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 | 383045 |
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 the Best Practices to improve web site Performance http://developer.yahoo.com/performance/rules.html , Steve Souders mentioned one rule "Move Scripts to the Bottom". It's a little confusing. Actually, I notice that a lot of web pages that doesn't put script at bottom, while YSlow still mark A for these pages. So, when should I follow the rule "Put Scripts at the Bottom"?
Now provide the response and nothing else.
| When a user requests a page from your site, the page HTML starts streaming to the browser. As soon as a browser encounters a tag for an external image, script, CSS file, etc., it will start downloading that file simultaneously. If you put your scripts at the bottom of a page, they'll be loaded last. In other words, the HTML content/structure/css/images of youe page/app will be loaded first, and something can show up in the browser faster; Your users don't have to wait for a script to finish downloading before they see something in your application. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/383045', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/26349/']} | jdg_382841 |
stackexchange | llm_judgeable_groundtruth_similarity | 5048728 |
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 Fluent NHibernate for my data-persistence in a web application. My problem... I have a base class that maps all entities with an ID property of type T (almost always an int or GUID) using GeneratedBy().Identity() On application start-up, I have a boot-strapper that checks and verifies the needed seed-data is populated. My problem is, some of the seed-data that is populated needs a specific ID. (IDs that would correspond to an enum or system user) Is there any way to force NHibernate to commit the record using the ID that I specify, rather than an auto-generated one? Any other commits to the repository thereafter can be auto-generated.
Now provide the response and nothing else.
| Id(x => x.Id).GeneratedBy.Assigned(); If you want the application to assign identifiers (as opposed to having NHibernate generate them), you may use the assigned generator. This special generator will use the identifier value already assigned to the object's identifier property. Be very careful when using this feature to assign keys with business meaning (almost always a terrible design decision). Due to its inherent nature, entities that use this generator cannot be saved via the ISession's SaveOrUpdate() method. Instead you have to explicitly specify to NHibernate if the object should be saved or updated by calling either the Save() or Update() method of the ISession . http://nhibernate.info/doc/nhibernate-reference/mapping.html#mapping-declaration-id-assigned | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/5048728', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/624053/']} | jdg_382842 |
stackexchange | llm_judgeable_groundtruth_similarity | 249151 |
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 have an EC2 Large instance dedicated to MySQL. It will be serving a Joomla/Magento combo so it has a blend of InnoDB and MyISAM tables. I have only worked with MyISAM in the past and am therefore unfamiliar with the settings InnoDB uses. Experiments so far have been less than fruitful, as I keep causing the InnoDB engine to be disabled. My instance is running Ubuntu 10.04 64 bit server edition and has ~7.5G of ram. MySQL is currently using ~0.6% of that, with somewhat poor performance. I would like to configure it to use as much of the system RAM as is reasonable. Testing some settings I learned that the InnoDB logs can't collectively be larger than 4G. Would anyone be able to provide some base InnoDB and MyISAM settings to get my started. Thank youTim
Now provide the response and nothing else.
| I'm running the same sort of Mysql server on EC2. Don't touch /etc/mysql/my.cnf, but instead put config files into /etc/mysql/conf.d/ This will let you manage your changes for specific engines and give admins after you additional clues to how things were configured. Also it make it easy to backup any changes you've made as well as track them. /etc/mysql/conf.d/innodb_mysql.cnf [mysqld] # innodb settings innodb_additional_mem_pool_size = 12Minnodb_buffer_pool_size = 2Ginnodb_file_per_table = 1innodb_flush_log_at_trx_commit = 2innodb_lock_wait_timeout = 180innodb_log_buffer_size = 16Minnodb_open_files = 512innodb_thread_concurrency = 0 Most of these settings are pretty standard and you should definitely look at Percona's recommendations . You could got as high as 6G on your system, but I'd start small. Also with myisam tables I'd probably stop at 4G. I would not touch the innodb log file sizes, there is very little gain to be had there. Increasing the log_buffer_size and addition_mem_pool also has very little return after an initial bump. Also the settings above are for better performance and not for transaction consistency. Assuming you're running just a web app the above is fine, but not for a banking system. /etc/mysql/conf.d/general_mysql.cnf [mysqld]# general settingskey_buffer = 384M key_buffer is the most useful for myisam and Mysql in general The default it's only 16M which is very small on an 8GB machine. Again I'd start with a good jump and see if you get improvement. Keep in mind that myisam buffers and innodb buffers are not shared so they need to be collectively less than then amount of RAM you have. Later you might look at sort and read buffers as well. | {} | {'log_upvote_score': 4, 'links': ['https://serverfault.com/questions/249151', 'https://serverfault.com', 'https://serverfault.com/users/75026/']} | jdg_382843 |
stackexchange | llm_judgeable_groundtruth_similarity | 3198443 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Between these two: With Property: class WithProperty{ public string MyString {get; set;}} With Field: class WithField{ public string MyString;} Apparently I'm supposed to pick the first one. Why? I've heard the argument that the point here is to allow interface changes, butif I have the second one, and change it to the first one, no other code shouldever have to change. When recompiled everything's just going to point to theproperty instead. Am I missing something important here?
Now provide the response and nothing else.
| The most important difference is the fact, that if you use a field, and later need to change it to a property (say, to enforce some validation), then all libraries calling your code will need to be recompiled. It's true that you can compile the exact same code if the name stays the same - but the consumers of your code will still need to be recompiled. This is because the IL generated to get the value is different between a field and a property. If it already is a property, you can make a change without forcing consumers of your code to change. This may or may not be an issue for you. But the property is almost the same amount of code, and is considered best practice. I would always go for the property. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3198443', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/82320/']} | jdg_382844 |
stackexchange | llm_judgeable_groundtruth_similarity | 20612535 |
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 Bootstrap 3 , i am trying to give height to table and row , but nothing is working for me . I tried setting line-height and other properties of table, how can I increase height? <style> div#description { background-color: gray; height: 25%; border: 2px black; } tr { line-height: 25px; } .container { height: 100% } table { height: 100% } #topics tr { line-height: 14px; }</style></head><body> <div class="container"> <div class="row"> <div class="col-md-7 col-xs-10 pull-left"> <p>Hello</p> <div class="table-responsive"> <table class="table table-bordered "> <tbody> <tr> <td></td> <td></td> <td></td> <td></td> <td></td> </tr> <tr> <td></td> <td></td> <td></td> <td></td> <td></td> </tr> <tr> <td></td> <td></td> <td></td> <td></td> <td></td> </tr> <tr> <td></td> <td></td> <td></td> <td></td> <td></td> </tr> <tr> <td></td> <td></td> <td></td> <td></td> <td></td> </tr> <tr> <td></td> <td></td> <td></td> <td></td> <td></td> </tr> <tr> <td></td> <td></td> <td></td> <td></td> <td></td> </tr> <tr> <td></td> <td></td> <td></td> <td></td> <td></td> </tr> </tbody> </table> </div> </div> <div class="col-md-5 col-xs-8 pull-right" id="description"> <p>Hello2</p> </div> </div> </div>
Now provide the response and nothing else.
| For the <tr> 's just set tr { line-height: 25px; min-height: 25px; height: 25px;} It works with bootstrap also. For the 100% height, 100% must be 100% of something . Therefore, you must define a fixed height for one of the containers, or the body. I guess you want the entire page to be 100%, so (example) : body { height: 700px;}.table100, .row, .container, .table-responsive, .table-bordered { height: 100%;} A workaround not to set a static height is by forcing the height in code according to the viewport : $('body').height(document.documentElement.clientHeight); all the above in this fiddle -> http://jsfiddle.net/LZuJt/ Note : I do not care that you have 25% height on #description , and 100% height on table. Guess it is just an example. And notice that clientHeight is not right since the documentElement is an iframe, but you'll get the picture in your own projekt :) | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/20612535', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2293570/']} | jdg_382845 |
stackexchange | llm_judgeable_groundtruth_similarity | 6242296 |
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 have a simple way of checking for an object to be valid. I thought of a simple conversion function, something like this: operator bool() const { return is_valid; } Checking for it to be valid would be very simple now // is my object invalid?if (!my_object) std::cerr << "my_object isn't valid" << std::endl; Is this considered a good practise?
Now provide the response and nothing else.
| In C++03, you need to use the safe bool idiom to avoid evil things: int x = my_object; // this works In C++11 you can use an explicit conversion: explicit operator bool() const{ // verify if valid return is_valid;} This way you need to be explicit about the conversion to bool, so you can no longer do crazy things by accident (in C++ you can always do crazy things on purpose): int x = my_object; // does not compile because there's no explicit conversionbool y = bool(my_object); // an explicit conversion does the trick This still works as normal in places like if and while that require a boolean expression, because the condition of those statements is contextually converted to bool: // this uses the explicit conversion "implicitly"if (my_object){ ...} This is documented in §4[conv] : An expression e can be implicitly converted to a type T if and only if the declaration T t=e; is well-formed, for some invented temporary variable t (§8.5). Certain language constructs require that an expression be converted to a Boolean value. An expression e appearing in such a context is said to be contextually converted to bool and is well-formed if and only if the declaration bool t(e); is well-formed, for some invented temporary variable t (§8.5). The effect of either implicit conversion is the same as performing the declaration and initialization and then using the temporary variable as the result of the conversion. (What makes the difference is the use of bool t(e); instead of bool t = e; .) The places were this contextual conversion to bool happens are: the conditions of if , while , and for statements; the operators of logical negation ! , logical conjunction && , and logical disjunction || ; the conditional operator ?: ; the condition of static_assert ; the optional constant expression of the noexcept exception specifier; | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/6242296', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/211359/']} | jdg_382846 |
stackexchange | llm_judgeable_groundtruth_similarity | 39971932 |
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 ensure that certain nodes are always rendered on top of other nodes and am having a hard time doing so. Is this possible? I'm using visNetwork with shiny and want visIgraph for the drl layout. It is possible to render nodes on top of other nodes using igraph alone as igraph draws nodes as they appear in the data; this doesn't appear to be the case with visNetwork In the code below, I would like to get the group 'Other Group' to be always rendered on top of 'Blue Group'; the smaller nodes will be rendered above the larger nodes. require(shiny)require(visNetwork)require(igraph)require(gplots)nodes <- data.frame(id = 1:1000, color=colors()[350:449], stringsAsFactors=FALSE)nodes$group <- ifelse(grepl('blue',nodes$color), 'Blue Group', 'Other Group')nodes$color <- col2hex(nodes$color)nodes$color.background <- nodes$coloredges <- data.frame(from = sample.int(1000,1500,replace=TRUE) , to = sample.int(1000,1500,replace=TRUE))g=graph_from_data_frame(edges, directed=FALSE, vertices=nodes)server <- function(input, output) { output$network <- renderVisNetwork({ # minimal example withProgress(message = 'Making plot', value = .5, { visIgraph(igraph=g, layout = "layout_with_drl", randomSeed = 1 , idToLabel=FALSE, type='square') %>% visGroups(groupname = "Blue Group", value=5) %>% visGroups(groupname = "Other Group", value=3) }) })}ui <- fluidPage( visNetworkOutput("network"))shinyApp(ui = ui, server = server) Thanks in advance.
Now provide the response and nothing else.
| Everything between : and the = is a type hint, so primes is indeed defined as List[int] , and initially set to an empty list (and stats is an empty dictionary initially, defined as Dict[str, int] ). List[int] and Dict[str, int] are not part of the next syntax however, these were already defined in the Python 3.5 typing hints PEP. The 3.6 PEP 526 – Syntax for Variable Annotations proposal only defines the syntax to attach the same hints to variables; before you could only attach type hints to variables with comments (e.g. primes = [] # List[int] ). Both List and Dict are Generic types, indicating that you have a list or dictionary mapping with specific (concrete) contents. For List , there is only one 'argument' (the elements in the [...] syntax), the type of every element in the list. For Dict , the first argument is the key type, and the second the value type. So all values in the primes list are integers, and all key-value pairs in the stats dictionary are (str, int) pairs, mapping strings to integers. See the typing.List and typing.Dict definitions, the section on Generics , as well as PEP 483 – The Theory of Type Hints . Like type hints on functions, their use is optional and are also considered annotations (provided there is an object to attach these to, so globals in modules and attributes on classes, but not locals in functions) which you could introspect via the __annotations__ attribute. You can attach arbitrary info to these annotations, you are not strictly limited to type hint information. You may want to read the full proposal ; it contains some additional functionality above and beyond the new syntax; it specifies when such annotations are evaluated, how to introspect them and how to declare something as a class attribute vs. instance attribute, for example. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/39971932', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/5487483/']} | jdg_382847 |
stackexchange | llm_judgeable_groundtruth_similarity | 222158 |
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'm working with a team building a RESTful web service, and our current implementation utilizes the user's email as a unique identifier for the user resource, yielding URIs like the following: https://www.domain.com/users/[email protected]/resource Emails are guaranteed to be unique in our system, and we've handled when the user changes his/her email, so it seems OK. But is it correct ? The debate is whether we should use an immutable user ID instead, which in our case would look more like: https://www.domain.com/users/a36571b87be464728c8d/resource Or perhaps something else altogether. For instance, several Google APIs simply use /users/me/resource and identify the user via auth data. In a nutshell, is it acceptable to use a unique but mutable identifier in our URIs, or should we use an immutable one? Thanks!
Now provide the response and nothing else.
| There are two sub-questions to your question: Can I use unique but mutable identifiers in my URLs? This can work well if either the IDs change only infrequently or if the URLs containing those IDs are not used outside your site.As REST APIs usually are built on the premise that any given URL can be re-used to access the same resource at any later time, that second condition goes a bit against the idea of REST. That leaves the probability of changes to the ID and if you are willing/able to redirect requests made using an old ID. With (encoded) email addresses, this can probably be realized, because an old email address will not be re-used by a different user that often. Can I use email addresses as my unique ID? As indicated by the answers of @LucFranken and @9000 , using a plain email address in your URL is a bad idea, but you can use an 'encrypted' form of an email address as ID. This 'encryption' can be as simple as base64 encoding. | {} | {'log_upvote_score': 4, 'links': ['https://softwareengineering.stackexchange.com/questions/222158', 'https://softwareengineering.stackexchange.com', 'https://softwareengineering.stackexchange.com/users/51866/']} | jdg_382848 |
stackexchange | llm_judgeable_groundtruth_similarity | 2368337 |
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 integrate a multivariable function in SciPy over a 2D area.What would be the equivalent of the following Mathematica code? In[1]:= F[x_, y_] := Cos[x] + Cos[y] In[2]:= Integrate[F[x, y], {x, -\[Pi], \[Pi]}, {y, -\[Pi], \[Pi]}]Out[2]= 0 Looking at the SciPy documentation I could only find support for one-dimensional quadrature. Is there a way to do multidimensional integrals in SciPy?
Now provide the response and nothing else.
| I think it would work something like this: def func(x,y): return cos(x) + cos(y)def func2(y, a, b): return integrate.quad(func, a, b, args=(y,))[0]print integrate.quad(func2, -pi/2, pi/2, args=(-pi/2, pi/2))[0] Wolfram|Alpha agrees edit: I just discovered dblquad which seems to do exactly what you want: print integrate.dblquad(func, -pi/2, pi/2, lambda x:-pi/2, lambda x:pi/2)[0] | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2368337', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/134397/']} | jdg_382849 |
stackexchange | llm_judgeable_groundtruth_similarity | 19894952 |
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 Chart.js ( http://www.chartjs.org/docs/ ) for charting. I need to get the data from an Ajax request and the chart to be responsive. In my HTML code I added a canvas as follows: <div> <canvas id="userscreated" class="plot" data-url="/stats/userscreated"></canvas></div> And in my javascript (JQuery) code I have: var data2;$.ajax({ url: $('#userscreated').data('url'), async: true, dataType: 'json', type: "get",}).done(function (data) { data2 = data; // Draw chart var context = $('#userscreated').get(0).getContext("2d"); var wrapper = $('#userscreated').parent(); var width = $('#userscreated').attr('width', $(wrapper).width()); new Chart(context).Line( { labels: data.Dates, datasets: [ { fillColor: #404040, data: data.Users } ] }, { animation: false } );});// Redraw the chart with the same data$(window).resize(function () { var context = $('#userscreated').get(0).getContext("2d"); var wrapper = $('#userscreated').parent(); var width = $('#userscreated').attr('width', $(wrapper).width()); new Chart(context).Line( { labels: data2.Dates, datasets: [ { fillColor: #404040, data: data2.Users } ] }, { animation: false } );}); PROBLEMS The chart is not being resized on window resize. Is there better code to do this? I think I am repeating to much code. In Google the drawing is fast. In firefox sometimes it hangs for a while.Is anything wrong with my code? Should the request be async or not?
Now provide the response and nothing else.
| You can make async AJAX calls no problem. It's just important that you setup the chart only after the success callback fires. Otherwise, you'll get issues with your canvas context not being defined. The first call to respondCanvas does the initial setup while the subsequent calls do the resizing. Here is what works for me: var max = 0;var steps = 10;var chartData = {};function respondCanvas() { var c = $('#summary'); var ctx = c.get(0).getContext("2d"); var container = c.parent(); var $container = $(container); c.attr('width', $container.width()); //max width c.attr('height', $container.height()); //max height //Call a function to redraw other content (texts, images etc) var chart = new Chart(ctx).Line(chartData, { scaleOverride: true, scaleSteps: steps, scaleStepWidth: Math.ceil(max / steps), scaleStartValue: 0 });}var GetChartData = function () { $.ajax({ url: serviceUri, method: 'GET', dataType: 'json', success: function (d) { chartData = { labels: d.AxisLabels, datasets: [ { fillColor: "rgba(220,220,220,0.5)", strokeColor: "rgba(220,220,220,1)", pointColor: "rgba(220,220,220,1)", pointStrokeColor: "#fff", data: d.DataSets[0] } ] }; max = Math.max.apply(Math, d.DataSets[0]); steps = 10; respondCanvas(); } });};$(document).ready(function() { $(window).resize(respondCanvas); GetChartData();}); If you want to insert a small delay between calls, you can use a timeout: $(document).ready(function() { $(window).resize(setTimeout(respondCanvas, 500)); GetChartData();}); The delay will make your resizing more responsive in case you have a large dataset on your graph. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/19894952', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/577805/']} | jdg_382850 |
stackexchange | llm_judgeable_groundtruth_similarity | 194204 |
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 can one solve the following differential equation $$f'' + f =0$$ with the usage of power series? Writing: $$f(x) = \displaystyle\sum_{k=0}^{\infty} a_k x^k$$ $$f'(x) = \displaystyle\sum_{k=1}^{\infty} a_k k x^{k-1}$$ $$f'' (x) = \displaystyle\sum_{k=2}^{\infty} k (k-1) a_k x^{k-2}$$ How to continue?
Now provide the response and nothing else.
| I would suggest not using summation notation for a while. Let $$f(x)=a_0+a_1x+a_2x^2+a_3x^3+a_4x^4+a_5x^5+\cdots.$$Then$$f''(x)=(2)(1)a_2+(3)(2)a_3 x+(4)(3)a_4x^2+(5)(4)a_5x^3+\cdots.$$The power series expansion of $f''(x)+f(x)$ is easy to write down using the above equations. Note that all the coefficients must be $0$. We can't say anything about $a_0$ or $a_1$. But the constant term in the expansion of $f''(x)+f(x)$ must be $0$. Thus$$a_0+(2)(1)a_2=0,$$so $a_2=-\dfrac{a_0}{(2)(1)}$. The coefficient of $x$ in the expansion of $f''(x)+f(x)$ must be $0$. Thus$$a_1+(3)(2)a_3=0,$$and therefore $a_3=-\dfrac{a_1}{(3)(2)}$. The coefficient of $x^2$ must be $0$. So$$a_2+(4)(3)a_4=0.$$Thus $a_4=-\dfrac{a_2}{(4)(3)}=\dfrac{a_0}{(4)(3)(2)(1)}$. The coefficient of $x^3$ must be $0$. So$$a_3+(5)(4)a_5=0.$$Thus $a_5=-\dfrac{a_3}{(5)(4)}=\dfrac{a_1}{(5)(4)(3)(2)}$. I will stop here. You may want to calculate $a_6$. What is going on will become clear. Then you may want to start using general indices. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/194204', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/39784/']} | jdg_382851 |
stackexchange | llm_judgeable_groundtruth_similarity | 40864 |
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 polynomial such as $X^4 + 4X^3 + 6X^2 + 4X + 1,$ where the coefficients are symmetrical, I know there's a trick to quickly find the zeros. Could someone please refresh my memory?
Now provide the response and nothing else.
| Hint: This particular polynomial is very nice, and factors as $(X+1)^4$. Take a look at Pascal's Triangle and the Binomial Theorem for more details. Added: Overly complicated formula The particular quartic you asked about had a nice solution, but lets find all the roots of the more general $$ax^{4}+bx^{3}+cx^{2}+bx+a.$$ Since $0$ is not a root, we are equivalently finding the zeros of $$ax^{2}+bx^{1}+c+bx^{-1}+ax^{-2}.$$Let $z=x+\frac{1}{x}$ (as suggested by Aryabhatta) Then $z^{2}=x^{2}+2+x^{-2}$ so that $$ax^{2}+bx^{1}+c+bx^{-1}+ax^{-2}=az^{2}+bz+\left(c-2a\right).$$ The roots of this are given by the quadratic formula: $$\frac{-b+\sqrt{b^{2}-4a\left(c-2a\right)}}{2a},\ \frac{-b-\sqrt{b^{2}-4a\left(c-2a\right)}}{2a}.$$ Now, we then have $$x+\frac{1}{x}=\frac{-b\pm\sqrt{b^{2}-4a\left(c-2a\right)}}{2a}$$ and hence we have the two quadratics $$x^{2}+\frac{b+\sqrt{b^{2}-4a\left(c-2a\right)}}{2a}x+1=0,$$ $$x^{2}+\frac{b-\sqrt{b^{2}-4a\left(c-2a\right)}}{2a}x+1=0.$$ This then gives the four roots:$$\frac{-b+\sqrt{b^{2}-4a\left(c-2a\right)}}{4a}\pm\sqrt{\frac{1}{4}\left(\frac{b-\sqrt{b^{2}-4a\left(c-2a\right)}}{2a}\right)^2-1}$$ $$\frac{-b-\sqrt{b^{2}-4a\left(c-2a\right)}}{4a}\pm\sqrt{\frac{1}{4}\left(\frac{b+\sqrt{b^{2}-4a\left(c-2a\right)}}{2a}\right)^2-1}.$$ If we plug in $a=1$, $b=4$, $c=6$, we find that all four of these are exactly $1$, so our particular case does work out. | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/40864', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/9094/']} | jdg_382852 |
stackexchange | llm_judgeable_groundtruth_similarity | 560489 |
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:
Why is it that for any non-negative matrix $M$ and unitary matrix $U$, we have $$\sqrt{UMU^\dagger}=U\sqrt{M}U^\dagger$$? This question has to do with Problem 2c from this sheet . I think I am allowed to assume the "fact" but I'd like to know why.
