$ has all the elements of $\mathbb{R^+}$ and over that it has {0} and elements of $\mathbb{R^-}$. Now using pigeonhole principle , if we pair each element of $\mathbb{R^+}$ to itself from $\mathbb{R^+} \to \mathbb{R}$ (eg. 5.124 is paired to 5.124 and so on) now when the pairing gets over then you have elements of $\mathbb{R^-}$ which have not been paired. Now one can say that since they are infinite sets therefore we cannot talk about pairing as I did above. When we are dealing with the pigeonhole principle then at that time it is not necessary to know the exact numbers involved. Now whatever method you use for pairing you will always end with some elements of $\mathbb{R}$ which have not been paired (acc to pigeonhole principle). Most probably I'm wrong but how?. Kindly make me understand that I'm wrong and the above used logic by me is inappropriate.
Now provide the response and nothing else.
| The definition of equicardinal is that there exists a bijection between the sets. You are trying to define "not equicardinal" as "there exists a bijection between one set and a strict subset of another". This definition is not a good one, as all Dedekind infinite sets (such as $\mathbb{Z}, \mathbb{R}$) have the property that they are bijective with strict subsets of themselves; hence all Dedekind-infinite sets are "not equicardinal" with themselves by your definition. In answer to OP's comment, the specific problem with the pigeonhole principle argument in the OP is that this proves that some attempts at a bijection fail. But as discussed above, and in the other solution, and in the comments, is that if ANY bijection exists, then the two sets are equicardinal. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1071261', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/121735/']} | jdg_382659 |
stackexchange | llm_judgeable_groundtruth_similarity | 832709 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Is it possible to sort an array with Unicode / UTF-8 characters in PHP using a natural order algorithm? For example (the order in this array is correctly ordered): $array = array( 0 => 'Agile', 1 => 'Ágile', 2 => 'Àgile', 3 => 'Âgile', 4 => 'Ägile', 5 => 'Ãgile', 6 => 'Test',); If I try with asort($array) I get the following result: Array( [0] => Agile [6] => Test [2] => Àgile [1] => Ágile [3] => Âgile [5] => Ãgile [4] => Ägile) And using natsort($array): Array( [2] => Àgile [1] => Ágile [3] => Âgile [5] => Ãgile [4] => Ägile [0] => Agile [6] => Test) How can I implement a function that returns the correct result order (0, 1, 2, 3, 4, 5, 6) under PHP 5? All the multi byte string functions (mbstring, iconv, ...) are available on my system. EDIT: I want to natsort() the values, not the keys - the only reason why I'm explicitly defining the keys (and using asort() instead of sort()) is to ease the job of finding out where the sorting of unicode values went wrong.
Now provide the response and nothing else.
| The question is not as easy to answer as it seems on the first look. This is one of the areas where PHP's lack of unicode supports hits you with full strength. Frist of all natsort() as suggested by other posters has nothing to do with sorting arrays of the type you want to sort. What you're looking for is a locale aware sorting mechanism as sorting strings with extended characters is always a question of the used language. Let's take German for example: A and Ä can sometimes be sorted as if they were the same letter (DIN 5007/1), and sometimes Ä can be sorted as it was in fact "AE" (DIN 5007/2). In Swedish, in contrast, Ä comes at the end of the alphabet. If you don't use Windows, you're lucky as PHP provides some functions to exactly this. Using a combination of setlocale() , usort() , strcoll() and the correct UTF-8 locale for your language, you get something like this: $array = array('Àgile', 'Ágile', 'Âgile', 'Ãgile', 'Ägile', 'Agile', 'Test');$oldLocal = setlocale(LC_COLLATE, '<<your_RFC1766_language_code>>.utf8');usort($array, 'strcoll');setlocale(LC_COLLATE, $oldLocal); Please note that it's mandatory to use the UTF-8 locale variant in order to sort UTF-8 strings. I reset the locale in the example above to its original value as setting a locale using setlocale() can introduce side-effects in other running PHP script - please see PHP manual for more details. When you do use a Windows machine, there is currently no solution to this problem and there won't be any before PHP 6 I assume. Please see my own question on SO targeting this specific problem. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/832709', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/89771/']} | jdg_382660 |
stackexchange | llm_judgeable_groundtruth_similarity | 224972 |
Below is a question asked on the forum softwareengineering.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I found this statement from the gang of four's "Design Patterns" particularly odd; for some context, the authors are comparing inheritance versus composition as reuse mechanisms [p. 19]: "...you can't change the implementations inherited from parent classes at run-time, because inheritance is defined at compile-time." They go on to say of composition: "Object composition is defined dynamically at run-time through objects acquiring references to other objects." I am not sure why this phase distinction is important. I am familiar with compiling and inheritance but work as a JavaScript developer, so maybe I'm missing something fundamental.
Now provide the response and nothing else.
| Some languages are pretty strongly static, and only allow the specification of the inheritance relationship between two classes at the time of definition of those classes. For C++, definition time is practically the same as compilation time. (It's slightly different in Java and C#, but not very much.) Other languages allow much more dynamic reconfiguration of the relationship of classes (and class-like objects in Javascript) to each other; some go as far as allowing the class of an existing object to be modified, or the superclass of a class to be changed. (This can cause total logical chaos, but can also model real world nasties quite well.) But it is important to contrast this to composition, where the relationship between one object and another is not defined by their class relationship (i.e., their type ) but rather by the references that each has in relation to the other. General composition is a very powerful and ubiquitous method of arranging objects: when one object needs to know something about another, it has a reference to that other object and invokes methods upon it as necessary. As soon as you start looking for this super-fundamental pattern, you'll find it absolutely everywhere; the only way to avoid it is to put everything in one object, which would be massively dumb!(There's also stricter UML composition/aggregation, but that's not what the GoF book is talking about there.) One of the things about the composition relationship is that particular objects do not need to be hard-bound to each other. The pattern of concrete objects is very flexible, even in very static languages like C++. (There is an upside to having things very static: it is possible to analyse the code more closely and — at least potentially — issue better code with less overhead.)To recap, Javascript, as with many other dynamic languages, can pretend it doesn't use compilation at all; just pretence, of course, but the fundamental language model doesn't require transformation to a fixed intermediate format (e.g., a “binary executable on disk”). That compilation which is done is done at runtime, and can be easily redone if things vary too much. (The fascinating thing is that such a good job of compilation can be done, even starting from a very dynamic basis…) Some GoF patterns only really make sense in the context of a language where things are fairly static. That's OK; it just means that not all forces affecting the pattern are necessarily listed. One of the key points about studying patterns is that it helps us be aware of these important differences and caveats. (Other patterns are more universal. Keep your eyes open for those.) | {} | {'log_upvote_score': 4, 'links': ['https://softwareengineering.stackexchange.com/questions/224972', 'https://softwareengineering.stackexchange.com', 'https://softwareengineering.stackexchange.com/users/115607/']} | jdg_382661 |
stackexchange | llm_judgeable_groundtruth_similarity | 58046 |
Below is a question asked on the forum physics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I want to write a model for estimating incoming solar radiation for a specific latitude on earth but I am struggling to find an appropriate source which shows the required equations for doing so. Would anyone be able to provide me with a link to where I can find equations for estimating solar radiation (irradiance) given a specific cloud cover, latitude, time of day, and day of year?
Now provide the response and nothing else.
| Ok, I'm still not sure on what level you want to do this, but I will start you off with some basics. The most important factor is probably the solar elevation angle , $\theta$. As described on the wiki-page it can be calculated using this formula: $$\sin\theta=\cos h\cos\delta\cos\Phi+\sin\delta\sin\Phi$$ where $h$ is the hour angle, $\delta$ is the solar declination and $\Phi$ is the latitude. The trickiest to calculate of these is the solar declination. A few different formulas to calculate is can be found here . Which formula you use will depend on the accuarcy you need. I suggest starting with this formula: $$\delta=-\arcsin(0.39789\cos(0.98565(N+10)+1.914\sin(0.98565(N-2))))$$ where $N$ is the day of year beginning with $N=0$ at 00:00:00 UTC on January 1 (prefereably calulate $N$ as a decimal number to increase accuracy). Note that this formula uses degree-based trigonometric functions. Now, if we totally ignore atmosperic effects, total solar irradiance (of all wavelengths) incident on a horizontal surface will be: $$E=A\sin\theta$$ where $A$ is the solar constant which approximatley has the value 1360 W/m$^2$ (on average, it varies by roughly 7% over the year due to the ellipticity of Earth's orbit). Since this ignores atmospheric effects, the actual irradiance on the ground will be lower due to scattering and absorption. These effects will also depend on the solar elevation angle, since a lower angle gives a longer light path through the atmosphere. Maybe, starting from this, you can explain what further aspects you need to model. | {} | {'log_upvote_score': 4, 'links': ['https://physics.stackexchange.com/questions/58046', 'https://physics.stackexchange.com', 'https://physics.stackexchange.com/users/20059/']} | jdg_382662 |
stackexchange | llm_judgeable_groundtruth_similarity | 2831062 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Whenever I set the Border.Effect property to a drop shadow effect every control contained within the control has a drop shadow. Is there a way to set the shadow just to the border and not every control contained in the border? Here is a short example of my code: <Grid> <Border Margin="68,67,60,67" BorderBrush="Black" BorderThickness="1" CornerRadius="10"> <Border.Effect> <DropShadowEffect/> </Border.Effect> <Rectangle Fill="White" Stroke="Black" Margin="37,89,118,98" /> </Border></Grid>
Now provide the response and nothing else.
| Two choices: Option 1: Add a border element with the effect on it as a sibling of the border / rectangle element tree you have. Something like this: <Grid> <Border Margin="68,67,60,67" BorderBrush="Black" BorderThickness="1" CornerRadius="10"> <Border.Effect> <DropShadowEffect /> </Border.Effect> </Border> <Border Margin="68,67,60,67" BorderBrush="Black" BorderThickness="1" CornerRadius="10"> <Rectangle Fill="White" Stroke="Black" Margin="37,89,118,98"> </Rectangle> </Border></Grid> Option 2: Put the rectangle as a sibling of the border element like this: <Grid> <Border Margin="68,67,60,67" BorderBrush="Black" BorderThickness="1" CornerRadius="10"> <Border.Effect> <DropShadowEffect /> </Border.Effect> </Border> <Rectangle Fill="White" Stroke="Black" Margin="37,89,118,98"> </Rectangle></Grid> NOTE: You will have to tweak the layout on the second solution to make the rectangle line up where you want it | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/2831062', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/109041/']} | jdg_382663 |
stackexchange | llm_judgeable_groundtruth_similarity | 46374185 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I was looking for a Python library function which computes multinomial coefficients . I could not find any such function in any of the standard libraries. For binomial coefficients (of which multinomial coefficients are a generalization) there is scipy.special.binom and also scipy.misc.comb . Also, numpy.random.multinomial draws samples from a multinomial distribution, and sympy.ntheory.multinomial.multinomial_coefficients returns a dictionary related to multinomial coefficients. However, I could not find a multinomial coefficients function proper, which given a,b,...,z returns (a+b+...+z)!/(a! b! ... z!). Did I miss it? Is there a good reason there is none available? I would be happy to contribute an efficient implementation to SciPy say. (I would have to figure out how to contribute, as I have never done this). For background, they do come up when expanding (a+b+...+z)^n. Also, they count the ways of depositing a+b+...+z distinct objects into distinct bins such that the first bin contains a objects, etc. I need them occasionally for a Project Euler problem. BTW, other languages do offer this function: Mathematica , MATLAB , Maple .
Now provide the response and nothing else.
| To partially answer my own question, here is my simple and fairly efficient implementation of the multinomial function: def multinomial(lst): res, i = 1, 1 for a in lst: for j in range(1,a+1): res *= i res //= j i += 1 return res It seems from the comments so far that no efficient implementation of the function exists in any of the standard libraries. Update (January 2020). As Don Hatch has pointed out in the comments, this can be further improved by looking for the largest argument (especially for the case that it dominates all others): def multinomial(lst): res, i = 1, sum(lst) i0 = lst.index(max(lst)) for a in lst[:i0] + lst[i0+1:]: for j in range(1,a+1): res *= i res //= j i -= 1 return res | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/46374185', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/5235351/']} | jdg_382664 |
stackexchange | llm_judgeable_groundtruth_similarity | 13708294 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
How can I round times in MySQL to the nearest 15 minutes (e.g. 0,15,30,45)?
Now provide the response and nothing else.
| SELECT SEC_TO_TIME(FLOOR((TIME_TO_SEC(CURTIME())+450)/900)*900) In this example I have used CURTIME() for the input time, but you can use any time field. 900 seconds=15 minutes (the period to round to), 450 seconds is half that (to provide the rounding element). I've tested with 1800/900 to get nearest half hour, should work with others (600/300 for 10 minutes etc). | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/13708294', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1639910/']} | jdg_382665 |
stackexchange | llm_judgeable_groundtruth_similarity | 5944708 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I want to create a list that will contain the last 5 values entered into it. Here is an example: >>> l = []>>> l.append('apple')>>> l.append('orange')>>> l.append('grape')>>> l.append('banana')>>> l.append('mango')>>> print(l)['apple', 'orange', 'grape', 'banana', 'mango']>>> l.append('kiwi')>>> print(l) # only 5 items in list['orange', 'grape', 'banana', 'mango', 'kiwi'] So, in Python, is there any way to achieve what is demonstrated above? The variable does not need to be a list, I just used it as an example.
Now provide the response and nothing else.
| You might want to use a collections.deque object with the maxlen constructor argument instead: >>> l = collections.deque(maxlen=5)>>> l.append('apple')>>> l.append('orange')>>> l.append('grape')>>> l.append('banana')>>> l.append('mango')>>> print(l)deque(['apple', 'orange', 'grape', 'banana', 'mango'], maxlen=5)>>> l.append('kiwi')>>> print(l) # only 5 items in listdeque(['orange', 'grape', 'banana', 'mango', 'kiwi'], maxlen=5) | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/5944708', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/140848/']} | jdg_382666 |
stackexchange | llm_judgeable_groundtruth_similarity | 553846 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Find the values $a$ s.t. the integral $$\int_0^{\infty}\frac{\ln(1+x^2)}{x^a}dx$$ converges. I tried some values of $a$ by programming, it seems that for $a=2$, the integral converges, and for $a=3$, it diverges. But how can we explicitly determine the range of convergence?
Now provide the response and nothing else.
| Hint: Near $x=0$, $\frac{\log(1+x^2)}{x^a}\sim x^{2-a}$ and as $x\to\infty$, $\frac{\log(1+x^2)}{x^a}\le C_\epsilon x^{\epsilon-\alpha}$ for all $\epsilon\gt0$. Not that it matters to the question, but $C_\epsilon$ is approximately $\dfrac2{e\epsilon}$ . | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/553846', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/41622/']} | jdg_382667 |
stackexchange | llm_judgeable_groundtruth_similarity | 43938435 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I've spent a few hours on the web trying to find a solution for this with no joy. Essentially I'm downloading my bank statement in to a spreadsheet. I want to categorise each expenditure by searching its text and seeing if it matches a range of keywords that I've manually added. For example, Column A contains all my expenses and let's say cell A1 is "TESCO PS5 on 4th May" I've set up a range of my own text cells in another column such as:C3: MARKSC4: COFFEEC5: TESCOC6: GREENS Column D contains the following as categories of column C:D3: FoodD4: DrinkD5: FoodD6: Fun So in this example for A1 I want to add a formula to cell B1 that will search cells C3 to C6 and find the one that is contained within A1. Then it returns the corresponding value from column D. So in this example, the formula in B1 would search A1, "TESCO PS5 on 4th May" and identify that the value in C5 "TESCO" is contained within A1. It then returns the associated value in D5, "Food" Thus I'm able to categorise "TESCO PS5 on 4th May" as "Food" If I use something like Match it seems to do the opposite of what I want. It lets me search for one string within a range of strings. I want the opposite. I want to search if a range of strings are within one string and identify the one that matches. ***************!!!!!!!!EDIT!!!!!!**************** SOLUTION FOUND. Adding it on here as having trouble with formatting using comments. So I'm using this: =IFERROR(ArrayFormula(INDIRECT("D"&2+MATCH(TRUE,ISNUMBER(SEARCH($C$3:$C$6,$A1)),0)))) SEARCH: search range for text I want to find in a single cell followed by the single cell I want to search.The result is either an error or an index of a matching search. ArrayFormula: This allows SEARCH to work the opposite way to almost every example I found says it should be used.Instead of supplying a search term and a search range, instead I supply a range of search terms and specify one single cell to be matched against. ArrayForumla allows for multiple results to be output. It'll print those results one below the other in your spreadsheet. I don't actually want that but I can then use the two following functions to filter out undesired results: ISNUMBER: Just identifies which result from your search was a valid match. Returns an int. MATCH: This allows us to filter out all the non-results. Without this the spreadsheet will want to fill out multiple cells with useless data when using ArrayForumla. Using Match we are simply left with the one match result that matters, an index to the matched text field that is contained within our searched cell. INDIRECT: allows us to build a cell index so we can reference the appropriate category cell data. IFERROR: just makes sure the spreadsheet doesn't display errors for cells that it doesn't find a solution for.
Now provide the response and nothing else.
| It's all down to the division by zero rules for various types. 0 / 0 is an integer division by zero (as both arguments are integer literals), and that is required to throw a java.lang.ArithmeticException . 1.toDouble/0.toDouble is a floating point division by zero with a positive numerator, and that is required to evaluate to +Infinity . 0.0/0.0 is a floating point division by zero with a zero numerator, and that is required to evaluate to +NaN . The first is a Java and Scala convention, the other two are properties of IEEE754 floating point, which is what Java and Scala both use. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/43938435', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/8002918/']} | jdg_382668 |
stackexchange | llm_judgeable_groundtruth_similarity | 6413690 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have written a simple servlet with init() and doGet() , doPost() method. I have a requirement, that I have an API which i need to invoke an server startup. Is it possible to do so. I tried with init method, and setting default values in web.xml, but i am still unable to do so. Please tell if I am missing something. Thanks
Now provide the response and nothing else.
| Have you set the load-on-startup attribute to be positive? <servlet id=”servlet1”><load-on-startup>2</load-on-startup></servlet> Alternatively, you might want to use a ServletContextListener to do initialisation work when the container comes up. This is the 'de facto' standard for having a callback to do some initialisation work when the servlet container comes online e.g. we use that to read in some XML files and populate a cache. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/6413690', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/197831/']} | jdg_382669 |
stackexchange | llm_judgeable_groundtruth_similarity | 15980995 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
If I want to check to see if a field is NULL or empty using a MySQL query, I know I can do something like this: column = '' OR column IS NULL However, is there any way to check this without doing two separate comparisons?
Now provide the response and nothing else.
| Use COALESCE() to 'normalize' the value (convert NULL values to an empty string); WHERE COALESCE(mycolumn, '') = '' Read the documentation: COALESCE() Or the other way around; convert empty strings to NULL; WHERE NULLIF(mycolumn, '') IS NULL Documentation: NULLIF() Of those two, I would prefer COALESCE() as it is part of the ANSI SQL standard You can experiment with it yourself, just do this; SELECT mycolumn AS orig_value, COALESCE(mycolumn, '') AS coalesce_value, (COALESCE(mycolumn, '') = '') AS compare_resultFROM mytable; This will show the original value, the 'coalesce' value and the result of the comparison side by side for every row in the table | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/15980995', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/945974/']} | jdg_382670 |
stackexchange | llm_judgeable_groundtruth_similarity | 2068159 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I made a WPF/C# program and I am using the internet control for WYSIWYG HTML editing. it is a regular Executable program. it works on most computers however some computers are giving me the following error. Could not load file or assembly 'Microsoft.mshtml, Version=7.0.3300.0, Culture=neutral, PublicKeyToken=b03f5f7f11d50a3a' or one of its dependencies. Strong name validation failed. The 'Microsoft.mshtml.dll' file is distributed with the program. It is with all of the other required dlls in the same folder as the exe file. Here is the output from Fuslogvw *** Assembly Binder Log Entry (1/14/2010 @ 6:36:51 PM) ***The operation failed.Bind result: hr = 0x80070002. The system cannot find the file specified.Assembly manager loaded from: c:\WINDOWS\Microsoft.NET\Framework\v2.0.50727\mscorwks.dllRunning under executable C:\Documents and Settings\office\Desktop\Database\DATABASE.exe--- A detailed error log follows. === Pre-bind state information ===LOG: User = CAMPUSREMOTE\officeLOG: DisplayName = Microsoft.mshtml, Version=7.0.3300.0, Culture=neutral, PublicKeyToken=b03f5f7f11d50a3a (Fully-specified)LOG: Appbase = file:///C:/Documents and Settings/office/Desktop/Database/LOG: Initial PrivatePath = NULLLOG: Dynamic Base = NULLLOG: Cache Base = NULLLOG: AppName = DATABASE.exeCalling assembly : ChabadOnCampusMainFrontEnd, Version=1.0.0.0, Culture=neutral, PublicKeyToken=null.===LOG: Start binding of native image Microsoft.mshtml, Version=7.0.3300.0, Culture=neutral, PublicKeyToken=b03f5f7f11d50a3a.WRN: No matching native image found. Thanks
Now provide the response and nothing else.
| Verify that the 'Microsoft.mshtml.dll' file, distributed with the program is the PIA file and not an Office file. Some sites claims that the Office files are "delay signed" and the PIA file (installed with the VS installation) is a signed copy. on my computer I have 3 different versions of 'Microsoft.mshtml.dll' file, (same file-size, but different content): "c:\Program Files\Microsoft Visual Studio 9.0\Visual Studio Tools for Office\PIA\Office11\Microsoft.mshtml.dll" "c:\Program Files\Microsoft Visual Studio 9.0\Visual Studio Tools for Office\PIA\Office12\Microsoft.mshtml.dll" "c:\Program Files\Microsoft.NET\Primary Interop Assemblies\Microsoft.mshtml.dll" Remove "Microsoft.mshtml.dll" reference from the project.Use "Add Reference", ".Net" tab, select the PIA file, use "copy loacal" option.(It worked for me . . .) Atara | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2068159', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/200669/']} | jdg_382671 |
stackexchange | llm_judgeable_groundtruth_similarity | 424948 |
Below is a question asked on the forum stats.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a distribution, which I initially assumed to be a Rayleigh, but it almost certainly isn't. Before I consider convolutions of various distributions, e.g. Rayleigh convolved with Boltzmann, Rayleigh convolved with Gaussian and so on, I was hoping someone with a good eye might be able to identify it: I have plotted the data with a Rayleigh on top of it to illustrate that it is somewhat similar but clearly this isn't the distribution. I've been asked to provide a little more information about the data. The data itself are fit residuals from a freqeuncy spectrum. The units of the residuals are in $\rm{dBV_{pk}}$ , the definition of which is $\rm{dBV_{pk}} = 10\log_{10}(V^{2}_{pk})$ . I have converted the residuals from $\rm{dBV_{pk}}$ to $V^{2}_{pk}$ by $V^{2}_{pk} = 10^{\rm{dBV_{pk}} / 10}$ and this is what is shown in the histogram. I initially assumed a Rayleigh as the original spectrum is an FFT, which transforms a signal with real and imaginary parts (both of which are Gaussian distributed) and the absolute value of the FFT is taken, which is exactly how a Rayleigh is produced. I again will add some further details outlining my motivation. I have some FFT spectra, which I know the general lineshape of. I want to get an understanding on the noise that is on top of the lineshape, so I look at the fit residuals. The idea being that if I know how the residuals of a spectra are distributed, I can then add it to the lineshape model for simulation purposes. I don't want to add my noise in logorithmic units, i.e. $\rm{dBV_{pk}}$ , it is preferable to do this in $V_{pk}^{2}$ . The data I have provided are the residuals from 64 spectra, each having 801 residual points. I can of course just perform a KDE of this and use this for simulation but it is nice to understand where this profile comes from. For example if one has flat white noise in the frequency domain, and convert this to linear units this is absolutely a Rayleigh distribution -- emerging because the real and imaginary parts of the signal are Gaussian distributed and one always takes the absolute magnitude of a resultant FFT -- Rayleigh!! I would like to find a similar argument flow for this case. Data available here: https://filebin.net/17y3un9vs1kh5cq0
Now provide the response and nothing else.