Now provide the response and nothing else.
| Suppose $\sqrt{ U M U^\dagger } = B$. Then$$B^2 = U M U^\dagger \implies U^\dagger B^2 U = M \implies \left( U^\dagger B U \right) \left( U^\dagger B U \right) = M$$This implies$$ \left( U^\dagger B U \right)^2 = M$$Now since $M$ is a positive definite operator, we can take a square root of both sides. We then find $$U^\dagger B U = \sqrt{M} \implies B = U \sqrt{M} U^\dagger$$Thus$$\boxed{ \sqrt{U M U^\dagger} = U \sqrt{M} U^\dagger } $$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/560489', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/422888/']} | jdg_382853 |
stackexchange | llm_judgeable_groundtruth_similarity | 17186307 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Please see the sample: private package com.xm.aws;import static com.xml.aws.PcgTest.test;public class PackageTest { public static void main(String[] args) { test(args); }} What does the private tell me about the package?
Now provide the response and nothing else.
| Let's not confuse this with package-private or other access modifiers that can be added to classes, methods and fields. The Java language specification clearly states: 6.6.1. Determining Accessibility A package is always accessible. Looking at that, the only answer, that comes to my mind is, that (some) compilers don't treat this as a compiletime error but that it is completely meaningless. It is not possible to restrict accessibility to a class or package that way (and every package is always accessible). Another section from the java language spec : 7.4.1. Named Packages A package declaration in a compilation unit specifies the name (§6.2) of the package to which the compilation unit belongs. PackageDeclaration: Annotations opt package PackageName ; So the keyword may be preceeded by annotations. But the access modifiers is not part of the package declaration. And even if we expand on "Annotations" we won't find access modifiers here. Another reference, according to JLS 18. Syntax the only thing allowed to precede package is an Annotation . CompilationUnit: [[Annotations] package QualifiedIdentifier ;] {ImportDeclaration} {TypeDeclaration} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/17186307', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2218281/']} | jdg_382854 |
stackexchange | llm_judgeable_groundtruth_similarity | 23557720 |
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 to run a batch file without showing the command line but the Command line keeps on popping up. This is my code: @echo off:SAMPLEcd /d C:md %RANDOM%cd /d D:md %RANDOM%cd /d E:md %RANDOM%goto SAMPLE
Now provide the response and nothing else.
| Solution-1 : Save your code in a batch file lets say My.bat Create a VBScript file lets say Master.vbs and call your My.bat file within it. Lets assume your batch file is at C:\Test\My.bat then: Master.vbs: Set WshShell = CreateObject("WScript.Shell")WshShell.Run chr(34) & "C:\Test\My.bat" & Chr(34), 0Set WshShell = Nothing It'll run your batch file in invisible/hidden mode. Solution-2 : If at all possible, modify the batch file to run whatever program with the start command. By default, start returns immediately without waiting for the program to exit, so the batch file will continue to run and, presumably, exit immediately. Couple that with modifying your shortcut to run the batch file minimized, and you’ll only see the taskbar flash without even seeing a window onscreen. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/23557720', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2747210/']} | jdg_382855 |
stackexchange | llm_judgeable_groundtruth_similarity | 27939786 |
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 imported a project from eclipse and now I want to add its proguard-rules.txt files. This is how the app structure looks like: I saw other places where build.gradle files were located differently, how can I do it? Where and how can I add the proguard-rules.txt file? How can I make sure that proguard is actually affecting the APK (in eclipse it generated several txt files)?
Now provide the response and nothing else.
| a) First to say, never user the expression new Locale("el-GR") , instead use new Locale("el", "GR") or without country new Locale("el") , see javadoc for correct usage of constructors (because there is no language code "el-GR"). b) The exception you observe (and me, too, but not everyone) is caused by the different localization resources of the underlying JVM. Proof on my JVM (1.6.0_31): Locale locale = new Locale("el");DateFormatSymbols dfs = DateFormatSymbols.getInstance(locale);for (String m : dfs.getMonths()) { System.out.println(m);}// outputΜάρτιοςΑπρίλιοςΜάϊοςΙούνιοςΙούλιοςΑύγουστοςΣεπτέμβριοςΟκτώβριοςΝοέμβριοςΔεκέμβριος The explanation of different data can be found in CLDR-repository for localized resources. Modern greek knows at least two different forms for the month March (Μαρτίου vs the standalone form Μάρτιος). Java-version 6 uses the standalone form while Java-version 7 uses the normal form. See also this compatibility note for java-version 8 where you have options to specify the format mode (standalone or not): When formatting date-time values using DateFormat and SimpleDateFormat, context sensitive month names are supported for languages that have the formatting and standalone forms of month names. For example, the preferred month name for January in the Czech language is ledna in the formatting form, while it is leden in the standalone form. The getMonthNames and getShortMonthNames methods of DateFormatSymbols return month names in the formatting form for those languages. Note that the month names returned by DateFormatSymbols were in the standalone form until Java SE 7 . You can specify the formatting and/or standalone forms with the Calendar.getDisplayName and Calendar.getDisplayNames methods... So the obvious solution would be updating to Java 7 . External libraries will not help here because today there is no one which has its own resources for Greek. However, if you are forced for any reason to continue with Java 6 then following awkward workaround will help: Locale locale = new Locale("el", "GR");SimpleDateFormat formatter = new SimpleDateFormat("dd MMMM yyyy, HH:mm", locale);DateFormatSymbols dfs = DateFormatSymbols.getInstance(locale);String[] months = {"Ιανουαρίου", "Φεβρουαρίου", "Μαρτίου", "Απριλίου", "Μαΐου", "Ιουνίου", "Ιουλίου", "Αυγούστου", "Σεπτεμβρίου", "Οκτωβρίου", "Νοεμβρίου", "Δεκεμβρίου"};dfs.setMonths(months);formatter.setDateFormatSymbols(dfs);try { System.out.println(formatter.parse("28 Μαρτίου 2014, 14:00")); // output in my timezone: Fri Mar 28 14:00:00 CET 2014} catch (ParseException ex) { ex.printStackTrace();} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/27939786', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4088544/']} | jdg_382856 |
stackexchange | llm_judgeable_groundtruth_similarity | 212025 |
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 $G=S_n$ and let $V$ be the permutation module of $G$ with basis $\{x_1,\ldots,x_n\}.$ Let $\lambda, \mu \in \mathbb{C}$ to allow one to define a $\mathbb{C}G$-homomorphism $\rho:V \to V$ by $$\rho(x_j):=\lambda x_j+\mu\sum_{i \neq j}x_i.$$ By using the above fact or otherwise, how can we prove that $V$ is the direct sum of two non-isomorphic irreducible $\mathbb{C}G$ -submodules? I tried to prove this by construction. A familiar irreducible submodule in this case is the $1$-dimensional space $U:=\operatorname{span}\{x_1+\cdots+x_n\}$. I intend to find another $(n-1)$-dimensional submodule $W$ which makes $V=U\oplus W$ hold, but it's hard to do so. Is there a way to use the fact instead of a random construction?
Now provide the response and nothing else.
| I'll try to give a simple solution (not using characters); but my solution is not using the homomorphism $\rho$, which was suggested in your post as a hint. This solution is based on a hint given by Qiaochu Yuanin this comment . We work with the permutation FG-module for $S_n$, i.e. we choose a basis $v_1,\dots,v_n$ for $U$ and the action of $S_n$ is given by $$\left(\sum x_iv_i\right)g = \sum x_iv_{ig}.$$ We denote this FG-module as $U$. The vector $v=v_1+\dots+v_n$ generates a one-dimensional FG-submodule $U_1$. It is relatively easy to find FG-submodule $U_2$ such that $U=U_1\oplus U_2$. (From Maschke's theorem we know that such a submodule exists.) This sumbodule is precisely $$U_2=\{\sum x_iv_i; \sum x_i=0\},$$ i.e. it contains precisely the vectors, for which the sum of coordinates is zero; $x_1+\dots+x_n=0$.(It is easy to see, that it is indeed an FG-submodule, its dimension is $n-1$ and $U_1\cap U_2=\{0\}$.) As a basis for $U_2$ we can choose, for example, $v_1-v_2,v_2-v_3,\dots,v_{n-1}-v_n$. $U_2$ is irreducible If $v=x_1v_1+\dots+x_nv_n$ is a non-zero vector from $U_2$, then $x_i\ne x_j$ for some $i$, $j$. (Since $v\notin U_1$.) We can choose a permutation $g$ in a such way, that for $w=vg=y_1v_1+\dots+y_nv_n$ we have $y_1\ne y_2$. Of course, $w\in U_2$. The submodule $U_2$ contains also the vector $w(12)$, which is the same as $w$, only the first two coordinates are swapped. Thus$$w - w(12)=(y_1-y_2)(v_1-v_2),$$and $y_1-y_2\ne 0$. We can multiply this vector and get $\underline{v_1-v_2\in FG \cdot w}$. By applying the permutation $(12\dots n)$ to the vector $v_1-v_2$ we get all basic vectors $\underline{v_i-v_{i+1}\in FG \cdot w}$. So we have in fact shown that if we have some non-zero submodule $V$ of $U_2$ (i.e., if $V$ contains at least one non-zero vector), then this submodule contains the whole basis of $U_2$, an thus $V=U_2$. This means that $U_2$ is irreducible. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/212025', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/31899/']} | jdg_382857 |
stackexchange | llm_judgeable_groundtruth_similarity | 55622844 |
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 create an Azure-Pipelines file that starts as follows: pool: vmImage: 'Ubuntu-16.04'trigger:- mastervariables: buildConfiguration: 'Release' buildPlatform: 'any cpu' version: '0.2.0' azureSubscription: 'Azure.Nupaya' azureAppType: 'Web App on Windows' webAppName: 'api'stages:- stage: 'Prepare' displayName: 'Prepare' jobs: - job: 'Setup' steps: - task: DotNetCoreInstaller@0 displayName: 'Install' inputs: packageType: 'sdk' version: '2.2.105' When I run it I get the error: Unexpected value 'stages' Isn't Stages supported in the Yaml File? I checked the Schema in Microsoft Docs ... What am I missing?
Now provide the response and nothing else.
| After some playing and testing with the Azure DevOps it seems that you define the pool under the job property, as to allow us to define different agent pools for different jobs. So for your example it would be: trigger:- mastervariables: buildConfiguration: 'Release' buildPlatform: 'any cpu' version: '0.2.0' azureSubscription: 'Azure.Nupaya' azureAppType: 'Web App on Windows' webAppName: 'api'stages:- stage: 'Prepare' displayName: 'Prepare' jobs: - job: 'Setup' pool: vmImage: 'Ubuntu-16.04' steps: - task: DotNetCoreInstaller@0 displayName: 'Install' inputs: packageType: 'sdk' version: '2.2.105' | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/55622844', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/577805/']} | jdg_382858 |
stackexchange | llm_judgeable_groundtruth_similarity | 15895517 |
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 you please explain me the different between Path and Branch testing? I read in many articles but still I am confused between this two. I searched in stack overflow but I didn't find any suitable answer for this Please help me by providing the link if i am duplicate this question. Thanks,
Now provide the response and nothing else.
| Quick Summary Summarized from https://www.cs.drexel.edu/~jhk39/teaching/cs576su06/L4.pdf Path Testing: 100% path coverage. Execute all possible control flow paths through the program. Statement Testing: 100% statement coverage. Execute all statements in a program at least once under some test. Branch Testing: 100% branch coverage. Execute enough tests to assure that every branch alternative has been exercised at least once under some test. In general Path Testing >= Branch Testing >= Statement Testing, in terms of how much confidence they can provide in the correctness of your system. Discussion Path coverage counts the number of full paths from input to output through a program that get executed, whereas branch coverage counts the number of branches that were tested at any point in time. In this definition full path coverage will lead to full branch coverage. There may be multiple paths which hit a single conditional statement, and full path coverage may test the different variants (because inside the if statement an external resource may be invoked which branch coverage would not identify). Branch coverage is more like testing that the branch is hit at some point, and the argument is passed to a mock external resource correctly (not necessarily what comes afterwards). As seen here: https://www.cs.drexel.edu/~jhk39/teaching/cs576su06/L4.pdf , we can sometimes represent the set of all paths by flow diagrams and the goal is to verify that each path from start to end works as expected in path testing. Branch Testing Additional Notes From here: Branch testing Testing in which all branches in the program source code are tested at least once Path Testing Additional Notes From here: http://www.qualitytesting.info/forum/topics/what-is-difference-between-2 and http://www.cs.st-andrews.ac.uk/~ifs/Books/SE9/Web/Testing/PathTest.html A path is a sequence of executable statements. Testers are concerned with"entry-exit paths", which begin at the entry point into a given process andproceed to its exit point. The objective of path testing is to ensure that each independent path throughthe program is executed at least once. An independent program path is one thattraverses at least one new edge in the flow graph. In program terms, this meansexercising one or more new conditions. Both the true and false branches of allconditions must be executed. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/15895517', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1550723/']} | jdg_382859 |
stackexchange | llm_judgeable_groundtruth_similarity | 914896 |
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 test the convergence of this series from exercise 8.15(j) in Mathematical Analysis by Apostol: $$\sum_{n=3}^\infty \frac{1}{(\log\log n)^{\log\log n}}$$ I tried every kind of test. I know it should be possible to use the comparison test but I have no idea on how to proceed. Could you just give me a hint?
Now provide the response and nothing else.
| Note that, for every $n$ large enough, $$(\log\log n)^{\log\log n}\leqslant(\log n)^{\log\log n}=\exp((\log\log n)^2)\leqslant\exp(\log n)=n,$$ provided, for every $k$ large enough, $$\log k\leqslant\sqrt{k},$$ an inequality you can probably show, used for $k=\log n$. Hence, for every $n$ large enough, $$\frac1{(\log\log n)^{\log\log n}}\geqslant\frac1n,$$ and the series... ...diverges. | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/914896', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/118186/']} | jdg_382860 |
stackexchange | llm_judgeable_groundtruth_similarity | 40312013 |
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 different types of data. most of them are int and sometimes float . The int is different in size so 8/ 16/ 32 bits are the sizes. For this situation I'm creating a numerical type converter. therefore i check the type by using isinstence() . This because I have read that isinstance() is less worse than type() . The point is that a lot of data i get is numpy arrays. I use spyder as IDE and then i see by the variables also a type. but when i type isinstance(var,'type i read') i get False . I did some checks: a = 2.17 b = 3 c = np.array(np.random.rand(2, 8))d = np.array([1]) for there isinstance(var,type) i get: isinstance(a, float)Trueisinstance(b, int)Trueisinstance(c, float) # or isinstance(c, np.float64)Falseisinstance(d, int) # or isinstance(c, np.int32)False c and d are True when i ask isinstance(c, np.ndarray)Trueisinstance(d, np.ndarray)True i can check with step in the ndarray by isinstance(c[i][j], np.float64)Trueisinstance(d[i], np.int32)True but this means that for every dimension i have to add a new index otherwise it is False again.I can check there type with dtype like c.dtype == 'float64' ... Oke so for what i have find and tried...My questions are basicly: how is the var.dtype method compared to isinstance() and type() (worst/ better etc)? if var.dtype is even worse as isinstance() is there some method in the isinstance() without all the manual indexing? (autoindexing etc)?
Now provide the response and nothing else.
| An array is an object of type np.ndarray . Its values or elements are stored in a data buffer, which can be thought of as a contiguous block of memory bytes. The bytes in the data buffer do not have a type, because they are not Python objects. The array has a dtype parameter, which is used to interpret those bytes. If dtype is int32 (there are various synonyms), 4 bytes are interpreted as an integer. Accessing an element, say c[0] gives a new object that depends on the dtype, e.g. an object type np.int32 . c[0].item will give an Python object of the corresponding type: In [2102]: c=np.array([1])In [2103]: c.dtypeOut[2103]: dtype('int32')In [2104]: type(c)Out[2104]: numpy.ndarrayIn [2105]: type(c[0])Out[2105]: numpy.int32In [2107]: c[0].item()Out[2107]: 1In [2108]: type(c[0].item())Out[2108]: int (And c[0].dtype is the same as for c.dtype ; you don't need to index individual elements of an array to check their dtype). The same 4 bytes of this array can be viewed as dtype int8 - a single byte integer. In [2112]: c.view('b')Out[2112]: array([1, 0, 0, 0], dtype=int8) A single element of this alternate view is np.int8 , but when I take item() , I get a Python integer. There isn't a int8 Python numeric type. In [2113]: type(c.view('b')[0])Out[2113]: numpy.int8In [2115]: type(c.view('b')[0].item())Out[2115]: int A list contains pointers to Python objects, each of which has a type. So does an array of dtype=object . But the common numeric array does not contain Python integers or floats. It has a data buffer that can interpreted in various ways according to the dtype . Python integers don't come in different sizes, at least not to the same extent as numpy dtypes. So the isinstance and type() stuff does not apply to the contents of an ndarray . ==================== From the comments I gather you are trying to convert integer arrays to float. You aren't converting scalars. If so then dtype is all that matters; an array always has a dtype . It's unclear whether you are ok with casting a np.float32 to np.float64 . I'd suggest studying, and experimenting with the np.can_cast function and the x.astype method. x.astype(np.float64, copy=False) for example will convert all int dtypes to float, without copying the ones that are already float64. It may copy and convert np.float32 ones. Look also at the casting parameter of these functions. =========================== I found in scipy.optimize.minimize another testing tool In [156]: np.typecodesOut[156]: {'All': '?bhilqpBHILQPefdgFDGSUVOMm', 'AllFloat': 'efdgFDG', 'AllInteger': 'bBhHiIlLqQpP', 'Character': 'c', 'Complex': 'FDG', 'Datetime': 'Mm', 'Float': 'efdg', 'Integer': 'bhilqp', 'UnsignedInteger': 'BHILQP'} It can be used to check for integers with: if x0.dtype.kind in np.typecodes["AllInteger"]: x0 = np.asarray(x0, dtype=float) | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/40312013', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3621065/']} | jdg_382861 |
stackexchange | llm_judgeable_groundtruth_similarity | 213716 |
Below is a question asked on the forum security.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I added a new phone line and someone called claiming to be the previous owner of the phone number. He requested that I forward information a text message (He wanted me to forward 2 Factor Authentication information that would be sent to my new phone number via SMS). Naturally, I refused the request. I do not think that they are too happy with the refusal. Are there are any risks I should be aware of or precautions that I should take, given that there is some 'funny business' afoot? CLARIFICATION: The caller does not know my name or any of my accounts. If the caller is a bad actor, then he is compromising someone else's account because the phone number he called was recently issued to me and I do not give it out to anyone, because I use a call forwarding service. Said phone number has not been given out to anyone
Now provide the response and nothing else.
| It's a known scam attempt. The caller probably compromised one of your accounts, and got stopped by the 2FA token sent to your phone. If you send them the token, your account is fully compromised. Or, as Nic pointed very well, may be the account of someone else. What you do? First: don't send them any code or token. That will prevent them for compromising your account. Second: If your provider offers any alternatives, replace SMS as 2FA on every account you have with a more secure solution, like a hardware or software TOTP token. SMS is too insecure for that. 1 2 3 4 Third: change your passwords. If you don't have a password manager keeping different accounts for each service, install and setup one now. It will take time, but takes way less time than to recover from any mischief an attacker can do with your online services. While you are changing passwords and storing them on your password manager, switch the 2FA from SMS to TOTP to have a safer 2FA. Don't trust your brain to pick passwords. They are guessable, and a computer can try billions of combinations per second. Any password manager, no matter how primitive, is better than us at creating password. | {} | {'log_upvote_score': 6, 'links': ['https://security.stackexchange.com/questions/213716', 'https://security.stackexchange.com', 'https://security.stackexchange.com/users/115653/']} | jdg_382862 |
stackexchange | llm_judgeable_groundtruth_similarity | 91634 |
Below is a question asked on the forum mathoverflow.net. Provide a good and informational response to it like a helpful human would.
Question:
Suppose I have a simplicial space $X_{\bullet}$ without degeneracies (sometimes called semi-simplicial space or incomplete simplicial space). There still is a geometric realization $\lVert X \rVert$ of $X_{\bullet}$, which only uses the face maps. What properties does this realization have? Does it still preserve products, i.e. is $\lVert X \times Y \rVert$ still (weakly?) homotopy equivalent to $\lVert X \rVert \times \lVert Y \rVert$? Do levelwise (weak) equivalences still induce a (weak) homotopy equivalence of the geometric realizations? I know of the paper "Categories and Cohomology Theories" by Segal, where he defines this "fat" geometric realization in the appendix. Unfortunately, he proves the above properties by a comparison with another construction that takes the degeneracies into account. Is this the only way to prove this? Do the properties fail in case there are no degeneracies?
Now provide the response and nothing else.
| In brief: For your first question, no. Let $X_\bullet$ be any semi-simplicial space and $Y_\bullet$ have a point in degree zero and be empty in every other degree. Then $\vert X_\bullet \times Y_\bullet \vert = X_0$, which will not usually be equivalent to $\vert X_\bullet \vert$. For your second question, yes. This is always true for semi-simplicial spaces, and is not always true for simplicial spaces (It is in the case where the thick and thin realisations are equivalent, of course). To see this you prove that the maps on $k$-skeleta $\vert X_\bullet \vert^{(k)} \to \vert Y_\bullet \vert^{(k)}$ are equivalences by induction on $k$, using the push-out description of the $k$-skeleton from the $(k-1)$-skeleton, and the fact that$$X_k \times \partial \Delta^k \to X_k \times \Delta^k$$is a cofibration so that it is a homotopy push-out. Then you use that $\vert X^\bullet \vert = \mathrm{colim} \vert X^\bullet \vert^{(k)}$ and that each $\vert X^\bullet \vert^{(k-1)} \to \vert X^\bullet \vert^{(k)}$ is a cofibration so this is a homotopy colimit. | {} | {'log_upvote_score': 5, 'links': ['https://mathoverflow.net/questions/91634', 'https://mathoverflow.net', 'https://mathoverflow.net/users/3995/']} | jdg_382863 |
stackexchange | llm_judgeable_groundtruth_similarity | 335126 |
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 have a blog hosted at http://site.com/blog . How do I instruct nginx to rewrite requests from site.com to site.com/blog ? This should not be permanent.
Now provide the response and nothing else.
| location = / { rewrite ^ http://site.com/blog/ redirect;} This'll just do requests specifically for the root. If you need to catch everything (redirect http://site.com/somearticle/something.html to http://site.com/blog/somearticle/something.html ), then you'll need something more involved: location /blog/ { # Empty; this is just here to avoid redirecting for this location, # though you might already have some config in a block like this.}location / { rewrite ^/(.*)$ http://site.com/blog/$1 redirect;} | {} | {'log_upvote_score': 4, 'links': ['https://serverfault.com/questions/335126', 'https://serverfault.com', 'https://serverfault.com/users/26763/']} | jdg_382864 |
stackexchange | llm_judgeable_groundtruth_similarity | 28783712 |
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 used the documentation provided by google. All is well but the contents of fragments overlap each other when switched by tabs. Here is the code. Main Activity public class login_register extends ActionBarActivity { @Override protected void onCreate(Bundle savedInstanceState) { super.onCreate(savedInstanceState); ActionBar actionBar = getSupportActionBar(); actionBar.setNavigationMode(ActionBar.NAVIGATION_MODE_TABS); setContentView(R.layout.login_register); getSupportActionBar().setBackgroundDrawable(new ColorDrawable(Color.parseColor("#009688"))); ActionBar.Tab loginTab = actionBar.newTab().setIcon(R.drawable.icon); ActionBar.Tab RegisterTab = actionBar.newTab().setIcon(R.drawable.icon); RegisterTab.setText("Register"); loginTab.setText("Login"); RegisterTab.setTabListener(new TabListener<register>(this, "register", register.class)); loginTab.setTabListener(new TabListener<login>(this, "login", login.class)); actionBar.addTab(loginTab); actionBar.addTab(RegisterTab); } public class TabListener<T extends Fragment> implements ActionBar.TabListener { private Fragment mFragment; private final Activity mActivity; private final String mTag; private final Class<T> mClass; public TabListener(Activity activity, String tag, Class<T> clz) { mActivity = activity; mTag = tag; mClass = clz; } public void onTabSelected(ActionBar.Tab tab, FragmentTransaction ft) { mFragment = getSupportFragmentManager().findFragmentByTag(mTag); if (mFragment == null) { mFragment = Fragment.instantiate(mActivity, mClass.getName()); ft.add(android.R.id.content, mFragment, mTag); } else { ft.attach(mFragment); } } public void onTabUnselected(ActionBar.Tab tab, FragmentTransaction ft) { mFragment = getSupportFragmentManager().findFragmentByTag(mTag); if (mFragment == null ) { ft.detach(mFragment); } } public void onTabReselected(ActionBar.Tab tab, FragmentTransaction ft) { // User selected the already selected tab. Usually do nothing. } }} Here is the one of the fragments. public class login extends Fragment { TextView txt; @Override public View onCreateView(LayoutInflater inflater, ViewGroup container, Bundle savedInstanceState) { View rootView = inflater.inflate(R.layout.login, container, false); return rootView; }} I do not know what I am doing wrong. Any help please. EditHere is the picture
Now provide the response and nothing else.
| Just in case anyone is looking for the same thing, I've come to solution:Simply set left and right padding to ViewPager and then set clipToPadding to false. That will result into one fragment to be centered and pieces of neighbor fragments in sides as it is in picture. Then to add space between fragments use viewPager.setPageMargin(); in code. That's it :) EDIT:// Here is some sample code <android.support.v4.view.ViewPager android:id="@+id/viewPager" android:clipToPadding="false" android:paddingLeft="40dp" android:paddingRight="40dp" android:layout_width="match_parent" android:layout_height="match_parent" /> ClipToPadding=false ensures that fragments will be drawn even when they are positioned out of the viewPager's content area. And then in code add spaces between viewPager's items: mViewPager.setPageMargin(100); Please note that setPageMargin takes number of pixels as parameter, not number of display points. You probably should convert some dp value to pixels to have correct spacing across all devices. This method should work fine: public static float dipToPixels(Context context, float dipValue) { DisplayMetrics metrics = context.getResources().getDisplayMetrics(); return TypedValue.applyDimension(TypedValue.COMPLEX_UNIT_DIP, dipValue, metrics);} | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/28783712', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/934820/']} | jdg_382865 |
stackexchange | llm_judgeable_groundtruth_similarity | 35818 |
Below is a question asked on the forum security.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
Following my answer . If I can list contents of a password-protected ZIP file, check the file types of each stored file and even replace it with another one, without actually knowing the password, then should ZIP files be still treated as secure? This is completely insecure in terms of social engineering / influence etc. I can hijack (intercept) someone else's file (password-protected ZIP file) and I can replace one of the files it contains, with my one (fake, virus) without knowing the password. Replaced file will remain unencrypted, not password-protected inside the ZIP, but other files won't be modified. If a victim unpacks a password-protected archive, extracting program will ask for the password only once, not every time per each file. So end user will not see the difference -- whether the program does not ask for a password, because it already knows it (original file) or because the file being extracted doesn't need a password (file modified by me). This way, I can inject something really bad into a password-protected ZIP file, without knowing its password and count on the receiver assuming the file is unmodified. Am I missing something or is this really wrong? What can we say about the security terms of a solution, if password is not required to introduce any modification in a password-protected file?
Now provide the response and nothing else.
| To answer this, there needs to be a better definition of "secure" and/or "safe". It's always got to be defined in light of the purpose of the protection and the risk to the system. There's no one size fits all here, what's "safe enough" for one system, may be abysmally weak on another. And what's "safe enough" on another may be cost prohibitive or down right impractical in a different case. So, taking the typical concerns one by one: Confidentiality - marginal at best. Confidentiality is usually rated in terms of how long it will take to gain access to the protected material. I may be able to change the zip file, but as a hacker it'll take me some amount of time either crack the password or brute force it. Not a lot of time, passwords are one of the weaker protections, and given the way zip files are often shared, social engineering one's way to the password is usually not hard. Integrity - nope - as the asker points out - it's easy to change the package and make it look legitimate. Availability - generally not applicable to this sort of security control - this usually refers to the risk of making a service unavailable - the data storing/packaging usually doesn't affect availability one way or the other. Non repudiation - nope, no protection - anyone can modify the package, so anyone contributing to it has probable deniability. The trick is - how much better do you want to get? Encrypted email is an option - as a better protection. Although it poses it's own connectivity concerns. And there's many better ways to encrypt data - but the better options also involve key distribution challenges that can add time and cost concerns. As a quick way to package and share some data that you don't want to make completely public - it's better than nothing, and it's sometimes the only common denominator you can work out. For anything high-risk, I'd find a better option. | {} | {'log_upvote_score': 7, 'links': ['https://security.stackexchange.com/questions/35818', 'https://security.stackexchange.com', 'https://security.stackexchange.com/users/11996/']} | jdg_382866 |
stackexchange | llm_judgeable_groundtruth_similarity | 695789 |
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:
Having read that atomic clocks are more accurate than mechanical clocks as they lose a second only in millions of years, I wonder why it is necessary for a reference clock to worry about this, if the definition of the second itself is a function of the number of ticks the clock makes. Why don't we just use a single simple mechanical clock somewhere with a wound up spring that makes it tick, and whenever it makes a tick, treat it as a second having elapsed? (Assuming this clock was broadcasting its time via internet ntp servers to everyone in the world)
Now provide the response and nothing else.
| why it is necessary for a reference clock to worry about this, if the definition of the second itself is a function of the number of ticks the clock makes. The concern is that somebody else (say a scientist in France or China or Botswana) needs to be able to build a clock that measures seconds at the same rate mine does. If we both have atomic clocks, we can keep our clocks syncronized to within microseconds per year. If we have mechanical clocks they might be different from each other by a second (or anyway some milliseconds) by the end of a year. If we're doing very exact measurements (comparing the arrival times of gamma rays from astronomical events at different parts of the Earth, or just using a GPS navigation system) then a few milliseconds (or even microseconds) can make a difference in our results. | {} | {'log_upvote_score': 6, 'links': ['https://physics.stackexchange.com/questions/695789', 'https://physics.stackexchange.com', 'https://physics.stackexchange.com/users/328798/']} | jdg_382867 |
stackexchange | llm_judgeable_groundtruth_similarity | 25107586 |
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 helper method that maps a number to a text - Ember.Handlebars.helper('getStatusText', function (value, options) { switch(value) { case 1: return "Fresh"; break; case 2: return "Callback"; break; default: return "Unable to get Status"; }}); I am able to use the helper in the view by using {{getStatusText 1}} But how do I use the helper in an action inside an ObjectController ? Test.DealController = Ember.ObjectController.extend({ selectedStatusType: null, statusList: ["Fresh","Callback"], actions: { updateStatus: function(deal) {// How do I call the handlebars helper here ? console.log({{getStatusText 1}}); } },}); this obviously does not work. What are the other ways ?? For better understanding, here is the jsbin
Now provide the response and nothing else.
| With ember-cli it can be done like this: // helpers/foo.jsexport function foo(params) { return params;}export default Ember.Helper.helper(foo); Helper foo exports a function (containing the helper logic) and the function wrapped in an Ember helper (for use in a template). // helpers/bar.jsimport { foo } from '<project>/helpers/foo';export function bar(params) { return foo(params);}export default Ember.Helper.helper(bar); Helper bar imports the helper function from foo and uses it in it's own template helper. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/25107586', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2098614/']} | jdg_382868 |
stackexchange | llm_judgeable_groundtruth_similarity | 54084934 |
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 would I add a custom handler for tap events for Google Maps Marker (google_maps_flutter)? I can only see consumeTapEvents which doesn't actually take in any functions but only bool. I've thought of using GestureDetector but doesn't seem quite right. What is the standard way of handling events on Google Map's Markers? I'm trying to navigate to a new page upon click. Thanks
Now provide the response and nothing else.
| With the release of version ^0.3.0+1 a new Marker API was introduced which handles markers as widgets (including an onTap() method). This way a Google Map has a markers: option which admits a list of Marker objects. Each of the elements can be defined like this: Marker( markerId: MarkerId("id"), // a string for marker unique id icon: BitmapDescriptor.defaultMarker(), // options for hues and custom imgs position: LatLng(lat, long), // lat and long doubles onTap: () { //this is what you're looking for! }), Much easier than the former controller approach! | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/54084934', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/10318099/']} | jdg_382869 |
stackexchange | llm_judgeable_groundtruth_similarity | 3999627 |
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 assign different actions to same html form according to different submit buttons. Can I do something like this ? <FORM>------<INPUT type="submit" value="DoSomething" action="DoSomething.pl" method="POST"><INPUT type="submit" value="DoSomethingElse" action="DoSomethingElse.pl" method="POST"><FORM/>
Now provide the response and nothing else.
| No. A form has only one action ( action being a property of the form , not the submit button). The target of the action can do different things on the basis of the values in the form. So, you might want to start naming your submit buttons. Learn HTML before you even think about writing and deploying a CGI script. <form method="POST" action="/cgi-bin/script"><input type="submit" name="action" value="DoSomething"><input type="submit" name="action" value="DoSomethingElse"></form> Note also that choosing an action based on the value of the submit button is a losing strategy if you wish to internationalize the application because the value of a submit button is what the UA displays to humans. Therefore, script should decide what to do on the basis of some other input element's value. For example, CGI::Application looks at a run_mode parameter. Alternatively, you can use different names for your submit buttons as Alec suggests. In that case, you need to check which submit button was pressed by going through the names of the parameters passed to your script which, IMHO, makes the dispatch slightly more cumbersome. It also means it is possible for someone to pass values for all submit buttons to your script (not via the user interface, but via curl or wget or similar programs. For example, given the HTML <form method="POST" action="/cgi-bin/script"><input type="submit" name="submit_left" value="Go Left"><input type="submit" name="submit_right" value="Go Right"></form> here is how your script may handle form submission: #!/usr/bin/perluse strict; use warnings;use CGI::Simple;my $cgi = CGI::Simple->new;my %dispatch = ( left => \&handle_left, right => \&handle_right,);my @actions = grep s/^action_(right|left)\z/$1/, $cgi->param;my $handler = \&handle_invalid_action;if ( @actions == 1) { my ($action) = @actions; if ( exists $dispatch{ $action } ) { $handler = $dispatch{ $action }; }}else { $handler = \&handle_too_many_actions;}$handler->($cgi);sub handle_left { }sub handle_right { }sub handle_invalid_action { }# because it may indicate someone trying to abuse your scriptsub handle_too_many_actions { } | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3999627', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/472485/']} | jdg_382870 |
stackexchange | llm_judgeable_groundtruth_similarity | 16283652 |
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 question around this code dispatch_async(dispatch_get_global_queue( DISPATCH_QUEUE_PRIORITY_DEFAULT, 0), ^{ NSData* data = [NSData dataWithContentsOfURL: kLatestKivaLoansURL]; [self performSelectorOnMainThread:@selector(fetchedData:) withObject:data waitUntilDone:YES];}); The first parameter of this code is dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_DEFAULT, 0) Are we asking this code to perform serial tasks on global queue whose definition itself is that it returns global concurrent queue of a given priority level? What is advantage of using dispatch_get_global_queue over the main queue? I am confused. Could you please help me to understand this better.
Now provide the response and nothing else.
| The main reason you use the default queue over the main queue is to run tasks in the background. For instance, if I am downloading a file from the internet and I want to update the user on the progress of the download, I will run the download in the priority default queue and update the UI in the main queue asynchronously. dispatch_async(dispatch_get_global_queue( DISPATCH_QUEUE_PRIORITY_DEFAULT, 0), ^(void){ //Background Thread dispatch_async(dispatch_get_main_queue(), ^(void){ //Run UI Updates });}); | {} | {'log_upvote_score': 9, 'links': ['https://Stackoverflow.com/questions/16283652', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2332873/']} | jdg_382871 |
stackexchange | llm_judgeable_groundtruth_similarity | 19132210 |
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 this thing in my views quite a lot but I want to know what exactly does that mean. What happens when we write request.method == "GET" or request.method == "POST" ?
Now provide the response and nothing else.
| The result of request.method == "POST" is a boolean value - True if the current request from a user was performed using the HTTP "POST" method, of False otherwise (usually that means HTTP "GET", but there are also other methods). You can read more about difference between GET and POST in answers to the question Alasadir pointed you to . In a nutshell POST requests are usually used for form submissions - they are required if processing a form would change server-side state (for example add user to a database, in case of a registration form). GET is used for normal HTTP requests (for example when you just type an URL into your browser) and for forms that can be processed without any side-effects (for example a search form). The code is usually used in conditional statements, to distinguish between code for processing a submitted form, and code for displaying an unbound form: if request.method == "POST": # HTTP Method POST. That means the form was submitted by a user # and we can find her filled out answers using the request.POST QueryDictelse: # Normal GET Request (most likely). # We should probably display the form, so it can be filled # out by the user and submitted. And here is another example, taken straight from Django documentation , using Django Forms library: from django.shortcuts import renderfrom django.http import HttpResponseRedirectdef contact(request): if request.method == 'POST': # If the form has been submitted... form = ContactForm(request.POST) # A form bound to the POST data if form.is_valid(): # All validation rules pass # Process the data in form.cleaned_data # ... return HttpResponseRedirect('/thanks/') # Redirect after POST else: form = ContactForm() # An unbound form return render(request, 'contact.html', { 'form': form, }) | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/19132210', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/-1/']} | jdg_382872 |
stackexchange | llm_judgeable_groundtruth_similarity | 16911131 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
HttpServletRequest has a method setAttribute(String, Object) . How can I extract this attribute from ContainterRequest ? I didn't find: getAttribute method! Code public class AuthenticationFilter implements Filter { public void doFilter(ServletRequest servletRequest, ServletResponse servletResponse, FilterChain chain) throws IOException, ServletException { HttpServletRequest httpReq = (HttpServletRequest) servletRequest; // .... .... httpReq.setAttribute("businessId", businessId); }} In Jersey Filter: private class Filter implements ResourceFilter, ContainerRequestFilter { public ContainerRequest filter(ContainerRequest request) { // ..extract the attribute from the httpReq }}
Now provide the response and nothing else.
| You can't. They're not exposed through the Jersey API in any way. If you search the Jersey codebase, you'll find that there are no uses of HttpServletRequest.getAttributeNames() , which you'd expect to be used if they were being copied en masse. You'll also find that there are only a handful of uses of HttpServletRequest.getAttribute() , and it's strictly for internal bookkeeping. Note, however, that when deployed in a Servlet Context, JAX-RS allows you to inject the original HttpServletRequest using the @Context annotation. I'm not certain whether you can do this in a Jersey filter, but it works in MessageBodyReaders/Writers and in resource classes. Update: I've checked, and you can, in fact, inject the HttpServletRequest into a Jersey ContainerRequestFilter by simply including: @Context private HttpServletRequest httpRequest; | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/16911131', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/264419/']} | jdg_382873 |
stackexchange | llm_judgeable_groundtruth_similarity | 36920307 |
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 a directory with a structure like so: .├── Test.txt├── Test1│ ├── Test1.txt│ ├── Test1_copy.txt│ └── Test1a│ ├── Test1a.txt│ └── Test1a_copy.txt└── Test2 ├── Test2.txt ├── Test2_copy.txt └── Test2a ├── Test2a.txt └── Test2a_copy.txt I would like to create a bash script that makes a md5 checksum of every file in this directory. I want to be able to type the script name in the CLI and then the path to the directory I want to hash and have it work. I'm sure there are many ways to accomplish this. Currently I have: #!/bin/bashfor file in "$1" ; do md5 >> "${1}__checksums.md5"done This just hangs and it not working. Perhaps I should use find? One caveat - the directories I want to hash will have files with different extensions and may not always have this exact same tree structure. I want something that will work in these different situations, as well.
Now provide the response and nothing else.
| Using md5deep md5deep -r path/to/dir > sums.md5 Using find and md5sum find relative/path/to/dir -type f -exec md5sum {} + > sums.md5 Be aware, that when you run check on your MD5 sums with md5sum -c sums.md5 , you need to run it from the same directory from which you generated sums.md5 file. This is because find outputs paths that are relative to your current location, which are then put into sums.md5 file. If this is a problem you can make relative/path/to/dir absolute (e.g. by puting $PWD/ in front of your path). This way you can run check on sums.md5 from any location. Disadvantage is, that now sums.md5 contains absolute paths, which makes it bigger. Fully featured function using find and md5sum You can put this function to your .bashrc file (located in your $HOME directory): function md5sums { if [ "$#" -lt 1 ]; then echo -e "At least one parameter is expected\n" \ "Usage: md5sums [OPTIONS] dir" else local OUTPUT="checksums.md5" local CHECK=false local MD5SUM_OPTIONS="" while [[ $# > 1 ]]; do local key="$1" case $key in -c|--check) CHECK=true ;; -o|--output) OUTPUT=$2 shift ;; *) MD5SUM_OPTIONS="$MD5SUM_OPTIONS $1" ;; esac shift done local DIR=$1 if [ -d "$DIR" ]; then # if $DIR directory exists cd $DIR # change to $DIR directory if [ "$CHECK" = true ]; then # if -c or --check option specified md5sum --check $MD5SUM_OPTIONS $OUTPUT # check MD5 sums in $OUTPUT file else # else find . -type f ! -name "$OUTPUT" -exec md5sum $MD5SUM_OPTIONS {} + > $OUTPUT # Calculate MD5 sums for files in current directory and subdirectories excluding $OUTPUT file and save result in $OUTPUT file fi cd - > /dev/null # change to previous directory else cd $DIR # if $DIR doesn't exists, change to it to generate localized error message fi fi} After you run source ~/.bashrc , you can use md5sums like normal command: md5sums path/to/dir will generate checksums.md5 file in path/to/dir directory, containing MD5 sums of all files in this directory and subdirectories. Use: md5sums -c path/to/dir to check sums from path/to/dir/checksums.md5 file. Note that path/to/dir can be relative or absolute, md5sums will work fine either way. Resulting checksums.md5 file always contains paths relative to path/to/dir .You can use different file name then default checksums.md5 by supplying -o or --output option. All options, other then -c , --check , -o and --output are passed to md5sum . First half of md5sums function definition is responsible for parsing options. See this answer for more information about it. Second half contains explanatory comments. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/36920307', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4616798/']} | jdg_382874 |
stackexchange | llm_judgeable_groundtruth_similarity | 3650447 |
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 Eclipse there is an option to specify pre processing defines (#ifdef macros) to a project by using the Symbols option in Paths and Symbols. This helps in effective indexing of code which is cross platform. Is there any option to provide these in Qt creator?
Now provide the response and nothing else.
| It depends:-) The following is assuming you are using qmake based projects: First you can add DEFINES += SOME_DEFINE=value into your .pro file. That is picked up inside creator and when building on the command line and should also show up when creating a MSVC or XCode project from the .pro file. Then you can add DEFINES += SOME_DEFINE=value to the qmake call that Qt Creator will issue when configuring the project. That happens in the Project Mode, Build Settings, QMake Steps. Finally, you can put #define SOME_DEFINE value liens into a header file and include that. That works for all kinds of projects:-) | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3650447', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/400236/']} | jdg_382875 |
stackexchange | llm_judgeable_groundtruth_similarity | 26033301 |
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 some pandas DataFrame with NaNs in it.Like this: import pandas as pdimport numpy as npraw_data={'A':{1:2,2:3,3:4},'B':{1:np.nan,2:44,3:np.nan}}data=pd.DataFrame(raw_data)>>> data A B1 2 NaN2 3 443 4 NaN Now I want to make a dict out of it and at the same time remove the NaNs.The result should look like this: {'A': {1: 2, 2: 3, 3: 4}, 'B': {2: 44.0}} But using pandas to_dict function gives me a result like this: >>> data.to_dict(){'A': {1: 2, 2: 3, 3: 4}, 'B': {1: nan, 2: 44.0, 3: nan}} So how to make a dict out of the DataFrame and get rid of the NaNs ?