| For simulation purposes, a Weibull distribution may work well. Allow me to explain why and to say something about the limitations. A plot of the original (unexponentiated) residuals immediately suggested a Weibull distribution to me. (One reason this family comes to mind is that it includes Rayleigh distributions, which are Weibull with shape parameter $2.$ ) The formula will depend on three parameters: a shape parameter plus a scale and location. A standard exploratory technique to test such a distributional hypothesis is the (quantile-quantile) probability plot: one draws a scatterplot of quantiles of the data against the same quantiles of a reference distribution. When this scatterplot is nearly linear, the data differ from the reference distribution only by a change of units--the scaling and recentering. One exploratory way to find a good shape parameter is to adjust it until the probability plot looks as linear as possible. To avoid too much work, I used various approaches: only data from the first spectrum (optimal shape is $6.3$ ); equally spaced centiles of all data (optimum is $5.63$ ); and a variance-weighted version of the latter (optimum is $4.99$ ). There's little to choose from among those (they all fit the data pretty well). Taking the middle value produces the probability plot at the left: The probability plot is exceptionally straight throughout its range, indicating a good fit. The middle plot shows the corresponding Weibull frequency graph superimposed on the histogram. It tracks the peaks of the bars well, also suggesting a good fit. However, the corresponding chi-squared test indicates a little lack of fit ( $\chi^2=334.6,$ $p=2\times 10^{-15}$ with $154$ degrees of freedom based on length- $0.1$ bins from $-8.5$ to $7.0$ ). To analyze the lack of fit I created a "rootogram" as invented by John Tukey. This displays the square roots of the histogram densities relative to the fitted distribution, thereby greatly magnifying the deviations of the data distribution above and below the fit. This is the right plot in the figure. To interpret the rootogram, bear in mind that the square root of a count will, on average, be less than one unit from its expected value. You can see that's the case with most of the bars in the rootogram, confirming the previous good fits. In this plot, however, it is apparent that relative to the Weibull fit, the data are a little more numerous at the extremes and the center (the red positive bars) compared to the middle values (the blue negative bars), and this is a systematic, nearly symmetric pattern. In this sense the Weibull description is not entirely adequate: we should not conclude there is some underlying physical law to explain a Weibull distribution of residuals. The Weibull shape is merely a mathematical convenience that succinctly describes these data very well. (There are other issues, such as the possibility of serial correlation of the residuals within each spectrum. There is some correlation, but it extends only for a couple of lags and therefore is unlikely to suggest any meaningful modification of the foregoing description.) Ultimately, then, whether you use a Weibull distribution to simulate residuals (which you can exponentiate if you wish) depends on whether these small but systematic departures are important to capture in the simulation. For the record, the Weibull distribution shown here has shape parameter $5.63,$ scale parameter $11.85,$ and is shifted by $-10.95.$ Because Weibull distributions are just power transformations of Exponential (that is, Gamma $(1)$ ) distributions, and Exponential random variates are easily obtained as the negative logarithms of the Uniform $(0,1)$ variates supplied by standard pseudorandom number generators in computing systems, it is easy and computationally cheap to generate Weibull variates. Specifically, letting $U$ have this Uniform distribution, simulate the (raw) residuals as $$X = (-\log(U))^{1/5.63} * 11.85 - 10.95.$$ To illustrate this process, and to serve as a reference for interpreting the preceding data plots, I created a random sample in this manner of the same size as the original dataset ( $801\times 64$ values) and drew its histogram, the same Weibull frequency curve, and the corresponding rootogram. The typical bar is between 0 and 1 in height--but this time, the bar heights appear to vary randomly and independently, rather than following the systematic pattern in the data rootogram. | {} | {'log_upvote_score': 5, 'links': ['https://stats.stackexchange.com/questions/424948', 'https://stats.stackexchange.com', 'https://stats.stackexchange.com/users/186174/']} | jdg_382672 |
stackexchange | llm_judgeable_groundtruth_similarity | 5876809 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'd like to know if the POST method on HTTP sends data as a QueryString, or if it use a special structure to pass the data to the server. In fact, when I analyze the communication with POST method from client to server (with Fiddler for example), I don't see any QueryString, but a Form Body context with the name/value pairs.
Now provide the response and nothing else.
| The best way to visualize this is to use a packet analyzer like Wireshark and follow the TCP stream . HTTP simply uses TCP to send a stream of data starting with a few lines of HTTP headers. Often this data is easy to read because it consists of HTML, CSS, or XML, but it can be any type of data that gets transfered over the internet (Executables, Images, Video, etc). For a GET request, your computer requests a specific URL and the web server usually responds with a 200 status code and the the content of the webpage is sent directly after the HTTP response headers. This content is the same content you would see if you viewed the source of the webpage in your browser. The query string you mentioned is just part of the URL and gets included in the HTTP GET request header that your computer sends to the web server. Below is an example of an HTTP GET request to http://accel91.citrix.com:8000/OA_HTML/OALogout.jsp?menu=Y , followed by a 302 redirect response from the server. Some of the HTTP Headers are wrapped due to the size of the viewing window (these really only take one line each), and the 302 redirect includes a simple HTML webpage with a link to the redirected webpage (Most browsers will automatically redirect any 302 response to the URL listed in the Location header instead of displaying the HTML response): For a POST request, you may still have a query string, but this is uncommon and does not have anything to do with the data that you are POSTing. Instead, the data is included directly after the HTTP headers that your browser sends to the server, similar to the 200 response that the web server uses to respond to a GET request. In the case of POSTing a simple web form this data is encoded using the same URL encoding that a query string uses, but if you are using a SOAP web service it could also be encoded using a multi-part MIME format and XML data . For example here is what an HTTP POST to an XML based SOAP web service located at http://192.168.24.23:8090/msh looks like in Wireshark Follow TCP Stream : | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/5876809', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/732743/']} | jdg_382673 |
stackexchange | llm_judgeable_groundtruth_similarity | 59577 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
What is the difference between modding out by a primitive polynomial and modding out by a non-primitive irreducible polynomial in a finite field $F_q$? From what I understand either one should generate a field of $q^n$ elements, where $n$ is the degree of the polynomial, but a big deal is made out of finding primitive polynomials to make the larger field. What is the difference exactly in the way the resulting field works?
Now provide the response and nothing else.
| Qiaochu's comment contains the essential algebraic reason. I don't want to hog his priority, but as examples explaining why we are interested in primitive polynomials let me list the following: Discrete log-tables. One efficient way of presenting a finite field in a computer program is to have a look-up table of discrete logarithms at hand. Using such a LUT implementing multiplication of two field elements becomes easy. At least every program involving finite fields that I have ever written begins by generating such a discrete logarithm table. To that end it is imperative to have a primitive polynomial $p(x)$. If you have one, then its easy to recursively present the powers of the generator $x+(p(x))$ as low degree polynomials in $x$, and you can generate the log-table while doing that. As a concrete application, where we immediately see a primitive polynomial show an advantage I mention CRC-(=cyclic redundancy check) polynomials. These are polynomials in $F_2[D]$ (telecommunication engineers prefer to use $D$ as unknown here). The way these are used is that data to be protected by a CRC is first turned into a polynomial in $F_2[D]$ bit-by-bit. Then a few (redundancy) bits are appended to it so that in the end the resulting polynomial becomes divisible by a pre-determined CRC-polynomial $p(D)$. The point of the exercise is that whoever later reads the data can obtain a degree of confidence on its correctness by verifying that the data is, indeed, divisible by $p(D)$. What kind of errors might happen? Usually only a few bits will get toggled. If only a single bit is read incorrectly, then almost any $p(D)$ will work (as long as it is not a monomial). What about the occasions where two bits are toggled, say at positions $i$ and $j$? This would pass the CRC-test undetected only, if the binomial $D^i+D^j$ is divisible by $p(D)$. How does primitivity enter the scene? It is an easy exercise to show that any polynomial of $F_2[D]$ divides some binomials. The key question is: what's the degree of the lowest degree binomial divisible by $p(D)$? This is motivated by the fact the if we can maximize this degree, then we are maximizing the length of the data packet we can protect against such undetected errors. Because the number of redundant bits = the degree of $p(D)$, we are minimizing the nuymber of the redundancy bits needed to protect our data at this level of protection. W.l.o.g we can assume that $p(0)=1$, and then the we easily see that the lowest degree binomial divisible by $p(D)$ is $1+D^\ell$, where $\ell$ is the order of $D$ in the quotient ring $F_2[D]/p(D)$. So primitive polynomials show an advantage here. This is only the beginning of the theory, and occasionally we want to protect for more than two bit errors. A typical CRC-polynomial is of the form $p(D)=(1+D)q(D)$, where $q(D)$ is primitive. The extra factor $1+D$ has the effect that in order for an error to pass undetected, the number of errors must be even. Thus polynomials of the above form catch all the patterns of at most 3 errors up to a maximum size of data packet $2^{\deg q(D)}-1-\deg q(D)$ bits. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/59577', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/12952/']} | jdg_382674 |
stackexchange | llm_judgeable_groundtruth_similarity | 65360650 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm using springbooot 2.4.0 and I added the following dependencies for enabling prometheus metrics: <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-actuator</artifactId></dependency><dependency> <groupId>io.micrometer</groupId> <artifactId>micrometer-registry-prometheus</artifactId></dependency> then in my application.properties I have the following properties management.endpoints.web.exposure.include=*management.metrics.enable.all=true I'm trying to run a simple integration test to see my custom metrics appearing at /actuator/prometheus endpoint. Below the code package com.example.demo;import org.junit.jupiter.api.BeforeEach;import org.junit.jupiter.api.Test;import org.springframework.boot.test.context.SpringBootTest;import org.springframework.boot.web.server.LocalServerPort;import static io.restassured.RestAssured.given;@SpringBootTest(webEnvironment = SpringBootTest.WebEnvironment.RANDOM_PORT)public class IntegrationTest { @LocalServerPort private int port; private String baseUrl; @BeforeEach public void setup() { baseUrl = "http://localhost:" + port; } @Test public void metricsEndpoint() throws Exception { given().when().get(baseUrl + "/demo/actuator/prometheus") .then() .statusCode(200); }} The error I get here is java.lang.AssertionError: 1 expectation failed.Expected status code <200> but was <404>. while if I repeat the same request for any other endpoint provided by springboot actuator I correctly geth the response, for example I tried /actuator/health, /actuator/info, /actuator/metrics etc.. This happens only during integration tests with @Springboot annotation and this is strange because if I run my application and make a request with postman to the address localhost:8080/actuator/prometheus I correctly get a response. It is like the prometheus registry is not loaded during tests. Can anyone help? Thanks in advance. EDIT: the solution is the one suggested by Johannes Klug. Adding the annotation @AutoConfigureMetrics solved my problem
Now provide the response and nothing else.
| I faced the same issue. After some tracing through spring-context ConditionEvaluator, I found that the newly introduced @ConditionalOnEnabledMetricsExport("prometheus") condition on PrometheusMetricsExportAutoConfiguration prevented the endpoint from loading. This is intended behavior due to https://github.com/spring-projects/spring-boot/pull/21658 and impacts spring-boot 2.4.x Fix:add @AutoConfigureMetrics to your test @AutoConfigureMetrics@SpringBootTest(webEnvironment = SpringBootTest.WebEnvironment.RANDOM_PORT)public class IntegrationTest { | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/65360650', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/12966300/']} | jdg_382675 |
stackexchange | llm_judgeable_groundtruth_similarity | 2910205 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have two 3rd party libraries that seem to use the same class. That should be fine but I'm getting this type of error when building: ld: duplicate symbol .objc_class_name_CJSONScanner in /Users/myappOne/TapjoyConnect/Frameworks/libTapjoyConnectSimulatorRewardInstall_Ads_Pinch.a(CJSONScanner.o) and /Developer/Projects/BuildOutput/Debug-iphonesimulator/OtherLibrary_d.a(CJSONScanner.o) How can I handle this issue... -- EDIT -- ...if the source files are not available?
Now provide the response and nothing else.
| I'm going to assume that these are two third party libraries that have only provided you with the .a files and not the source code. You can use libtool, lipo and ar on the terminal to extract and recombine the files. To see what architectures are in the file: $ lipo -info libTapjoy.aArchitectures in the fat file: libTapjoy.a are: armv6 i386 Then to extract just armv6, for example: $ lipo -extract_family armv6 -output libTapjoy-armv6.a libTapjoy.a$ mkdir armv6$ cd armv6$ ar -x ../libTapjoy-armv6.a You can then extract the same architecture from the other library into the same directory and then recombine them like so: $ libtool -static -o ../lib-armv6.a *.o And then finally, after you've done this with each architecture, you can combine them again with lipo: $ cd ..$ lipo -create -output lib.a lib-armv6.a lib-i386.a This should get rid of any duplicate symbols, but will also combine the two libraries into one. If you want to keep them separate, or just delete the duplicate from one library, you can modify the process accordingly. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2910205', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/230949/']} | jdg_382676 |
stackexchange | llm_judgeable_groundtruth_similarity | 186663 |
Below is a question asked on the forum unix.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I was looking for a command to limit numbers read in from stdin . I wrote a little script for that purpose (critique is welcome), but I was wondering if there was not a standard command for this, simple and (I think) common use case. My script which finds the minimum of two numbers: #!/bin/bash# $1 limit[ -z "$1" ] && { echo "Needs a limit as first argument." >&2; exit 1; }read numberif [ "$number" -gt "$1" ]; then echo "$1"else echo "$number"fi
Now provide the response and nothing else.
| If you know you are dealing with two integers a and b , then these simple shell arithmetic expansions using the ternary operator are sufficient to give the numerical max: $(( a > b ? a : b )) and numerical min: $(( a < b ? a : b )) E.g. $ a=10$ b=20$ max=$(( a > b ? a : b ))$ min=$(( a < b ? a : b ))$ echo $max20$ echo $min10$ a=30$ max=$(( a > b ? a : b ))$ min=$(( a < b ? a : b ))$ echo $max30$ echo $min20$ Here is a shell script demonstrating this: #!/usr/bin/env bash[ -z "$1" ] && { echo "Needs a limit as first argument." >&2; exit 1; }read numberecho Min: $(( $number < $1 ? $number : $1 ))echo Max: $(( $number > $1 ? $number : $1 )) | {} | {'log_upvote_score': 7, 'links': ['https://unix.stackexchange.com/questions/186663', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/88357/']} | jdg_382677 |
stackexchange | llm_judgeable_groundtruth_similarity | 62678 |
Below is a question asked on the forum physics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
This is perhaps a simple tensor calculus problem -- but I just can't see why... I have notes (in GR) that contains a proof of the statement In space of constant sectional curvature, $K$ is independent of position. Here $$R_{abcd}\equiv K(x)(g_{bd}g_{ac}-g_{ad}g_{bc})$$ where $R_{abcd}$ is the Riemann curvature tensor and $g_{ab}$ is the metric of the spacetime. The proof goes like this: Contract the defining equation with $g^{ac}$, giving $$R_{bd}=3Kg_{bd}.$$ and so on. Problem is I don't understand why the contraction gives $$R_{bd}=3Kg_{bd}.$$ I can see the first term gives $$g^{ac}g_{bd}g_{ac}=4g_{bd}$$ since it's 4D spacetime. But as far as I can tell, the second term gives $g^{ac}g_{ad}g_{bc}=\delta_{bd}$ which is not necessarily $g_{bd}$. Where have I gone wrong?
Now provide the response and nothing else.
| As soon as you get something like $\delta_{bd}$, alarm bells should ring, as this is not a tensor. The inverse metric $g^{ac}$ is defined by the identity$$g^{ac}g_{cb} = \delta^a_b$$If you plug this into your expression (and use the fact that $g$ is symmetric), you will obtain the correct equation. | {} | {'log_upvote_score': 4, 'links': ['https://physics.stackexchange.com/questions/62678', 'https://physics.stackexchange.com', 'https://physics.stackexchange.com/users/23747/']} | jdg_382678 |
stackexchange | llm_judgeable_groundtruth_similarity | 16449386 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am using the QueryDslPredicateExecutor from Spring Data JPA project, and I am facing the need to eager fetch a lazy relation. I know that I can use a native JPA-QL query in the Repository interface, or even used the JPAQLQuery from Query DSL, but I was intrigued if this is even possible in order to facilitate building queries for future needs.
Now provide the response and nothing else.
| I had a similar problem where I had to fetch join a Collection while using Predicates and QueryDslPredicateExecutor. What I did was to create a custom repository implementation to add a method that allowed me to define the entities that should be fetched. Don't be daunted by the amount of code in here, it's actually very simple and you will need to do very few changes to use it on your application This is the interface of the custom repository @NoRepositoryBeanpublic interface JoinFetchCapableRepository<T, ID extends Serializable> extends JpaRepository<T, ID>, QueryDslPredicateExecutor<T> { Page<T> findAll(Predicate predicate, Pageable pageable, JoinDescriptor... joinDescriptors);} JoinDescriptor public class JoinDescriptor { public final EntityPath path; public final JoinType type; private JoinDescriptor(EntityPath path, JoinType type) { this.path = path; this.type = type; } public static JoinDescriptor innerJoin(EntityPath path) { return new JoinDescriptor(path, JoinType.INNERJOIN); } public static JoinDescriptor join(EntityPath path) { return new JoinDescriptor(path, JoinType.JOIN); } public static JoinDescriptor leftJoin(EntityPath path) { return new JoinDescriptor(path, JoinType.LEFTJOIN); } public static JoinDescriptor rightJoin(EntityPath path) { return new JoinDescriptor(path, JoinType.RIGHTJOIN); } public static JoinDescriptor fullJoin(EntityPath path) { return new JoinDescriptor(path, JoinType.FULLJOIN); }} Implementation of the custom repository public class JoinFetchCapableRepositoryImpl <T, ID extends Serializable> extends QueryDslJpaRepository<T, ID> implements JoinFetchCapableRepository<T, ID> { private static final EntityPathResolver DEFAULT_ENTITY_PATH_RESOLVER = SimpleEntityPathResolver.INSTANCE; private final EntityPath<T> path; private final PathBuilder<T> builder; private final Querydsl querydsl; public JoinFetchCapableRepositoryImpl(JpaEntityInformation<T, ID> entityInformation, EntityManager entityManager) { this(entityInformation, entityManager, DEFAULT_ENTITY_PATH_RESOLVER); } public JoinFetchCapableRepositoryImpl(JpaEntityInformation<T, ID> entityInformation, EntityManager entityManager, EntityPathResolver resolver) { super(entityInformation, entityManager, resolver); this.path = resolver.createPath(entityInformation.getJavaType()); this.builder = new PathBuilder<>(path.getType(), path.getMetadata()); this.querydsl = new Querydsl(entityManager, builder); } @Override public Page<T> findAll(Predicate predicate, Pageable pageable, JoinDescriptor... joinDescriptors) { JPQLQuery countQuery = createQuery(predicate); JPQLQuery query = querydsl.applyPagination(pageable, createFetchQuery(predicate, joinDescriptors)); Long total = countQuery.count(); List<T> content = total > pageable.getOffset() ? query.list(path) : Collections.<T> emptyList(); return new PageImpl<>(content, pageable, total); } protected JPQLQuery createFetchQuery(Predicate predicate, JoinDescriptor... joinDescriptors) { JPQLQuery query = querydsl.createQuery(path); for(JoinDescriptor joinDescriptor: joinDescriptors) join(joinDescriptor, query); return query.where(predicate); } private JPQLQuery join(JoinDescriptor joinDescriptor, JPQLQuery query) { switch(joinDescriptor.type) { case DEFAULT: throw new IllegalArgumentException("cross join not supported"); case INNERJOIN: query.innerJoin(joinDescriptor.path); break; case JOIN: query.join(joinDescriptor.path); break; case LEFTJOIN: query.leftJoin(joinDescriptor.path); break; case RIGHTJOIN: query.rightJoin(joinDescriptor.path); break; case FULLJOIN: query.fullJoin(joinDescriptor.path); break; } return query.fetch(); }} Factory to create the custom repositories, replacing the default QueryDslJpaRepository public class JoinFetchCapableQueryDslJpaRepositoryFactoryBean<R extends JpaRepository<T, I>, T, I extends Serializable> extends JpaRepositoryFactoryBean<R, T, I> { protected RepositoryFactorySupport createRepositoryFactory(EntityManager entityManager) { return new JoinFetchCapableQueryDslJpaRepositoryFactory(entityManager); } private static class JoinFetchCapableQueryDslJpaRepositoryFactory<T, I extends Serializable> extends JpaRepositoryFactory { private EntityManager entityManager; public JoinFetchCapableQueryDslJpaRepositoryFactory(EntityManager entityManager) { super(entityManager); this.entityManager = entityManager; } protected Object getTargetRepository(RepositoryMetadata metadata) { return new JoinFetchCapableRepositoryImpl<>(getEntityInformation(metadata.getDomainType()), entityManager); } protected Class<?> getRepositoryBaseClass(RepositoryMetadata metadata) { return JoinFetchCapableRepository.class; } }} Last step is to change the jpa configuration so it uses this factory instead of the default one: <jpa:repositories base-package="com.mycompany.repository" entity-manager-factory-ref="entityManagerFactory" factory-class="com.mycompany.utils.spring.data.JoinFetchCapableQueryDslJpaRepositoryFactoryBean" /> Then you can use it from your service layer like this: public Page<ETicket> list(ETicketSearch eTicket, Pageable pageable) { return eticketRepository.findAll(like(eTicket), pageable, JoinDescriptor.leftJoin(QETicket.eTicket.order));} By using JoinDescriptor you will be able to specify what you want to join based on your service needs. I was able to do this thanks to the Murali's response here: Spring Data JPA and Querydsl to fetch subset of columns using bean/constructor projection Please take a look. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/16449386', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/213882/']} | jdg_382679 |
stackexchange | llm_judgeable_groundtruth_similarity | 53731 |
Below is a question asked on the forum physics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I have just begun studying quantum field theory and am following the book by Peskin and Schroeder for that.So while quantising the Klein Gordon field, we Fourier expand the field and then work only in the momentum space. What is the need for this expansion?