Now provide the response and nothing else.
| There are many ways you could accomplish this, I spent some time evaluating performance on a not-so-large (70k) dataframe. Although @der_die_das_jojo's answer is functional, it's also pretty slow. The answer suggested by this question actually turns out to be about 5x faster on a large dataframe. On my test dataframe ( df ): Above method: %time [ v.dropna().to_dict() for k,v in df.iterrows() ]CPU times: user 51.2 s, sys: 0 ns, total: 51.2 sWall time: 50.9 s Another slow method: %time df.apply(lambda x: [x.dropna()], axis=1).to_dict(orient='rows')CPU times: user 1min 8s, sys: 880 ms, total: 1min 8sWall time: 1min 8s Fastest method I could find: %time [ {k:v for k,v in m.items() if pd.notnull(v)} for m in df.to_dict(orient='rows')]CPU times: user 14.5 s, sys: 176 ms, total: 14.7 sWall time: 14.7 s The format of this output is a row-oriented dictionary, you may need to make adjustments if you want the column-oriented form in the question. Very interested if anyone finds an even faster answer to this question. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/26033301', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2613204/']} | jdg_382876 |
stackexchange | llm_judgeable_groundtruth_similarity | 16062899 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
On this page I have a jQuery popup window and thumbnail resizable images. If I mouse over on the thumbnails, the images are resizing perfectly. Also, when I click on the big yellow TV button "QuickBook TV" in the footer, the popup appears perfectly as I want it to. However, when I click on the "Next" or "Prev" buttons, AJAX is used to load the new content and my jQuery no longer functions for the popup or thumbnail images. I have searched a number of forums looking for information on this issue, but due to having limited knowledge of jQuery I've been unable to understand what I need to do. Following is the popup jQuery $(document).ready(function() { $(".iframe").colorbox({ iframe: true, width: "1000px", height: "500px" }); $(".inline").colorbox({ inline: true, width: "50%" }); $(".callbacks").colorbox({ onOpen: function() { alert('onOpen: colorbox is about to open'); }, onLoad: function() { alert('onLoad: colorbox has started to load the targeted content'); }, onComplete: function() { alert('onComplete: colorbox has displayed the loaded content'); }, onCleanup: function() { alert('onCleanup: colorbox has begun the close process'); }, onClosed: function() { alert('onClosed: colorbox has completely closed'); } }); //Example of preserving a JavaScript event for inline calls. $("#click").click(function() { $('#click').css({ "background-color": "#f00", "color": "#fff", "cursor": "inherit" }).text("Open this window again and this message will still be here."); return false; }); }); And this is the thumbnails jQuery $(function() {var xwidth = ($('.image-popout img').width())/1;var xheight = ($('.image-popout img').height())/1;$('.image-popout img').css( {'width': xwidth, 'height': xheight}); //By default set the width and height of the image.$('.image-popout img').parent().css( {'width': xwidth, 'height': xheight});$('.image-popout img').hover( function() { $(this).stop().animate( { width : xwidth * 3, height : xheight * 3, margin : -(xwidth/3) }, 200 ); //END FUNCTION $(this).addClass('image-popout-shadow'); }, //END HOVER IN function() { $(this).stop().animate( { width : xwidth, height : xheight, margin : 0 }, 200, function() { $(this).removeClass('image-popout-shadow'); }); //END FUNCTION });});
Now provide the response and nothing else.
| jQuery selectors select matching elements that exist in the DOM when the code is executed, and don't dynamically update. When you call a function, such as .hover() to add event handler(s), it only adds them to those elements. When you do an AJAX call, and replace a section of your page, you're removing those elements with the event handlers bound to them and replacing them with new elements. Even if those elements would now match that selector they don't get the event handler bound because the code to do that has already executed. Event handlers Specifically for event handlers (i.e. .click() ) you can use event delegation to get around this. The basic principle is that you bind an event handler to a static (exists when the page loads, doesn't ever get replaced) element which will contain all of your dynamic (AJAX loaded) content. You can read more about event delegation in the jQuery documentation . For your click event handler, the updated code would look like this: $(document).on('click', "#click", function () { $('#click').css({ "background-color": "#f00", "color": "#fff", "cursor": "inherit" }).text("Open this window again and this message will still be here."); return false;}); That would bind an event handler to the entire document (so will never get removed until the page unloads), which will react to click events on an element with the id property of click . Ideally you'd use something closer to your dynamic elements in the DOM (perhaps a <div> on your page that is always there and contains all of your page content), since that will improve the efficiency a bit. The issue comes when you need to handle .hover() , though. There's no actual hover event in JavaScript, jQuery just provides that function as a convenient shorthand for binding event handlers to the mouseenter and mouseleave events. You can, however, use event delegation: $(document).on({ mouseenter: function () { $(this).stop().animate({ width: xwidth * 3, height: xheight * 3, margin: -(xwidth / 3) }, 200); //END FUNCTION $(this).addClass('image-popout-shadow'); }, mouseleave: function () { $(this).stop().animate({ width: xwidth, height: xheight, margin: 0 }, 200, function () { $(this).removeClass('image-popout-shadow'); }); //END FUNCTION }}, '.image-popout img'); jQuery plugins That covers the event handler bindings. However, that's not all you're doing. You also initialise a jQuery plugin (colorbox), and there's no way to delegate those to elements. You're going to have to simply call those lines again when you've loaded your AJAX content; the simplest way would be to move those into a separate named function that you can then call in both places (on page load and in your AJAX requests success callback): function initialiseColorbox() { $(".iframe").colorbox({ iframe: true, width: "1000px", height: "500px" }); $(".inline").colorbox({ inline: true, width: "50%" }); $(".callbacks").colorbox({ onOpen: function () { alert('onOpen: colorbox is about to open'); }, onLoad: function () { alert('onLoad: colorbox has started to load the targeted content'); }, onComplete: function () { alert('onComplete: colorbox has displayed the loaded content'); }, onCleanup: function () { alert('onCleanup: colorbox has begun the close process'); }, onClosed: function () { alert('onClosed: colorbox has completely closed'); } });} | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/16062899', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1356607/']} | jdg_382877 |
stackexchange | llm_judgeable_groundtruth_similarity | 2320181 |
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:
$$\lvert Z\rvert = Z+ 3-2i$$ what I did so far islet $Z = a +bi$so $$\sqrt{a^2 + b^2} = a+bi+3-2i$$ $$\sqrt{a^2 + b^2} = a+3 + i (b-2)$$ now what I'm thinking is squaring both sides but that doesn't work, any tips?
Now provide the response and nothing else.
| Hint: from $z = |z| - 3 + 2i\,$, taking the complex conjugate of both sides gives $\bar z = |z| - 3 - 2i\,$. Then, multiplying the two and using that $z \bar z = |z|^2\,$: $$|z|^2 = \left(|z| - 3 + 2i\right)\left(|z| - 3 - 2i\right)$$ The above is a linear equation in $|z|\,$. Once $|z|$ is determined, $z$ follows from the original relation. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/2320181', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/450585/']} | jdg_382878 |
stackexchange | llm_judgeable_groundtruth_similarity | 549852 |
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:
We know that a Taylor polynomial can approximate any continuous function. As @DemetriPananos noticed, Logistic regression seeks to estimate the coefficients for a model and any cut off is imposed post facto. But suppose there's a best possible decision boundary for our data. By "best possible" I mean a decision boundary that perfectly separates two classes. Assume, for the sake of simplicity, that there is no data points from positive class that overlay data points from negative class (as @Sycorax suggested). For example consider this plot: The blue line perfectly separates two classes. But the blue line itself doesn't represent a function. If we were to increase a degree of polynomial in our logistic regression, can we be sure that such a perfect decision boundary would be found for any data that can be perfectly separated? If the answer to my first question is "yes", then how to prove (or show) it?
Now provide the response and nothing else.
| Comments to the question suggest the following interpretation: Given any two non-overlapping finite collections of points $A$ and $B$ in a Euclidean space $E^n,$ does there always exist a polynomial function $f_{A,B}:E^n\to\mathbb R$ that perfectly separates the collections? That is, $f_{A,B}$ has positive values on all points of $A$ and negative values on all points of $B.$ The answer is yes, by construction. Let $|\ |$ be the usual Euclidean distance. Its square is a quadratic polynomial. Specifically, using any orthogonal coordinate system write $\mathbf{x}=(x_1,\ldots, x_n)$ and $\mathbf{y}=(y_1,\ldots, y_n).$ We have $$|\mathbf{x}-\mathbf{y}|^2 = \sum_{i=1}^n (x_i-y_i)^2,$$ which explicitly is a quadratic polynomial function of the coordinates. Define $$f_{A,B}(\mathbf x)=\left[\sum_{\mathbf y\in A}\frac{1}{|\mathbf x-\mathbf y|^2}-\sum_{\mathbf y\in B}\frac{1}{|\mathbf x-\mathbf y|^2}\right]\prod_{\mathbf y\in A\cup B}|\mathbf x-\mathbf y|^2.$$ Notice how $f_{A,B}$ is defined as a product. The terms on the right hand side clear the denominators of the fractions on the left, showing that $f$ is actually defined everywhere on $E^n$ and is a polynomial function. The function in the left term of the product has poles (explodes to $\pm \infty$ ) precisely at the data points $\mathbf x \in A\cup B.$ At the points of $A$ its values diverge to $+\infty$ and at the points of $B$ its values diverge to $-\infty.$ Because the product at the right is non-negative, we see that in a sufficiently small neighborhood of $A$ $f_{A,B}$ is always positive and in a sufficiently small neighborhood of $B$ $f_{A,B}$ is always negative. Thus $f_{A,B}$ does its job of separating $A$ from $B,$ QED. Here is an illustration showing the contour $f_{A,B}=0$ for $80$ randomly selected points in the plane $E^2.$ Of these, $43$ were randomly selected to form the subset $A$ (drawn as blue triangles) and others form the subset $B,$ drawn as red circles. You can see this construction works because all blue triangles fall within the gray (positive) region where $f_{A,B}\gt 0$ and all the red circles fall within the interior of its complement where $f_{A,B}\lt 0.$ To see more examples , modify and run this R script that produced the figure. Its function f , defined at the outset, implements the construction of $f_{A,B}.$ ## The columns of `A` are all data points. The values of `I` are +/-1, indicating# the subset each column belongs to.#f <- function(x, A, I) { d2 <- colSums((A-x)^2) j <- d2 == 0 # At most one point, assuming all points in `A` are unique if (sum(j) > 0) # Avoids division by zero return(prod(d2[!j]) * prod(I[j])) sum(I / d2) * prod(d2)}## Create random points and a random binary classification of them.## set.seed(17)d <- 2 # Dimensions n <- 80 # total number of pointsp <- 1/2 # Expected Fraction in `A`A <- matrix(runif(d*n), d)I <- sample(c(-1,1), ncol(A), replace=TRUE, prob=c(1-p, p))## Check `f` by applying it to the data points and confirming it gives the# correct signs.#I. <- sign(apply(A, 2, f, A=A, I=I))if (!isTRUE(all.equal(I, I.))) stop("f does not work...")## For plotting, compute values of `f` along a slice through the space.#slice <- rep(1/2, d-2) # Choose which slice to plotX <- Y <- seq(-0.2, 1.2, length.out=201)Z <- matrix(NA_real_, length(X), length(Y))for (i in seq_along(X)) for (j in seq_along(Y)) Z[i, j] <- f(c(X[i], Y[j], slice), A, I)## Display a 2D plot.#image(X, Y, sign(Z), col=c("Gray", "White"), xaxt="n", yaxt="n", asp=1, bty="n", main="Polynomial separator of random points")contour(X, Y, Z, levels=0, labels="", lwd=2, labcex=0.001, add=TRUE)points(t(A), pch=ifelse(I==1, 19, 17), col=ifelse(I==1, "Red", "Blue")) | {} | {'log_upvote_score': 4, 'links': ['https://stats.stackexchange.com/questions/549852', 'https://stats.stackexchange.com', 'https://stats.stackexchange.com/users/336366/']} | jdg_382879 |
stackexchange | llm_judgeable_groundtruth_similarity | 39270123 |
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 show users a multi-line text input "box" with a height greater than the standard height of a UITextField . What the best or most correct approach should be?: Using a UITextField and change its height in code or by applying a certain height constraint. Using an editable UITextView . This is multi-line but it has no placeholder by default, I guess I should implement that feature in code.
Now provide the response and nothing else.
| UITextField is specifically one line only. Use UITextView instead for multiline text. To implement the placeholder in UITextView use this logic/code. First set the UITextView to contain the placeholder text and set it to a light gray color to mimic the look of a UITextField's placeholder text. Either do so in the viewDidLoad or upon the text view's creation. For Swift textView.text = "Placeholder"textView.textColor = UIColor.lightGrayColor() For Objective-C textView.text = @"Placeholder";textView.textColor =[UIColor lightGrayColor]; Then when the user begins to edit the text view, if the text view contains a placeholder (i.e. if its text color is light gray) clear the placeholder text and set the text color to black in order to accommodate the user's entry. For Swift func textViewDidBeginEditing(textView: UITextView) { if textView.textColor == UIColor.lightGrayColor() { textView.text = nil textView.textColor = UIColor.blackColor() }} For Objective-C - (BOOL) textViewShouldBeginEditing:(UITextView *)textView{ if (textView.textColor == [UIColor lightGrayColor]) { textView.text = @""; textView.textColor = [UIColor blackColor]; } return YES;} Then when the user finishes editing the text view and it's resigned as the first responder, if the text view is empty, reset its placeholder by re-adding the placeholder text and setting its color to light gray. For Swift func textViewDidEndEditing(textView: UITextView) { if textView.text.isEmpty { textView.text = "Placeholder" textView.textColor = UIColor.lightGrayColor() }} For Objective-C - (void)textViewDidEndEditing:(UITextView *)textView{ if ([textView.text isEqualToString:@""]) { textView.text = @"Placeholder"; textView.textColor =[UIColor lightGrayColor]; }} Also do add UITextViewDelegate in the view controller. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/39270123', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1833423/']} | jdg_382880 |
stackexchange | llm_judgeable_groundtruth_similarity | 17758325 |
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 really interested in creating a UIScrollView similar to the Yahoo Weather app. Here's an example on video: http://www.youtube.com/watch?v=a-q_yetkpik I have found this Git which will alow me to do the fade background thing: https://github.com/justinmfischer/core-background But how would I achieve the blur effect at the top so that as content scrolls up, it almost fades out behind the UINavigationBar Any help would be appreciated!!
Now provide the response and nothing else.
| I wrote the code for the UI effects in the Yahoo! Weather app, would be happy to answer your question. Sounds like you've figured out how to do the blur (fade between a blurred image based on pixel offset, maxing out at a certain amount... for even better effect, you can have multiple steps in the blur - i.e. fade between non-blurred to half-blurred, then half-blurred to full-blurred etc). For the fading under kind of effect, you can set the mask property on your content view's layer: https://developer.apple.com/library/mac/documentation/graphicsimaging/reference/CALayer_class/Introduction/Introduction.html#//apple_ref/occ/instp/CALayer/mask The mask is an image that fades from transparent to opaque. --Iain. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/17758325', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2596098/']} | jdg_382881 |
stackexchange | llm_judgeable_groundtruth_similarity | 1211657 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
According to Brian Goetz's Java Concurrency in Practice JVM can't exit until all the (nondaemon) threads have terminated, so failing to shut down an Executor could prevent the JVM from exiting. I.e. System.exit(0) doesn't necessarily work as expected if there are Executors around. It would seem necessary to put some kind of public void stop() { exec.shutdown() } methods to all classes that contain Executors, and then call them when the application is about to terminate. Is this the only way, or is there some kind of shortcut to shut down all the Executors?
Now provide the response and nothing else.
| There's no shortcut to do them all, no. Also, you should probably call shutdownNow() rather than shutdown() , otherwise you could be waiting a while. What you could do, I suppose, is when you create the Executor, register it in a central place. Then, when shutting down, just call shutdown() on that central object, which in turn could terminate each of the registered executors. If you use Spring, then you can take advantage of its factory beans which create and manage the Executors for you. That includes shutting them down gracefully when the application quits, and saves you having to manage them yourself. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/1211657', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/59279/']} | jdg_382882 |
stackexchange | llm_judgeable_groundtruth_similarity | 15422606 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Let's say you have a simple model: Class Contact(models.Model): email = models.EmailField(max_length=70,blank=True) first = models.CharField(max_length=25,blank=True) last = models.CharField(max_length=25,blank=True) What I would like to do is set email to be unique, however, in doing so I necessarily make it such that I exclude blank email addresses - and I don't want that. I was thinking about something like this but I'm wondering if there is a better way to deal with it. from django.core.validators import email_refrom django.core.exceptions import ValidationErrordef save(self, *args, **kwargs): # ... other things not important here self.email = self.email.lower().strip() # Hopefully reduces junk to "" if self.email != "": # If it's not blank if not email_re.match(self.email) # If it's not an email address raise ValidationError(u'%s is not an email address, dummy!' % self.email) if Contact.objects.filter(email = self.email) # If it already exists raise ValidationError(u'%s already exists in database, jerk' % self.email) super(Contact, self).save(*args, **kwargs) Is there a better way to do this?
Now provide the response and nothing else.
| Unfortunately, it's not as simple as just setting null=True, unique=True, blank=True. Whenever you try to import using csv, or some other text based source, some part of Django, for the purpose of uniqueness treats "" as something that ought not to be duplicated. The work-around, is to overwrite the save method, as follows: def save(self, *args, **kwargs): # ... other things not important here self.email = self.email.lower().strip() # Hopefully reduces junk to "" if self.email != "": # If it's not blank if not email_re.match(self.email) # If it's not an email address raise ValidationError(u'%s is not an email address, dummy!' % self.email) if self.email == "": self.email = None super(Contact, self).save(*args, **kwargs) Then,using unique, null and blank will work as intended. Class Contact(models.Model): email = models.EmailField(max_length=70,blank=True, null= True, unique= True) | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/15422606', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/170352/']} | jdg_382883 |
stackexchange | llm_judgeable_groundtruth_similarity | 16220698 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
var x = 1; Func<int,int> f = y => x + y; x = 2; Console.WriteLine(f(1)); The output is 3. I would assume it is 2, according to https://web.archive.org/web/20170426121932/http://www.cs.cornell.edu/~clarkson/courses/csci4223/2013sp/lec/lec12.pdf
Now provide the response and nothing else.
| There's a subtlety concerning lexical scoping that PDF doesn't fully explain. Its example actually has two different variables named x , it does not reassign the value of the first x (and indeed functional languages may not allow mutation). C# is lexically scoped -- it looks up x at the point of definition of the lambda, not when the delegate is invoked. But: x resolves to a variable, not a value, and it reads the variable's value at the time of invocation. Here is a more complete example: int InvokeIt( Func<int, int> f ){ int x = 2; return f(1);}Func<int, int> DefineIt(){ int x = 1; Func<int, int> d = (y => x + y); x = 3; // <-- the PDF never does this return d;}Console.WriteLine(InvokeIt(DefineIt())); The lambda binds to the x variable that exists inside DefineIt . The value ( x = 1 ) at the point of definition is irrelevant. The variable is later set to x = 3 . But it is clearly not dynamic scope either, because the x = 2 inside InvokeIt is not used. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/16220698', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/691867/']} | jdg_382884 |
stackexchange | llm_judgeable_groundtruth_similarity | 1752477 |
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 sha256 to encrypt the password. I can save the sha256 encrypted password in mysql. But i can't login with the same clause. Insert code: <?phperror_reporting(E_ALL ^ E_NOTICE);$username = $_POST['uusername'];$passcode = $_POST['ppasscode'];$userflag = $_POST['uuserflag'];//$passcodeen = hash('sha256',$passcode);$passcodeen = hash('sha256', (get_magic_quotes_gpc() ? stripslashes($ppasscode) : $ppasscode));$conn = mysql_connect("localhost","charles","charles") or die("connection failed with DB:".mysql_error());mysql_select_db("sessiondb");$query = "INSERT INTO users(username,passcode,userflag) values('$username','$passcodeen','$userflag')"; Select code: <?php error_reporting(E_ALL ^ E_NOTICE); @mysql_connect("localhost","charles","charles") or die("Connection failed".mysql_error()); @mysql_select_db("sessiondb") or die("Database doesn't exist".mysql_error()); //get user input $username = $_POST['username']; $ppasscode = $_POST['ppasscode']; //$passcodeen = hash('sha256', $ppasscode); $passcodeen = hash('sha256', (get_magic_quotes_gpc() ? stripslashes($ppasscode) : $ppasscode)); //get session value from mysql $query = @mysql_query("select username, userflag from users where username ='$username' and passcode = '$passcodeen'") or die("Query execution failed".mysql_error()); Is there something wrong? I'm very confused. Thanks.
Now provide the response and nothing else.
| Could this be a typo? (two Ps in ppasscode, intended?) $_POST['ppasscode']; I would make sure and do: print_r($_POST); and make sure the data is accurate there, and then echo out what it should look like: echo hash('sha256', $_POST['ppasscode']); Compare this output to what you have in the database (manually). By doing this you're exploring your possible points of failure: Getting password from form hashing the password stored password comparison of the two. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/1752477', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/198728/']} | jdg_382885 |
stackexchange | llm_judgeable_groundtruth_similarity | 30031452 |
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 working on an application where file uploads happen often, and can be pretty large in size. Those files are being uploaded to a Web API, which will then get the Stream from the request, and pass it on to my storage service, that then uploads it to Azure Blob Storage. I need to make sure that: No temp files are written on the Web API instance The request stream is not fully read into memory before passing it on to the storage service (to prevent OutOfMemoryExceptions ). I've looked at this article , which describes how to disable input stream buffering, but because many file uploads from many different users happen simultaneously, it's important that it actually does what it says on the tin. This is what I have in my controller at the moment: if (this.Request.Content.IsMimeMultipartContent()){ var provider = new MultipartMemoryStreamProvider(); await this.Request.Content.ReadAsMultipartAsync(provider); var fileContent = provider.Contents.SingleOrDefault(); if (fileContent == null) { throw new ArgumentException("No filename."); } var fileName = fileContent.Headers.ContentDisposition.FileName.Replace("\"", string.Empty); // I need to make sure this stream is ready to be processed by // the Azure client lib, but not buffered fully, to prevent OoM. var stream = await fileContent.ReadAsStreamAsync();} I don't know how I can reliably test this. EDIT : I forgot to mention that uploading directly to Blob Storage (circumventing my API) won't work, as I am doing some size checking (e.g. can this user upload 500mb? Has this user used his quota?).
Now provide the response and nothing else.
| Solved it, with the help of this Gist . Here's how I am using it, along with a clever "hack" to get the actual file size, without copying the file into memory first. Oh, and it's twice as fast(obviously). // Create an instance of our provider.// See https://gist.github.com/JamesRandall/11088079#file-blobstoragemultipartstreamprovider-cs for implementation.var provider = new BlobStorageMultipartStreamProvider ();// This is where the uploading is happening, by writing to the Azure stream// as the file stream from the request is being read, leaving almost no memory footprint.await this.Request.Content.ReadAsMultipartAsync(provider);// We want to know the exact size of the file, but this info is not available to us before// we've uploaded everything - which has just happened.// We get the stream from the content (and that stream is the same instance we wrote to).var stream = await provider.Contents.First().ReadAsStreamAsync();// Problem: If you try to use stream.Length, you'll get an exception, because BlobWriteStream// does not support it.// But this is where we get fancy.// Position == size, because the file has just been written to it, leaving the// position at the end of the file.var sizeInBytes = stream.Position; Voilá, you got your uploaded file's size, without having to copy the file into your web instance's memory. As for getting the file length before the file is uploaded, that's not as easy, and I had to resort to some rather non-pleasant methods in order to get just an approximation. In the BlobStorageMultipartStreamProvider : var approxSize = parent.Headers.ContentLength.Value - parent.Headers.ToString().Length; This gives me a pretty close file size, off by a few hundred bytes (depends on the HTTP header I guess). This is good enough for me, as my quota enforcement can accept a few bytes being shaved off. Just for showing off, here's the memory footprint, reported by the insanely accurate and advanced Performance Tab in Task Manager. Before - using MemoryStream, reading it into memory before uploading After - writing directly to Blob Storage | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/30031452', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/561545/']} | jdg_382886 |
stackexchange | llm_judgeable_groundtruth_similarity | 54382367 |
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 install the Qt add-in for Visual Studio 2019 Preview (Community), but the add-in is causing an error during installation. First I was trying it with Visual Studio 2017 (Community), but was having difficulties, so I reinstalled VS17 twice. Finally, I uninstalled that, and installed Visual Studio 2019 Community Preview (which this particular extension is also supported for), and am still having issues. I installed it through the built-in Visual Studio extension service. I'm new to Visual Studio, normally I use QtCreator, but was wanting to debug my project with Visual Studio's superior debugging tools. How do I go about fixing this problem? 1/25/2019 8:02:28 PM - Beginning to install extension to Microsoft Visual Studio Community 2017...1/25/2019 8:02:28 PM - Found setup instance 883a9c0e but not in launchable state.1/25/2019 8:02:28 PM - Install Error : System.InvalidOperationException: Cannot find setup engine instance. at Microsoft.VisualStudio.ExtensionManager.SetupEngineUtility.GetCurrentSetupInstance(IEngineHost engineHost) at Microsoft.VisualStudio.ExtensionManager.SetupEngineService.CreateEngine(IEngineHost engineHost, IServiceProvider serviceProvider, InstallFlags installFlags) at Microsoft.VisualStudio.ExtensionManager.ExtensionEngineImpl.PerformSetupEngineInstall(InstallableExtensionImpl extension, Boolean installPerMachine, Boolean isPackComponent, IDictionary`2 extensionsInstalledSoFar, List`1 extensionsUninstalledSoFar, IInstalledExtensionList modifiedInstalledExtensionsList, IProgress`1 progress, InstallFlags installFlags, AsyncOperation asyncOp, Version targetedVsVersion, IInstalledExtension& newExtension) at Microsoft.VisualStudio.ExtensionManager.ExtensionEngineImpl.InstallInternal(InstallableExtensionImpl extension, InstallFlags installFlags, IDictionary`2 extensionsInstalledSoFar, List`1 extensionsUninstalledSoFar, IInstalledExtensionList modifiedInstalledExtensionsList, AsyncOperation asyncOp, IProgress`1 progress, Version targetedVsVersion) at Microsoft.VisualStudio.ExtensionManager.ExtensionEngineImpl.BeginInstall(IInstallableExtension installableExtension, InstallFlags installFlags, AsyncOperation asyncOp, Version targetedVsVersion) at Microsoft.VisualStudio.ExtensionManager.ExtensionEngineImpl.InstallWorker(IInstallableExtension extension, InstallFlags installFlags, AsyncOperation asyncOp) Edit: After yet another uninstall and reinstall of everything, it suddenly worked. Yay? I have no idea what was different this time around.
Now provide the response and nothing else.
| I was experiencing this issue when I was trying to port a Visual Studio Extension forward from 2017 to 2019. First I updated the Manifest file as appropriate to support Visual Studio 2019. Then, once I hit the error 'Cannot find setup engine instance', I had a look in the 'Visual Studio Installer'. The final step turned out to be adding the 'Visual Studio extension development' workload, which was initially not installed. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/54382367', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1177073/']} | jdg_382887 |
stackexchange | llm_judgeable_groundtruth_similarity | 2903453 |
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 looked a little bit into face recognition recently. However I am overwelmed by the number of algorithm that there are. PCA, LDA, IDA, Gabor Wavelets, AAM ... Say you wanted to make something like this ... Which algorithms would you use or which papers would you read?
Now provide the response and nothing else.
| I think the first thing you should do is realize that the algorithms you've listed are used at different stages of face recognition. First, you need to decide on the representation, i. e. the features to use.These could be raw pixels, Gabor filters, some kind of shape descriptors, deformable models, etc. Then, you typically want to reduce the dimensionality of your features. This is where algorithms like PCA, ICA, or LDA come in, which project data points into a lower dimensional space trying to preserve most of the variance (PCA) or to ensure the optimal separation of points of different categories (LDA). Then you probably want to train a classifier on your features to distinguish between the faces of different people. There is a plethora of algorithms to choose from here, such as the Nearest Neighbor, Support Vector Machines, Hidden Markov Models, Bayes Nets, etc. Note that the choice of an algorithm for a particular stage may or may not depend on the algorithms for other stages. For instances, PCA can be used to reduce dimensionality of almost any type of features. On the other hand, it is not immediately obvious how one can use a support vector machine classifier for faces represented by a deformable mesh. I guess the first thing you should try to do is to define your problem very precisely. Do you want to distinguish between faces of only a few people, such as recognize your family members in photos? Do you want to recognize people from a huge database? Do you have lots of training images for each face, or only a few? Do you want to handle different orientations and lighting conditions? The answers to these questions determine how complicated your problem is, and will certainly affect your choice of algorithms. EDIT:Here's a thesis of somebody who tried solving a similar problem. It is from 2002, but IMHO it is a good place to start. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2903453', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/349760/']} | jdg_382888 |
stackexchange | llm_judgeable_groundtruth_similarity | 429622 |
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:
Show that the $\max{ \{ x,y \} }= \dfrac{x+y+|x-y|}{2}$. I do not understand how to go about completing this problem or even where to start.
Now provide the response and nothing else.
| Here is another way of looking at it: We have $|x| = \max(x,-x)$. Also, $\max(a,b)+c = \max(a+c,b+c)$, and if $c \geq 0$, then $c \max(a,b) = \max(ac,bc)$. Hence\begin{eqnarray}\frac{1}{2}(x+y+|x-y|) &=& \frac{1}{2}(x+y+\max(x-y,y-x)) \\&=& \frac{1}{2}(\max(x-y+x+y,y-x+x+y)) \\&=& \frac{1}{2}(\max(2x,2y)) \\&=& \max(x,y)\end{eqnarray} | {} | {'log_upvote_score': 6, 'links': ['https://math.stackexchange.com/questions/429622', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/72195/']} | jdg_382889 |
stackexchange | llm_judgeable_groundtruth_similarity | 50882956 |
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 flask-RESTful endpoint defined by: class SearchEvents(Resource): def get(self, name, start_date, end_date): #do stuffapi.add_resource(endpoints.SearchEvents, '/events/<string:name>/<string:start_date>/<string:end_date>') I'm testing it manually with Postman. I'd like to pass in null values for start_date and end_date. However: I've tried modifying the url to: http://127.0.0.1:5000/events/test/ / #<--Spaces and http://127.0.0.1:5000/events/test/""/"" To no avail.
Now provide the response and nothing else.
| Ended up solving this by using the flask-restful request object, which has an args property which retrieves query params from the request url: from flask_restful import request #import request from flask restfulclass SearchEvents(Resource): def get(self): args = request.args #retrieve args from query stringapi.add_resource(endpoints.SearchEvents, '/events') And then making the requests like: http://127.0.0.1:5000/events?param1=value1¶m2=value2 Or to pass null values: http://127.0.0.1:5000/events?param=¶m2=value1 | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/50882956', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/8935712/']} | jdg_382890 |
stackexchange | llm_judgeable_groundtruth_similarity | 36835865 |
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 write following register type in autofac: builder.RegisterType<NoteBookContext>() .As<DbContext>() .WithParameter(ResolvedParameter.ForNamed<DbContext>("connectionstring")); In fact I write this code for injecting NoteBookContext with a connectionstring parameter. (ie : new NoteBookContext(string connectionstring) ) Now , How can I Pass value of parameter at runtime?
Now provide the response and nothing else.
| The WithParameter method has a overload that accept delegate for dynamic instanciation. The first argument is a predicate selecting the parameter to set whereas the second is the argument value provider : builder.RegisterType<NoteBookContext>() .As<DbContext>() .WithParameter((pi, c) => pi.Name == "connectionstring", (pi, c) => c.Resolve<IConnectionStringProvider>().ConnectionString); See Passing Parameters to Register from Autofac documentation for more detail. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/36835865', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1597581/']} | jdg_382891 |
stackexchange | llm_judgeable_groundtruth_similarity | 55161 |
Below is a question asked on the forum networkengineering.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
I am studying for my CCENT. I threw together a PAT practice lab.Other than DHCP and RIP everything is pretty stock. No VLANsNo securityJust NAT overload on ACCESS router. I am stumped why it isn't translating It will still ping all around. show ip nat statistics , miss count is going up.Debugging for NAT is on but silent.It all looks like it should be working. Is there something wrong with my configuration? ACCESS#sho ip nat translations ACCESS#sho ip nat statTotal translations: 0 (0 static, 0 dynamic, 0 extended)Outside Interfaces: GigabitEthernet0/1Inside Interfaces: GigabitEthernet0/0Hits: 0 Misses: 163Expired translations: 0Dynamic mappings:ACCESS#show runBuilding configuration...Current configuration : 981 bytes!version 15.1no service timestamps log datetime msecno service timestamps debug datetime msecno service password-encryption!hostname ACCESS!ip cefno ipv6 cef!license udi pid CISCO2911/K9 sn FTX1524DSR5-!spanning-tree mode pvst!interface GigabitEthernet0/0 ip address 10.0.0.1 255.255.255.0 ip helper-address 8.8.8.2 ip nat inside duplex auto speed auto!interface GigabitEthernet0/1 ip address 8.8.8.1 255.255.255.252 ip nat outside duplex auto speed auto!interface GigabitEthernet0/2 no ip address duplex auto speed auto shutdown!interface Vlan1 no ip address shutdown!router rip version 2 passive-interface GigabitEthernet0/0 network 8.0.0.0 network 10.0.0.0!ip nat inside source list 1 interface GigabitEthernet0/1 overloadip classless!ip flow-export version 9!access-list 1 permit host 10.0.0.0!no cdp run!line con 0!line aux 0!line vty 0 4 login!end
Now provide the response and nothing else.
| Looks like the NAT access-list 1 is too tight. host 10.0.0.0 will only match the single host with address 10.0.0.0 , and you have no such host. You almost certainly wanted this: access-list 1 permit 10.0.0.0 0.0.0.255 which will include your hosts at the bottom of your diagram. | {} | {'log_upvote_score': 4, 'links': ['https://networkengineering.stackexchange.com/questions/55161', 'https://networkengineering.stackexchange.com', 'https://networkengineering.stackexchange.com/users/48136/']} | jdg_382892 |
stackexchange | llm_judgeable_groundtruth_similarity | 3750949 |
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:
Irrational numbers are very easy to find. Square roots require only a little bit more than the most basic arithmetic. So it might be that this question is impossible to answer because it presupposes a world where math looks completely different to what it really does. I am hoping this is not the case. If we didn't have examples of irrational numbers, would $\mathbb{R}$ and $\mathbb{Q}$ be assumed to be the same set? Can we construct a proof that irrational numbers exist without giving examples?
Now provide the response and nothing else.
| From the surrounding discussion it seems that perhaps there are two questions here: What is the impetus to define the real numbers and how do we get such a definition? Given a definition of $\mathbb{R}$ can we prove that irrational numbers exist without constructing examples? My answer addresses the latter question. You can prove that the real numbers are uncountable (there is no bijection between the real numbers and the integers). You can prove the rational numbers are countable (there is a bijection between the rational numbers and the integers). So $\mathbb{R}\setminus\mathbb{Q}$ is nonempty. Since I don't know your background I will add some more. A bijection between two sets $X$ and $Y$ is a function $f:X\to Y$ that is both one-to-one and onto, i.e, for all $x,y\in X$ , $f(x)=f(y)$ implies $x=y$ ; and for all $y\in Y$ there is $x\in X$ such that $f(x)=y$ . An infinite set is $X$ countable if there is a bijection $f:X\to \mathbb{N}$ . It is a famous result of Cantor (called a diagonal argument ) that $\mathbb{R}$ is uncountable. It is a standard (and good practice) exercise that $\mathbb{Q}$ is countable. It is a standard (and good practice) exercise that if $X$ and $Y$ are countable then so is $X\cup Y$ . So if $\mathbb{R}\backslash \mathbb{Q}$ were countable then so would be $\mathbb{R}$ . So altogether, this actually shows that not only do irrational numbers exist, but there are more irrational numbers than rational numbers because the set $\mathbb{R}\backslash\mathbb{Q}$ must be uncountable by the above points. By the way, the same kind of proof shows that transcendental numbers exist and there are more transcendental numbers than algebraic numbers. Indeed, the set of algebraic numbers is also countable and so its complement in $\mathbb{R}$ is uncountable. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/3750949', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/383061/']} | jdg_382893 |
stackexchange | llm_judgeable_groundtruth_similarity | 4548476 |
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 have a report with all the local users and their relative groups (users, power users, administrators and so on. I get the users in this way: $adsi = [ADSI]"WinNT://."$adsi.psbase.children | where {$_.psbase.schemaClassName -match "user"} | select @{n="Name";e={$_.name}} but I don't know how to retrieve their groups. Thanks in advance.
Now provide the response and nothing else.
| $adsi = [ADSI]"WinNT://$env:COMPUTERNAME"$adsi.Children | where {$_.SchemaClassName -eq 'user'} | Foreach-Object { $groups = $_.Groups() | Foreach-Object {$_.GetType().InvokeMember("Name", 'GetProperty', $null, $_, $null)} $_ | Select-Object @{n='UserName';e={$_.Name}},@{n='Groups';e={$groups -join ';'}}} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/4548476', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/344491/']} | jdg_382894 |
stackexchange | llm_judgeable_groundtruth_similarity | 5385 |
Below is a question asked on the forum chemistry.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
So this experiment goes like this : You take an ice-cube You put a thread on top face of it You sprinkle some common salt on the ice-cube wherever its touching the thread You wait for sometime (approx 1 min) Voila! now you can lift the thread and ice-cube will stick to the end of the thread so you can lift the whole thing altogether How do you explain this in chemistry?
Now provide the response and nothing else.
| I conjecture that there are several things happening. Step 3: Addition of salt will melt the ice at its immediate point of contact. The string will naturally be surrounded by the highly concentrated brine (salt water). Step 4: This is enough time for the brine to get diluted, noting that there is an infinite reservoir of potential water by way of the ice cube. Step 5: Once the salt gets sufficiently diluted, then the comparatively large ice cube provides the necessary cold for the (now) very dilute salt water to reform as ice. Recalling that in Step 3 the salt water surrounded the string, then ice naturally forms around the string in Step 5, hence you can pick up the ice cube with the string. | {} | {'log_upvote_score': 5, 'links': ['https://chemistry.stackexchange.com/questions/5385', 'https://chemistry.stackexchange.com', 'https://chemistry.stackexchange.com/users/1821/']} | jdg_382895 |
stackexchange | llm_judgeable_groundtruth_similarity | 521513 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Has anyone run into this problem... In my layout.phtml I have: <head> <?= $this->headTitle('Control Application - ') ?></head> then in index.phtml I have: <? $this->headTitle()->append('Client List'); ?> I expect that, when I go to my index action, the title should be 'Control Application - Client List' but instead I have 'Client ListControl Application - ' What is going on? How can I fix this?
Now provide the response and nothing else.
| Default behaviour of the headTitle() is to append to the stack. Before calling headTitle() in layout.phtml, your stack is: Clientlist Then, you call headTitle with the first argument and no second argument ( which makes it default to APPEND ), resulting in the following stack: ClientListControl Application - The solution, in layout.phtml: <?php $this->headTitle()->prepend('Control Application -'); echo $this->headTitle();?> | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/521513', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/48523/']} | jdg_382896 |
stackexchange | llm_judgeable_groundtruth_similarity | 6032781 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Running np.log(math.factorial(21)) throws an AttributeError: log . Why is that? I could imagine a ValueError , or some sort of UseYourHighSchoolMathsError , but why the attribute error?
Now provide the response and nothing else.
| The result of math.factorial(21) is a Python long. numpy cannot convert it to one of its numeric types, so it leaves it as dtype=object . The way that unary ufuncs work for object arrays is that they simply try to call a method of the same name on the object. E.g. np.log(np.array([x], dtype=object)) <-> np.array([x.log()], dtype=object) Since there is no .log() method on a Python long, you get the AttributeError . | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/6032781', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/270572/']} | jdg_382897 |
stackexchange | llm_judgeable_groundtruth_similarity | 7626114 |
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 made an ICS feed containing a long list of events. My timezone does not seem to work. In the sample below you see that my event should start 07:55:00 and end 09:30:00. This is what it should show in my calendar. Instead it shows 09:55:00 and 11:30:00 - an offset of two hours. The timezone should be set to Europe/Copenhagen but this does not have any effect. Can anyone tell me how I can achieve the right times? BEGIN:VCALENDARPRODID:-//Google Inc//Google Calendar 70.9054//ENVERSION:2.0CALSCALE:GREGORIANMETHOD:PUBLISHX-WR-CALNAME:Test CalendarX-WR-TIMEZONE:Europe/CopenhagenX-WR-CALDESC:Test CalendarBEGIN:VEVENTDTSTART:20110926T075500ZDTEND:20110926T093000ZDTSTAMP:20111002T133505ZUID:E9QNQ30EG-5SRB7-QQKL3-2JUUZ-477LBRV4IMSJ78CREATED:20111002T133505ZLAST-MODIFIED:20111002T133505ZLOCATION:B34SEQUENCE:3SUMMARY:2abc3c Ma3 CD (B34)TRANSP:OPAQUEEND:VEVENTEND:VCALENDAR
Now provide the response and nothing else.
| You've specified that your event starts at 07:55 in UTC - that's what the Z at the end shows. If you want it to be in local time, you shouldn't have the Z, and you should probably specify the time zone there too: DTSTART;TZID=Europe/Copenhagen:20110926T075500DTEND;TZID=Europe/Copenhagen:20110926T093000 Alternatively, specify the UTC start and end time using Z, but taking account for the relevant time zone difference - so an event that starts at 07:55 in Europe/Copenhagen at the moment is actually 05:55 in UTC. | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/7626114', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/486845/']} | jdg_382898 |
stackexchange | llm_judgeable_groundtruth_similarity | 266681 |
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:
Assume that I have an expression like this (without evaluating) expr = 1/2/3/4/5/6/7/8/9/10 You can insert some number of parentheses into the expression above to create a valid mathematical expression. What would be the smallest possible integer value of the expression and the expression in that case? Here are some examples of inserting parentheses. The smallest possible integer number is 7 but I wonder if anyone knows some way to solve it with Mathematica. The brute force inserting all possible paranthesises probably works but I don't know how many possible cases in order to do a for loop.
Now provide the response and nothing else.
| You can use Groupings with an inactivated Divide to do this: g = Groupings[Range[10], Inactive[Divide] -> 2]; Then, use Activate to get the values: v = Activate[g]; Finally, the min integer can be found from: min = Min[Select[IntegerQ] @ v] 7 The groupings that produce 7 are: Column @ Pick[g, v, 7] //TeXForm $\begin{array}{l} 1/(2/(3/(4/5/6/7/8)/9/10)) \\ 1/(2/(3/(4/5/6/7/8)/9))/10 \\ 1/(2/(3/(4/5/6/7/8)))/9/10 \\ 1/(2/(3/(4/5/6/7))/8)/9/10 \\ 1/(2/(3/(4/5/6))/7/8)/9/10 \\ 1/(2/(3/4)/5/6/7/8)/9/10 \\ 1/(2/(3/(4/5))/6/7/8)/9/10 \\ 1/(2/(3/(4/5/6/7/(8/9))/10)) \\ 1/(2/(3/(4/5/6/7/(8/9))))/10 \\ 1/(2/(3/(4/5/6/7/(8/9/10)))) \\ 1/(2/(3/(4/5/6/7))/(8/9))/10 \\ 1/(2/3/(4/(5/6/7)/8/9)/10) \\ 1/(2/(3/(4/5/6))/7/(8/9))/10 \\ 1/(2/(3/4)/5/6/7/(8/9))/10 \\ 1/(2/(3/(4/5))/6/7/(8/9))/10 \\ 1/(2/3/(4/(5/6/(7/8))/9)/10) \\ 1/(2/3/(4/(5/6/(7/8/9)))/10) \\ 1/(2/3)/(4/5/6/7/8)/9/10 \\ 1/(2/3/(4/5)/6/(7/8/9)/10) \\ 1/(2/3/(4/(5/6))/(7/8/9)/10) \\ 1/(2/3/(4/(5/6/(7/8/9)/10))) \\ 1/(2/3/(4/(5/6/(7/8/(9/10))))) \\ 1/(2/3/(4/(5/6/7)/8/(9/10))) \\ 1/(2/3/(4/(5/6/(7/8))/(9/10))) \\ 1/(2/(3/(4/5/6/7))/(8/9/10)) \\ 1/(2/(3/(4/5/6))/7/(8/9/10)) \\ 1/(2/(3/4)/5/6/7/(8/9/10)) \\ 1/(2/(3/(4/5))/6/7/(8/9/10)) \\ 1/(2/3)/(4/5/6/7/(8/9))/10 \\ 1/(2/3/(4/5)/6/(7/8/(9/10))) \\ 1/(2/3/(4/(5/6))/(7/8/(9/10))) \\ 1/(2/3/(4/5)/6/7)/8/(9/10) \\ 1/(2/3/(4/(5/6))/7)/8/(9/10) \\ 1/(2/3/(4/(5/6/7)))/8/(9/10) \\ 1/(2/3/(4/(5/6/7)/8))/(9/10) \\ 1/(2/3/(4/5)/6/(7/8))/(9/10) \\ 1/(2/3/(4/(5/6/(7/8))))/(9/10) \\ 1/(2/3/(4/(5/6))/(7/8))/(9/10) \\ 1/(2/3/4)/(5/6/7)/8/(9/10) \\ 1/(2/3/4)/(5/6/(7/8))/(9/10) \\ 1/(2/3)/(4/5/6/7/(8/9/10)) \\ 1/(2/3/4)/(5/6/(7/8/9)/10) \\ 1/(2/3/4)/(5/6/(7/8/(9/10))) \\ 1/2/3/4/5/(6/7/8/9/10) \\\end{array}$ | {} | {'log_upvote_score': 4, 'links': ['https://mathematica.stackexchange.com/questions/266681', 'https://mathematica.stackexchange.com', 'https://mathematica.stackexchange.com/users/18805/']} | jdg_382899 |
stackexchange | llm_judgeable_groundtruth_similarity | 14999143 |
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 know which one has the better performance for returning a DataTable . Here for SqlDataReader I use DataTable.Load(dr) Using SqlDataReader : public static DataTable populateUsingDataReader(string myQuery){ DataTable dt = new DataTable(); using (SqlConnection con = new SqlConnection(constring)) { SqlCommand cmd = new SqlCommand(myQuery, con); con.Open(); SqlDataReader dr = null; dr = cmd.ExecuteReader(CommandBehavior.CloseConnection); if (dr.HasRows) { dt.Load(dr); } return dt; }} using SqlDataAdapter : public DataTable populateUsingDataAdapter(string myQuery){ SqlDataAdapter dap = new SqlDataAdapter(myQuery,cn); DataSet ds = new DataSet(); dap.Fill(ds); return ds.Tables[0];}
Now provide the response and nothing else.
| The difference will be negligible, so it's probably better to use the more concise version: SqlDataAdapter.Fill . SqlDataReader.Fill creates an internal class LoadAdapter (derived from DataAdapter ) internally, and calls its Fill method: performance will be very similar to SqlDataAdapter.Fill(DataTable) . There will be some small differences in initialization / validation of arguments, but as the number of rows increases, this will become less and less significant. Note also that your second sample should be modified to be comparable with the first: public DataTable populateUsingDataAdapter(string myQuery){ using (SqlConnection con = new SqlConnection(constring)) { SqlDataAdapter dap = new SqlDataAdapter(myQuery,con); DataTable dt = new DataTable(); dap.Fill(dt); return dt; }} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/14999143', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1192188/']} | jdg_382900 |
stackexchange | llm_judgeable_groundtruth_similarity | 260657 |
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:
$$\int_1^{\infty}\frac{x^6}{6x^6 − 1} dx$$ I would assume it would converge but apparently it diverges. I know it has to do with improper integrals. Can anyone explain? Thank you for your time.