Now provide the response and nothing else.
| First of all, this is just a change of basis, which is up to us to make. Furthermore we should always choose a basis that makes our calculations easier, and hopefully makes things more intuitive. For a simpler example - just try finding the volume of a sphere in cartesian coordinates, its just a bad choice. Second of all, you don't have to use a Fourier basis, to my knowledge everything -loops renormalization etc can be done in a position basis. Now as to why the Fourier basis is a convenient choice: (1) It simplifies derivative terms in the Lagrangian - as usual the Fourier basis turns derivative expressions into algebraic ones, which are much easier to manipulate. (2) It it more intuitive - written in terms of a Fourier basis the Feynman rules are in terms of momentum. So for example at the vertices momentum is conserved - its just a nice tidy way to think about whats happening at the vertex. (3) Even if you start in position space, one method for doing the integrals you will encounter when writing for your loop expressions will be going to momentum space - so you sort of cut this step out from the outset. (4) (following up on Vibert's comment) Plane waves are the basis we do the experiment in. That is, we send in wave packets highly localized in p space, i.e. this is the exact solution we perturb around. | {} | {'log_upvote_score': 4, 'links': ['https://physics.stackexchange.com/questions/53731', 'https://physics.stackexchange.com', 'https://physics.stackexchange.com/users/20871/']} | jdg_382680 |
stackexchange | llm_judgeable_groundtruth_similarity | 4195202 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
We've got a Python-based web server that unpickles a number of large data files on startup using cPickle . The data files (pickled using HIGHEST_PROTOCOL ) are around 0.4 GB on disk and load into memory as about 1.2 GB of Python objects -- this takes about 20 seconds . We're using Python 2.6 on 64-bit Windows machines. The bottleneck is certainly not disk (it takes less than 0.5s to actually read that much data), but memory allocation and object creation (there are millions of objects being created). We want to reduce the 20s to decrease startup time. Is there any way to deserialize more than 1GB of objects into Python much faster than cPickle (like 5-10x)? Because the execution time is bound by memory allocation and object creation, I presume using another unpickling technique such as JSON wouldn't help here. I know some interpreted languages have a way to save their entire memory image as a disk file, so they can load it back into memory all in one go, without allocation/creation for each object. Is there a way to do this, or achieve something similar, in Python?
Now provide the response and nothing else.
| Try the marshal module - it's internal (used by the byte-compiler) and intentionally not advertised much, but it is much faster. Note that it doesn't serialize arbitrary instances like pickle, only builtin types (don't remember the exact constraints, see docs). Also note that the format isn't stable. If you need to initialize multiple processes and can tolerate one process always loaded, there is an elegant solution: load the objects in one process, and then do nothing in it except forking processes on demand. Forking is fast (copy on write) and shares the memory between all processes. [Disclaimers: untested; unlike Ruby , Python ref counting will trigger page copies so this is probably useless if you have huge objects and/or access a small fraction of them.] If your objects contain lots of raw data like numpy arrays, you can memory-map them for much faster startup. pytables is also good for these scenarios. If you'll only use a small part of the objects, then an OO database (like Zope's) can probably help you. Though if you need them all in memory, you will just waste lots of overhead for little gain. (never used one, so this might be nonsense). Maybe other python implementations can do it? Don't know, just a thought... | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/4195202', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/68707/']} | jdg_382681 |
stackexchange | llm_judgeable_groundtruth_similarity | 11770552 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Same as title: How to get Rails.logger printing to the console/stdout when running rspec? Eg. Rails.logger.info "I WANT this to go to console/stdout when rspec is running"puts "Like how the puts function works" I still want Rails.logger to go to log/test.log too.
Now provide the response and nothing else.
| For Rails 4, see this answer. For Rails 3.x, configure a logger in config/environments/test.rb : config.logger = Logger.new(STDOUT)config.logger.level = Logger::ERROR This will interleave any errors that are logged during testing to STDOUT. You may wish to route the output to STDERR or use a different log level instead. Sending these messages to both the console and a log file requires something more robust than Ruby's built-in Logger class. The logging gem will do what you want. Add it to your Gemfile , then set up two appenders in config/environments/test.rb : logger = Logging.logger['test']logger.add_appenders( Logging.appenders.stdout, Logging.appenders.file('example.log'))logger.level = :infoconfig.logger = logger | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/11770552', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1090482/']} | jdg_382682 |
stackexchange | llm_judgeable_groundtruth_similarity | 7231 |
Below is a question asked on the forum mathematica.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Background: consider the following two snippets. GeometricTransformation[{Cyan, Polygon[{{0, 0}, {.2, .6}, {.8, .2}}]}, Table[RotationTransform[2 \[Pi] k/6], {k, 0, 5}]] // Graphics Table[GeometricTransformation[{Opacity[.15*k], Cyan, Polygon[{{0, 0}, {.2, .6}, {.8,.2}}]}, RotationTransform[2 \[Pi] k/6]], {k, 0, 5}] // Graphics I make most of my graphics as in the first example. Because that is ( supposedly ) the most efficient way. But I have to add gradient colors ( and other options later ), I found no other way to do it as in the second example. What I in fact want is this: GeometricTransformation[g, {ListOfTransformations}] where g is some geometry. I want to be able to apply different colors to the transformed g's. But not in the way as done in example 2. Question: How can I apply a different color to the result of a geometric transformation?
Now provide the response and nothing else.
| Here is an alternative that tries to use the "listability" of Polygon for both, the points and the colors. The idea is that all individual polygons and their corresponding (different) colors can be provided as two single lists if we use VertexColors : Graphics@Polygon[#1, VertexColors -> #2] &[ Table[RotationTransform[ 2 Pi k/6][{{0, 0}, {.2, .6}, {.8, .2}}], {k, 0, 5}], Table[{#, #, #} &@Directive[Cyan, Opacity[.15 k]], {k, 0, 5}]] Now although I have to supply two separate tables here, I at least need only one single Polygon command. The separate tables aren't such a big problem, I think, because we have gained a simplification in the graphical part of the code (which is often the slowest). And by using VertexColors , I of course gain some new flexibility that you don't have if you add face colors the "old-fashioned" way. For example, one can do this with only a small modification of the code: Graphics@Polygon[#1, VertexColors -> #2] &[ Table[RotationTransform[ 2 Pi k/6][{{0, 0}, {.2, .6}, {.8, .2}}], {k, 0, 5}], Table[Directive[Hue[#], Opacity[.15 (k + 1)]] & /@ ({.1, .2, .3} (k + 1)), {k, 0, 5}]] | {} | {'log_upvote_score': 4, 'links': ['https://mathematica.stackexchange.com/questions/7231', 'https://mathematica.stackexchange.com', 'https://mathematica.stackexchange.com/users/156/']} | jdg_382683 |
stackexchange | llm_judgeable_groundtruth_similarity | 13132805 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Is it possible to change the order in which the VoiceOver feature for accessibility in iPad reads out the elements, when the 'Two-finger Flick Down' gesture is done? For the attached image, which contains 3 labels and a button, the VoiceOver reads the elements in the following way, Label 1 -> Label 2 -> Button -> Label 3 Can the order be changed to, Label 1 -> Label 2 -> Label 3 -> Button
Now provide the response and nothing else.
| The quickest way to achieve this for your example is to place the three labels in a transparent UIView subclass to serve as a container for your labels. This subclass will have to be properly setup to let VoiceOver know how to interpret it. If your deployment target is iOS6 then you can simply answer the "should group accessibility children" question in this subclass. -(BOOL)shouldGroupAccessibilityChildren{ return YES;} For below iOS6 it would be more complicated, except that your UIView container subclass would contain only UILabels which are accessibility elements. You could implement it like this: -(BOOL)isAccessibilityElement{ return NO;}-(NSInteger)accessibilityElementCount{ return self.subviews.count;}-(id)accessibilityElementAtIndex:(NSInteger)index{ return [self.subviews objectAtIndex:index];}-(NSInteger)indexOfAccessibilityElement:(id)element{ return [self.subviews indexOfObject:element];} I have tested this example code and it does what you are looking for, if you need any clarification please add a comment. Always happy to help make things more accessible. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/13132805', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1263455/']} | jdg_382684 |
stackexchange | llm_judgeable_groundtruth_similarity | 38567796 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm setting up various windows servers to host asp.net core apps, and I need to be able to determine if they have the asp.net hosting bundle installed. https://docs.asp.net/en/latest/publishing/iis.html#install-the-net-core-windows-server-hosting-bundle says: "Install the .NET Core Windows Server Hosting bundle on the server. The bundle will install the .NET Core Runtime, .NET Core Library, and the ASP.NET Core Module. The module creates the reverse-proxy between IIS and the Kestrel server." I'm setting up a deployment, and I need to make sure my server is configured so I can run asp.net core apps. I'm looking, basically, for a registry key or some other way to tell me if I should run the installer setup. (something like the way we'd tell if older versions of the framework are installed, like https://support.microsoft.com/en-us/kb/318785 does for earlier versions)
Now provide the response and nothing else.
| You can use powershell to check if the hosting module is registered with IIS In the local powershell session Import-module WebAdministration$vm_dotnet_core_hosting_module = Get-WebGlobalModule | where-object { $_.name.ToLower() -eq "aspnetcoremodule" }if (!$vm_dotnet_core_hosting_module){ throw ".Net core hosting module is not installed"} If you want to do in the remote session replace first 2 lines with Invoke-Command -Session $Session {Import-module WebAdministration}$vm_dotnet_core_hosting_module = Invoke-Command -Session $Session {Get-WebGlobalModule | where-object { $_.name.ToLower() -eq "aspnetcoremodule" }} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/38567796', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/81377/']} | jdg_382685 |
stackexchange | llm_judgeable_groundtruth_similarity | 14360822 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have the following code, it works but I am trying to separate SUM for each Banksphere.servicio_id column, this code SUM only one servicio_id... I'm a bit lost, can someone help me? As you can see, every WHERE clause is exactly the same but Banksphere.peticion_id which is the only one that changes... So maybe there's some better way just to filter once the common clauses and leave only peticion_id for OK and KO? SELECT(SELECT SUM(valor)FROM BanksphereWHERE Banksphere.fecha = '2013-01-14'AND Banksphere.servicio_id = '6'AND Banksphere.entidad_id = '2'AND Banksphere.peticion_id = '0') AS OK,(SELECT SUM(valor)FROM BanksphereWHERE Banksphere.fecha = '2013-01-14'AND Banksphere.servicio_id = '6'AND Banksphere.entidad_id = '2'AND Banksphere.peticion_id = '1') AS KO EDIT WITH WORKING CODE SELECT Servicios.nombre as servicio, SUM(case when peticion_id = '0' then valor end) as OK, SUM(case when peticion_id = '1' then valor end) as KOFROM BanksphereINNER JOIN ServiciosON Banksphere.servicio_id = Servicios.idWHERE Banksphere.fecha = '2013-01-14' AND Banksphere.entidad_id = '2' AND Banksphere.peticion_id in ('0', '1')group by Servicios.nombre
Now provide the response and nothing else.
| I think you want something along these lines: SELECT banksphere.servicio_id, SUM(valor), SUM(case when peticion_id = '0' then valor end) as OK, SUM(case when peticion_id = '1' then valor end) as KOFROM BanksphereWHERE Banksphere.fecha = '2013-01-14' AND Banksphere.entidad_id = '2' AND Banksphere.peticion_id in ('0', '1', ...)group by banksphere.servicio_id This has a group by so you can get multiple "servicio_ids" and it adds separate columns for OK and KO. If you want only servicio_id = 6, then add that back into the where clause. And, you might want other variables in the group by as well, but you only mention service in the question. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/14360822', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1381537/']} | jdg_382686 |
stackexchange | llm_judgeable_groundtruth_similarity | 18640169 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am having a strange problem. I have successfully ran this code on my laptop, but when I try to run it on another machine first I get this warning Distribution not specified, assuming bernoulli ..., which I expect but then I get this error: Error in object$var.levels[[i]] : subscript out of bounds library(gbm)gbm.tmp <- gbm(subxy$presence ~ btyme + stsmi + styma + bathy, data=subxy, var.monotone=rep(0, length= 4), n.trees=2000, interaction.depth=3, n.minobsinnode=10, shrinkage=0.01, bag.fraction=0.5, train.fraction=1, verbose=F, cv.folds=10) Can anybody help? The data structures are exactly the same, same code, same R. I am not even using a subscript here. EDIT: traceback() 6: predict.gbm(model, newdata = my.data, n.trees = best.iter.cv)5: predict(model, newdata = my.data, n.trees = best.iter.cv)4: predict(model, newdata = my.data, n.trees = best.iter.cv)3: gbmCrossValPredictions(cv.models, cv.folds, cv.group, best.iter.cv, distribution, data[i.train, ], y)2: gbmCrossVal(cv.folds, nTrain, n.cores, class.stratify.cv, data, x, y, offset, distribution, w, var.monotone, n.trees, interaction.depth, n.minobsinnode, shrinkage, bag.fraction, var.names, response.name, group)1: gbm(subxy$presence ~ btyme + stsmi + styma + bathy, data = subxy,var.monotone = rep(0, length = 4), n.trees = 2000, interaction.depth = 3, n.minobsinnode = 10, shrinkage = 0.01, bag.fraction = 0.5, train.fraction = 1, verbose = F, cv.folds = 10) Could it have something to do because I moved the saved R workspace to another machine? EDIT 2: ok so I have updated the gbm package on the machine where the code was working and now I get the same error. So at this point I am thinking that the older gbm package did perhaps not have this check in place or that the newer version has some problem. I don't understand gbm well enough to say.
Now provide the response and nothing else.
| just a hunch since I can't see you data, but I believe that error occurs when you have variable levels that exist in the test set which don't exist in the training set. this can easily happen when you have a factor variable with a high number of levels, or one level has a low number of instances. since you're using CV folds, it's possible the holdout set on one of the loops has foreign levels to the training data. I'd suggest either: A) use model.matrix() to one-hot encode your factor variables B) keep setting different seeds until you get a CV split that doesn't have this error occur. EDIT: yep, with that traceback, your 3rd CV holdout has a factor level in its test set that doesn't exist in the training. so the predict function sees a foreign value and doesn't know what to do. EDIT 2: Here's a quick example to show what I mean by "factor levels not in the test set" #Example data with low occurrences of a factor level:set.seed(222)data = data.frame(cbind( y = sample(0:1, 10, replace = TRUE), x1 = rnorm(10), x2 = as.factor(sample(0:10, 10, replace = TRUE))))data$x2 = as.factor(data$x2)data y x1 x2 [1,] 1 -0.2468959 2 [2,] 0 -1.2155609 6 [3,] 0 1.5614051 1 [4,] 0 0.4273102 5 [5,] 1 -1.2010235 5 [6,] 1 1.0524585 8 [7,] 0 -1.3050636 6 [8,] 0 -0.6926076 4 [9,] 1 0.6026489 3[10,] 0 -0.1977531 7#CV fold. This splits a model to be trained on 80% of the data, then tests against the remaining 20%. This is a simpler version of what happens when you call gbm's CV fold.CV_train_rows = sample(1:10, 8, replace = FALSE) ; CV_test_rows = setdiff(1:10, CV_train_rows)CV_train = data[CV_train_rows,] ; CV_test = data[CV_test_rows,]#build a model on the training... CV_model = lm(y ~ ., data = CV_train)summary(CV_model)#note here: as the model has been built, it was only fed factor levels (3, 4, 5, 6, 7, 8) for variable x2CV_test$x2#in the test set, there are only levels 1 and 2.#attempt to predict on the test setpredict(CV_model, CV_test)Error in model.frame.default(Terms, newdata, na.action = na.action, xlev = object$xlevels) : factor x2 has new levels 1, 2 | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/18640169', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2319308/']} | jdg_382687 |
stackexchange | llm_judgeable_groundtruth_similarity | 312 |
Below is a question asked on the forum politics.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I was browsing the Wikipedia article on Voting age and the following map struck me. The colours refer to different ages, full legend here : Regardless of other restrictions (only men, only one party, etc.), this map seems to show every single country in the world has some form of elections. Is there any country with no elections at all? See also: Are there countries considered socialist that do NOT have parlaments and elections?
Now provide the response and nothing else.
| Based on this Wiki article and its links: Brunei seems to have no elections (see details in @gerrit's asnwer) Qatar has no elections. But this will presumably no longer be true in 2013 he Consultative Assembly (Majlis as-Shura) has 35 appointed members with only consultative tasks. However, the 2003 Constitution of Qatar calls for a 45 member elected Legislature, which is to be made up of 30 elected representatives and 15 appointed by the Emir. In 2006, Prime Minister Al Thani – then the Deputy PM – announced that elections would be held in 2007. However, only a legislative council to review the subject was created that year. The actual elections have been postponed three times; most recently in June 2010 3 , when the Emir extended the Consultative Assembly's tenure until 2013 Oman is kind of an edge case. You can make arguments that it has elections, and arguments that it does not - the actual process is caucuses selecting representatives, and Sultan appointing them; and the parliamentary body has no true legislative powers either. Saudi Arabia only has municipal level elections , but not country level. Somalia didn't have elections between 1980 and 2012 . No longer true as they held an election in 2012. UAE (United Arab Emirates) is another reason to quibble . The Federal National Council (al-Majlis al-Watani al-Ittihadi) is the UAE’s legislative body and consists of 40 members. Half are appointed by the rulers of their respective emirates, and hold all of the council's political power . The other half, who have only advisory tasks and serve two-year terms, are elected by a 6,689-member electoral college whose members are appointed by the emirates. | {} | {'log_upvote_score': 6, 'links': ['https://politics.stackexchange.com/questions/312', 'https://politics.stackexchange.com', 'https://politics.stackexchange.com/users/130/']} | jdg_382688 |
stackexchange | llm_judgeable_groundtruth_similarity | 6933096 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Edit: It appears I was a bit confused on what I was trying to accomplish. For those that took the time to explain this, thank you. I'm trying to create a two dimensional array in Jquery/Javascript. I've done a decent amount of searching, testing and more searching but i'm unable to find a solution that really makes sense to me. (it's been a very long week already....) Below is the desired format of the array. {"product":[{"attribute":"value","attribute":"value"}]}
Now provide the response and nothing else.
| That's not a 2D array, but rather an object. Also, your product array contains only one object. I think you need something like this: var obj = {};obj.product = [];for(var i=0; i < someObj.length; i++) { obj.product.push[{"attribute": someObj[i]}]} This will produce an array inside the product property: {"product":[{"attribute":"value"}, {"attribute":"value"}]} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/6933096', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/261312/']} | jdg_382689 |
stackexchange | llm_judgeable_groundtruth_similarity | 5072155 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a contenteditable div, like so: <div id="test" contentEditable="true" style="width: 600px; height:300px;">Lorem ipsum dolor sit amet</div> for which I use the following code: <input type="button" value="Click me" onclick="alert(window.getSelection().focusOffset.toString());"></button> Clicking on the button when I move the caret around in the div, returns to me the actual position (offset) of the caret within the div. The problem is when I replace the contenteditable div with an input type=text or password control, and keep the contenteditable property=true, and click on the button, I always get a zero. Why is this? Thanks for looking.
Now provide the response and nothing else.
| In most browsers, window.getSelection() only works with selections within text nodes and elements within the document. It doesn't apply to text within <input> and <textarea> elements (although in WebKit window.getSelection().toString() will return the selected text within a focussed text input or textarea. See http://jsfiddle.net/PUdaS/ ). To get the selection within an input, use the input's selectionStart and selectionEnd properties: <input type="text" id="test" value="Some text"><input type="button" value="Click me" onclick="alert(document.getElementById('test').selectionEnd);"> Note that IE up to and including version 8 does not support the selectionStart and selectionEnd properties, and a different, more complicated solution is required. IE doesn't support window.getSelection() either, so this code will work in all the browsers your original code does. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/5072155', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/378628/']} | jdg_382690 |
stackexchange | llm_judgeable_groundtruth_similarity | 45655412 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I need to import some training data from my local directory into a python program. Currently I am following a tutorial and in this tutorial the data is imported with the help of the following code: from tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("/tmp/data/", one_hot = True) But my problem is that my data is present in my local directory so I cannot use this approach. Your help will be highly appreciated. My local directory contains multiple files and I have to import them all through one variable.
Now provide the response and nothing else.
| You have some options for this, and like most things, you can go the easy route (Nick Coons posted a good example as I'm typing this) or progressively more involved routes. Here are some questions to ask yourself about how you see this working: Do you want uniformity in your measurements? (Do you want to always show "tsp" for teaspoon, or can it be freeform as in Nick's example) How often will you need to add units? Will you need to add the dram or hogshead, or whatever as units as time goes on, or will you probably just stick to the basics? A good middle ground would be something like CREATE TABLE `recipe` ( `recipe_id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT, `name` VARCHAR(128) DEFAULT NULL, `description` TEXT, `instructions` TEXT, PRIMARY KEY (`recipe_id`))CREATE TABLE `ingredient` ( `ingredient_id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT, `recipe_id` INT(10) UNSIGNED NOT NULL, `ingredient` VARCHAR(64) DEFAULT NULL, `amount` DECIMAL(4, 2) DEFAULT NULL, `unit` ENUM ('tsp', 'tbsp', 'oz', 'g', 'lb', 'cup', 'gallon', 'pinch') DEFAULT NULL, PRIMARY KEY (`ingredient_id`)) This satisfies #1 by enforcing a set of units, which is nice. The downside is that you have to alter your table to update the units. It also may be more difficult to keep your front end up to date with the valid choices. Next, you could add a table for units and reference it via foreign key from the ingredients table like so: CREATE TABLE `unit` ( `unit_id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT, `label` VARCHAR(64) DEFAULT NULL, `sort` INT(10) UNSIGNED NOT NULL DEFAULT 0, PRIMARY KEY (`unit_id`), UNIQUE KEY `unit_label_uk` (`label`))CREATE TABLE `ingredient` ( `ingredient_id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT, `unit_id` INT(10) UNSIGNED NOT NULL, `recipe_id` INT(10) UNSIGNED NOT NULL, `ingredient` VARCHAR(64) DEFAULT NULL, `amount` DECIMAL(4, 2) DEFAULT NULL, `sort` INT(10) UNSIGNED NOT NULL DEFAULT 0, PRIMARY KEY (`ingredient_id`)) This satisfies #1 and #2, allowing you to easily manage your units and access the list for use in your front end, so you don't have to alter your front end when you change units. From there you could spin off into space coming up with ways to handle unit conversion, etc. but that is probably overkill for what you're trying to do. EDIT:Per your comment, I would set it up like this: CREATE TABLE `recipe` ( `recipe_id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT, `name` VARCHAR(128) NOT NULL, `description` TEXT, `instructions` TEXT, PRIMARY KEY (`recipe_id`))CREATE TABLE `ingredient` ( `ingredient_id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT, `label` VARCHAR(64) NOT NULL, `sort` INT(10) UNSIGNED NOT NULL DEFAULT 0, PRIMARY KEY (`ingredient_id`) UNIQUE KEY `ingredient_label_uk` (`label`))CREATE TABLE `unit` ( `unit_id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT, `label` VARCHAR(64) DEFAULT NULL, `sort` INT(10) UNSIGNED NOT NULL DEFAULT 0, PRIMARY KEY (`unit_id`), UNIQUE KEY `unit_label_uk` (`label`))CREATE TABLE `recipe_ingredient` ( `recipe_ingredient_id` INT(10) UNSIGNED NOT NULL AUTO_INCREMENT, `recipe_id` INT(10) UNSIGNED NOT NULL, `ingredient_id` INT(10) UNSIGNED NOT NULL, `unit_id` INT(10) UNSIGNED NOT NULL, `amount` DECIMAL(4, 2) DEFAULT NULL, `sort` INT(10) UNSIGNED NOT NULL DEFAULT 0, PRIMARY KEY (`recipe_ingredient_id`)) Your recipe_ingredient table is doing the bulk of the work here, tying everything together. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/45655412', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/8405618/']} | jdg_382691 |
stackexchange | llm_judgeable_groundtruth_similarity | 33556050 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have the following series: s = pd.Series([['a', 'b'], ['c', 'd'], ['f', 'g']])>>> s0 [a, b]1 [c, d]2 [f, g]dtype: object what is the easiest - preferably vectorized - way to concatenate all lists in the series, so that I get: l = ['a', 'b', 'c', 'd', 'f', 'g'] Thanks!
Now provide the response and nothing else.
| A nested list comprehension should be much faster. >>> [element for list_ in s for element in list_] ['a', 'b', 'c', 'd', 'f', 'g']>>> %timeit -n 100000 [element for list_ in s for element in list_]100000 loops, best of 3: 5.2 µs per loop>>> %timeit -n 100000 s.sum()100000 loops, best of 3: 50.7 µs per loop Directly accessing the values of the list is even faster. >>> %timeit -n 100000 [element for list_ in s.values for element in list_]100000 loops, best of 3: 2.77 µs per loop | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/33556050', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4380945/']} | jdg_382692 |
stackexchange | llm_judgeable_groundtruth_similarity | 2382855 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a page where I load a table of information using ajax. Once the table is loaded I use jQuery to wire up some event handlers on the table's rows. From that page it's possible for the user to refresh that table. My jQuery code to refresh the table looks something like this: $.post("/myurl", { id: 0}, function (d) { $("tblWrapper").html(d); //Wire events $("table tr", $("tblWrapper")).click(function (e) { ... }); ...etc }, "text"); I've noticed that after doing this several times that the page will respond very sluggishly when I try to do any scrolling or animation in IE8. My question is, what am I doing wrong, that makes it get slower and slower? Can I clean up the old html/event handlers before replacing it with new html and new handlers? I had thought JS engine might do that automatically. Maybe it does and its just slow to do the cleanup, it I don't know. I've noticed CPU time on IExplorer goes to like 50%. I'd greatly appreciate any help.
Now provide the response and nothing else.
| Your checkElements() function is not marked as const so you can't call it on const qualified objects. top() , however is const qualified so in top() , this is a pointer to a const Stack (even if the Stack instance on which top() was called happens to be non- const ), so you can't call checkElements() which always requires a non- const instance. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/2382855', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/169867/']} | jdg_382693 |
stackexchange | llm_judgeable_groundtruth_similarity | 19576202 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm trying to create an input mask for a EU money field using http://jquerypriceformat.com/ So far in my directive, the input shows correctly to the user with the mask applied, but I believe there's something wrong, because the POST values are being sent with weird formatting, totally different than what we see in the input field. I include the priceformat.js <script src="js/jquery.price_format.1.8.min.js"></script><input type="text" currency-input ng-model...> And on angular: app.directive('currencyInput', function() { return { require: '?ngModel', link: function($scope, element, attrs, controller) { element.priceFormat({ prefix: '', centsSeparator: ',', thousandsSeparator: '.' }); } };}); My input shows the value with the mask correctly, but on POST data (called by angular) it's a different value, what am I missing? input > 2.200,80 | post > 22,0080 Thanks
Now provide the response and nothing else.
| From your example I don't see that link returns something. I would write directive something like: .directive('format', ['$filter', function ($filter) { return { require: '?ngModel', link: function (scope, elem, attrs, ctrl) { if (!ctrl) return; ctrl.$formatters.unshift(function (a) { return $filter(attrs.format)(ctrl.$modelValue) }); ctrl.$parsers.unshift(function (viewValue) { elem.priceFormat({ prefix: '', centsSeparator: ',', thousandsSeparator: '.' }); return elem[0].value; }); } };}]); Demo 1 Fiddle If you want on start fire the filter, use $formatters : Now link is: link: function (scope, elem, attrs, ctrl) { if (!ctrl) return; var format = { prefix: '', centsSeparator: ',', thousandsSeparator: '' }; ctrl.$parsers.unshift(function (value) { elem.priceFormat(format); return elem[0].value; }); ctrl.$formatters.unshift(function (value) { elem[0].value = ctrl.$modelValue * 100 ; elem.priceFormat(format); return elem[0].value; }) } Demo 2 Fiddle | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/19576202', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/165084/']} | jdg_382694 |
stackexchange | llm_judgeable_groundtruth_similarity | 30556196 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Yesterday I decided to try Polymer 1.0 and I'm already facing difficulties when trying to styling the paper-toolbar. The documentation says that the background colour can be changed by using:--paper-toolbar-background But how can I use it on CSS? I tried the following: paper-toolbar { --paper-toolbar-background: #e5e5e5; } Also this: paper-toolbar { --paper-toolbar { background: #e5e5e5; } } But neither worked. What is the correct way to do it? Thanks.
Now provide the response and nothing else.
| If you are styling it on your main page, then you have to apply styles using <style is='custom-style'> . This is to make Custom CSS Properties work. Applying is relatively easy. paper-toolbar provides 2 custom properties and one mixin. --paper-toolbar-background is a property that changes the background color of the toolbar while --paper-toolbar-color changes its foreground color. --paper-toolbar is a mixin applied to the toolbar. To use these properties is just the same as applying styles in your elements. As an example <style is="custom-style"> paper-toolbar { --paper-toolbar-background: #00f; /* changes the background to blue*/ --paper-toolbar-color: #0f0; /* changes the foreground color to green */ --paper-toolbar: { font-size: 40px; /* Change default font size */ }; /* Notice the semicolon here */ }</style> | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/30556196', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1438187/']} | jdg_382695 |
stackexchange | llm_judgeable_groundtruth_similarity | 13630849 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have local changes to a file that I don't want to commit to my repository. It is a configuration file for building the application on a server, but I want to build locally with different settings. Naturally, the file always shows up when I do 'git status' as something to be staged. I would like to hide this particular change and not commit it. I won't make any other changes to the file. To clarify, using .gitignore is not what I want since that only prevents new files from being added. I want to ignore changes to a file already in the repository. After some digging around, I see 2 options: assume-unchanged and skip-worktree . A previous question here talks about them but doesn't really explain their differences. How are the two commands different? Why would someone use one or the other?
Now provide the response and nothing else.
| You want skip-worktree . assume-unchanged is designed for cases where it is expensive to check whether a group of files have been modified; when you set the bit, git (of course) assumes the files corresponding to that portion of the index have not been modified in the working copy. So it avoids a mess of stat calls. This bit is lost whenever the file's entry in the index changes (so, when the file is changed upstream). skip-worktree is more than that: even where git knows that the file has been modified (or needs to be modified by a reset --hard or the like), it will pretend it has not been, using the version from the index instead. This persists until the index is discarded. There is a good summary of the ramifications of this difference and the typical use cases here: http://fallengamer.livejournal.com/93321.html . From that article: --assume-unchanged assumes that a developer shouldn’t change a file. This flag is meant for improving performance for not-changing folders like SDKs. --skip-worktree is useful when you instruct git not to touch a specific file ever because developers should change it. For example, if the main repository upstream hosts some production-ready configuration files and you don’t want to accidentally commit changes to those files, --skip-worktree is exactly what you want. | {} | {'log_upvote_score': 11, 'links': ['https://Stackoverflow.com/questions/13630849', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1668964/']} | jdg_382696 |
stackexchange | llm_judgeable_groundtruth_similarity | 1269 |
Below is a question asked on the forum astronomy.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
In reference to the question, "How can we tell that the milky way is a spiral galaxy?" The answers there clearly sum up the question asked. But Milky Way is not just a spiral galaxy. It is further classified as a barred spiral galaxy. Question: Which particular feature in the distribution of stars, or in general a feature in observations led us to believe that it is a barred galaxy? Note: The edge-on picture is not sufficient to establish it, since a dense distribution at smaller radii could also arise from a non-uniform density on the spiral disk if modeled to fit the observations. We don't have any data from other angles or orientations.
Now provide the response and nothing else.
| There are several different lines of evidence which together form a coherent picture: that of a barred galaxy. Moreover, as most disc galaxies are barred, we should expect the same from the Milky Way. The various evidences are: The observed light distribution (2MASS) shows a left-right asymmetry in brightness and the vertical height. This is explained by the near end of the bar being located on that side. The distribution of magnitudes of red-clump stars (which have very nearly the same luminosity) is split towards the Galactic centre, as expected from a boxy/peanut bulge (which is always associated with a bar). The observed gas velocities show velocities which are "forbidden" in an axisymmetric or near-axisymmetric (spiral arms only) galaxy. These velocities occur naturally from the orbits of gas in a barred potential. The velocity distribution of stars in the Solar neighbourhood shows some asymmetries and clumping which is most naturally explained by orbital resonance with the bar rotation. The extent, pattern speed, and orientation of the bar is consistent between all of these. | {} | {'log_upvote_score': 6, 'links': ['https://astronomy.stackexchange.com/questions/1269', 'https://astronomy.stackexchange.com', 'https://astronomy.stackexchange.com/users/63/']} | jdg_382697 |
stackexchange | llm_judgeable_groundtruth_similarity | 36072327 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
We are trying to invoke the TFS 2015 REST API's from a web-page using Javascript and have a challenge in establishing valid authentication with the TFS server. We do not know how to generate a personal access tokens or an OAuth access tokens. The instruction below seem to apply more toward VSO than on-premise TFS. https://www.visualstudio.com/en-us/integrate/get-started/rest/basics How can I generate an authentication key/token? UPDATE: As on Mar 2017, the latest release of On-Prem TFS supports creating personal access tokens for all users. Using the below javascript code by @Elmar you can make requests to update, edit TFS workitems from REST API.
Now provide the response and nothing else.
| The OAuth mechanism is used against the VSO api at the time of writing this as you've seemingly identified. official docs for VSO OAuth tokens here . For on-prem however, the following is required: Via a javascript client (note I'm using jquery for the ajax request here) Since alternative creds or token based auth isn't available on-prem to match current vso implementation; You can consider the following approach: If you have admin permissions on the TFS app tier, you can configure basic authentication for the tfs application in IIS, and set the default domain . And then invoke as follows: var self = this; self.tasksURI = 'https://<SERVER>/tfs/<COLLECTION>/<PROJECT>/_apis/build/builds?api-version=2.0'; self.username = "<USERNAME>"; //basic username so no domain here. self.password = "<PASSWORD>"; self.ajax = function (uri, method, data) { var request = { url: uri, type: method, contentType: "application/json", accepts: "application/json", cache: false, dataType: 'json', data: JSON.stringify(data), beforeSend: function (xhr) { xhr.setRequestHeader("Authorization", "Basic " + btoa(self.username + ":" + self.password)); }, error: function (jqXHR) { console.log("ajax error " + jqXHR.status); } }; return $.ajax(request); } self.ajax(self.tasksURI, 'GET').done(function (data) { alert(data); }); IMPORTANT NOTE! : If you enable basic auth you really should configure your site to use https too or your credentials will be sent in clear text (as indicated in the warning seen -> top right of the image above). Via a .NET client In on-prem (currently rtm'd: 2015 update 1) the api is generally gated/fenced off with NTLM, meaning a pre-flight request is made, 401 returned from server to challenge for auth, in this case, setting the request Credential as follows allows the request to auth against the server once the preflight challenge is received.To accommodate the challenge you can do this: request.Credentials = new NetworkCredential(this.UserName, this.Password);//you may want to specify a domain too If you've enabled basic auth for tfs on prem you can attempt authenticating as follows, this pattern matches the mechanism used when invoking vso after enabling alternative credentials in the ui: request.Headers[HttpRequestHeader.Authorization] = "Basic " + Convert.ToBase64String(Encoding.UTF8.GetBytes(this.UserName + ":" + this.Password)); Note: In some code I modified a few weeks ago; support for both VSO and on-prem was required so I used the two patterns above to deal with the specific scenario. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/36072327', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1185842/']} | jdg_382698 |
stackexchange | llm_judgeable_groundtruth_similarity | 944436 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I know that I can use $.html to set the HTML content of something, and $.text to set the content (and that this escapes the HTML). Unfortunately, I'm using $.append , which doesn't escape the HTML. I've got something like this: function onTimer() { $.getJSON(url, function(data) { $.each(data, function(i, item) { $('#messages').append(item); } }} ...where the url returns an array of strings. Unfortunately, if one of those strings is (e.g.) <script>alert('Hello')</script> , this gets executed. How do I get it to escape HTML?
Now provide the response and nothing else.
| Check out how jQuery does it: text: function( text ) { if ( typeof text !== "object" && text != null ) return this.empty().append( (this[0] && this[0].ownerDocument || document).createTextNode( text ) ); var ret = ""; jQuery.each( text || this, function(){ jQuery.each( this.childNodes, function(){ if ( this.nodeType != 8 ) ret += this.nodeType != 1 ? this.nodeValue : jQuery.fn.text( [ this ] ); }); }); return ret;}, So something like this should do it: $('#mydiv').append( document.createTextNode('<b>Hey There!</b>')); EDIT : Regarding your example, it's as simple as: $('#messages').append(document.createTextNode(item)); | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/944436', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/8446/']} | jdg_382699 |
stackexchange | llm_judgeable_groundtruth_similarity | 1083959 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
In C++ it is possible to create a struct: struct MyStruct{ ...} And also possible to do the following: typedef struct{ ...} MyStruct; And yet as far as I can tell, no discernable difference between the two. Which is preferable? Why do both ways exist if there is no difference? Is one better than the other in style or readability?
Now provide the response and nothing else.
| The typedef version is a special case of typedef foo bar; which defines a new "type" bar as an alias for foo. In your case, foo happens to be a struct. In C, this was the only way to introduce new "types" (in quotes, because they are not really equivalent to int, float and co). In C++, this is not so useful, because C++ was designed to make definition of new types easier and more complete than C (at least at the beginnings of C++), and the typedef is not even necessary to refer to a previously declared struct (or class). | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/1083959', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/112765/']} | jdg_382700 |
stackexchange | llm_judgeable_groundtruth_similarity | 21646658 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm currently working on a Python program that uses 2D OpenGL graphics. It's mostly intended for use with large screen resolution and a relatively slow computer, so, while it's all working fine, it could use some performance gain by optimizing the graphics. So here's what I've got: the screen background is formed from multiple images on program startup, and never changes afterwards. So, I'm wondering if it is possible to write the resulting screen data into a buffer, which is then constantly used in the main drawing loop, to bypass all the functions involved in drawing the background. So here's what I'd like to do: def drawBackground(self): #Called once on startup for item in BackObjects: item.draw() # [CODE HERE] Writing the screen pixel data to a buffer (a lower layer?)def drawObjects(self): #Called in the main drawing loop # [CODE HERE] Clear the buffer (possibly only the top layer?) glLoadIdentity() glPushMatrix() # [CODE HERE] Read the previously defined background buffer to the screen? for item in FrontObjects: item.draw() glPopMatrix() glutSwapBuffers() I've read through the manual on the different GL functions related to buffers, and tried using the ones such as glDrawBuffer() and glReadBuffer(), but haven't quite figured out how to get that working... So, if I want to have 2 drawing layers, one of which always remains unchanged, how should I operate the buffers to do that, maximizing the program's performance? I'd appreciate if you could provide an example code based on what I've posted above!
Now provide the response and nothing else.
| Under Windows stdout is a wrapper to the low-level functions accessing the handle returned by GetStdHandle(STD_OUTPUT_HANDLE) . When starting a non-console application by double-clicking (I tried under Windows 7, 64 bit) then GetStdHandle(STD_OUTPUT_HANDLE) will return an invalid handle. This means that printf and other commands will write nothing at all but the low-level functions internally called by printf will return an error code. However as already said even a non-console program can be started the following way: program_name > output_file.txt In this case the printf output will be written to the output file. -- EDIT -- If you wish to "catch" the printf() output and write it to MessageBox() there are two ways to achieve this: The first one is running the program twice while the input of one instance is the standard output of the other one. The behavior could be explained by the following command line: program_name | program_name /msgbox The second possibility works without running two programs and without running the program twice: You may hook file handle #1. This should be at least possible when using msvcrt.dll: HANDLE hRead,hWrite;CreatePipe(&hRead,&hWrite,NULL,0);dup2(_open_osfhandle(hWrite,O_WRONLY),1);// Now printf() output can be read from handle hReadprintf("Hello world 2!\n");// In a separate thread do:ReadFile(hRead,...); | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/21646658', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3287187/']} | jdg_382701 |
stackexchange | llm_judgeable_groundtruth_similarity | 146741 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
While studying some CA, I ran across methods of evaluating $$\int_0^\infty \frac{\sin x}{x} \, dx, \;\ \int_0^\infty \frac{\sin^2 x}{x^2} \, dx, \;\ \text{and} \ \int_0^\infty \frac{\sin^3 x}{x^{3}} \, dx.$$ Is there a way to find a closed form for $$\int_0^\infty \frac{\sin^n x}{x^n} \, dx, \ n \in \mathbb{N}_{>0} ?$$ Rather it be contour integration or some clever method using real analysis.
Now provide the response and nothing else.
| $$ \int_0^\infty \frac{\sin^n(x)}{x^n} \mathrm{d} x = \frac{\pi}{2^{n+1} \cdot (n-1)!} \sum_{k=0}^n (-1)^{n-k} \binom{n}{k} (2k-n)^{n-1} \operatorname{sign}(2k-n)$$ where $\operatorname{sign}(x) = \cases{ 1 & $x > 0$ \\ 0 & $x = 0$\\ -1 & $x < 0$}$. As to the (probabilistic) proof, notice that $\frac{\sin(t)}{t}$ is the characteristic function of a uniform random variable on $(-1,1)$. The sum of $n$ independent identically distributed such uniform random variables is known as Irwin-Hall random variable $Y_n$, and the integral in question is a multiple of its PDF evaluated at $x=0$:$$ \phi_{Y_n}(x) = \frac{1}{2 \pi} \int_{-\infty}^\infty \frac{\sin^n(t)}{t^n} \mathrm{e}^{-i t x} \mathrm{d} t = \frac{1}{\pi} \int_{0}^\infty \frac{\sin^n(t)}{t^n} \cos(t x) \mathrm{d} t$$The closed form for the PDF is given on the wikipedia with the reference. As to more explicit derivation. We first integrate by parts, $n-1$ times, then use binomial theorem for $\sin^n(x)$:$$ \begin{eqnarray} \int_0^\infty \frac{\sin^n(x)}{x^n} \mathrm{d} x &=& \int_0^\infty \frac{\mathrm{d}^{n-1}}{\mathrm{d} x^{n-1}}\left( \sin^n(x) \right) \frac{1}{(n-1)!}\frac{\mathrm{d} x}{x} \\ &=& \frac{1}{(n-1)!} \int_0^\infty \frac{1}{2^n i^n} \sum_{k=0}^n (-1)^{n-k} \binom{n}{k} \frac{\mathrm{d}^{n-1}}{\mathrm{d} x^{n-1}}\left( \mathrm{e}^{i (2k-n)x} \right) \frac{\mathrm{d} x}{x} \\ &=& \frac{1}{(n-1)!} \int_0^\infty \frac{1}{2^n i^n} \sum_{k=0}^n (-1)^{n-k} \binom{n}{k} \left(i (2k-n)\right)^{n-1} \mathrm{e}^{i (2k-n)x} \frac{\mathrm{d} x}{x} \\ &=& \frac{1}{(n-1)!} \int_0^\infty \frac{1}{2^n} \sum_{k=0}^n (-1)^{n-k} \binom{n}{k} \left((2k-n)\right)^{n-1} \sin((2k-n)x) \frac{\mathrm{d} x}{x} \end{eqnarray}$$In the last line, $\mathrm{e}^{i (2k-n) x}$ was expanded use Euler's formula, and since the sum is real, only real summands are retained. Then, integrating term-wise nails it:$$ \begin{eqnarray} \int_0^\infty \frac{\sin^n(x)}{x^n} \mathrm{d} x &=& \frac{1}{2^n} \frac{1}{(n-1)!} \sum_{k=0}^n (-1)^{n-k} \binom{n}{k} \left((2k-n)\right)^{n-1} \int_0^\infty \sin((2k-n)x) \frac{\mathrm{d} x}{x} \\ &=& \frac{1}{2^n} \frac{1}{(n-1)!} \sum_{k=0}^n (-1)^{n-k} \binom{n}{k} \left((2k-n)\right)^{n-1} \frac{\pi}{2} \operatorname{sign}(2k-n)\end{eqnarray}$$ | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/146741', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/13295/']} | jdg_382702 |
stackexchange | llm_judgeable_groundtruth_similarity | 8716824 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I recently had to change the linkage specification of several classes and ran into a problem. Two of the classes contain a std::map with a std::unique_ptr as the value type. After the linkage was changed the compiler started complaining with "cannot access private member declared in class 'std::unique_ptr<_Ty>'" errors. Anyone know why this only happens when an export specification is supplied or have a solution? Sample Code: #include <map>struct SomeInterface{ virtual ~SomeInterface() = 0;};// This class compiles with no problemsstruct LocalClass{ std::map<int, std::unique_ptr<SomeInterface>> mData;};// This class fails to compilestruct __declspec(dllexport) ExportedClass{ std::map<int, std::unique_ptr<SomeInterface>> mData;}; Compiler output: c:\program files (x86)\microsoft visual studio 10.0\vc\include\utility(163): error C2248: 'std::unique_ptr<_Ty>::unique_ptr' : cannot access private member declared in class 'std::unique_ptr<_Ty>' with [ _Ty=SomeInterface ] c:\program files (x86)\microsoft visual studio 10.0\vc\include\memory(2347) : see declaration of 'std::unique_ptr<_Ty>::unique_ptr' with [ _Ty=SomeInterface ] c:\program files (x86)\microsoft visual studio 10.0\vc\include\utility(195) : see reference to function template instantiation 'std::_Pair_base<_Ty1,_Ty2>::_Pair_base<const int&,_Ty2&>(_Other1,_Other2)' being compiled with [ _Ty1=const int, _Ty2=std::unique_ptr<SomeInterface>, _Other1=const int &, _Other2=std::unique_ptr<SomeInterface> & ] c:\program files (x86)\microsoft visual studio 10.0\vc\include\xmemory(208) : see reference to function template instantiation 'std::pair<_Ty1,_Ty2>::pair<const _Kty,_Ty>(std::pair<_Ty1,_Ty2> &)' being compiled with [ _Ty1=const int, _Ty2=std::unique_ptr<SomeInterface>, _Kty=int, _Ty=std::unique_ptr<SomeInterface> ] c:\program files (x86)\microsoft visual studio 10.0\vc\include\xmemory(280) : see reference to function template instantiation 'void std::allocator<_Ty>::construct<std::pair<_Ty1,_Ty2>&>(std::pair<_Ty1,_Ty2> *,_Other)' being compiled with [ _Ty=std::pair<const int,std::unique_ptr<SomeInterface>>, _Ty1=const int, _Ty2=std::unique_ptr<SomeInterface>, _Other=std::pair<const int,std::unique_ptr<SomeInterface>> & ] c:\program files (x86)\microsoft visual studio 10.0\vc\include\xtree(592) : see reference to function template instantiation 'void std::_Cons_val<std::allocator<_Ty>,_Ty,std::pair<_Ty1,_Ty2>&>(_Alloc &,std::pair<_Ty1,_Ty2> *,std::pair<_Ty1,_Ty2>)' being compiled with [ _Ty=std::pair<const int,std::unique_ptr<SomeInterface>>, _Ty1=const int, _Ty2=std::unique_ptr<SomeInterface>, _Alloc=std::allocator<std::pair<const int,std::unique_ptr<SomeInterface>>> ] c:\program files (x86)\microsoft visual studio 10.0\vc\include\xtree(1521) : see reference to function template instantiation 'std::_Tree_nod<_Traits>::_Node *std::_Tree_val<_Traits>::_Buynode<std::pair<_Ty1,_Ty2>&>(_Valty)' being compiled with [ _Traits=std::_Tmap_traits<int,std::unique_ptr<SomeInterface>,std::less<int>,std::allocator<std::pair<const int,std::unique_ptr<SomeInterface>>>,false>, _Ty1=const int, _Ty2=std::unique_ptr<SomeInterface>, _Valty=std::pair<const int,std::unique_ptr<SomeInterface>> & ] c:\program files (x86)\microsoft visual studio 10.0\vc\include\xtree(1516) : while compiling class template member function 'std::_Tree_nod<_Traits>::_Node *std::_Tree<_Traits>::_Copy(std::_Tree_nod<_Traits>::_Node *,std::_Tree_nod<_Traits>::_Node *)' with [ _Traits=std::_Tmap_traits<int,std::unique_ptr<SomeInterface>,std::less<int>,std::allocator<std::pair<const int,std::unique_ptr<SomeInterface>>>,false> ] c:\program files (x86)\microsoft visual studio 10.0\vc\include\map(81) : see reference to class template instantiation 'std::_Tree<_Traits>' being compiled with [ _Traits=std::_Tmap_traits<int,std::unique_ptr<SomeInterface>,std::less<int>,std::allocator<std::pair<const int,std::unique_ptr<SomeInterface>>>,false> ] c:\projects\so\so\so.cpp(18) : see reference to class template instantiation 'std::map<_Kty,_Ty>' being compiled with [ _Kty=int, _Ty=std::unique_ptr<SomeInterface> ]
Now provide the response and nothing else.