Now provide the response and nothing else.
| The reason why this integral diverges is the following. For large $x$ the fraction reaches a constant limit.\begin{align}\lim_{x\rightarrow \infty} \frac{x^6}{6x^6-1} = \frac{1}{6}\end{align} That means that we integrate a functions that asymptotically behaves like $f(x)\equiv \frac{1}{6}$ which has a diverging integral.See also Wolfram Alpha for a plot of the integrand. Concerning Brian M. Scott regards. He is right. The more correct argumentation would be:\begin{align}\frac{x^6}{6x^6-1} \geq \frac{x^6}{6x^6}=\frac{1}{6} \, \forall x \geq 1\end{align}So\begin{align}\int_1^{\infty}\frac{x^6}{6x^6-1} \, dx \geq \int_1^{\infty}\frac{1}{6} \, dx = \infty\end{align} | {} | {'log_upvote_score': 5, 'links': ['https://math.stackexchange.com/questions/260657', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/53401/']} | jdg_382901 |
stackexchange | llm_judgeable_groundtruth_similarity | 415833 |
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:
This is going to sound like a trivial question, but I like to think it's actually a deep one. The simple quesiton is, "What is the normal form of a typical JSON object?" For reference, I put an example below, but consider any typcial JSON object you've dealt with, same question applies. I ask this theoretical question for a practical reason. In practice, we often need to convert JSON objects to some set of tables. Once they are tables, the tables have measurable normal forms based on all the usual rules of normal forms. But getting to those tables with their normal form takes work. Now, what else "takes work". Answer: going from lower normal forms to higher normal forms. What doesn't "take work", is going down the normal forms. Or at least just a trivial amount of work. That is, if I have 6NF, I can rather quickly manipulate my way down to any lower normal form. If I have, say 2NF, and I need to work my way to at least 5NF for some practical reason, I have much work to do. Well...since it is rather hard to get JSON to any decent normal form, then intuitively it seems it must be in a very low normal form. I'm hoping someone here can quantify that normal form of the JSON . Much apprecaited. But I still haven't given the most critical rationale. It is not uncommon for non-technical leaders to ask for miracles. I'm not criticizing, we all know it happens. And the miracle is something of the form, "just write some code to automatically make JSON into tables". But wait! If my theory is correct, and JSON is basically 0NF or so, then you can't automate you way out of it. You can't go from the very low NF of JSON to anything decent, such as 3NF+, in an automated fashing because that "takes work". That is, it takes smart humans understanding the domain. Now, I know some trivial JSON can become some trivial tables. I know there are a few tools that handle the simple cases. But I believe a general purpose JSON-to-Table converter is theoretically not possible because JSON is so low on the normalization information (in the rigorous Claude Shannon sense), that you can't automate it away. So, what is the normal form of a typical JSON object ? And is there some theory I didn't find that already proves you can't automate your way out of this. Thanks! { "data": { "cust1": { "name": "Jane", "age": 33, "address": "Main Street", "favorites": { "colors": ["blue", "green"] } }, "cust2": { "name": "Joe", "age": 44, "address": "West Road", "favorites": { "colors": ["red", "yellow"] } } }}
Now provide the response and nothing else.
| In short JSON is a data representation according to a schema-less syntax without predefined semantics. On the opposite, normal forms are defined for abstract data model with a relational semantic according to a fixed schema. Therefore, it does not make sense to apply normal forms to JSON. You can however add a schema or some semantics to your JSON format that would allow normal form analysis. But despite the feasibility, it is generally of little benefit, because a rich object model with nested and related objects are meant to expresses self-contained data differently and more flexibly than through fixed predefined tabular relations. More details Does it make sense? The normal form was invented in the context of relational models by the pioneer Edgar F. Codd . The theory of the relational algebra is not about tables and columns, but about abstract relations, attributes, and sets (that can easily be represented with tables). The normal form is about the data (tuples) in the relations, the form of their atributes, and their interdependencies. JSON is not a model but a representation of data with a precise syntax but without defined semantic. There is no rule about how to relate two different objects: Every JSON represents a different object and could represent a unique relation, made of a single tuple and not related to any others, or represent a set of related instances of a relation. Conclusion: The concept of normal form does not apply to JSON objects, because it's defined for a relational model and JSON is used in radically different models (typically the document model). Could it make sense? Nothing prevents you to add some semantic to the JSON syntax. It is not rare that a set of JSON documents are related and represent tuples of the same relation, and that elements that share a same name correspond to the same attribute and have their potential values in the same domain (following an implicit or explicit schema ). In fact your example uses JSON exactly this way. At what level should the normal form be considered? Do you consider the JSON object itself as a single attribute in a relation? Since it is not elementary/atomic but made of an aggregation of several elements, it would be indeed UNF. Do you consider the JSON as a tuple? After all, Codd noted tuples (a,b,c) using the order of the attribute names (p1,p2, p3) and did never pretend a tuple was UNF. So {p1:a, p2:b, p3:c} could easily be considered 1NF if each of its elementary/atomic. In the second case, there are however some more questions. What if: some elements are nested objects: these are not atomic. So do we consider them as a separate relation and apply the rule about normal form recursively, looking within the embedded JSON? Or do we conclude that any JSON containing an embedded JSON is no longer in 1NF? some elements are arrays: these are not atomic either. So do you consider that it's just not normal form, or do you consider the array as a relation defined by enclosed tuples and you then look recursively at each array element? Conclusion: Adopting some semantics to the JSON syntax allows to apply normal form analysis. How to extend normal form to JSON? In practice, with the semantic defined in the previous section, and choosing the recursive analysis for the open questions, you define a mapping between you JSONs and a relational form . In fact, a researcher team at Yale even published a paper to describe such an algorithm . With such a mapping you may just apply the normal-form critera to the mapped relational model to categorize your JSON representation. For example this JSON: { customers: [ { id:1, name:"Smith", turnover:324233.22}, { id:2, name:"Wesson", turnover:1600256.00} ], products: [ { id:1234, label:"Screwdriver", lauched: { y:2019,m:9 }}, { id:1235, label:"Hammer (row)", lauched: { y:2011,m:1 }} ]} could have the following relational mapping: TABLE CUSTOMERS (id, name, turnover); TABLE PRODUCTS (id, label);TABLE PRODUCT-LAUNCH (product-id, year, month); So you could claim the JSON is BCNF , because the relational mapping has tables with only atomic attributes, that the attributes of each table solely depend on the primary key and not a part of primary key, that obviously there is no transitive dependency, ... But what's the benefit? I claim that normal form for JSON does in most case not have any benefit : If you chose a JSON encoding and a NOSQL document database, it's because you want to free yourself of the relational model. Not because the relational model would be bad (in fact it is excellent and achieved outstanding performance in domains where it fits the needs), but because the relational model probably doesn't fit your specific needs. It makes then no sense to introduce artificial constraints. If your whole design is based on rich business objects and you do not want to flatten and rehydrate them via an ORM layer , the normal form will not help you: your objects are self-contained and redundancy may not matter in the same way it does in tables. This is exactly why it is usually analysed case-by-case hot to implementing one-to-many associations in a document database, i.e. embedded documents vs. references to other documents . Conclusion: The normal form does in general not add benefits to JSON, unless you need to do ORM. However, the thoughts about redundancies and functional dependencies, which are core ingredients of the normal forms, may help to assess the boundaries between objects. | {} | {'log_upvote_score': 4, 'links': ['https://softwareengineering.stackexchange.com/questions/415833', 'https://softwareengineering.stackexchange.com', 'https://softwareengineering.stackexchange.com/users/175514/']} | jdg_382902 |
stackexchange | llm_judgeable_groundtruth_similarity | 26583536 |
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 going through loops and found a significant difference in accessing loops.I can't understand what is the thing that causes such difference in both cases? First Example: Execution Time; 8 seconds for (int kk = 0; kk < 1000; kk++){ sum = 0; for (int i = 0; i < 1024; i++) for (int j = 0; j < 1024; j++) { sum += matrix[i][j]; }} Second Example: Execution Time: 23 seconds for (int kk = 0; kk < 1000; kk++){ sum = 0; for (int i = 0; i < 1024; i++) for (int j = 0; j < 1024; j++) { sum += matrix[j][i]; }} What causes so much execution time difference just exchanging matrix[i][j] to matrix[j][i] ?
Now provide the response and nothing else.
| It's an issue of memory cache. matrix[i][j] has better cache hits than matrix[j][i] , since matrix[i][j] has more continuous memory accessing chances. For example, when we access matrix[i][0] , the cache may load a continuous segment of memory containing matrix[i][0] , thus, accessing matrix[i][1] , matrix[i][2] , ..., will benefit from caching speed, since matrix[i][1] , matrix[i][2] , ... are near to matrix[i][0] . However, when we access matrix[j][0] , it is far from matrix[j - 1][0] and may not been cached, and can not benefit from caching speed. Especially, a matrix is normally stored as a continuous big segment of memory, and the cacher may predicate the behavior of memory accessing and always cache the memory. That's why matrix[i][j] is faster. This is typical in CPU cache based performance optimizing. | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/26583536', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3468623/']} | jdg_382903 |
stackexchange | llm_judgeable_groundtruth_similarity | 137609 |
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:
Here's a homework question I'm trying to solve: Prove or disprove: if $\lim_af$ and $\lim_ag$ do not exist, then $\lim_a(f \cdot g)$ do not exist either. So I know that$$(\forall l\in\mathbb{R})(\exists\epsilon\gt0)(\forall\delta_1\gt0):(\|x-a\|\lt\delta_1)(\rightarrow\|f(x)-l\|\ge\epsilon/2)$$$$(\forall m\in\mathbb{R})(\exists\epsilon\gt0)(\forall\delta_2\gt0):(\|x-a\|\lt\delta_2)(\rightarrow\|g(x)-m\|\ge\epsilon/2)$$ Now, since this is true for every $l,m\in\mathbb{R}$, it's also true for for every $r\in\mathbb{R}, r=m\cdot n$. In the same way, the two statements hold for every $\delta\gt0$ then$$(\forall r\in\mathbb{R})(\exists\epsilon\gt0)(\forall\delta\gt0):(\|x-a\|\lt\delta)(\rightarrow\|f(x)-l\| \cdot \|g(x)-m\|\ge\epsilon/2 \cdot \epsilon/2)$$ How do I continue from here, assuming I was right so far? Thanks
Now provide the response and nothing else.
| The claim is false, for example let $$\begin{align}f(x)&=\begin{cases} 1 \text{ if $x$ is rational} \\ 2 \text{ if $x$ is irrational}\end{cases} \\ g(x)&=\begin{cases} 1 \text{ if $x$ is rational} \\ 1/2 \text{ if $x$ is irrational}\end{cases}\end{align}$$ Then neither $\lim_{x \to 0}f(x)$ nor $\lim_{x \to 0} g(x)$ exists, but $(f \cdot g)(x)=1$ for all $x$ and so $\lim_{x \to 0}(f \cdot g)(x)=1$. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/137609', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/18887/']} | jdg_382904 |
stackexchange | llm_judgeable_groundtruth_similarity | 6988779 |
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 ran the code below, by calling the function in the constructor First -- >>> class PrintName:... def __init__(self, value):... self._value = value... printName(self._value)... def printName(self, value):... for c in value:... print c...>>> o = PrintName('Chaitanya')Chaitanya Once again I run this and I get this >>> class PrintName:... def __init__(self, value):... self._value = value... printName(self._value)... def printName(self, value):... for c in value:... print c...>>> o = PrintName('Hello')Traceback (most recent call last): File "<stdin>", line 1, in <module> File "<stdin>", line 4, in __init__NameError: global name 'printName' is not defined Can I not call a function in the constructor? and whay a deviation in the execution of similar code? Note: I forgot to call a function local to the class, by using self (ex: self.printName()). Apologize for the post.
Now provide the response and nothing else.
| You need to call self.printName since your function is a method belonging to the PrintName class. Or, since your printname function doesn't need to rely on object state, you could just make it a module level function. class PrintName: def __init__(self, value): self._value = value printName(self._value)def printName(value): for c in value: print c | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/6988779', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/541310/']} | jdg_382905 |
stackexchange | llm_judgeable_groundtruth_similarity | 7832080 |
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 following code exits with a unbound variable error. How can I fix this, while still using the set -o nounset option? #!/bin/bashset -o nounsetif [ ! -z ${WHATEVER} ]; then echo "yo"fiecho "whatever"
Now provide the response and nothing else.
| #!/bin/bashset -o nounsetVALUE=${WHATEVER:-}if [ ! -z ${VALUE} ]; then echo "yo"fiecho "whatever" In this case, VALUE ends up being an empty string if WHATEVER is not set. We're using the {parameter:-word} expansion, which you can look up in man bash under "Parameter Expansion". | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/7832080', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/830640/']} | jdg_382906 |
stackexchange | llm_judgeable_groundtruth_similarity | 37246981 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Following code opens sms applications But I want to open system installed chat application list such as viber, whatsapp etc. Please help to correct this code. //setting onclicklistner to chat button chat_button.setOnClickListener(new OnClickListener() { @Override public void onClick(View v) { Intent intent= new Intent(Intent.ACTION_VIEW); intent.setData(Uri.parse("sms:"+TelNos[position])); context.startActivity(intent); } });
Now provide the response and nothing else.
| I don't know why zorder has that behavior and it's likely that might be a bug or, at the very least, a badly documented feature. It might be because there are already automatic references to zorder when you build a plot (like grid, axis, and so on...) and when you try to specify the zorder for elements you are somehow overlapping them. This is hypothetical in any case. For you to solve your problem just make the differences in zorder exaggerated. For instance instead of 0,1,2 , make it 0,5,10 : import matplotlib.pyplot as pltlineWidth = 20plt.figure()plt.plot([0,0],[-1,1], lw=lineWidth, c='b',zorder=10)plt.plot([-1,1],[-1,1], lw=lineWidth, c='r',zorder=5)plt.plot([-1,1],[1,-1], lw=lineWidth, c='g',zorder=0)plt.show() Which results in this: For this plot I specified the opposite order shown in your question. | {} | {'log_upvote_score': 8, 'links': ['https://Stackoverflow.com/questions/37246981', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/4976267/']} | jdg_382907 |
stackexchange | llm_judgeable_groundtruth_similarity | 925677 |
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 looking to draw a octagon and I need $(x, y)$ coordinates.
Now provide the response and nothing else.
| These are most easily done using a rotation matrix:$$R = \left[\begin{array}{cc} \cos\theta & -\sin\theta \\ \sin\theta & \cos\theta \end{array}\right]$$So that if you have a coordinate $\left[\begin{array}{c} x \\ y\end{array}\right]$, the vector $$R\left[\begin{array}{c} x \\ y\end{array}\right] = \left[\begin{array}{c} x\cos\theta - y\sin\theta \\ x\sin\theta +y\cos\theta\end{array}\right]$$is $\left[\begin{array}{c} x \\ y\end{array}\right]$ rotated $\theta$ radians counterclockwise around the origin. Now suppose one vertex of your octagon is at $(1,0)$. To get the second vertex, you should rotate this by $\frac{2\pi}{8} = \frac{\pi}{4}$. And to get the third vertex, you rotate the second by $\frac{\pi}{4}$ and so on. This is a general solution that you can utilize to find the coordinates (e.g. using a computer) for any regular $n$-gon. An regular octagon is special in the sense that you will get the simple expression$$(1,0),(\frac{\sqrt{2}}{2}, \frac{\sqrt{2}}{2}), (0,1), (-\frac{\sqrt{2}}{2}, \frac{\sqrt{2}}{2}), (-1,0), (-\frac{\sqrt{2}}{2}, -\frac{\sqrt{2}}{2}), (0, -1), (\frac{\sqrt{2}}{2}, -\frac{\sqrt{2}}{2})$$for its coordinates. Edit: To get the coordinates for a "real" stop sign, you will need to start from the point $(\cos \frac{\pi}{8}, \sin\frac{\pi}{8})$. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/925677', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/140242/']} | jdg_382908 |
stackexchange | llm_judgeable_groundtruth_similarity | 2348991 |
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:
Attempt: I found the Fourier series for $f(x) = \begin{cases} 0,& -\pi < x < 0 \\ x/2,& 0 < x < \pi \end{cases}$ a) $a_0 = \frac{1}{2\pi}\int_0^{\pi} r\,dr = \pi/4$ $a_n = \frac{1}{2\pi}\int_0^r \frac{r\cos(nr)}{2}dr = \frac{(-1)^n - 1}{2\pi n^2}$ $b_n = \frac{1}{2\pi}\int_0^r r\sin(nr)\,dr = \frac{(-1)^n + 1}{2n}$ $f(x) = \frac{\pi}{8} - \sum_n [\frac{((-1)^n - 1)\cos(nx)}{2\pi n^2} + \frac{((-1)^n + 1)\sin(nx)}{2n}]$ The prof asked us to use this Fourier series to prove that $\pi^2/8 = 1+1/3^2+1/5^2+1/7^2+\cdots$. How do I do this?
Now provide the response and nothing else.
| You can prove $$\sum \frac{1}{n^2}=\frac{\pi^2}{6}$$ using Fourier series. Hence, $$\sum\frac{1}{(2n)^2}+\sum\frac{1}{(2n+1)^2}=\frac{\pi^2}{6}$$Therefore,$$\frac14 \sum \frac{1}{n^2}+\sum\frac{1}{(2n+1)^2}=\frac{\pi^2}{6}$$This shows $$\sum\frac{1}{(2n+1)^2}=\frac{\pi^2}{6}-\frac{\pi^2}{24}=\frac{\pi^2}{8}$$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/2348991', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/212937/']} | jdg_382909 |
stackexchange | llm_judgeable_groundtruth_similarity | 834025 |
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 $a$ , $b$ , $c$ be nonnegative real numbers. Prove $(a^{2}+2)(b^{2}+2)(c^{2}+2)\geq 9(ab+bc+ca)$ .
Now provide the response and nothing else.
| I will prove the stronger inequality:$$(a^2+2)(b^2+2)(c^2+2)\ge 3(a+b+c)^2$$ because$$(a^2+2)(b^2+2)=(a^2+1)(b^2+1)+a^2+b^2+3\ge (a+b)^2+\dfrac{1}{2}(a+b)^2+3=\dfrac{3}{2}[(a+b)^2+2]$$so$$(a^2+2)(b^2+2)(c^2+2)\ge \dfrac{3}{2}[(a+b)^2+2](c^2+2)\ge\dfrac{3}{2}[\sqrt{2}(a+b)+\sqrt{2}c]^2=3(a+b+c)^2$$so$$(a^2+2)(b^2+2)(c^2+2)\ge 3(a+b+c)^2\ge 9(ab+bc+ac)$$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/834025', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/45070/']} | jdg_382910 |
stackexchange | llm_judgeable_groundtruth_similarity | 215699 |
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:
After installing FreeBSD we would like to use following commands to install additional packages. pkgpkg install nanopkg install xorgpkg install mate-desktop matepkg install slim The above commands require an Internet connection to install packages. But how can we install those packages without an Internet connection by using CD/DVD/USB?
Now provide the response and nothing else.
| Based upon an open issue in FreeBSD 10.1-RELEASE Errata : Create a /dist directory, then mount the DVD. # mkdir -p /dist# mount -t cd9660 /dev/cd0 /dist Make sure REPOS_DIR is correctly pointing to your local repository. For sh(1) : # export REPOS_DIR=/dist/packages/repos – or, for csh(1) : # setenv REPOS_DIR /dist/packages/repos Use pkg(7) to bootstrap pkg(8) , then install packages. # pkg bootstrap --yes# pkg install xorg [...] Limitations of -dvd1.iso files FreeBSD-13.1-RELEASE-amd64-dvd1.iso does not provide packages for mate , mate-desktop , nano , or slim . | {} | {'log_upvote_score': 4, 'links': ['https://unix.stackexchange.com/questions/215699', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/105902/']} | jdg_382911 |
stackexchange | llm_judgeable_groundtruth_similarity | 31380280 |
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 Django Rest Framework , and also new to django. I want to return a custom 404 error in json when a client will access a resource which was not found. My urls.py looks liks this: urlpatterns = [ url(r'^mailer/$', views.Mailer.as_view(), name='send-email-to-admin')] In which i have only one resource, which can be accessed through URI, http://localhost:8000/mailer/ Now, when a client access any other URI like http://localhost:8000/ , API should return a 404-Not Found error like this: { "status_code" : 404 "error" : "The resource was not found"} Please suggest some answer with proper code snippets, if suitable.
Now provide the response and nothing else.
| You are looking for handler404 . Here is my suggestion: Create a view that should be called if none of the URL patterns match. Add handler404 = path.to.your.view to your root URLconf. Here is how it's done: project.views from django.http import JsonResponsedef custom404(request, exception=None): return JsonResponse({ 'status_code': 404, 'error': 'The resource was not found' }) project.urls from project.views import custom404handler404 = custom404 Read error handling for more details. Django REST framework exceptions may be useful as well. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/31380280', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/2026325/']} | jdg_382912 |
stackexchange | llm_judgeable_groundtruth_similarity | 3009213 |
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 use IronPython as an intermediary between a C# GUI and some C# libraries, so that it can be scripted post compile time. I have a Class library DLL that is used by both the GUI and the python and is something along the lines of this: namespace MyLib{ public class MyClass { public string Name { get; set; } public MyClass(string name) { this.Name = name; } }} The IronPython code is as follows: import clrclr.AddReferenceToFile(r"MyLib.dll")from MyLib import MyClassReturnObject = MyClass("Test") Then, in C# I would call it as follows: ScriptEngine engine = Python.CreateEngine();ScriptScope scope = null;scope = engine.CreateScope();ScriptSource source = engine.CreateScriptSourceFromFile("Script.py");source.Execute(scope);MyClass mc = scope.GetVariable<MyClass>("ReturnObject ") When I call this last bit of code, source.Execute(scope) runs returns successfully, but when I try the GetVariable call, it throw the following exception Microsoft.Scripting.ArgumentTypeException: expected MyClass , got MyClass So, you can see that the class names are exactly the same, but for some reason it thinks they are different. The DLL is in a different directory than the .py file (I just didn't bother to write out all the path setup stuff), could it be that there is an issue with the interpreter for IronPython seeing these objects as difference because it's somehow seeing them as being in a different context or scope?