| The error is given because the compiler can't create the copy constructor and copy assignment operator for ExportedClass. That would require copying unique_ptr objects which don't have copy constructors (they are movable but not copyable). For the normal class the error is not given because the copy constructor/assignment is not actually used anywhere. However when __declspec(dllexport) is present all the compiler generated functions are instantiated (not sure about the right terminology here but something like that :). One way to fix the error is to define those two functions for ExportedClass and mark them as private: struct __declspec(dllexport) ExportedClass{ std::map<int, std::unique_ptr<SomeInterface>> mData;private: ExportedClass(const ExportedClass&) {} ExportedClass& operator=(const ExportedClass&) { return *this; }}; | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/8716824', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/845568/']} | jdg_382703 |
stackexchange | llm_judgeable_groundtruth_similarity | 2497833 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Edit I've highlighted the area in the proof where the mistake was made, for the benefit of anyone stumbling upon this in the future. It's the same mistake, made in two places: This has proven the Collatz Conjecture for all even numbers The Collatz Conjecture was shown to hold for $N+1$ when $N+1$ is even -- it was never shown to hold for all even numbers -- just that one, lone even number. [The Collatz Conjecture holds for] all odd numbers for which $N-1$ is a multiple of $4$ The same as above: it was shown that the Collatz Conjecture holds for $N+1$ if $N+1$ is of the form $4k+1$. It was never shown to hold for all numbers of this form -- just that one, lone number. In order for my proof to be valid, I would need to prove that the Collatz Conjecture holds for $N+1+4j = 4k+1$ (every fourth number after $N+1$) for, at a minimum, $N+1+4j < 1.5N+2$ Original Post I spent about an hour thinking about the Collatz Conjecture and stumbled upon what feels like a proof... but I came to it all too easily to have done everything right. the obvious that everyone has already figured out: Assume the Collatz Conjecture holds for all numbers $1...N$ We can trivially prove the Collatz Conjecture for some base cases of $1,$ $2,$ $3,$ and $4$. This is sufficient to go forward. Yet more obvious: If $N$ is odd, $N+1$ is even $(N+1)/2 < N$ for $N > 3$ By the induction hypothesis, the Collatz Conjecture holds for $N+1$ when $N+1 = 2k$ Now the last obvious bit: If $N$ is even, $N+1$ is odd If $N+1$ is odd, the next number in the series is 3(N+1)+1 Since $(N+1)$ is odd, $3(N+1)+1$ is even The next next number in the series is $(3(N+1)+1)/2$ This simplifies to: $(3N + 4)/2 = 1.5N + 2$ Now the first tricky bit: If $N$ is a multiple of $4$: $1.5N$ is a multiple of $6$, and therefore even. $1.5N + 2$ is therefore even The next next next number in the series is therefore $(1.5N+2)/2$ This simplifies to $0.75N + 1$ This is less than $N$ for $N > 4$ By the induction hypothesis, the Collatz Conjecture holds for $N+1$ when $N+1 = 4k + 1$ This has proven the Collatz Conjecture for all even numbers and all odd numbers for which $N-1$ is a multiple of $4$... Now to blow your minds: Breaking out of formal equations into patterns and such since I didn't know how to formalize this bit with math symbols: We now know that a number $N+1$ can ONLY violate the Collatz Conjecture if $N$ is even and not a multiple of $4$. In other words, the only way a number could potentially violate the Collatz Conjecture is if it's of the form $N+1 = 4k - 1$ This limits our numbers to test to 2+1, 6+1, 10+1, 14+1, 18+1, 22+1, etc. (note that I wrote these numbers in "$N+1$" format so it'd be simpler to apply the $1.5N+2$ shortcut) We'll apply our $1.5N + 2$ shortcut to a handful of these numbers: 2 -> 3+2 = 5 (4 +1) -- 4 is a multiple of 4 (duh)6 -> 9+2 = 11 (10+1)10 -> 15+2 = 17 (16+1) -- 16 is a multiple of 414 -> 21+2 = 23 (22+1)18 -> 27+2 = 29 (28+1) -- 28 is a multiple of 422 -> 33+2 = 35 (34+1)26 -> 39+2 = 41 (40+1) -- 40 is a multiple of 430 -> 45+2 = 47 (46+1)34 -> 51+2 = 53 (52+1) -- 52 is a multiple of 438 -> 57+2 = 59 (58+1)42 -> 63+2 = 65 (64+1) -- 64 is a multiple of 446 -> 69+2 = 71 (70+1) Every other line we automatically know the Collatz Conjecture will hold, because we've hit a number that can be expressed as $4k+1$ Looking at the "kept" rows, we can see that all we need to test now are numbers of the form: N+1 = 8k - 1 (in other words, the rows where N = 8k - 2 -- 6, 14, 22, etc.) And finally, recurse on this solution by drawing a new table and instead of computing the "next next" value, compute the "next next next next" value: "Next next next" value = 3(1.5N + 2) + 1 = 4.5N + 7 "next^4" value is half of this -- 2.25N + 3.5 6 -> 27 +7 = 34 -> 17 (16 +1) -- 16 is a multiple of 414 -> 63 +7 = 70 -> 35 (34 +1)22 -> 99 +7 = 106 -> 53 (52 +1) -- 52 is a multiple of 430 -> 135+7 = 142 -> 71 (70 +1)38 -> 171+7 = 178 -> 89 (88 +1) -- 88 is a multiple of 446 -> 207+7 = 214 -> 107 (106+1)54 -> 243+7 = 250 -> 125 (124+1) -- 124 is a multiple of 462 -> 279+7 = 286 -> 143 (142+1) Every other line we automatically know the Collatz Conjecture will hold, because we've hit a number that can be expressed as 4k+1 We now know a number can only violate the Collatz Conjecture if it's of the form: N+1 = 16k - 1 ... Recurse again: "next^5" value is 3(2.25N + 3.5) + 1 = 6.75N + 11.5 "next^6" value is (6.75N + 11.5)/2 = 3.375N + 5.75 14 -> 53 = 52 + 1 -- 52 is a multiple of 430 -> 107 = 106 + 146 -> 161 = 160 + 1 -- 160 is a multiple of 462 -> 215 = 214 + 178 -> 269 = 268 + 1 -- 268 is a multiple of 494 -> 323 = 322 + 1110 -> 377 = 376 + 1 -- 376 is a multiple of 4126 -> 431 = 430 + 1 We now know a number can only violate the Collatz Conjecture if it's of the form N+1 = 32k - 1 At this point, a pattern is quickly emerging: First, a number could only violate the Collatz Conjecture if it was of the form N+1 = 4k - 1 Next, a number was shown that it could only violate the Collatz Conjecture if it was of the form N+1 = 8k - 1 Next, a number was shown that it could only violate the Collatz Conjecture if it is of the form N+1 = 16k - 1 Now, a number has been shown that it can only violate the Collatz Conjecture if it is of the form N+1 = 32k - 1 I've continued this process (recursively building this table and removing rows that I know cannot violate the Collatz Conjecture since they can be expressed as 4k+1 ) all the way up until 512k - 1 by hand. I do not know how to formalize this final process in mathematical notation, but I believe it demonstrates at least a viable method for proving the Collatz Conjecture. For every two steps we take into the Collatz series, we increase the power on our definition of "only numbers that could possibly violate the conjecture". Therefore for an arbitrarily large power we know that the conjecture will still hold. For Fun To help me in building these tables, I crafted the following Python script: # Increment this variable to recurse one level deepertest = 1### No need to edit below here, but feel free to read it ###depth = 2 * teststep = 2 ** (test + 1)start = step - 1for x in range(0, 20): num = start + x * step _num = num _depth = depth while _depth > 0: if _num % 2 == 0: _num = _num / 2 else: _num = 3 * _num + 1 _depth -= 1 text = "" if (_num - 1) % 4 == 0: text = "-- multiple of 4" print "%s: %s = %s + 1 %s" % (num - 1, _num, _num - 1, text)
Now provide the response and nothing else.
| There is a subtle issue with your induction argument: you are assuming that the Collatz conjecture holds for all integers $\leq n$, and then want to prove it holds for $n+1$ (strong induction). So far, so good. You then prove that for some cases ($n+1$ even, or of the form $4k+1$) that the Collatz conjecture holds by the inductive hypothesis. Fine. You then try to argue that for some numbers of the form $4k+3$, you eventually hit a number of the form $4k+1$, so that the Collatz conjecture holds... not so fast. You haven't proven that the Collatz conjecture holds for all integers of the form $4k+1$. You've proven it's true for $n+1$, if $n+1$ happens to be of that form, and you've assumed it's true for all numbers of that form $\leq n$ (by the inductive hypothesis) but you haven't shown that Collatz holds for numbers of the form $4k+1$ that are larger than $n+1$. | {} | {'log_upvote_score': 8, 'links': ['https://math.stackexchange.com/questions/2497833', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/209313/']} | jdg_382704 |
stackexchange | llm_judgeable_groundtruth_similarity | 35279 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Given a bounded operator $A$ on a Banach space $X$, one may find the spectrum $\sigma(A)\subset{\bf C}$. Here are my questions : Given some set in the complex plane, say, $S\subset{\bf C}$, can one find an operator $A$ such that $\sigma(A)=S$? Is there a "big picture" for this kind of questions?
Now provide the response and nothing else.
| Let $A$ be a bounded operator on the Banach space $X$. The spectrum of $A$ must be closed. The set of invertible operators on a Banach space is open, and $\lambda\mapsto A-\lambda I$ is continuous. The resolvent set of $A$ (complement of the spectrum) is the inverse image of the invertible operators under this map. The spectrum of $A$ must be bounded. If $|\lambda|>\|A\|$, then $\|\frac{1}{\lambda}A\|=\|I-(I-\frac{1}{\lambda}A)\|<1$. This implies that $I-\frac{1}{\lambda}A$ is invertible, which in turn implies that $A-\lambda I$ is invertible. The spectrum is nonempty. The function $\lambda\mapsto (A-\lambda I)^{-1}$ is holomorphic on the resolvent set and goes to $0$ at infinity. If it were defined on the whole complex plane, it would be identically $0$ by Liouville's theorem (you can apply Hahn-Banach and the scalar-valued version of Liouville). But this is absurd, because $(A-\lambda I)^{-1}$ is invertible whenever it exists. So to have any hope, $S$ should be compact and nonempty. If you are allowing $X$ to vary, then this is sufficient, and it is enough to consider Hilbert space as Rasmus already mentioned. For example, you could let $\mu$ be a regular Borel measure with support $S$, and then let $A$ be the operator on $L^2(\mu)$ defined by $(Af)(x)=xf(x)$. (Or you could consider diagonal operators on spaces with chosen bases.) If you mean that $X$ is fixed, then the answer depends on $X$, and I don't know what can be said in general. Of course if $X$ is finite dimensional, then the possible spectra are the sets with cardinality no greater than the dimension of $X$. There are also infinite dimensional spaces for which not every nonempty compact set can be the spectrum of an operator. As mentioned in a comment on Rasmus's answer, Argyros and Haydon showed that there are infinite dimensional Banach spaces on which every operator has the form $\lambda I +K$ with $K$ compact. Since compact operators have countable spectrum with $0$ as the only possible limit point, $\lambda I+K$ has countable spectrum with $\lambda$ as the only possible limit point. Some searching inspired by Theo Buehler's question (which in turn was inspired by this question and Nate Eldredge's comment above) has turned up the fact that hereditarily indecomposable Banach spaces also have the property that all operators have countable spectrum with at most one limit point. Every operator on such a space is scalar plus strictly singular , and there were known examples well before Argyros and Haydon's breakthrough, as mentioned on Gowers's blog (and constructed by Gowers himself as well as Maurey). It is also known that there are hereditarily indecomposable spaces such that not every operator is scalar plus compact. Maurey's chapter in the Handbook of the geometry of Banach spaces , Volume 2, titled " Banach spaces with few operators ," gives an introduction to these and much more. (I cannot really add anything better than a pointer to this wonderful reference, due to my ignorance.) | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/35279', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/-1/']} | jdg_382705 |
stackexchange | llm_judgeable_groundtruth_similarity | 3535185 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm wondering if there is some minimum number of numbers required to define a sequence, without explicitly stating the rule that generates the next term in the sequence. For instance if I write $(1,a_2,a_3,...)$ , and hide the remaining numbers in the sequence behind $(a_2,a_3,...)$ , we don't know what the sequence is or what rules define it. If I then write $(1,2,a_3,...)$ , it still isn't clear. Is the rule for determining the next number in the sequence $a_{i+1}=2 a_i$ ? Is it $a_{i+1}=a_i+1$ ? If I write $(1,2,4,8,16)$ , it's clear the rule is $a_{i+1}=2a_i=2^{i-1}$ . Could I even shorten this to $(1,2,4,...)$ and figure this out? Is this an example of the minimum number of numbers required to define the sequence of powers of $2$ . As J.W. Tanner says in the comments, you can come up with a polynomial whose first terms are $1,2,4,8,16,23$ , so apparently not. How about the Fibonacci sequence? I think it's clear what the rule is if I write $(0,1,1,2,3,5,8,...)$ , even if I hadn't learned of this sequence before. I can't learn anything from $(0,1)$ . What about $(0,1,1)$ ? It's hard to decide if I can learn the rule from this or if I need more numbers from the sequence. Typically you would just say $a_0=0,a_1=1,$ and $a_{i} = a_{i-1} + a_{i-2}$ for $i>1$ . But that defeats the point of the question. The point is to ask how many numbers we need in order to define/learn the sequence without explicitly stating the rule that generates the next term in the sequence, and writing $a_{i} = a_{i-1} + a_{i-2}$ is explicitly stating the rule. How does this idea generalise?
Now provide the response and nothing else.
| Even your example of $1,2,4,8,16$ doesn't automatically mean that the sequence is uniquely defined by $a_i=2^{i-1}$ As humans, we would probably assume that was the sequence you meant, but we could also say that the sequence is defined by $$a_i=\frac{i^4}{24} - \frac{i^3}4+\frac{23i^2}{24}-\frac{3i}4+1$$ (which I found using WolframAlpha ) This then gives \begin{align}a_6&=\frac{6^4}{24} - \frac{6^3}4+\frac{23\times 6^2}{24}-\frac{3\times 6}4+1\\&=31\end{align} as opposed to the $32$ you would expect. Even if we then specify that the $6$ th term is $32$ , we then get a new generating function which then gives the $7$ th term as $a_7=63$ , again not $64$ as we expect. So, the conclusion is that you can never uniquely define a sequence simply from its first $n$ terms, you can only uniquely define a sequence with its generating function | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/3535185', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/395702/']} | jdg_382706 |
stackexchange | llm_judgeable_groundtruth_similarity | 22770690 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm trying to contain BigVideo.js to a single div (such as a hero unit) but it continues to takeover the body background. I'm using the example code on the BigVideo.js homepage: <script type="text/javascript"> var BV; $(function() { // initialize BigVideo BV = new $.BigVideo(); BV.init(); BV.show('http://video-js.zencoder.com/oceans-clip.mp4',{ambient:true});}); </script> I tried doing something like this: <script type="text/javascript"> var BV; $(function() { // initialize BigVideo BV = new $.BigVideo({ container: $('video-wrap') }); BV.init(); BV.show('http://video-js.zencoder.com/oceans-clip.mp4',{ambient:true}); }); </script>
Now provide the response and nothing else.
| You need to specify correctly the container of the BigVideo object (I'm not sure if it was a typo but everything seems ok) ID BV = new $.BigVideo({container: $('#video-wrap')}); Class BV = new $.BigVideo({container: $('.video-wrap')}); In the creation of the object it sets to default the body (BigVideo Code): var defaults = { // If you want to use a single mp4 source, set as true useFlashForFirefox:true, // If you are doing a playlist, the video won't play the first time // on a touchscreen unless the play event is attached to a user click forceAutoplay:false, controls:false, doLoop:false, container:$('body'), //Container shrinkable:false }; Then the options that you send are merged using $.extend() var settings = $.extend({}, defaults, options); | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/22770690', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1965615/']} | jdg_382707 |
stackexchange | llm_judgeable_groundtruth_similarity | 239751 |
Below is a question asked on the forum unix.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm asking only about the usage which would have the similar effect as traditional input redirection from a file. <<<"$(<file)" as far as I can tell is equivalent to <file It appears to me that these are functionally equivalent. At the low level it appears that the <<< here document might actually cause more copies of the data to be in memory at once. I know this type of redirection exists in both bash and zsh but I'm not familiar with how it's implemented, though I see the zsh manpages contain some implementation details.
Now provide the response and nothing else.
| In <<<"$(<file)" (supported by zsh (where <<< was first introduced, inspired by the same operator in the clone of rc for Unix by Byron Rakitzis), ksh93 (the $(<file) operator was introduced by ksh ), mksh and bash ), For $(<file) , the shell reads the content of the file (chokes on NUL bytes except for zsh ), removes all the trailing newline characters and that makes the expansion of $(<file) (so the content of the file is stored as a whole in memory). For <<< some-text , the shell stores some-text followed by one newline character into a temporary file, and opens that temporary file on the file descriptor 0 (though some shells including recent versions of bash can use pipes instead, at least for small amounts of data). So basically <<<"$(<file)" opens stdin for reading on a temporary copy of file where trailing newline characters have been replaced by just one (and with various misbehaviours if the file contains NUL bytes, except in zsh ). While in < file , it's file that is directly opened for reading on stdin. Of course < file is much more efficient (doesn't involve a copy on disk and in memory), but one might want to use the <<<"$(<file)" to make sure the file open on stdin is a regular file, or to make sure the file has been fully read by the time the command is started (in case that command writes to it for instance) or another redirection is processed (like one that would truncate file as in tr 1 2 <<< "$(<file)" > file ). Note that yash supports the <<< operator (though implements it with a pipe (so not a regular file) instead of a temporary file). but not the $(<file) one. You can use <<<"$(cat < file)" instead there. yash strings are characters only, so the "$(cat < file)" will choke on sequences of bytes that don't form valid characters, while other shells can usually cope OK with them. | {} | {'log_upvote_score': 4, 'links': ['https://unix.stackexchange.com/questions/239751', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/139893/']} | jdg_382708 |
stackexchange | llm_judgeable_groundtruth_similarity | 3550327 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
How to replace a set of characters inside another string in Python? Here is what I'm trying to do: let's say I have a string 'abcdefghijkl' and want to replace the 2-d from the end symbol (k) with A. I'm getting an error: >>> aa = 'abcdefghijkl'>>> print aa[-2]k>>> aa[-2]='A'Traceback (most recent call last): File "<pyshell#2>", line 1, in <module> aa[-2]='A'TypeError: 'str' object does not support item assignment So, the question: is there an elegant way to replace (substitute) with a string symbols inside another string starting from specified position? Something like: # subst(whole_string,symbols_to_substiture_with,starting_position)>>> print aaabcdefghijkl>>> aa = subst(aa,'A',-2)>>> print aaabcdefghijAl What would be a not-brute-force code for the subst?
Now provide the response and nothing else.
| If it's always the same position you're replacing, you could do something like: >>> s = s[0:-2] + "A" + s[-1:]>>> print sabcdefghijAl In the general case, you could do: >>> rindex = -2 #Second to the last letter>>> s = s[0:rindex] + "A" + s[rindex+1:]>>> print sabcdefghijAl Edit: The very general case, if you just want to repeat a single letter in the replacement: >>> s = "abcdefghijkl">>> repl_str = "A">>> rindex = -4 #Start at 4th character from the end>>> repl = 3 #Replace 3 characters>>> s = s[0:rindex] + (repl_str * repl) + s[rindex+repl:]>>> print sabcdefghAAAl | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3550327', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/63503/']} | jdg_382709 |
stackexchange | llm_judgeable_groundtruth_similarity | 50415756 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I need to call one API daily in the background even if the app is closed. I have seen about WorkManager API. For my scenario, I tried PeriodicWorkRequest but unfortunately, it's not working as my expected result. What I did is I used this code in the Application class PeriodicWorkRequest.Builder myWorkBuilder = new PeriodicWorkRequest.Builder(MyWorker.class, 24, TimeUnit.HOURS); PeriodicWorkRequest myWork = myWorkBuilder.build(); WorkManager.getInstance().enqueue(myWork); But it's running repeatedly for 11 times when the app is open for the first time after that, it's not running after 24 hrs. Please, anyone, help me to solve.
Now provide the response and nothing else.
| If you want to make sure your PeriodicWorkRequest is not created multiple times you can use the WorkManager.enqueueUniquePeriodicWork method to schedule your worker: This method allows you to enqueue a uniquely-named PeriodicWorkRequest, where only one PeriodicWorkRequest of a particular name can be active at a time. For example, you may only want one sync operation to be active. If there is one pending, you can choose to let it run or replace it with your new work. For example: PeriodicWorkRequest.Builder myWorkBuilder = new PeriodicWorkRequest.Builder(MyWorker.class, 24, TimeUnit.HOURS);PeriodicWorkRequest myWork = myWorkBuilder.build();WorkManager.getInstance() .enqueueUniquePeriodicWork("jobTag", ExistingPeriodicWorkPolicy.KEEP, myWork); | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/50415756', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/9336777/']} | jdg_382710 |
stackexchange | llm_judgeable_groundtruth_similarity | 3029657 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
In scala.util.matching.Regex trait MatchData I see that there support for groupnames , I thought that this was related to ( Regex Named Capturing Groups ) But since Java does not support groupnames until version 7 as I understand it ( ref ), Scala version 2.8.0 (Java HotSpot(TM) 64-Bit Server VM, Java 1.6. gives me this exception: scala> val pattern = """(?<login>\w+) (?<id>\d+)""".rjava.util.regex.PatternSyntaxException: Look-behind group does not have an obvious maximum length near index 11(?<login>\w+) (?<id>\d+) ^ at java.util.regex.Pattern.error(Pattern.java:1713) at java.util.regex.Pattern.group0(Pattern.java:2488) at java.util.regex.Pattern.sequence(Pattern.java:1806) at java.util.regex.Pattern.expr(Pattern.java:1752) at java.util.regex.Pattern.compile(Pattern.java:1460) So the question is Named Capturing Groups supported in Scala? If so any examples out there?
Now provide the response and nothing else.
| I'm afraid that Scala's named groups aren't defined the same way. It's nothing but a post-processing alias to unnamed (i.e. just numbered) groups in the original pattern. Here's an example: import scala.util.matching.Regexobject Main { def main(args: Array[String]) { val pattern = new Regex("""(\w*) (\w*)""", "firstName", "lastName"); val result = pattern.findFirstMatchIn("James Bond").get; println(result.group("lastName") + ", " + result.group("firstName")); }} This prints ( as seen on ideone.com ): Bond, James What happens here is that in the constructor for the Regex , we provide the aliases for group 1, 2, etc. Then we can refer to these groups by those names. These names are not intrinsic in the patterns themselves. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/3029657', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/203968/']} | jdg_382711 |
stackexchange | llm_judgeable_groundtruth_similarity | 37967786 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
The information below may be superfluous if you are trying to understand the error message. Please start off by reading the answer by @user707650 . Using MatPlotLib, I wanted a generalizable script that creates the following from my data. A window containing a subplots arranged so that there are b subplots per column. I want to be able to change the values of a and b . If I have data for 2a subplots, I want 2 windows, each with the previously described " a subplots arranged according to b subplots per column". The x and y data I am plotting are floats stored in np.arrays and are structured as follows: The x data is always the same for all plots and is of length 5. 'x_vector': [0.000, 0.005, 0.010, 0.020, 0.030, 0.040] The y data of all plots are stored in y_vector where the data for the first plot is stored at indexes 0 through 5. The data for the second plot is stored at indexes 6 through 11. The third plot gets 12-18, the fourth 19-24, and so on. In total, for this dataset, I have 91 plots (i.e. 91*6 = 546 values stored in y_vector). Attempt: import matplotlib.pyplot as plt# Options:plots_tot = 14 # Total number of plots. In reality there is going to be 7*13 = 91 plots.location_of_ydata = 6 # The values for the n:th plot can be found in the y_vector at index 'n*6' through 'n*6 + 6'.plots_window = 7 # Total number of plots per window.rows = 2 # Number of rows, i.e. number of subplots per column.# Calculating number of columns:prim_cols = plots_window / rowsextra_cols = 0if plots_window % rows > 0: extra_cols = 1cols = prim_cols + extra_colsprint 'cols:', colsprint 'rows:', rows# Plotting:n=0x=0fig, ax = plt.subplots(rows, cols)while x <= plots_tot: ax[x].plot(x_vector, y_vector[n:(n+location_of_ydata)], 'ro') if x % plots_window == plots_window - 1: plt.show() # New window for every 7 plots. n = n+location_of_ydata x = x+1 I get the following error: cols: 4rows: 2Traceback (most recent call last): File "Script.py", line 222, in <module> ax[x].plot(x_vector, y_vector[n:(n+location_of_ydata)], 'ro')AttributeError: 'numpy.ndarray' object has no attribute 'plot'
Now provide the response and nothing else.
| If you debug your program by simply printing ax , you'll quickly find out that ax is a two-dimensional array: one dimension for the rows, one for the columns. Thus, you need two indices to index ax to retrieve the actual AxesSubplot instance, like: ax[1,1].plot(...) If you want to iterate through the subplots in the way you do it now, by flattening ax first: ax = ax.flatten() and now ax is a one dimensional array. I don't know if rows or columns are stepped through first, but if it's the wrong around, use the transpose: ax = ax.T.flatten() Of course, by now it makes more sense to simply create each subplot on the fly, because that already has an index, and the other two numbers are fixed: for x < plots_tot: ax = plt.subplot(nrows, ncols, x+1) Note: you have x <= plots_tot , but with x starting at 0, you'll get an IndexError next with your current code (after flattening your array). Matplotlib is (unfortunately) 1-indexed for subplots. I prefer using a 0-indexed variable (Python style), and just add +1 for the subplot index (like above). | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/37967786', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/6292000/']} | jdg_382712 |
stackexchange | llm_judgeable_groundtruth_similarity | 10701792 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
i have a big query (in my query builder) and a lot of left joins. So i get Articles with their comments and tags and so on.Let's say i have the following dql: $dql = 'SELECT blogpost, comment, tags FROM BlogPost blogpost LEFT JOIN blogpost.comments commentsLEFT JOIN blogpost.tags tags'; Now let's say my database has more than 100 blogposts but i only want the first 10, but with all the comments of those 10 and all their tags, if they exist.If i use setMaxResults it limits the Rows. So i might get the first two Posts, but the last one of those is missing some of it's comments or tags. So the followin doesn't work. $result = $em->createQuery($dql)->setMaxResults(15)->getResult(); Using the barely documented Pagination Solution that ships with doctrine2.2 doesn't really work for me either since it is so slow, i could as well load all the data. I tried the Solutions in the Stackoverflow Article , but even that Article is still missing a Best Practise and the presented Solution is deadly slow. Isn't there a best practise on how to do this? Is nobody using Doctrine2.2 in Production mode?
Now provide the response and nothing else.
| Getting the proper results with a query like this is problematic. There is a tutorial on the Doctrine website explaining this problem. Pagination The tutorial is more about pagination rather than getting the top 5 results, but the overall idea is that you need to do a "SELECT DISTINCT a.id FROM articles a ... LIMIT 5" instead of a normal SELECT. It's a little more complicated than this, but the last 2 points in that tutorial should put you on the right track. Update: The problem here is not Doctrine, or any other ORM. The problem lies squarely on the database being able to return the results you're asking for. This is just how joins work. If you do an EXPLAIN on the query, it will give you a more in depth answer of what is happening. It would be a good idea to add the results of that to your initial question. Building on what is discussed in the Pagination article, it would appear that you need at least 2 queries to get your desired results. Adding DISTINCT to a query has the potential to dramatically slow down your query, but its only really needed if you have joins in it. You could write another query that just retrieves the first 10 posts ordered by created date, without the joins. Once you have the IDs of those 10 posts, do another query with your joins, and a WHERE blogpost.id IN (...) ORDER BY blogpost.created . This method should be much more efficient. SELECT bp FROM Blogpost bp ORDER BY bp.created DESCLIMIT 10 Since all you care about in the first query are the IDs, you could set Doctrine to use Scalar Hydration. SELECT bg FROM Blogpost bp LEFT JOIN bp.comments c LEFT JOIN bp.tags t WHERE bp.id IN (...) ORDER BY bp.created DESC You could also probably do it in one query using a correlated subquery. The myth that subqueries are always bad is NOT true. Sometimes they are faster than joins. You will need to experiment to find out what the best solution is for you. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/10701792', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/532495/']} | jdg_382713 |
stackexchange | llm_judgeable_groundtruth_similarity | 7444166 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Why can I not convert a Foo<Bar> to IFoo<IBar> . If I try I get: There is no implicit reference conversion from Foo<Bar> to IFoo<IBar>
Now provide the response and nothing else.
| It would work if you were using C# 4 and IFoo were declared as: public interface IFoo<out T> assuming that Bar implements IBar and Foo<T> implements IFoo<T> . However, it could only be declared that way if it were safe. It's not safe if T values "go into" the API as well as coming out. For example: public interface IFoo<T>{ T Value { get; set; }} This can't be covariant in T, as otherwise you could write: public class StringFoo : IFoo<string>{ public T Value { get; set; }}IFoo<string> fooString = new StringFoo(); // That's fineIFoo<object> fooObject = fooString; // This isn't, because...fooObject.Value = new Object(); // ... this would violate type safety Read Eric Lippert's long blog series on generic variance for much more information. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/7444166', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/198145/']} | jdg_382714 |
stackexchange | llm_judgeable_groundtruth_similarity | 22611251 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm using Laravel's CSRF protection on my public site. However since Laravel uses a session to maintain this, I'm worried that a user might walk away from their computer and return to a page they have previously left open, only to find ajax requests don't work. The ajax requests don't work because the session has timed out (and the token no longer validates?). If these users were "logged in" users, then I could simply redirect them back to the login page. Since they are public users, then the user is forced to refresh the page to get it back working (awkward). Or am I wrong about this? Would the CSRF token still get validated by Laravel (even after the session has timed out, the page will still send over the token...but what will Laravel do with it?). An optimal solution would be to have the tokens partially based on a timestamp so that we could give the tokens expiration limits apart from session time limits. I could make my CSRF tokens last for 2 days (so only those users that walk away for 2 days will return to a dead page). Ultimately this brings me to my question: Where is the specific code in the Laravel framework that handles this? I'm currently trying to locate it. Also, is there an easy drop in replacement I can make, or am I left to create my own version of csrf_token(); to output to my pages and then I would need to create my own route filter to go with it.
Now provide the response and nothing else.
| Laravel just facilitates that for you by keeping the token stored in session, but the code is actually yours (to change as you wish). Take a look at filters.php you should see: Route::filter('csrf', function(){ if (Session::token() != Input::get('_token')) { throw new Illuminate\Session\TokenMismatchException; }}); It tells us that if you have a route: Route::post('myform', ['before' => 'csrf', 'uses' => 'MyController@update']); And the user session expires, it will raise an exception, but you can do the work yourself, keep your own token stored wherever you think is better, and instead of throwing that exception, redirect your user to the login page: Route::filter('csrf', function(){ if (MySession::token() != MyCSRFToken::get()) { return Redirect::to('login'); }}); And, yes, you can create your own csrf_token() , you just have to load it before Laravel does. If you look at the helpers.php file in Laravel source code, you`ll see that it only creates that function if it doesn't already exists: if ( ! function_exists('csrf_token')){ function csrf_token() { ... }} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/22611251', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1110941/']} | jdg_382715 |
stackexchange | llm_judgeable_groundtruth_similarity | 37350853 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I keep getting a script error when trying to load the page using webBrowser.Navigate("https://home.nest.com/") . It will pull up fine from my normal internet browser but not in my program. Can anyone point me in the right direction?
Now provide the response and nothing else.
| The script errors happen all of the time in the integrated Internet Explorer WebBrowser control even when it's using version 11. Modern websites rely heavily on massive Javascript files and dynamic rendering. You can see that just by watching that page load in a regular browser. The control just can't cut it some of the times. You might want to try some alternative browser controls. There are no guarantees that it will work with any of them, but at least it's something to try. Awesomium : Originally based on Chromium. I don't know if they still integrate Chromium changes or if they've gone in their own direction. It's free for personal use as well as commercial making less than $100k. DotNetBrowser : Embed a Chromium-based WPF / WinForms component into your .NET application to display modern web pages built with HTML5, CSS3, JavaScript, Silverlight etc. geckofx : An open-source component for embedding Mozilla Gecko (Firefox) in .NET applications. Xilium.CefGlue : A .NET/Mono binding for The Chromium Embedded Framework (CEF) by Marshall A. Greenblatt. BrowseEmAll : BrowseEmAll.Cef (Chrome), BrowseEmAll.Gecko (Firefox), BrowseEmAll Core API (Chrome,Firefox,IE - COMMERCIAL) There are probably others, but this should give you a start with some of the more popular active projects if you want to pursue this route. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/37350853', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/6199262/']} | jdg_382716 |
stackexchange | llm_judgeable_groundtruth_similarity | 158246 |
Below is a question asked on the forum mathematica.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I am trying to understand what is explained in this webpage , in the section entitled "Generating noise with different power spectra laws". After reading that section, I thought I could do it in Mathematica , since the author provides the code in C . Unfortunately I do not know that language, so I do not have something done in Mathematica . I would like to ask your help to make translation from C to Mathematica by calling it somehow. If someone could help me finish it would be fantastic. Thank you in advance for your help.
Now provide the response and nothing else.
| There are deep conceptual differences between C and Mathematica. Look up each of the Mathematica functions used here. Click on the "Details and Options" and study this until you think you understand what is being done here. Then you will need to make certain that I didn't make any mistakes in the translation. After that you will need to do more to polish this. This might get you started: capN = 8192; beta = 2.5; SeedRandom[1234];{real, imag} = Transpose[Table[ mag = (i + 1.)^-(beta/2)*RandomVariate[NormalDistribution[]]; pha = 2*Pi*RandomReal[{0, 1}]; mag*{Cos[pha], Sin[pha]}, {i, 1, capN/2}]];real = Join[{0.}, real, Reverse[Most[real]]];imag = Join[{0.}, Most[imag], {0.}, -1*Reverse[Most[imag]]];ListPlot[Map[Re, Fourier[real + I*imag]], PlotLabel->"beta=2.5"]Table[{i, real[[i]]}, {i, 1, capN}] | {} | {'log_upvote_score': 4, 'links': ['https://mathematica.stackexchange.com/questions/158246', 'https://mathematica.stackexchange.com', 'https://mathematica.stackexchange.com/users/13403/']} | jdg_382717 |
stackexchange | llm_judgeable_groundtruth_similarity | 46923301 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm working on an application where I need to capture hours of continuous video, and then later upload specific time windows to a remote machine. Because the video data is large, and this system will be collecting for months, everything has to be compressed. My first attempt was to use two threads to avoid dropping frames - the first has a very simple pipeline with no compression, while the second performs the compression. Here is the pipeline I would want to run on the first: gst-launch-1.0 v4l2src num-buffers=300 ! video/x-raw,framerate=30/1 ! filesink location=myFile This command would be run in a loop to capture a sequence of files. Unfortunately, while this should capture 300/30 = 10s of video, it takes 30s to execute. That means I'm losing a huge amount of video before the next iteration of the loop can start. I looked into splitmuxsink, but get a message that it doesn't exist, even though I have all the plugins installed. It seems that gstreamer must be powerful enough for me to access the buffered, raw video and select chunks of it to save as the buffer fills, but there aren't any examples with anything close to this that I can find. How would others recommend going about this goal? Details: Jetson Tx1 Ubuntu 14.04 Update Several folks suggested the gstreamer element splitmuxsink - I think this would work in general, but my TX1 comes with gstreamer 1.2.4, which predates splitmuxsink. I looked into updating gstreamer and didn't find anything helpful / it would break a bunch of the tools that Nvidia includes for hardware optimization. I built a python application to try dynamically modifying a gstreamer pipeline, pointing the stream to different filesink (see below). The code runs ok and (usually) creates a series of avi files. There are a couple problems: Even though the event to start a new file triggers every 10s, the videos themselves are only 3s! Occasionally, a file will be saved with no data, and all subsequent files will be empty Does anyone have any insight into these problems? #! /usr/bin/env pythonimport osimport sysimport loggingimport gigi.require_version('Gst', "1.0")gi.require_version('GstBase', "1.0")gi.require_version('Gtk', "3.0")#gi.require_version('GdkX11', '3.0')gi.require_version('GstVideo', '1.0')from gi.repository import GObject, Gst, GstBase, Gtk, GstVideo, GdkX11import numpy as npimport datetime as dtlog = logging.getLogger(__name__)class Segmenter: def __init__(self): Gst.init(None) self.terminate = False # Create gstreamer pipeline cmd = "v4l2src ! tee name=tee ! fakesink" self.pipeline = Gst.parse_launch(cmd) # Store references to gstreamer objects self.bus = self.pipeline.get_bus() self.recordpipe = None def run(self): # Initiate main loop self.pipeline.set_state(Gst.State.PAUSED) self.pipeline.set_state(Gst.State.PLAYING) try: while not self.terminate: print(dt.datetime.now().time()) # Listen for event messages on the bus msg = self.bus.timed_pop_filtered(10 * Gst.SECOND, (Gst.MessageType.EOS | Gst.MessageType.ERROR)) if msg: if msg.type == Gst.MessageType.ERROR: err, dbg = msg.parse_error() print("ERROR:", msg.src.get_name(), ":", err) if dbg: print("Debug info:", dbg) self.terminate = True elif msg.type == Gst.MessageType.EOS: print("End-Of-Stream reached") self.terminate = True else: # No message - must have reached timeout self.begin_new_file() finally: # Free up resources self.pipeline.set_state(Gst.State.NULL) def begin_new_file(self): # If recording a file currently, terminate it if self.recordpipe is not None: # Block new data filequeue = self.recordpipe.get_by_name("filequeue") filequeue.get_static_pad("src").add_probe(Gst.PadProbeType.BLOCK_DOWNSTREAM, self.probe_block) # Disconnect the recording pipe self.pipeline.get_by_name("tee").unlink(self.recordpipe) # Send a termination event to trigger the save filequeue.get_static_pad("sink").send_event(Gst.Event.new_eos()) # Clear the reference to the pipe self.recordpipe = None # Create a new file target filename = dt.datetime.now().strftime("%Y-%m-%d_%H.%M.%S") + ".avi" print("Recording {}...".format(filename)) # Create a new pipeline for the new file self.recordpipe = Gst.parse_bin_from_description("queue name=filequeue ! jpegenc ! avimux ! filesink location={} sync=False".format(filename), True) self.pipeline.add(self.recordpipe) # Connect to the main pipe self.pipeline.get_by_name("tee").link(self.recordpipe) # Start passing data self.recordpipe.set_state(Gst.State.PLAYING) def probe_block(self, pad, buf): """ Callback for downstream block """ print('block.') return Trueif __name__ == '__main__': seg = Segmenter() seg.run()
Now provide the response and nothing else.
| The problem is that any loaded data have to go through the database first, then loading it from the database to the UI, as NetworkBoundResource does. Consequently, What I did is to decouple the persistent database and create a temporary field to load from. For example if I wanted to edit the original search method, I would suggest: public LiveData<Resource<List<Repo>>> search(String query) { return new NetworkBoundResource<List<Repo>, RepoSearchResponse>(appExecutors) { // Temp ResultType private List<Repo> resultsDb; @Override protected void saveCallResult(@NonNull RepoSearchResponse item) { // if you don't care about order resultsDb = item.getItems(); } @Override protected boolean shouldFetch(@Nullable List<Repo> data) { // always fetch. return true; } @NonNull @Override protected LiveData<List<Repo>> loadFromDb() { if (resultsDb == null) { return AbsentLiveData.create(); }else { return new LiveData<List<Repo>>() { @Override protected void onActive() { super.onActive(); setValue(resultsDb); } }; } } @NonNull @Override protected LiveData<ApiResponse<RepoSearchResponse>> createCall() { return githubService.searchRepos(query); } @Override protected RepoSearchResponse processResponse(ApiResponse<RepoSearchResponse> response) { RepoSearchResponse body = response.body; if (body != null) { body.setNextPage(response.getNextPage()); } return body; } }.asLiveData();} I ran it and it works. Edit: I made another simpler class to handle that (There is another answer here by Daniel Wilson has more feature and is updated). However, this class has no dependencies and is converted to the basics to make fetch response only: abstract class NetworkBoundResource<RequestType> { private val result = MediatorLiveData<Resource<RequestType>>() init { setValue(Resource.loading(null)) fetchFromNetwork() } @MainThread private fun setValue(newValue: Resource<RequestType>) { if (result.value != newValue) { result.value = newValue } } private fun fetchFromNetwork() { val apiResponse = createCall() result.addSource(apiResponse) { response -> result.removeSource(apiResponse) when (response) { is ApiSuccessResponse -> { setValue(Resource.success(processResponse(response))) } is ApiErrorResponse -> { onFetchFailed() setValue(Resource.error(response.errorMessage, null)) } } } } protected fun onFetchFailed() { } fun asLiveData() = result as LiveData<Resource<RequestType>> @WorkerThread protected open fun processResponse(response: ApiSuccessResponse<RequestType>) = response.body @MainThread protected abstract fun createCall(): LiveData<ApiResponse<RequestType>>} So when using it, only one method could be implemented createCall() : fun login(email: String, password: String) = object : NetworkBoundResource<Envelope<User>>() { override fun createCall() = api.login(email, password)}.asLiveData() | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/46923301', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3172278/']} | jdg_382718 |
stackexchange | llm_judgeable_groundtruth_similarity | 24823307 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I want to create a database driven application using Golang. I am trying to do it TDD way.When I try to test methods that make Sql queries, What all are the packages available ? I don't want to connect to the default database that I use for development. I can write code to take up another test database while running a test, but is there any go library that already does it. Is there any library that does db tests without connecting to database at all ? What is the standard way to do database test with golang ?