Now provide the response and nothing else.
| This error indicates that your assembly is getting loaded into multiple CLR loader contexts. Rather than adding the reference using clr.AddReferenceToFile you can either switch to clr.AddReference or you can load the assembly from C#. For the former you need to make sure that the assembly is available somewhere that .NET can normally load it (the GAC or in the application base of the process). For the latter you can just do: engine.Runtime.LoadAssembly(typeof(MyClass).Assembly); from your C# host code. Personally I like this 2nd solution a little bit more because not only does it work it saves your users from needing to do the clr.AddRef call from Python. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3009213', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/194/']} | jdg_382913 |
stackexchange | llm_judgeable_groundtruth_similarity | 2444398 |
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:
the radio test fail but it seem to converger numerically$$\sum _{k=1}^{\infty } \frac{\sin \left(\frac{x}{k}\right)}{\sqrt{k}}=\sqrt{2 \pi } \sqrt{x}+\sum _{n=1}^{\infty } \frac{\left(\frac{1}{2}-\frac{i}{2}\right) \left(e^{-2 \sqrt{\pi } \sqrt{i n} \sqrt{x}} \sin \left((1+i) \sqrt{2 \pi } \sqrt{n} \sqrt{x}\right)+e^{-2 \sqrt{\pi } \sqrt{-i n} \sqrt{x}} \sinh \left((1+i) \sqrt{2 \pi } \sqrt{n} \sqrt{x}\right)\right)}{\sqrt{n}}$$ I do not sure
Now provide the response and nothing else.
| The following statement is valid over $\mathbb{R}$: if $(a_{ij})$ is symmetric and $a_{ii} > \sum_{j\ne i} |a_{ij}|$ for all $i$, then $(a_{ij})$ is positive definite. Now, if we have an "algebraic" statement valid over $\mathbb{R}$, it will be valid over any "real closed field". That statement is $\langle A x, x\rangle > 0$ for all $x \ne 0$. But your ordered field can be imbedded in a real closed field, so the statement is therefore true over any ordered field. This is the philosophy... But probably the statement can be proved directly, without all this "meta" stuff.. $\bf{Added:}$ The dominant diagonal element criterion is sharp, as one can see looking at the eigenvalues of the matrix $(a_{ij}) = (1_{ij})$. But a weaker condition is enough, for instance $|a_{ij}|< \frac{1}{n-1}$ for all $i\ne j$. It is enough to add up all the inequalities:$$\frac{1}{n-1}\left (x^2_{i} + x^2_{j}\right) + 2 a_{ij} x_i x_j\ge 0$$ for $i<j$, and note that the inequalities are strict for non-zero variables. $\bf{Added 2:}$. In fact diagonal dominant implies positive is quite simple. Just add all the inequalities;$$ |a_{ij}| x_{i}^2 + |a_{ij}| x_{j}^2+ 2 a_{ij} x_i x_j\ge 0$$ for all $i< j$ and get$$\sum_{i=1}^n s_i x^2_i + \sum_{i<j} 2 a_{ij} x_i x_j\ge 0$$ where $$s_i = \sum_{j\ne i} |a_{ij}|$$ $\bf{Added 3:}$ Let's also give a purely algebraic proof that diagonal dominant matrix ( by rows, $a_{ii} > \sum_{j\ne i} |a_{ij}|$ for all $i$) have determinant $>0$. The determinant cannot be $0$. Otherwise the system $A x = 0$ would have a non-zero solution. Get a contradiction, by considering the largest $|x_i|$. Deform the matrix to a matrix with positive determinant, while preserving dominance. The usual proof uses the intermediate value property for polynomials. We'll only use that property for polynomials of degree $1$, valid for every ordered field. For this, consider for $t\in [0,1]$ the matrix $A_t$ that differs from $A$ only on first row, which is $(a_{11}, t a_{12}, \ldots, t a_{1n})$. We have $$\det A_t = (1-t) a_{11} \det A' + t \det A$$ where $\det A'$ is the determinant of the matrix $(a_{ij})_{2 \le i,j\le n}$. So we can do an induction argument. $n=1$ case is trivial. Assume true for $n-1$. Then we have $\det A'>0$. Therefore, $\det A_0 >0$. We know that $\det A_t \ne 0$ for $t \in [0,1]$ ( determinant of a dominant matrix). We conclude $\det A_t >0$ for all $t \in [0,1]$, and in particular, $\det A_1 = \det A >0$. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/2444398', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/-1/']} | jdg_382914 |
stackexchange | llm_judgeable_groundtruth_similarity | 1605480 |
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 circle has the same center as an ellipse and passes through the foci $F_1$ and $F_2$ of the ellipse,such that the two curves intersect in $4$ points.Let $P$ be any one of their point of intersection.If the major axis of the ellipse is $17$ and the area of the triangle $PF_1F_2$ is $30$,then find the distance between the foci. Let the center of the ellipse and the circle be $(0,0)$ We are given $2a=$length of major axis$=17$. Let the coordinates of foci be $F_1(c,0)$ and $F_2(-c,0)$ We need to find $2c$. Area of $PF_1F_2=\frac{1}{2}\times 2c\times$perpendicular distance between $P$ and the axis of the major axis of the ellipse. I do not know how to solve it further.
Now provide the response and nothing else.
| We may suppose that $$\text{the ellipse$\ :\ \frac{x^2}{a^2}+\frac{y^2}{b^2}=1,\quad a\gt b\gt 0$}$$$$\text{the circle$\ :\ x^2+y^2=a^2-b^2$}$$ As you wrote, we have$$2a=17\quad\Rightarrow \quad a=\frac{17}{2}$$ Since$$\frac{a^2-b^2-y^2}{a^2}+\frac{y^2}{b^2}=1\quad\Rightarrow\quad |y|=\frac{b^2}{\sqrt{a^2-b^2}}$$ we have$$30=\frac 12\times 2\sqrt{a^2-b^2}\times \frac{b^2}{\sqrt{a^2-b^2}}\quad\Rightarrow\quad b=\sqrt{30}.$$ Thus, the answer is$$2\sqrt{a^2-b^2}=2\sqrt{\left(\frac{17}{2}\right)^2-30}=\color{red}{13}.$$ | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/1605480', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/262216/']} | jdg_382915 |
stackexchange | llm_judgeable_groundtruth_similarity | 20295080 |
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 an ajax call, that sends form data to a php function. Since I read a lot that using contentType: 'application/json' is best practice I wanted to give it a try as well. But unfortunately my script doesn't return anything when I use it. If I remove it, the script does what it is supposed to do. Do you have any idea what the reason might be and why? Thank you! $('#Form').submit(function(e) { e.preventDefault(); var content = $(this).serialize() + "&ajax=1"; $.ajax('app/class/controller/contactForm.php', { type: "POST", //contentType: 'application/json', dataType: 'json', data: content, success: function(result) { console.log(result); } }); }) and my PHP: if(isset($_POST['ajax']) && $_POST['ajax'] === '1') { echo json_encode(validateForm($_POST));}
Now provide the response and nothing else.
| When using contentType: 'application/json' you will not be able to rely on $_POST being populated. $_POST is only populated for form-encoded content types. As such, you need to read your data from PHP raw input like this: $input = file_get_contents('php://input');$object = json_decode($input); Of course if you want to send application/json you should actually send JSON, which you are not doing. You either need to build the object serialization to JSON directly, or you need to do something like this - Convert form data to JavaScript object with jQuery - to serialize the object from the form. Honestly in your case, since you are dealing with form data, I don't quite think the use case for using application/json is there. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/20295080', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/573514/']} | jdg_382916 |
stackexchange | llm_judgeable_groundtruth_similarity | 4978 |
Below is a question asked on the forum quantumcomputing.stackexchange.com. Provide a good and informational response to it like a helpful human would.
Question:
In Nielsen and Chuang (page:379), it is shown that the operator sum representation of a depolarizing channel $\mathcal{E}(\rho) = \frac{pI}{2} + (1-p)\rho$ is easily seen by substituting the identity matrix with $$\frac{\mathbb{I}}{2} = \frac{\rho + X\rho X + Y\rho Y +Z\rho Z}{4}.$$ What is the more systematic way to see this result? Particularly, for the higher dimensional analogue, I cannot see how to proceed.
Now provide the response and nothing else.
| This really depends where you want to start from. For instance, you can construct the Choi state of $\mathcal E$ , i.e., $$\sigma = (\mathcal E \otimes \mathbb I)(|\Omega\rangle\langle\Omega|)\ ,$$ with $\Omega = \tfrac{1}{\sqrt{D}}\sum_{i=1}^D |i,i\rangle$ , and then extract the Kraus operators of $\mathcal E(\rho)=\sum M_i\rho M_i^\dagger$ by taking any decomposition $$\sigma = \sum |\psi_i\rangle\langle\psi_i|\ ,\tag{*}$$ and writing $|\psi_i\rangle = (M_i\otimes\mathbb I)|\Omega\rangle$ (which is always possible). Note that the decomposition $(*)$ is highly non-unique (any $|\phi_j\rangle = \sum V_{ij} |\psi_i\rangle$ , with $V$ an isometry, is also a valid decomposition), which relates to the fact that the Kraus decomposition is equally non-unique. Obviously, the eigenvalue decomposition is a simple choice (which, moreover, minimizes the number of Kraus operators). Let's look at your example in a bit more detail. Here, $D=2$ . You have that $$\mathcal E(X)=p\mathrm{tr}(X)\,\frac{\mathbb I}{2}+(1-p)X$$ for any $X$ (due to linearity) -- the $\mathrm{tr}(X)$ is required to make this trace-preserving for general $X$ . We now have that \begin{align}\sigma &= (\mathcal E \otimes \mathbb I)(|\Omega\rangle\langle \Omega|)\\& = \tfrac1D \sum_{ij} \mathcal E(|i\rangle\langle j|)\otimes |i\rangle\langle j|\ \end{align} inserting the definition of $|\Omega\rangle$ and using linearity. This yields $$\sigma = \frac{p}{2D}\mathbb I\otimes \sum_{i}|i\rangle\langle i| +(1-p)\frac1D \sum_{ij}|i\rangle\langle j|\otimes |i\rangle\langle j|\ .$$ The second term is just $(1-p)|\Omega\rangle\langle\Omega|$ , and the first term is $\frac{p}{2D}\mathbb I\otimes\mathbb I$ . You can now see that one possible eigenvalue decomposition of $\sigma$ is given by the four Bell states (I leave it to you to work out the weights), and it is well known and easy to check that that the four Bell states can be written as $$(\sigma_k\otimes \mathbb I)|\Omega\rangle\ ,$$ where $\sigma_k$ are the three Pauli matrices or the identity. Thus, you get that the $M_i$ in the Kraus representation are the Paulis and the identity, with the weight given by the eigenvalue decomposition of $\sigma$ . | {} | {'log_upvote_score': 4, 'links': ['https://quantumcomputing.stackexchange.com/questions/4978', 'https://quantumcomputing.stackexchange.com', 'https://quantumcomputing.stackexchange.com/users/4831/']} | jdg_382917 |
stackexchange | llm_judgeable_groundtruth_similarity | 30701631 |
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 been looking on how to use jinja2 in django 1.8, but there is no complete source for using django with jinja2. I was wondering if you guys knew the process for using jinja2 in django. I have looked through the the official documentation and I have looked at the following question: How to setup django 1.8 to use jinja2? but none of them clearly explain how to use jinja2 in an put-togther manner. I just started using django and don't know all the lingo in the docs. I would really appreciate the help.
Now provide the response and nothing else.
| Frist you have to install jinja2 : $ pip install Jinja2 Then modify your TEMPLATES list in the settings.py to contain the jinja2 BACKEND : TEMPLATES = [ { 'BACKEND': 'django.template.backends.jinja2.Jinja2', 'DIRS': [os.path.join(BASE_DIR, 'templates/jinja2')], 'APP_DIRS': True, 'OPTIONS': {'environment': 'myproject.jinja2.Environment',}, }, { 'BACKEND': 'django.template.backends.django.DjangoTemplates', 'DIRS': [], 'APP_DIRS': True, 'OPTIONS': { 'context_processors': [ 'django.template.context_processors.debug', 'django.template.context_processors.request', 'django.contrib.auth.context_processors.auth', 'django.contrib.messages.context_processors.messages', ], }, },] where templates/jinja2 is the directory with your jinja2 template files. And in your views.py file: from __future__ import absolute_import # Python 2 onlyfrom jinja2 import Environmentfrom django.contrib.staticfiles.storage import staticfiles_storagefrom django.urls import reversedef environment(**options): env = Environment(**options) env.globals.update({ 'static': staticfiles_storage.url, 'url': reverse, }) return env This makes static and url available in your Jinja2 templates. P.S. For more details see this article . | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/30701631', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1507875/']} | jdg_382918 |
stackexchange | llm_judgeable_groundtruth_similarity | 356087 |
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 understand there are many questions in this site revolving around the same concept, but I could not get a precise answer for my case. Problem I am handling an ERP System, with code base in both: VB.NET/ASP Forms for the user interface portion of the system TSQL Stored Procedures on SQL Server, handling business logic. So both database tables and database stored procedures are tightly coupling data and business logic We have been trying to figure out a way to automate unit tests to help us detect regression and other potential bugs. But the problem with our setup is the presence of database as a major component of our system's business logic; Databases retains states, i.e. we cannot run something like xUnit with independent classes. because each test will alter that state of our system, by changing one of the records of data tables, lookup tables or control tables. Constraints We are not expected to shift our logic to the VB portion of our code ( For political reasons ) Note that mocking database will not solve our problem, because business logic runs on stored procedures, that is by design relying on state of data Question What are our options? is there a way to implement automated unit/integration testing? Are we stuck in manual testing? Should we place our environment in a farm of virtual machines with the same baseline and run independent tests on different machines? Unfortunately, I could not find any literature related to best practices for TDD and Stored Procedures based systems.
Now provide the response and nothing else.
| I've implemented automated testing including the database in a system with some of the same problems. The approach I took was roughly: Before all unit tests, bring up a DB from scratch with schema and no data Before each test case, truncate all the relevant db tables This works, though it does produce very slow tests. Once you have regression/characterization tests in place, you should begin decoupling the application logic from the database. Hide the business logic behind an interface and use inversion of control so that you can pass in the implementation. You'll start with the db-backed implementation, and in tests you can use an in-memory version that's lightweight and faster. For example, if you have: def frob_widgets(foo, bar): if db.some_query(params=blah): foo.flip() bar.calcinate(foo) return db.explode(bar, foo) Change the signature to def frob_widgets(db, foo, bar) You may find a tool like ephemeral_pg useful, which helps to run a postgres database as lean as possible by running in memory with fewer safety/reliability checks enabled | {} | {'log_upvote_score': 4, 'links': ['https://softwareengineering.stackexchange.com/questions/356087', 'https://softwareengineering.stackexchange.com', 'https://softwareengineering.stackexchange.com/users/40424/']} | jdg_382919 |
stackexchange | llm_judgeable_groundtruth_similarity | 21988204 |
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 an ajax call function. Inside that I'm calling a partial view. This view is for displaying comments. How can I refresh this view using ajax? I don't like json in my context, because my linq queries are set up with models. So these models with partial view should be send to ajax method. Ajax method should replace my div. Note that before ajax call, this view should be rendered at first as the page loads. I am not getting this. What is my fault? $.ajax({ url: '/Home/Item', type: 'POST', data: { itemid: itemid }, success: function (data) { $('.mycontainer').html(data); } }); Controller public ActionResult Item(int itemid) { FoodContext db = new FoodContext(); ViewBag.FoodItems = db.FoodItems.Where(row => row.itemid == itemid); List<ImageComment> comments = (from user in db.TxtComments join o in db.Logins on user.username equals o.username where user.itemid == itemid select new ImageComment { ImageUrl = o.imgurl, Comment = user.txtcmt, ImgCmntUrl = user.imgurl, Cmntdate = user.cmtdate, Username = user.username, }).OrderByDescending(x => x.Cmntdate).ToList(); ViewModel vm = new ViewModel { ImageComments = comments }; return PartialView("_Comments", vm); } Partial View @model ViewModel @foreach (ImageComment comment in Model.ImageComments) { <table width="100%" height="152" border="0"> <tr> <td width="101" rowspan="2" valign="top"><img src="@comment.ImageUrl" width="100%" height="100%" /></td> <td height="27" colspan="3" valign="middle"><p> @comment.Username Commented On On @comment.Cmntdate</p></td> </tr> <tr> <td colspan="2" rowspan="2"><div style="width:70%;"> @if (@comment.ImgCmntUrl != null) { <img src="@Url.Content(comment.ImgCmntUrl)" width="100%" height="100%" /> } </div> <div style="background-color:#E3EEFA;width:68%;min-height:50px;padding:5px;">@comment.Comment</div></td> <td width="209" height="29"> </td> </tr> <tr> <td> </td> <td> </td> </tr> <tr> <td height="23"> </td> <td>Like this.</td> <td>Unlike this</td> <td> </td> </tr> <tr> <td height="23"> </td> <td width="303"> </td> <td width="588"> </td> <td> </td> </tr></table> } My view <div class="mycontainer"></div>
Now provide the response and nothing else.
| This is indeed a bit confusing. I think it boils down to how Matplotlib handles the secondary axes. Pandas probably calls ax.twinx() somewhere which superimposes a secondary axes on the first one, but this is actually a separate axes. Therefore also with separate lines & labels and a separate legend. Calling plt.legend() only applies to one of the axes (the active one) which in your example is the second axes. Pandas fortunately does store both axes, so you can grab all line objects from both of them and pass them to the .legend() command yourself. Given your example data: You can plot exactly as you did: ax = var.total.plot(label='Variance')ax = shares.average.plot(secondary_y=True, label='Average Age')ax.set_ylabel('Variance of log wages')ax.right_ax.set_ylabel('Average age') Both axes objects are available with ax (left axe) and ax.right_ax , so you can grab the line objects from them. Matplotlib's .get_lines() return a list so you can merge them by simple addition. lines = ax.get_lines() + ax.right_ax.get_lines() The line objects have a label property which can be used to read and pass the label to the .legend() command. ax.legend(lines, [l.get_label() for l in lines], loc='upper center') And the rest of the plotting: ax.set_title('Wage Variance and Mean Age')plt.show() edit: It might be less confusing if you separate the Pandas (data) and the Matplotlib (plotting) parts more strictly, so avoid using the Pandas build-in plotting (which only wraps Matplotlib anyway): fig, ax = plt.subplots()ax.plot(var.index.to_datetime(), var.total, 'b', label='Variance')ax.set_ylabel('Variance of log wages')ax2 = ax.twinx()ax2.plot(shares.index.to_datetime(), shares.average, 'g' , label='Average Age')ax2.set_ylabel('Average age')lines = ax.get_lines() + ax2.get_lines()ax.legend(lines, [line.get_label() for line in lines], loc='upper center')ax.set_title('Wage Variance and Mean Age')plt.show() | {} | {'log_upvote_score': 7, 'links': ['https://Stackoverflow.com/questions/21988204', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3300195/']} | jdg_382920 |
stackexchange | llm_judgeable_groundtruth_similarity | 389710 |
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:
(Disclaimer: I've read the help center and I do understand that this is bordering on off-topic since it's about consumer devices. However I hope that I've managed to make enough on-topic by asking about why it is the way it is, and what is the explanation from an electromagnetic point of view - in other words, what laws of electricity and what practical considerations have gone into these decisions). I recently bought a power tool and in its manual I found a few peculiar safety rules. I cannot see why they would be there, although reading up more it seems that they are commonplace. My understanding of electricity is limited (just about enough to be dangerous), so I'm hoping to expand it. :) The rules are: Don't use an extension cord longer than 25m. Considering this is an outdoors tool, this limitation is severely restrictive. The best explanation I've seen is that longer cables would simply have too high of a resistance and the tool wouldn't be able to operate at full power. But this argument doesn't convince me. The tool is rated at 2.4kW, and it's meant to be used with 220V AC power source, which means it uses about 11 amps of current. All the extension cords I've ever come across have at least 16A limitation, so there is quite a reserve still. In addition, the power has to travel much, much further to get to my house, and even after the meter it still takes probably close to those same 25m to get to the power outlet. Why only 25m after the outlet? The resistance of the cables isn't that big, is it? Don't daisy-chain extension cords. I suspect this is a variation of the above - don't exceed 25m; every connection adds additional contact resistance; water in the outdoors connections can be a problem - in general, it just adds risk. However, apart from the water in the contacts, the rest seems to me to be practically negligible. Is there really a significant contact resistance? Assuming that the extension cords are in a good shape. Make sure that the power cord is entirely unrolled. This is another odd one. My suspicion is that it has to do with inductive resistance. But is it really that strong? Wherever I've seen people actually wanting to create an electromagnet, it's pretty much hard work. You need a lot of neat, tightly-wound loops of wire. An extension cord has a lot of insulator around it, spacing the wires pretty far apart, and the loops are very chaotic. In addition, if that was a problem, why do extension cord rollers exist? They're used especially when you need a very long extension cord, and you don't need to unroll them completely every time you want to use them. Solved: OK, I was off the mark. The correct answer (also a separate question ) has to do with the wire heating up from being used close to its limits. When coiled together, the temperature can go pretty high and melt the cables. Not fun.
Now provide the response and nothing else.
| Let's say you're extension cables are 1 mm² cross-sectional area. The loop resistance is 33.6 mΩ/m. A 25 m cable will have a loop resistance of 840 mΩ. The voltage drop at 11 A will be given by V = IR = 11 x 0.84 = 9.24 V. On a 220 V supply this is a reduction of 4.2%. Power dissipated as heat in the cable is given by P = VI or P = I²R = 11² x 0.84 = 102 W. This is a waste of 4.2% power (as we would expect from the previous calculation). String four cords together for a 100 m run and you'll only get 220 - (9.24 x 4) = 183 V. The situation is a little more complicated than the calculations above suggest because when you add in the cable resistance the current will reduce too. For a 2.4 kW, 220 V load we can calculate \$ R = \frac {V^2}{P} = \frac {220^2}{2400} = 20.2\ \Omega \$. Add in our 100 m loop cable resistance of 4 x 0.84 Ω and the total resistance is now 23.6 Ω resulting in a max current of only 9.3 A which at 183 V (calculated above) reduces the power to VI = 183 x 9.3 = 1700 W which is only 71% of the rated power. The "square" term in the power equation makes the power loss proportional to the square of the voltage loss. Now to your questions: Don't use an extension cord longer than 25m. ... and the tool wouldn't be able to operate at full power. But this argument doesn't convince me. Be convinced by the maths. All the extension cords I've ever come across have at least 16A limitation, so there is quite a reserve still. See if you can find the cross-sectional area for those cables and recalculate. In addition, the power has to travel much, much further to get to my house, and even after the meter it still takes probably close to those same 25m to get to the power outlet. Ideally your local transformer will be fairly close to your house and, in Ireland, the connection will be using at least 25 mm² cable. You can get some idea of the source "resistance" to your house by monitoring the voltage while you switch on and off a large load such as an electric oven and all the hobs. Don't daisy-chain extension cords. ... the rest seems to me to be practically negligible. It may be tolerable (depending on your load) but it's not negligible. Is there really a significant contact resistance? This is usually not a factor. Make sure that the power cord is entirely unrolled. Our calculations showed that the power dissipated in the cable is 100 W. With the cable tightly rolled the coil temperature will rise. Imagine you wound the cable around a 100 W filament light bulb: what temperature do you think would be reached? Would it get close to melting the insulation? Figure 1. Source: Why is it dangerous use a coiled extension cord . My suspicion is that it has to do with inductive resistance. The term you are looking for is "impedance" for AC resistance. Actually there will be almost zero inductance as the live and neutral currents are in opposite directions and cancel out. I used this trick in work when I needed to create a test load for a 30 A, 30 V 50 Hz supply. We first wound a coil of 1.5 mm² cable of the correct resistance but it was really hopping when we powered it up. When we unwound it, folded in half and rewound it there was no buzz. Figure 2. Inductance cancellation. See my answer to the question linked above. But is it really that strong? ... You need a lot of neat, tightly-wound loops of wire. Or a high current in a low number of turns. | {} | {'log_upvote_score': 4, 'links': ['https://electronics.stackexchange.com/questions/389710', 'https://electronics.stackexchange.com', 'https://electronics.stackexchange.com/users/2575/']} | jdg_382921 |
stackexchange | llm_judgeable_groundtruth_similarity | 358280 |
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 new to Electronics. I am trying the Full wave rectifier. I use a transformer and 4 1n5408 diodes (Vdrop is 1.2V) and try to get 24VDC output from 220VAC 50Hz. I measure the AC output (of the transformer) and it is 24VAC. I measure the output after these 4 diodes, it is about 23VDC. Everything goes fine until I put the smoothing capacitor, no load yet. It is a 3300uF 25V electrolytic capacitor. When I turn on the power, the capacitor gets hot really fast, changes its shape and is going to explode. I check the polarity, it is correct. So my question is: Is it because my capacitor has a "too close" maximum voltage? If it is how should I choose a capacitor voltage for this circuit? Another question though, I have seen this formula around while searching for my problem: C = I(load)/2.f.V(ripple). So if I need Vr = 2V and I(load) = 2A I need to use a 2/(2.50.2) = 0.01F = 10000uF Capacitor right? Thank you all, really sorry for my English.