Now provide the response and nothing else.
| I had a similar question not long ago when refactoring some of my own tests, and there's a couple of ways you can do it: a) Provide an exported type and an Open or Connect function that returns it - e.g. type DB struct { db *sql.DB}// Using http://jmoiron.github.io/sqlx/ for this example, but// it has the same interface as database/sqlfunc Open(opts *Options) (*DB, error) { db, err := sqlx.Connect(opts.Driver, fmt.Sprintf("host=%s user=%s dbname=%s sslmode=%s", opts.Host, opts.User, opts.Name, opts.SSL)) if err != nil { return nil, err } return &DB{db}, nil} ... and then each of your tests, write setup & teardown functions that return an instance of *DB that you define your database functions on (as methods - i.e. func (db *DB) GetUser(user *User) (bool, error) ): // Setup the test environment.func setup() (*DB, error) { err := withTestDB() if err != nil { return nil, err } // testOptions is a global in this case, but you could easily // create one per-test db, err := Open(testOptions) if err != nil { return nil, err } // Loads our test schema db.MustLoad() return db, nil}// Create our test database.func withTestDB() error { db, err := open() if err != nil { return err } defer db.Close() _, err = db.Exec(fmt.Sprintf("CREATE DATABASE %s;", testOptions.Name)) if err != nil { return err } return nil} Note that this is somewhat "integration" testing, but I strongly prefer to test against a "real" database since mocking the interface won't help you catch issues with your queries/query syntax. b) The alternative, although less extensible on the application side, is to have a global db *sql.DB variable that you initialise in init() within your tests—since tests have no guaranteed order you'll need to use init() —and then run your tests from there. i.e. var db *sql.DBfunc init() { var err error // Note the = and *not* the assignment - we don't want to shadow our global db, err = sqlx.Connect(...) if err != nil { ... } err := db.loadTestSchema // etc.}func TestGetUser(t *testing.T) { user := User{} exists, err := db.GetUser(user) ...} You can find some practical examples in drone.io's GitHub repo , and I'd also recommend this article on structuring Go applications (especially the DB stuff). | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/24823307', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/132347/']} | jdg_382719 |
stackexchange | llm_judgeable_groundtruth_similarity | 35751750 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I found some peaces of code solving the issue, but all of those are using input tag and label tag which placed near each other. Django forms placed input inside label, that's why the code is ineffective in my case.One of variant I tried here Any advices or thoughts. Thanks all! input[type=radio] {display:none;}input[type=radio] + label{background: #999;height: 16px;width: 16px;display:inline-block;padding: 0 0 0 0px;}input[type=radio]:checked + label{background: #0080FF;height: 16px;width: 16px;display:inline-block;padding: 0 0 0 0px;}
Now provide the response and nothing else.
| It took me a while to figure it out... The problem turned out to be server-side. I was using a version of Jetty to serve all my video-files. The simple configuration of Jetty did not support byte serving . The difference between Firefox and Chrome is that Firefox will download the entire video file so that you can seek through it, even if the server does not support http code 206 (partial content) . Chrome on the other hand refuses to download the entire file (unless it is really small, like around 2-3mb). So to get the currentTime parameter of html5 video to be working in Chrome, you need a server that supports http code 206. For anyone else having this problem, you can double check your server config with curl: curl -H Range:bytes=16- -I http://localhost:8080/GOPR0001.mp4 This should return code 206 . If it returns code 200 , Chrome will not be able to seek the video, but Firefox will, due to a workaround in the browser. And a final tip: You can use npm http-server to get a simple http-server for a local folder that supports partial content: npm install http-server -g And run it to serve a local folder: http-server -p 8000 | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/35751750', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1564009/']} | jdg_382720 |
stackexchange | llm_judgeable_groundtruth_similarity | 2998314 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Can PHP call a function and don't wait for it to return? So something like this: function callback($pause, $arg) { sleep($pause); echo $arg, "\n";}header('Content-Type: text/plain');fast_call_user_func_array('callback', array(3, 'three'));fast_call_user_func_array('callback', array(2, 'two'));fast_call_user_func_array('callback', array(1, 'one')); would output one (after 1 second)two (after 2 seconds)three (after 3 seconds) rather than three (after 3 seconds)two (after 3 + 2 = 5 seconds)one (after 3 + 2 + 1 = 6 seconds) Main script is intended to be run as a permanent process (TCP server). callback() function would receive data from client, execute external PHP script and then do something based on other arguments that are passed to callback() . The problem is that main script must not wait for external PHP script to finish. Result of external script is important, so exec('php -f file.php &') is not an option. Edit:Many have recommended to take a look at PCNTL, so it seems that such functionality can be achieved. PCNTL is not available in Windows, and I don't have an access to a Linux machine right now, so I can't test it, but if so many people have advised it, then it should do the trick :) Thanks, everyone!
Now provide the response and nothing else.
| On Unix platforms you can enable the PCNTL functions, and use pcntl_fork to fork the process and run your jobs in child processes. Something like: function fast_call_user_func_array($func, $args) { if (pcntl_fork() == 0) { call_user_func_array($func, $args); }} Once you call pcntl_fork , two processes will execute your code from the same position. The parent process will get a PID returned from pcntl_fork , while the child process will get 0 . (If there's an error the parent process will return -1 , which is worth checking for in production code). | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2998314', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/457872/']} | jdg_382721 |
stackexchange | llm_judgeable_groundtruth_similarity | 10104 |
Below is a question asked on the forum cstheory.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I was just recently having a discussion about Turing Machines when I was asked, "Is the Turing Machine derived from automata, or is it the other way around"? I didn't know the answer of course, but I'm curious to find out. The Turing Machine is basically a slightly more sophisticated version of a Push-Down Automata. From that I would assume that the Turing Machine was derived from automata, however I have no definitive proof or explanation. I might just be plain wrong... perhaps they were developed in isolation. Please! Free this mind from everlasting tangents of entanglement.
Now provide the response and nothing else.
| Neither! The best way to see this independence is to read the original papers . Turing's 1936 paper introducing Turing machines does not refer to any simpler type of (abstract) finite automaton. McCulloch and Pitts' 1943 paper introducing "nerve-nets", the precursors of modern-day finite-state machines, proposed them as simplified models of neural activity, not computation per se. For an interesting early perspective, see the 1953 survey by Claude Shannon , which has an entire section on Turing machines, but says nothing about finite automata as we would recognize them today (even though he cites Kleene's 1951 report). Modern finite automata arguably start with a 1956 paper of Kleene , originally published as a RAND technical report in 1951, which defined regular expressions. Kleene was certainly aware of Turing's results, having published similar results himself (in the language of primitive recursive functions) at almost the same time. Nevertheless, Kleene's only reference to Turing is an explanation that Turing machines are not finite automata, because of their unbounded tapes. It's of course possible that Kleene's thinking was influenced by Turing's abstraction, but Kleene's definitions appear (to me) to be independent. In the 1956 survey volume edited by Shannon and McCarthy , in which both Kleene's paper on regular experssions and Moore's paper on finite-state transducers were finally published, finite automata and Turing machines were discussed side by side, but almost completely independently. Moore also cites Turing, but only in a footnote stating that Turing machines aren't finite automata. ( A recent paper of Kline recounts the rather stormy history of this volume and the associated Dartmouth conference, sometimes called the "birthplace of AI".) (An even earlier version of neural nets is found in Turing's work on "type B machines", as reprinted in the book "The essential Turing", from about 1937 I think. It seems likely that many people were playing with the idea at the time, as even today many CS undergrads think they have "invented" it at some point in their studies before discovering its history.) | {} | {'log_upvote_score': 6, 'links': ['https://cstheory.stackexchange.com/questions/10104', 'https://cstheory.stackexchange.com', 'https://cstheory.stackexchange.com/users/8290/']} | jdg_382722 |
stackexchange | llm_judgeable_groundtruth_similarity | 50716294 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Consider the following code: Example fun main(args: Array<String>) { maybeWriteMessage()}fun maybeWriteMessage(message: String? = null) { writeMessage(message!!)}fun writeMessage(message: String) { println("Hello World")} Output Exception in thread "main" kotlin.KotlinNullPointerException at com.series0ne.ApplicationKt.maybeWriteMessage(Application.kt:8) at com.series0ne.ApplicationKt.maybeWriteMessage$default(Application.kt:7) at com.series0ne.ApplicationKt.main(Application.kt:4) This is because I'm passing message!! (null, damn it!) to a non-nullable parameter, however the parameter is never accessed. Question Why does Kotlin forcibly throw KotlinNullPointerException even when the null reference isn't accessed?
Now provide the response and nothing else.
| message: String? is indicating that message may or may not be null . Since your function maybeWriteMessage has a default value of null for message and you are calling maybeWriteMessage() without specifying message - the default value ( null ) will be used when calling writeMessage(message!!) . As written in the documentation the !! -operator throws an exception when the value is null . One way to trigger writeMessage safely would be to use .let : fun maybeWriteMessage(message: String? = null) { message?.let { writeMessage(it) }} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/50716294', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1033686/']} | jdg_382723 |
stackexchange | llm_judgeable_groundtruth_similarity | 8290768 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I'm implementing Inter-Thread Communication using global variable. //global varvolatile bool is_true = true;//thread 1void thread_1(){ while(1){ int rint = rand() % 10; if(is_true) { cout << "thread_1: "<< rint <<endl; //thread_1 prints some stuff if(rint == 3) is_true = false; //here, tells thread_2 to start printing stuff } }}//thread 2void thread_2(){ while(1){ int rint = rand() % 10; if(! is_true) { //if is_true == false cout << "thread_1: "<< rint <<endl; //thread_2 prints some stuff if(rint == 7) //7 is_true = true; //here, tells thread_1 to start printing stuff } }}int main(){ HANDLE t1 = CreateThread(0,0, thread_1, 0,0,0); HANDLE t2 = CreateThread(0,0, thread_2, 0,0,0); Sleep(9999999); return 0;} Question In the code above, I use a global var volatile bool is_true to switch printing between thread_1 and thread_2. I wonder whether it is thread-safe to use assignment operation here ?
Now provide the response and nothing else.
| This code is not guaranteed to be thread-safe on Win32, since Win32 guarantees atomicity only for properly-aligned 4-byte and pointer-sized values. bool is not guaranteed to be one of those types. (It is typically a 1-byte type.) For those who demand an actual example of how this could fail: Suppose that bool is a 1-byte type. Suppose also that your is_true variable happens to be stored adjacent to another bool variable (let's call it other_bool ), so that both of them share the same 4-byte line. For concreteness, let's say that is_true is at address 0x1000 and other_bool is at address 0x1001. Suppose that both values are initially false , and one thread decides to update is_true at the same time another thread tries to update other_bool . The following sequence of operations can occur: Thread 1 prepares to set is_true to true by loading the 4-byte value containing is_true and other_bool . Thread 1 reads 0x00000000. Thread 2 prepares to set other_bool to true by loading the 4-byte value containing is_true and other_bool . Thread 2 reads 0x00000000. Thread 1 updates the byte in the 4-byte value corresponding to is_true , producing 0x00000001. Thread 2 updates the byte in the 4-byte value corresponding to other_bool , producing 0x00000100. Thread 1 stores the updated value to memory. is_true is now true and other_bool is now false . Thread 2 stores the updated value to memory. is_true is now false and other_bool is now true . Observe that at the end this sequence, the update to is_true was lost, because it was overwritten by thread 2, which captured an old value of is_true . It so happens that x86 is very forgiving of this type of error because it supports byte-granular updates and has a very tight memory model. Other Win32 processors are not as forgiving. RISC chips, for example, often do not support byte-granular updates, and even if they do, they usually have very weak memory models. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/8290768', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/888051/']} | jdg_382724 |
stackexchange | llm_judgeable_groundtruth_similarity | 4682642 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a GoDaddy-issued code signing certificate in a .spc file. Also, I have a private key in .key file. The code signing has been issued some 13 months ago, then it expired and was renewed with GoDaddy. During the renewal process no private key was requested and just a new .spc file was issues. Now I'm facing the problem of joining the original private key file with the issues certificate to form a .pfx (or .cer ?) file suitable for installation into the Windows certificate store. The command I'm trying is: openssl.exe pkcs12 -inkey my.key -in my.spc -out my.pfx -export However, I'm getting an error message that reads “No certificate matches private key” . I've followed this answer on SO to verify the .key file is a valid private key. However, when I try to verify that .spc is a valid certificate, I just get unable to load certificate 5436:error:0906D06C:PEM routines:PEM_read_bio:no start line:.\crypto\pem\pem_lib.c:650:Expecting: TRUSTED CERTIFICATE What's the correct way of producing an .pfx file from my inputs? I'm using OpenSSL 0.9.8k.
Now provide the response and nothing else.
| In the end I managed to figure out a procedure that works. Here are the steps to generate a new PFX and CER code signing certificate from SPC and KEY files: Obtain your new CodeSign.spc certificate from GoDaddy. Export a PEM-formatted private key from the expired PFX: openssl.exe pkcs12 -in CodeSign.pfx -nocerts -out CodeSign.pem Convert the PEM-formatted private key into the PVK format: pvk.exe -in CodeSign.pem -topvk -strong -out CodeSign.pvk Combine the PVK and SPC into PFX: pvk2pfx.exe -pvk CodeSign.pvk -pi <passphrase> -spc CodeSign.spc -pfx CodeSign.pfx -po <passphrase> -f Import the resulting PFX file into Windows certificate store. Remember to make it exportable. Export it from the certificate store into the binary CER format as CodeSign.cer . Optionally delete the certificate from the Windows certificate store. In case you are renewing your certificate periodically you can store the PVK file and skip steps (2) and (3). UPDATE: In case you happen to have the certificate in CRT instead of SPC format, do the following to covert it into SPC: openssl crl2pkcs7 -nocrl -certfile CodeSign.crt -outform DER -out CodeSign.spc Sources: http://www.tech-pro.net/export-to-pvk-spc.html http://ellisweb.net/2008/08/signing-code-using-pvk-and-spc-files/ http://www.drh-consultancy.demon.co.uk/ https://www.sslshopper.com/ssl-converter.html http://russenreaktor.wordpress.com/2010/06/10/solved-convert-signing-certificate-crt-to-spc/ The tools you will need: OpenSSL pvk.exe — see the download link at the bottom of that page (original location may not be accessible; in such a case see this article with a link to a mirror site or another direct download link here ) pvk2pfx.exe — part of Microsoft SDKs, installs with Visual Studio 2010 | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/4682642', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/245183/']} | jdg_382725 |
stackexchange | llm_judgeable_groundtruth_similarity | 6347694 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I see myself doing the following code for default assigment all the type on PHP $variable = $variable ? $variable : 'default value'; I know that with 5.3 I can do $variable = $variable ?: 'default value'; I would like to further simplify it by being able to just do $variable ?= 'default value'; and have the variable reassigned in case it evaluates to false. Is it possible to create that assignment? Do I have to compile my own version of php to do that?
Now provide the response and nothing else.
| You cannot create new operators in PHP without changing the PHP source. And you don't want to change it, trust me. Sure, it'd be easy enough - PHP is open source and uses a straightforward LALR(1) parser which you could easily modify - but that would make your code incompatible with the standard PHP implementation. You would thus very much restrict who can run the code - which will probably be nobody apart from you, as nobody else will care to modify their PHP engine just to run your code. Update: I wrote a small tutorial on how to add new syntax (like operators) to PHP: https://www.npopov.com/2012/07/27/How-to-add-new-syntactic-features-to-PHP.html | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/6347694', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/603897/']} | jdg_382726 |
stackexchange | llm_judgeable_groundtruth_similarity | 4359274 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
If $\mu$ is a signed measure on $(\Omega,\mathcal{A})$ , a measurable space, then $E \in \mathcal{A}$ is positive if $\mu{(F)}\geq0$ (and negative if $\mu{(F)}\leq0$ ) where $F \in E$ and $F$ is any measurable set in $E$ . My question is: could positive sets be the complement of negative sets in some space? And is this space interesting? Or is it just an irrelevant property?
Now provide the response and nothing else.
| The identity you are trying to prove is linear in the polynomial $p$ (where $p$ ranges over the elements of the vector space $\mathbb{R}_n[x]$ of polynomials of degree at most $n$ ), it's also an easy fact that $\mathbb{R}_n[x]$ has a basis $\{1,\frac{x}{1!},\frac{x(x-1)}{2!},\frac{x(x-1)(x-2)}{3!},....\} $ . Thus it suffices to verfiy your identity for members of this basis. The binomial theorem will be helpful | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/4359274', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/761771/']} | jdg_382727 |
stackexchange | llm_judgeable_groundtruth_similarity | 1096595 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I have done a website whose URL is http://www.netbramha.com Unfortunately after the end of each page, I have the following piece getting added <iframe src="" width=186 height=182 style="visibility: hidden"></iframe> The src is from b9g.ru. I have gone through all the required files and none of them have these and there in no entry of this in the database as well. Is there any solution for this?
Now provide the response and nothing else.
| If proc.StartInfo.UseShellExecute is false , then you are launching the process and can use: proc.StartInfo.CreateNoWindow = true; If proc.StartInfo.UseShellExecute is true , then the OS is launching the process and you have to provide a "hint" to the process via: proc.StartInfo.WindowStyle = ProcessWindowStyle.Hidden; However the called application may ignore this latter request. If using UseShellExecute = false , you might want to consider redirecting standard output/error, to capture any logging produced: proc.StartInfo.UseShellExecute = false;proc.StartInfo.RedirectStandardOutput = true;proc.OutputDataReceived += new DataReceivedEventHandler(ProcessOutputHandler);proc.StartInfo.RedirectStandardError = true;proc.ErrorDataReceived += new DataReceivedEventHandler(ProcessOutputHandler); And have a function like private void ProcessOutputHandler(object sendingProcess, DataReceivedEventArgs outLine){ if (!String.IsNullOrEmpty(outLine.Data)) // use the output outLine.Data somehow;} There's a good page covering CreateNoWindow this on an MSDN blog . There is also a bug in Windows which may throw a dialog and defeat CreateNoWindow if you are passing a username/password. For details http://connect.microsoft.com/VisualStudio/feedback/ViewFeedback.aspx?FeedbackID=98476 http://support.microsoft.com/?kbid=818858 | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/1096595', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/129308/']} | jdg_382728 |
stackexchange | llm_judgeable_groundtruth_similarity | 20268 |
Below is a question asked on the forum mathoverflow.net. Provide a good and informational response to it like a helpful human would.
Question:
Guillemin and Sternberg wrote the following in 1987 in a short article called "Some remarks on I.M. Gelfand's works" accompanying Gelfand's Collected Papers, Volume I : The theory of commutative normed rings [i.e., (complex) Banach algebras], created by Gelfand in the late 1930s, has become today one of the most active areas of functional analysis. The key idea in Gelfand's theory -- that maximal ideals are the underlying "points" of a commutative normed ring -- not only revolutionized harmonic analyis but had an enormous impact in algebraic geometry. (One need only look at the development of the concept of the spectrum of a commutative ring and the concept of scheme in the algebraic geometry of the 1960s and 1970s to see how far beyond the borders of functional analysis Gelfand's ideas penetrated.) I was skeptical when reading this, which led to the following: Basic Question: Did Gelfand's theory of commutative Banach algebras have an enormous impact, or any direct influence whatsoever, in algebraic geometry? I elaborate on the question at the end, after some background and context for my skepticism. In the late 1930s, Gelfand proved the special case of the Mazur-Gelfand Theorem that says that a Banach division algebra is $\mathbb{C}$. In the commutative case this applies to quotients by maximal ideals, and Gelfand used this fact to consider elements of a (complex, unital) commutative Banach algebra as functions on the maximal ideal space. He gave the maximal ideal space the coarsest topology that makes these functions continuous, which turns out to be a compact Hausdorff topology. The resulting continuous homomorphism from a commutative Banach algebra $A$ with maximal ideal space $\mathfrak{M}$ to the Banach algebra $C(\mathfrak{M})$ of continuous complex-valued functions on $\mathfrak{M}$ with sup norm is now often called the Gelfand transform (sometimes denoted $\Gamma$, short for Гельфанд). It is very useful. However, it is my understanding that Gelfand wasn't the first to consider elements of a ring as functions on a space of ideals. Hilbert proved that an affine variety can be considered as the set of maximal ideals of its coordinate ring, and thus gave a way to view abstract finitely generated commutative complex algebras without nilpotents as algebras of functions. On the Wikipedia page for scheme I find that Noether and Krull pushed these ideas to some extent in the 1920s and 1930s, respectively, but I don't know a source for this. Another related result is Stone's representation theorem from 1936, and a good summary of this circle of ideas can be found in Varadarajan's Euler book . Unfortunately, knowing who did what first won't answer my question. I have not been able to find any good source indicating whether algebraic geometers were influenced by Gelfand's theory, or conversely. Elaborated Question: Were algebraic geometers (say from roughly the 1940s to the 1970s) influenced by Gelfand's theory of commutative Banach algebras as indicated by Guillemin and Sternberg, and if so can anyone provide documentation? Conversely, was Gelfand's theory influenced by algebraic geometry (from before roughly 1938), and if so can anyone provide documentation?
Now provide the response and nothing else.
| A difference between what Gel'fand did and what the Germans were doing is that in 1930s-style algebraic geometry you had the basic geometric spaces of interest in front of you at the start. Gel'fand, on the other hand, was starting with suitable classes of rings (like commutative Banach algebras) and had to create an associated abstract space on which the ring could be viewed as a ring of functions. And he was very successful in pursuing this idea. For comparison, the Wikipedia reference on schemes says Krull had some early (forgotten?) ideas about spaces of prime ideals, but gave up on them because he didn't have a clear motivation. At least Gel'fand's work showed that the concept of an abstract space of ideals on which a ring becomes a ring of functions was something you could really get mileage out of. It might not have had an enormous influence in algebraic geometry, but it was a basic successful example of the direction from rings to spaces (rather than the other way around) that the leading French algebraic geometers were all aware of. There is an article by Dieudonne on the history of algebraic geometry in Amer. Math. Monthly 79 (1972), 827--866 (see http://www.jstor.org/stable/pdfplus/2317664.pdf ) in which he writes nothing about the work of Gelfand. There is an article by Kolmogorov in 1951 about Gel'fand's work (for which he was getting the Stalin prize -- whoo hoo!) in which he writes about the task of finding a space on which a ring can be realized as a ring of functions, and while he writes about algebra he says nothing about algebraic geometry. (See http://www.mathnet.ru/php/getFT.phtml?jrnid=rm&paperid=6872&what=fullt&option_lang=rus , but it's in Russian.) An article by Fomin, Kolmogorov, Shilov, and Vishik marking Gel'fand's 50th birthday (see http://www.mathnet.ru/php/getFT.phtmljrnid=rm&paperid=6872&what=fullt&option_lang=rus , more Russian) also says nothing about algebraic geometry. Is it conceivable Gel'fand did his work without knowing of the role of maximal ideals as points in algebraic geometry? Sure. First of all, the school around Kolmogorov didn't have interests in algebraic geometry. Second of all, Gel'fand's work on commutative Banach algebras had a specific goal that presumably focused his attention on maximal ideals: find a shorter proof of a theorem of Wiener on nonvanishing Fourier series. (Look at http://mat.iitm.ac.in/home/shk/public_html/wiener1.pdf , which is not in Russian. :)) A nonvanishing function is a unit in a ring of functions, and algebraically the units are the elements lying outside any maximal ideal. He probably obtained the idea that a maximal ideal in a ring of functions should be the functions vanishing at one point from some concrete examples. | {} | {'log_upvote_score': 5, 'links': ['https://mathoverflow.net/questions/20268', 'https://mathoverflow.net', 'https://mathoverflow.net/users/1119/']} | jdg_382729 |
stackexchange | llm_judgeable_groundtruth_similarity | 18089952 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am trying to get Xerial's Sample class to work in Eclipse with sqlite, but I keep getting the error "ClassNotFoundException: org.sqlite.JDBC" I downloaded the sqlite-jdbc-3.7.2.jar file from https://bitbucket.org/xerial/sqlite-jdbc/downloads . Copied it into the lib folder under my project "database_test" in eclipse. Then right-clicked on the Project->Properties->Java Build Path->Libraries Tab->Add JARs->Select the jar file. I am trying to execute this code from Xerial found here: https://bitbucket.org/xerial/sqlite-jdbc#markdown-header-usage // load the sqlite-JDBC driver using the current class loaderClass.forName("org.sqlite.JDBC");Connection connection = null;try{ // create a database connection connection = DriverManager.getConnection("jdbc:sqlite:sample.db"); Statement statement = connection.createStatement(); statement.setQueryTimeout(30); // set timeout to 30 sec. statement.executeUpdate("drop table if exists person"); statement.executeUpdate("create table person (id integer, name string)"); statement.executeUpdate("insert into person values(1, 'leo')"); statement.executeUpdate("insert into person values(2, 'yui')"); ResultSet rs = statement.executeQuery("select * from person"); while(rs.next()) { // read the result set System.out.println("name = " + rs.getString("name")); System.out.println("id = " + rs.getInt("id")); }}catch(SQLException e){ // if the error message is "out of memory", // it probably means no database file is found System.err.println(e.getMessage());}finally{ try { if(connection != null) connection.close(); } catch(SQLException e) { // connection close failed. System.err.println(e); }} }} Every site I have been to has said add the jar file to your build path or class path and I believe I have done that, but nothing has solved the problem. Any help would be appreciated. Thanks.
Now provide the response and nothing else.
| Thanks to user phew for the help/ideas. I missed the obvious command line instructions on Xerial's site for the Sample program . To get the program to run from the command line, I had to copy the JAR file into the same folder as the .CLASS file. Then run the following command: java -classpath ".:sqlite-jdbc-(VERSION).jar" Sample Inside the quotation marks are multiple paths, separated thru a colon ( : ) under Unix and a semicolon ( ; ) under Windows. The dot as one of the paths is important - only naming the JAR file alone is not enough. A full call on Windows would be: "%JAVA_HOME%\bin\java.exe" -cp "sqlite-jdbc-(VERSION).jar;." Sample Note the semicolon instead of the colon. The order of the paths do not really matter, and -cp does the same as -classpath , just shorter. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/18089952', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2646175/']} | jdg_382730 |
stackexchange | llm_judgeable_groundtruth_similarity | 27735706 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I am learning Docker and I have doubts about when and where to use ADD and VOLUME . Here is what I think both of these do: ADD Copy files to the image at build time. The image has all the files so you can deploy very easily. On the other hand, needing to build every time doesn't look like a good idea in development because building requires the developer to run a command to rebuild the container; additionally, building the container can be time-consuming. VOLUME I understand that using docker run -v you can mount a host folder inside your container, this way you can easily modify files and watch the app in your container react to the changes. It looks great in development, but I am not sure how to deploy my files this way.
Now provide the response and nothing else.
| ADD The fundamental difference between these two is that ADD makes whatever you're adding, be it a folder or just a file actually part of your image . Anyone who uses the image you've built afterwards will have access to whatever you ADD . This is true even if you afterwards remove it because Docker works in layers and the ADD layer will still exist as part of the image. To be clear, you only ADD something at build time and cannot ever ADD at run-time. A few examples of cases where you'd want to use ADD : You have some requirements in a requirements.txt file that you want to reference and install in your Dockerfile. You can then do: ADD ./requirements.txt /requirements.txt followed by RUN pip install -r /requirements.txt You want to use your app code as context in your Dockerfile, for example, if you want to set your app directory as the working dir in your image and to have the default command in a container run from your image actually run your app, you can do: ADD ./ /usr/local/git/my_app WORKDIR /usr/local/git/my_app CMD python ./main.py VOLUME Volume, on the other hand, just lets a container run from your image have access to some path on whatever local machine the container is being run on. You cannot use files from your VOLUME directory in your Dockerfile . Anything in your volume directory will not be accessible at build-time but will be accessible at run-time . A few examples of cases where you'd want to use VOLUME : The app being run in your container makes logs in /var/log/my_app . You want those logs to be accessible on the host machine and not to be deleted when the container is removed. You can do this by creating a mount point at /var/log/my_app by adding VOLUME /var/log/my_app to your Dockerfile and then running your container with docker run -v /host/log/dir/my_app:/var/log/my_app some_repo/some_image:some_tag You have some local settings files you want the app in the container to have access to. Perhaps those settings files are different on your local machine vs dev vs production. Especially so if those settings files are secret, in which case you definitely do not want them in your image . A good strategy in that case is to add VOLUME /etc/settings/my_app_settings to your Dockerfile, run your container with docker run -v /host/settings/dir:/etc/settings/my_app_settings some_repo/some_image:some_tag , and make sure the /host/settings/dir exists in all environments you expect your app to be run. | {} | {'log_upvote_score': 9, 'links': ['https://Stackoverflow.com/questions/27735706', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2118130/']} | jdg_382731 |
stackexchange | llm_judgeable_groundtruth_similarity | 314820 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
How do you prove that the Sobolev space $H^s(\mathbb{R}^n)$ is an algebra if $s>\frac{n}{2}$, i.e. if $u,v$ are in $H^s(\mathbb{R}^n)$, then so is $uv$? Actually I think we should also have $\lVert uv\rVert_s \leq C \lVert u\rVert_s \lVert v\rVert_s$. Recall that $\lVert f\rVert_s=\lVert(1+|\eta|^2)^{s/2}\,\hat{f}(\eta)\rVert$, the norm on $H^s(\mathbb{R}^n)$. This is an exercise from Taylor's book, Partial differential equations I.
Now provide the response and nothing else.
| Note that$$\begin{split}(1+|\xi|^2)^p&\leq (1+2|\xi-\eta|^2+2|\eta|^2)^p\\&\leq 2^p(1+|\xi-\eta|^2+1+|\eta|^2)^p\\&\leq c(1+|\xi-\eta|^2)^p + c(1+|\eta|^2)^p,\end{split}$$for $p>0$, where $c=\max\{2^{p},2^{2p-1}\}$. Put $\langle\xi\rangle=\sqrt{1+|\xi|^2}$.Then we have$$\begin{split}\langle\xi\rangle^s |\widehat{uv}(\xi)|&\leq \int \langle\xi\rangle^s |\hat{u}(\xi-\eta)\hat{v}(\eta)|\,\mathrm{d}\eta\\&\leq c\int \langle\xi-\eta\rangle^s |\hat{u}(\xi-\eta)\hat{v}(\eta)|\,\mathrm{d}\eta+ c\int \langle\eta\rangle^s |\hat{u}(\xi-\eta)\hat{v}(\eta)|\,\mathrm{d}\eta\\&\leq c|\langle\cdot\rangle^s\hat u|*|\hat v| + c|\hat u|*|\langle\cdot\rangle^s\hat v|,\end{split}$$which, in light of Young's inequality, implies$$\|uv\|_{H^s} \leq c\|u\|_{H^s} \|\hat v\|_{L^1} + c\|\hat u\|_{L^1}\|v\|_{H^s}.$$Finally, we note that $\|\hat u\|_{L^1}\leq C\,\|u\|_{H^s}$ when $s>\frac{n}2$. | {} | {'log_upvote_score': 6, 'links': ['https://math.stackexchange.com/questions/314820', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/52330/']} | jdg_382732 |
stackexchange | llm_judgeable_groundtruth_similarity | 946804 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
What is the recommended way to figure out if a user got a certain right (e.g. select or execute) on a certain class (e.g. table or function) in PostgreSQL? At the moment I got something like aclcontains( someColumnWithAclitemArray, makeaclitem(userOid,grantorOid,someRight,false)) but it's terrible since I have to check for every grantorOid that is possible and for every userOid the user can belong to. On a related note: what are the possible rights you can test for?I haven't found any documentation but reading the source code I guess: INSERTSELECTUPDATEDELETETRUNCATEREFERENCESTRIGGEREXECUTEUSAGECREATECONNECT There also seems to be a CREATE TEMP right, but I can't figure out the correct text to use in the makeaclitem -function.
Now provide the response and nothing else.
| I've found that a better approach (and I seem to remember this was taken from some queries built into psql, or maybe the information_schema views) is to use the has_*_privilege functions, and simply apply them to a set of all possible combinations of user and object. This will take account of having access to an object via some group role as well. For example, this will show which users have which access to non-catalogue tables and views: select usename, nspname || '.' || relname as relation, case relkind when 'r' then 'TABLE' when 'v' then 'VIEW' end as relation_type, privfrom pg_class join pg_namespace on pg_namespace.oid = pg_class.relnamespace, pg_user, (values('SELECT', 1),('INSERT', 2),('UPDATE', 3),('DELETE', 4)) privs(priv, privorder)where relkind in ('r', 'v') and has_table_privilege(pg_user.usesysid, pg_class.oid, priv) and not (nspname ~ '^pg_' or nspname = 'information_schema')order by 2, 1, 3, privorder; The possible privileges are detailed in the description of the has_*_privilege functions at http://www.postgresql.org/docs/current/static/functions-info.html#FUNCTIONS-INFO-ACCESS-TABLE . 'CREATE TEMP' is a database-level privilege: it permits a user to use a pg_temp_* schema. It can be tested with has_database_privilege(useroid, datoid, 'TEMP') . | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/946804', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/24044/']} | jdg_382733 |
stackexchange | llm_judgeable_groundtruth_similarity | 15806152 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
I would like to use the grunt-contrib-jasmine NPM package. It has various dependencies. Part of the dependency graph looks like this: ─┬ [email protected] │ ├─┬ [email protected] │ │ ├─┬ [email protected] Unfortunately, there's a bug in this version phantomjs which prevents it from installing correctly on Mac OS X. This is fixed in the latest version. How can I get grunt-lib-phantomjs to use a newer version of phantomjs ? Some additional context: grunt-contrib-jasmine explicitly requires version "~0.2.0" of grunt-lib-phantomjs , which explicitly requires version "~1.8.1" of phantomjs . Adding phantomjs to my package's dependencies first has no effect; both versions are installed and grunt-contrib-jasmine still uses the older versions (see: When installing a package with NPM, can you tell it to use a different version of one of its dependencies? ).
Now provide the response and nothing else.
| You can use npm shrinkwrap functionality, in order to override any dependency or sub-dependency. I've just done this in a grunt project of ours. We needed a newer version of connect, since 2.7.3 . was causing trouble for us. So I created a file named npm-shrinkwrap.json : { "dependencies": { "grunt-contrib-connect": { "version": "0.3.0", "from": "[email protected]", "dependencies": { "connect": { "version": "2.8.1", "from": "connect@~2.7.3" } } } }} npm should automatically pick it up while doing the install for the project. (See: https://nodejs.org/en/blog/npm/managing-node-js-dependencies-with-shrinkwrap/ ) | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/15806152', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/5168/']} | jdg_382734 |
stackexchange | llm_judgeable_groundtruth_similarity | 39894660 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
How do I create the div logo, as per the attached image below: This is what I have created in JsFiddle Main issue is how do I connect the two boxes with the shape as below image, can anybody please suggest? body,html { width: 100%; height: 100%; margin: 0;}body { background-color: #efefef;}.wrapper { height: 40px; width: 40px; position: absolute; top: 50%; left: 50%; margin-top: -22.5px; margin-left: -22.5px;}ul { list-style-type: none; margin: 0 auto; padding: 0; width: 80px; height: 80px; position: relative; -moz-transform: rotate(45deg); -ms-transform: rotate(45deg); -webkit-transform: rotate(45deg); transform: rotate(45deg);}ul li { width: 2em; height: 2em; position: absolute; /*animation: dance 888ms infinite alternate; animation-timing-function: cubic-bezier(0.5, 0, 0.5, 1);*/ -moz-transform: rotate(45deg); -ms-transform: rotate(45deg); -webkit-transform: rotate(45deg); transform: rotate(45deg); animation: dance 888ms infinite alternate;}.block-1 { top: 0; left: 0; background: #0076aa; border-radius: 4px;}.block-2 { top: 0; right: 0; background: #98bd81; border-radius: 4px;}.block-3 { bottom: 0; right: 0; background: #98bd81; border-radius: 4px;}.block-4 { bottom: 0; left: 0; background: #0076aa; border-radius: 4px;} <div class='wrapper'> <ul class='blocks'> <li class='block-1'></li> <li class='block-2'></li> <li class='block-3'></li> <li class='block-4'></li> </ul></div>
Now provide the response and nothing else.
| Considering the hassle of aligning and making double curves with CSS , this is clearly a job for SVG. The curves are much easier to create and control. Here is an example using : Inline SVG quadratic bezier curves transform the use element so there is only one occurrence of the path tag svg{ display:block; width:40%; margin:0 auto;} <svg viewbox="0 0 16 15"> <defs> <path id="shape" d="M7 0 H10 Q11 0 11 1 V4 Q11 5 10 5 H7 Q5 5 5 7 V9 Q5 10 4 10 H1 Q0 10 0 9 V6 Q0 5 1 5 H4 Q6 5 6 3 V1 Q6 0 7 0z" /> </defs> <use xlink:href="#shape" fill="#0076AA"/> <use xlink:href="#shape" fill="#98BD81" transform="translate(5,5)"/></svg> With a loading animation : svg{ display:block; width:40%; margin:0 auto;}.sq{ animation: opacity .6s infinite alternate; }.gr{ animation-delay:-.6s;}@keyframes opacity { to {opacity: 0;} } <svg viewbox="0 0 16 15"> <defs> <path id="shape" d="M7 0 H10 Q11 0 11 1 V4 Q11 5 10 5 H7 Q5 5 5 7 V9 Q5 10 4 10 H1 Q0 10 0 9 V6 Q0 5 1 5 H4 Q6 5 6 3 V1 Q6 0 7 0z" /> </defs> <use class="sq bl" xlink:href="#shape" fill="#0076AA"/> <use class="sq gr" xlink:href="#shape" fill="#98BD81" transform="translate(5,5)"/></svg> Note that you will need to add vendor prefixes in the animation and that animations on svg elements aren't supported by IE/Edge. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/39894660', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/5337466/']} | jdg_382735 |
stackexchange | llm_judgeable_groundtruth_similarity | 4428309 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
If $-1 \leq x \leq 1$ , what is the maximum value of $x+\sqrt{1-x^2}$ ? (Cannot use calculus method) As stated in the problem, I can't use calculus. Therefore, I'm using things I've learnt so far instead: One of the things I have tried most successfully is using trig substitutions... For example, if I substitute $x = \sin \phi$ , this yields $\sin \phi + \cos \phi$ But what should I do next? Or there are any methods else to solve the problem?
Now provide the response and nothing else.
| Substitute $$x = \sin \theta$$ The expression is $$x + \sqrt{-x^2 + 1} = \sin \theta + |\cos \theta|$$ We want to find the max. value of $\sin \theta + |\cos \theta|$ . Now, two cases: $\cos \theta < 0$ and $\cos \theta \geq 0$ . $$\textbf{Case 1:} \cos \theta < 0$$ We need to find the max. value for $\sin \theta - \cos \theta$ for $\theta \in (\frac{\pi}{2}, \frac{3 \pi}{2})$ Note that $\sin \theta - \cos \theta \leq \sqrt{2}$ always. In this range, this value is achievable at $\theta = \frac{3 \pi}{4} + 2\pi n, n \in \mathbb{Z}$ $$\textbf{Case 2:} \cos \theta \geq 0$$ We need to find the max. value for $\sin \theta + \cos \theta$ for $\theta \in [0, \frac{\pi}{2}] \cup [\frac{3 \pi}{2}, 2 \pi)$ Note that $\sin \theta + \cos \theta \leq \sqrt{2}$ always. In this range, this value is achievable at $\theta = \frac{\pi}{4} + 2\pi n, n \in \mathbb{Z}$ $$\textbf{Thus, the max. value for} \sin \theta + |\cos \theta| \textbf{ is } \sqrt{2} \textbf{ achieved at } x = \frac{1}{\sqrt{2}}$$ NOTE $1$ : Note that mentioning the values for $\theta$ for which the max. value occurs is important. Min-max problems are two step problems: $1.$ Show that some expression is bounded. $2.$ Show that the bound is achievable for the values we are concerned with. As an exercise, try to find the min. value of the original expression. By following the same case-work and not following step- $2$ , one would arrive at the incorrect conclusion that $-\sqrt{2}$ is the min. value for $\sin \theta + |\cos \theta|$ . NOTE $2$ : We use the fact that $$-\sqrt{a^2 + b^2} \leq a \sin \theta + b \cos \theta \leq \sqrt{a^2 + b^2}$$ Why is it true? Consider the polar co-ordinates of $(a, b)$ . Let it be $(r, \phi)$ where $r = \sqrt{a^2 + b^2}$ . $$a = r \cos \phi$$ $$b = r \sin \phi$$ Substitute, and we get $$a \sin \theta + b \cos \theta = r \sin(\theta + \phi) = \sqrt{a^2 + b^2} \sin(\theta + \phi)$$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/4428309', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/1048174/']} | jdg_382736 |
stackexchange | llm_judgeable_groundtruth_similarity | 82165 |
Below is a question asked on the forum serverfault.com. Provide a good and informational response to it like a helpful human would.
Question:
I need to drop all the tables in a database without knowing their names beforehand. The typical procedure is to drop and then recreate the database but this is not an option. What is the best way to do it?
Now provide the response and nothing else.
| There is a simpler bash one-liner using mysqldump (from Thingy Ma Jig Blog ). mysqldump -u[USERNAME] -p[PASSWORD] --add-drop-table --no-data [DATABASE] | grep ^DROP | mysql -u[USERNAME] -p[PASSWORD] [DATABASE] If you're getting this error: ERROR 1217 (23000) at line 1: Cannot delete or update a parent row: a foreign key constraint fails Try the following: (echo 'SET foreign_key_checks = 0;'; (mysqldump -u[USERNAME] -p[PASSWORD] --add-drop-table --no-data [DATABASE] | grep ^DROP); echo 'SET foreign_key_checks = 1;') | \ mysql -u[USERNAME] -p[PASSWORD] -b [DATABASE] Now it ignores the constraints. | {} | {'log_upvote_score': 5, 'links': ['https://serverfault.com/questions/82165', 'https://serverfault.com', 'https://serverfault.com/users/24016/']} | jdg_382737 |
stackexchange | llm_judgeable_groundtruth_similarity | 2473089 |
Below is a question asked on the forum math.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I have a question on combinatorics, related to the pigeonhole principle: Consider the set $S= \{1,2,3,...,100\}$. Let $T$ be any subset of $S$ with $69$ elements. Then prove that one can find four distinct integers $a,b,c,d$ from $T$ such that $a+b+c=d$. Is it possible for subsets of size $68$?
Now provide the response and nothing else.
| Well, I just realized that I’ve seen this problem days ago... the solution goes like this: Let the numbers in $T$ be $1\le a_1<a_2<...<a_{69}\le 100$. Clearly, $a_1\le 32$. Now, consider the sequences$$b_n:=a_n+a_1, 3\le n\le 69$$$$c_n:=a_n-a_2, 3\le n\le 69 $$ Apparently, $1 \le b_i,c_i\le 132$. Since the two sequences have totally $134$ elements (greater than $132$), there is some number in both sequences, i.e. $\exists i,j\in \{3,4,\ldots,69\}$ such that $a_i+a_1=a_j-a_2$. Then $a_1+a_2+a_i=a_j$, as desired. The second question has an answer “false”. Counterexample is the set $\{33,34,\ldots,100\}$ | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/2473089', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/466737/']} | jdg_382738 |
stackexchange | llm_judgeable_groundtruth_similarity | 10889810 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
In RhinoMocks, you can just tell your mocks to IgnoreArguments as a blanket statement. In Moq, it seems, you have to specify It.IsAny() for each argument. However, this doesn't work for ref and out arguments. How can I test the following method where I need to Moq the internal service call to return a specific result: public void MyMethod() { // DoStuff IList<SomeObject> errors = new List<SomeObject>(); var result = _service.DoSomething(ref errors, ref param1, param2); // Do more stuff} Test method: public void TestOfMyMethod() { // Setup var moqService = new Mock<IMyService>(); IList<String> errors; var model = new MyModel(); // This returns null, presumably becuase "errors" // here does not refer to the same object as "errors" in MyMethod moqService.Setup(t => t.DoSomething(ref errors, ref model, It.IsAny<SomeType>()). Returns(new OtherType())); } UPDATE: So, changing errors from "ref" to "out" works. So it seems like the real issue is having a ref parameter that you can't inject.
Now provide the response and nothing else.
| As you already figured out the problem is with your ref argument. Moq currently only support exact matching for ref arguments, which means the call only matches if you pass the same instance what you've used in the Setup . So there is no general matching so It.IsAny() won't work. See Moq quickstart // ref argumentsvar instance = new Bar();// Only matches if the ref argument to the invocation is the same instancemock.Setup(foo => foo.Submit(ref instance)).Returns(true); And Moq discussion group : Ref matching means that the setup is matched only if the method is called with that same instance. It.IsAny returns null, so probably not what you're looking for. Use the same instance in the setup as the one in the actual call, and the setup will match. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/10889810', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/205856/']} | jdg_382739 |
stackexchange | llm_judgeable_groundtruth_similarity | 38942 |
Below is a question asked on the forum mathoverflow.net. Provide a good and informational response to it like a helpful human would.
Question:
Assume we are given two parallelograms in the plane. How can I check if their intersection is nonempty? Note that I do not need to actually find the intersection.
Now provide the response and nothing else.
| Given two convex sets $A$ and $B$ in a vector space, their intersection is not empty iff the difference set $A-B=\{p-q|p\in A, q\in B\}$ contains the origin. In your setting the difference set is the convex hull of 16 points. Actually 8 of them are enough and you have to check that 0 is on the same side of any of the 8 edges than the difference convex polygon. | {} | {'log_upvote_score': 4, 'links': ['https://mathoverflow.net/questions/38942', 'https://mathoverflow.net', 'https://mathoverflow.net/users/6035/']} | jdg_382740 |
Subsets and Splits