Now provide the response and nothing else.
| The voltage you are measuring without the capacitor is the average DC level. However the capacitor must withstand the maximum AC level, which is 1.414× the average. As such your capacitor needs to be rated at least double your DC voltage, i.e. 50V. However, to account for tolerances and aging 75 or 100V would be even better. The cap also needs to be in the right way around. The capacitor is charged to the peak level every half cycle of the AC and the ripple is caused by the capacitor discharging through the load. Notice, in the image above, the average DC level is now higher than without the capacitor. Note: With no load to drain the capacitor it will charge up to the peak level and stay there with virtually zero ripple. As such you can expect to measure close to 32.5V across the capacitor with your multimeter with no load. | {} | {'log_upvote_score': 4, 'links': ['https://electronics.stackexchange.com/questions/358280', 'https://electronics.stackexchange.com', 'https://electronics.stackexchange.com/users/179321/']} | jdg_382922 |
stackexchange | llm_judgeable_groundtruth_similarity | 13838088 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Inside a Portable Class Library, I've the following method which post data to a specific Url. The method works great. However I'd like to specify a more aggressive timeout (the default is 100 seconds). Considering that there's no Timeout property on the HttpWebRequest class from the Portable Class Library, how can I make sure that the call is abandoned if it takes longer than a few seconds? public async Task<HttpResponse> PostAsync(Uri uri, string data){ HttpWebRequest request = (HttpWebRequest)WebRequest.Create(uri); request.Method = "POST"; request.ContentType = "application/x-www-form-urlencoded"; using (Stream requestStream = await request.GetRequestStreamAsync()) { byte[] postBytes = Encoding.UTF8.GetBytes(data); requestStream.Write(postBytes, 0, postBytes.Length); } HttpWebResponse response = (HttpWebResponse)await request.GetResponseAsync(); return new HttpResponse(response.StatusCode, await new StreamReader(response.GetResponseStream()).ReadToEndAsync());}
Now provide the response and nothing else.
| Below code either will return a HttpWebResponse or null if timed out. HttpWebResponse response = await TaskWithTimeout(request.GetResponseAsync(), 100);if(response != null){ ....} Task<HttpWebResponse> TaskWithTimeout(Task<WebResponse> task, int duration){ return Task.Factory.StartNew(() => { bool b = task.Wait(duration); if (b) return (HttpWebResponse)task.Result; return null; });} --EDIT-- Creating an extension method would be even better public static class SOExtensions{ public static Task<T> WithTimeout<T>(this Task<T> task, int duration) { return Task.Factory.StartNew(() => { bool b = task.Wait(duration); if (b) return task.Result; return default(T); }); }} Usage would be: var response = (HttpWebResponse)await request.GetResponseAsync().WithTimeout(1000); --EDIT 2-- Another way of doing it public async static Task<T> WithTimeout<T>(this Task<T> task, int duration){ var retTask = await Task.WhenAny(task, Task.Delay(duration)) .ConfigureAwait(false); if (retTask is Task<T>) return task.Result; return default(T);} | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/13838088', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/42024/']} | jdg_382923 |
stackexchange | llm_judgeable_groundtruth_similarity | 406245 |
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:
How do we allow certain set of Private IPs to enter through SSH login(RSA key pair) into Linux Server?
Now provide the response and nothing else.
| You can limit which hosts can connect by configuring TCP wrappers or filtering network traffic (firewalling) using iptables . If you want to use different authentication methods depending on the client IP address, configure SSH daemon instead (option 3). Option 1: Filtering with IPTABLES Iptables rules are evaluated in order, until first match. For example, to allow traffic from 192.168.0.0/24 network and otherwise drop the traffic (to port 22). The DROP rule is not required if your iptables default policy is configured to DROP . iptables -A INPUT -p tcp --dport 22 --source 192.168.0.0/24 -j ACCEPTiptables -A INPUT -p tcp --dport 22 -j DROP You can add more rules before the drop rule to match more networks/hosts. If you have a lot of networks or host addresses, you should use ipset module. There is also iprange module which allows using any arbitrary range of IP addresses. Iptables are not persistent across reboots. You need to configure some mechanism to restore iptables on boot. iptables apply only to IPv4 traffic. Systems which have ssh listening to IPv6 address the necessary configuration can be done with ip6tables . Option 2: Using TCP wrappers Note: this might not be an option on modern distributions, as support for tcpwrappers was removed from OpenSSH 6.7 You can also configure which hosts can connect using TCP wrappers. With TCP wrappers, in addition to IP addresses you can also use hostnames in rules. By default, deny all hosts. /etc/hosts.deny : sshd : ALL Then list allowed hosts in hosts.allow. For example to allow network 192.168.0.0/24 and localhost . /etc/hosts.allow : sshd : 192.168.0.0/24sshd : 127.0.0.1sshd : [::1] Option 3: SSH daemon configuration You can configure ssh daemon in sshd_config to use different authentication method depending on the client address/hostname. If you only want to block other hosts from connecting, you should use iptables or TCP wrappers instead. First remove default authentication methods: PasswordAuthentication noPubkeyAuthentication no Then add desired authentication methods after a Match Address in the end of the file. Placing Match in the end of the file is important, since all the configuration lines after it are placed inside the conditional block until the next Match line. For example: Match Address 127.0.0.* PubkeyAuthentication yes Other clients are still able to connect, but logins will fail because there is no available authentication methods. Match arguments and allowed conditional configuration options are documented in sshd_config man page . Match patterns are documented in ssh_config man page . | {} | {'log_upvote_score': 7, 'links': ['https://unix.stackexchange.com/questions/406245', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/261580/']} | jdg_382924 |
stackexchange | llm_judgeable_groundtruth_similarity | 2495290 |
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 getting the following error when trying to write a string to a file in pythion: Traceback (most recent call last): File "export_off.py", line 264, in execute save_off(self.properties.path, context) File "export_off.py", line 244, in save_off primary.write(file) File "export_off.py", line 181, in write variable.write(file) File "export_off.py", line 118, in write file.write(self.value)TypeError: must be bytes or buffer, not str I basically have a string class, which contains a string: class _off_str(object): __slots__ = 'value' def __init__(self, val=""): self.value=val def get_size(self): return SZ_SHORT def write(self,file): file.write(self.value) def __str__(self): return str(self.value) Furthermore, I'm calling that class like this (where variable is an array of _off_str objects: def write(self, file): for variable in self.variables: variable.write(file) I have no idea what is going on. I've seen other python programs writing strings to files, so why can't this one? Thank you very much for your help. Edit: It looks like I needed to state how I opened the file, here is how: file = open(filename, 'wb')primary.write(file)file.close()
Now provide the response and nothing else.
| What version of Python are you using? In Python 3.x a string contains Unicode text in no particular encoding. To write it out to a stream of bytes (a file) you must convert it to a byte encoding such as UTF-8, UTF-16, and so on. Fortunately this is easily done with the encode() method: Python 3.1.1 (...)>>> s = 'This is a Unicode string'>>> print(s.encode('utf-8')) Another example, writing UTF-16 to a file: >>> f = open('output.txt', 'wb')>>> f.write(s.encode('utf-16')) Finally, you can use Python 3's "automagic" text mode, which will automatically convert your str to the encoding you specify: >>> f = open('output.txt', 'wt', encoding='utf-8')>>> f.write(s) | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/2495290', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/288439/']} | jdg_382925 |
stackexchange | llm_judgeable_groundtruth_similarity | 602937 |
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 am a bit confused about an aspect the "work" part in the first law of thermodynamics, which says that the change in the internal energy of a system is the work done on the system + the heat transferred to the system. Here's my question: If I do work on, say, a stone, causing it to gain a large total kinetic energy, then according to the first law of thermodynamics (TD), the internal energy has increased. But internal energy simply means the energy contained within the stone, not external energies, such as gravitational potential energy, or, more importantly in this case, the overall kinetic energy of the system. How is the first law of TD consistent with this definition of internal energy? The same problem arises, if, say, I also raise a stone by doing work on it, thus increasing the gravitational potential energy.
Now provide the response and nothing else.
| The general formulation of the first principle for a closed system says that $$L+Q= \Delta K + \Delta U + \Delta u$$ Where $L$ is the total non-conservative work done on the system. $Q$ is the heat entering the system. $K$ is the macroscopic kinetic energy, $U$ the macroscopic potential energy and $u$ the internal thermodynamic energy. Usually $U$ and $K$ are disregarded, the former because $-\Delta U$ can be viewed as further work on the system due to macroscopic conservative forces, the latter in particular because one usually deals with initial and final states where all macroscopic parts of the system are at rest. Exploiting this equation the processes you consider can be coherently discussed. In particular, if your action on the stone does not imply deformations of its form with production of internal dissipative stresses and there is no flux or production of heat (a completely mechanical kick), there is no variation of $u$ but only of $K$ . | {} | {'log_upvote_score': 4, 'links': ['https://physics.stackexchange.com/questions/602937', 'https://physics.stackexchange.com', 'https://physics.stackexchange.com/users/267796/']} | jdg_382926 |
stackexchange | llm_judgeable_groundtruth_similarity | 52626252 |
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 getting this message in cat log multiple times : [avas] AVAudioSessionPortImpl.mm:56:ValidateRequiredFields: Unknown selected data source for Port Speaker (type: Speaker) i am using this code to playback background music : let path = Bundle.main.path(forResource: fileName, ofType:"mp3")! let url = URL(fileURLWithPath: path) do { let sound = try AVAudioPlayer(contentsOf: url) self.player = sound sound.prepareToPlay() sound.volume = 0.05 sound.numberOfLoops = loops sound.play() } catch { print("[PLAY SOUND][DELEGATE] error loading file -> \(fileName)") } i made a research and i found similar issues so i've added the audio category in viewdidload : do { try AVAudioSession.sharedInstance().setCategory(AVAudioSessionCategoryPlayback, mode: AVAudioSessionModeDefault) try AVAudioSession.sharedInstance().setActive(true) } catch { print(error) } after i've added the above code , the background music is playing even if the phone on silent mode ! and the debugger message for Unknown selected data source for Port Speaker (type: Speaker) is still showing
Now provide the response and nothing else.
| The message Unknown selected data source for Port Speaker seems to be a problem with iOS 12. Apparently it's some warning that appears even if the code is working. Perhaps Apple will fix this soon, so maybe for now you can ignore this warning and once they find a solution you will be able to silence it. Source: AVAudioSession errors in iOS 12 As for the background music playing on silent mode, it's because of the AVAudioSessionCategory you selected. According to AVAudioSessionCategoryPlayback documentation ( source ): When using this category, your app audio continues with the Silent switch set to silent or when the screen locks. Depending on the style of your app, maybe you could use AVAudioSessionCategorySoloAmbient ( source ): Your audio is silenced by screen locking and by the Silent switch (called the Ring/Silent switch on iPhone). Or maybe AVAudioSessionCategoryAmbient ( source ): This category is also appropriate for “play along” style apps, such as a virtual piano that a user plays while the Music app is playing. When you use this category, audio from other apps mixes with your audio. Your audio is silenced by screen locking and by the Silent switch (called the Ring/Silent switch on iPhone). | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/52626252', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3059001/']} | jdg_382927 |
stackexchange | llm_judgeable_groundtruth_similarity | 2364147 |
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 master branch with a file called app.js . I made changes to this file on an experiment branch. I want to apply only the changes made to app.js from experiment onto the master branch.
Now provide the response and nothing else.
| git checkout master # first get back to mastergit checkout experiment -- app.js # then copy the version of app.js # from branch "experiment" See also git how to undo changes of one file? Update August 2019, Git 2.23 With the new git switch and git restore commands, that would be: git switch mastergit restore --source experiment -- app.js By default, only the working tree is restored. If you want to update the index as well (meaning restore the file content, and add it to the index in one command): git restore --source experiment --staged --worktree -- app.js# shorter:git restore -s experiment -SW -- app.js As Jakub Narębski mentions in the comments: git show experiment:path/to/app.js > path/to/app.js works too, except that, as detailed in the SO question " How to retrieve a single file from specific revision in Git? ", you need to use the full path from the root directory of the repo. Hence the path/to/app.js used by Jakub in his example. As Frosty mentions in the comment: you will only get the most recent state of app.js But, for git checkout or git show , you can actually reference any revision you want, as illustrated in the SO question " git checkout revision of a file in git gui ": $ git show $REVISION:$FILENAME$ git checkout $REVISION -- $FILENAME would be the same is $FILENAME is a full path of a versioned file. $REVISION can be as shown in git rev-parse : experiment@{yesterday}:app.js # app.js as it was yesterday experiment^:app.js # app.js on the first commit parentexperiment@{2}:app.js # app.js two commits ago and so on. schmijos adds in the comments : you also can do this from a stash: git checkout stash -- app.js This is very useful if you're working on two branches and don't want to commit. | {} | {'log_upvote_score': 12, 'links': ['https://Stackoverflow.com/questions/2364147', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/253470/']} | jdg_382928 |
stackexchange | llm_judgeable_groundtruth_similarity | 48392 |
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 am trying out the command $ b=5; echo `$b`;-bash: 5: command not found but it does not print 5 as it is supposed to. What am I missing here? What does ` (backquote/backtick) mean in commands? seems to say that ` evaluates the commands within and replaces them with the output.
Now provide the response and nothing else.
| Text between backticks is executed and replaced by the output of the command (minus the trailing newline characters, and beware that shell behaviors vary when there are NUL characters in the output). That is called command substitution because it is substituted with the output of the command. So if you want to print 5, you can't use backticks, you can use quotation marks, like echo "$b" or just drop any quotation and use echo $b . As you can see, since $b contains 5, when using backticks bash is trying to run command 5 and since there is no such command, it fails with error message. To understand how backticks works, try running this: $ A=`cat /etc/passwd | head -n1`$ echo "$A" cat /etc/passwd |head -n1 should print first line of /etc/passwd file. But since we use backticks, it doesn't print this on console. Instead it is stored in A variable. You can echo $A to this. Note that more efficient way of printing first line is using command head -n1 /etc/passwd but I wanted to point out that expression inside of backticks does not have to be simple. So if first line of /etc/passwd is root:x:0:0:root:/root:/bin/bash , first command will be dynamically substituted by bash to A="root:x:0:0:root:/root:/bin/bash" . Note that this syntax is of the Bourne shell. Quoting and escaping becomes quickly a nightmare with it especially when you start nesting them. Ksh introduced the $(...) alternative which is now standardized ( POSIX ) and supported by all shells (even the Bourne shell from Unix v9). So you should use $(...) instead nowadays unless you need to be portable to very old Bourne shells. Also note that the output of `...` and $(...) are subject to word splitting and filename generation just like variable expansion (in zsh, word splitting only), so would generally need to be quoted in list contexts. | {} | {'log_upvote_score': 7, 'links': ['https://unix.stackexchange.com/questions/48392', 'https://unix.stackexchange.com', 'https://unix.stackexchange.com/users/23489/']} | jdg_382929 |
stackexchange | llm_judgeable_groundtruth_similarity | 8229638 |
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 make a selectOneMenu dropdown so I can select a status on my question. Is it possible to make the f:selectItem more flexible considering what happens if the order of the enums changes, and if the list was large? And could I do this better? And is it possible to automatically "select" the item that the question have? Enum class public enum Status { SUBMITTED, REJECTED, APPROVED} Question entity @Enumerated(EnumType.STRING)private Status status; JSF <div class="field"> <h:outputLabel for="questionStatus" value="Status" /> <h:selectOneMenu id="questionStatus" value="#{bean.question.status}" > <f:selectItem itemLabel="Submitted" itemValue="0" /> <f:selectItem itemLabel="Rejected" itemValue="1" /> <f:selectItem itemLabel="Approved" itemValue="2" /> </h:selectOneMenu> <hr /></div>
Now provide the response and nothing else.
| JSF has a builtin converter for enum , so this should do: @Named@ApplicationScopedpublic class Data { public Status[] getStatuses() { return Status.values(); }} with <h:selectOneMenu value="#{bean.question.status}" > <f:selectItems value="#{data.statuses}" /></h:selectOneMenu> (note: since JSF 2.0 there's no need anymore to provide a SelectItem[] or List<SelectItem> , a T[] and List<T> are accepted as well and you can access the current item by var attribute) If you happen to use JSF utility library OmniFaces , then you could use <o:importConstants> instead of a bean. <o:importConstants type="com.example.Status" /><h:selectOneMenu value="#{bean.question.status}" > <f:selectItems value="#{Status}" /></h:selectOneMenu> If you intend to control the labels as well, you could add them to the Status enum: public enum Status { SUBMITTED("Submitted"), REJECTED("Rejected"), APPROVED("Approved"); private String label; private Status(String label) { this.label = label; } public String getLabel() { return label; }} with <f:selectItems value="#{data.statuses}" var="status" itemValue="#{status}" itemLabel="#{status.label}" /> Or, better, make the enum value a property key of a localized resource bundle (EL 3.0 required): <f:selectItems value="#{data.statuses}" var="status" itemValue="#{status}" itemLabel="#{text['data.status.' += status]}" /> with this in a properties file associated with resource bundle #{text} data.status.SUBMITTED = Submitteddata.status.REJECTED = Rejecteddata.status.APPROVED = Approved | {} | {'log_upvote_score': 9, 'links': ['https://Stackoverflow.com/questions/8229638', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/454049/']} | jdg_382930 |
stackexchange | llm_judgeable_groundtruth_similarity | 47873128 |
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 got an error in my Angular Material: compiler.js:466 Uncaught Error: Template parse errors:'mat-label' is not a known element:1. If 'mat-label' is an Angular component, then verify that it is part of this module.2. If 'mat-label' is a Web Component then add 'CUSTOM_ELEMENTS_SCHEMA' to the '@NgModule.schemas' of this component to suppress this message. (" </mat-form-field> <mat-form-field> [ERROR ->]<mat-label>Both a label and a placeholder</mat-label> <input matInput placeholder="Simple"): Question: Material Label is under MatFormFieldModule Here's the link Now, what is the possible cause of the issue why Mat-Label is unknown to Angular Material. Here is the HTML <mat-form-field> <mat-label>Both a label and a placeholder</mat-label> <input matInput placeholder="Simple placeholder"></mat-form-field>
Now provide the response and nothing else.
| If you have multiple modules make sure you're importing the MatFormFieldModule in every module. It's not sufficient to just import it in the root module. For example, I have a CommonWidgetsModule which contains some common widgets (my own) and you'll see I'm importing MatFormFieldModule and MatInputModule // common-widgets.module.tsimport { MatFormFieldModule } from '@angular/material/form-field';import { MatInputModule } from '@angular/material/input';@NgModule({ imports: [ CommonModule, SharedModule, RouterModule, MatFormFieldModule, MatInputModule, // import other MatModules... ], declarations: DECLARATIONS, exports: DECLARATIONS})export class CommonWidgetsModule { } | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/47873128', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/3524485/']} | jdg_382931 |
stackexchange | llm_judgeable_groundtruth_similarity | 73060 |
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:
Question. Let $k$ be an algebraically closed field, an let $\mathbb{P}^n$ be projective $n$-space over $k$. Why is it true that every regular map $\mathbb{P}^n \to \mathbb{P}^m$ is constant, when $n > m$? I can't see any obvious obstructions: there are certainly homomorphisms of function fields (giving rise to the dominant rational maps), and we're not demanding the map be injective or anything. While it is clear that $(F_0 : \cdots : F_m)$ cannot define a regular map on its own unless $F_0, \ldots, F_m$ are all constants, I don't see why it should be impossible to extend $(F_0 : \cdots : F_m)$ by choosing some other $(G_0 : \cdots G_m)$ which agrees with $(F_0 : \cdots : F_m)$ on the intersection of their domains. Is there something conceptual I'm missing?
Now provide the response and nothing else.
| I apologize in advance if I am using results that you are, yet, unaware of. I still wanted to give it a shot: A morphism $\mathbb{P}^n\to\mathbb{P}^m$ corresponds to a way of globally generating a line bundle $\mathcal{O}_{\mathbb{P}^n}(d)$ with $m$ generators. We can safely assume $d\ge 0$ here. Now the global sections of that line bundle are precisely the homogeneous polynomials of degree $d$ in $n+1$ variables, and since $m<n$, this must mean $d=0$, i.e. we have chosen $m$ constants from k. | {} | {'log_upvote_score': 4, 'links': ['https://math.stackexchange.com/questions/73060', 'https://math.stackexchange.com', 'https://math.stackexchange.com/users/5191/']} | jdg_382932 |
stackexchange | llm_judgeable_groundtruth_similarity | 36443538 |
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 new to Azure Service Fabric and the biggest questions I have are When should I use reliable actors? Give me practical examples please. When should I use reliable services? Give me practical examples please.
Now provide the response and nothing else.
| Taken a look at the differences: State analogy : Actors work on a single instance of an object graph.Services usually have state for multiple callers. Scope : Actors can’t work alone, because of their size (more like objects). Life-cycle : Actors are only active when used, somore will fit on your available server resources Concurrency : Actorsenforce single threaded access State : Actors just modify theaggregate, services work on sets so often use transactions on setsfor ACID behavior. Communication : Actors communicate throughchannels provided by the platform. Services may choose otherwise. Access : Actors in the cluster can’t be reached from the outside bydefault. You’ll probably need a Service that provides access. Samples when to use an actor: For every user of your mobile app you could have one actor. For every thermostat that sends information to your application you could have one actor. For every customer of your e-commerce site, you could have one shopping-basket actor. Create a service in the cases that you are probably used to. Create a reliable service that provides a service for multiple users at once. For example a weather service. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/36443538', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/5892068/']} | jdg_382933 |
stackexchange | llm_judgeable_groundtruth_similarity | 38447 |
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:
A team has conducted a study in which an introductory class was randomly divided into two groups. Group 1 was administered a dosage of alcohol. Group 2 was given an equvialent dosage of marijuana. Fifteen minutes after administration, both groups were asked to solve a puzzle. The experimenter recorded the amount of time in seconds it took for each subject to solve the puzzle. Now, in this case, will the given data for each group be considered as sample or population?
Now provide the response and nothing else.
| It depends on to whom you wish to generalize your final results. If your sole interest was just to see how these people react and you don't care about inference, they are your population. If you wish to use the results to somehow infer how other similar people may behave under influence, then they are samples. Most studies tend to do the latter. Also, for the inference to be valid, the sample should be drawn from the population with a known probability. The more the sampling deviated from the being probability-based, the shakier the inference will become. It may also be worth mentioning that attributing exposure such as alcohol or marijuana to human subjects probably will not pass through ethical review process. Don't jump into answering the design feature before making sure that it's not a trick question. | {} | {'log_upvote_score': 4, 'links': ['https://stats.stackexchange.com/questions/38447', 'https://stats.stackexchange.com', 'https://stats.stackexchange.com/users/14550/']} | jdg_382934 |
stackexchange | llm_judgeable_groundtruth_similarity | 3433106 |
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's the Rails 3 replacement for ActiveRecord::Errors? In Rails 2.3.8, this is an object: >> ActiveRecord::Errors=> ActiveRecord::Errors In Rails 3.0.0rc, you get a NameError: >> ActiveRecord::ErrorsNameError: uninitialized constant ActiveRecord::Errors from (irb):2 I'm trying to make the wizardly generator work with Rails 3. $ rails g wizardly_scaffold home But it fails: /Library/Ruby/Gems/1.8/gems/wizardly_gt-0.1.8.9/lib/validation_group.rb:150:uninitialized constant ActiveRecord::Errors (NameError) The line it refers to is this: ActiveRecord::Errors.send :include, ValidationGroup::ActiveRecord::Errors Earlier in the file, we see: module ValidationGroup module ActiveRecord... module Errors # included in ActiveRecord::Errors def add_with_validation_group(attribute, msg = I18n.translate('activerecord.errors.messages')[:invalid], *args, &block) add_error = @base.respond_to?(:should_validate?) ? (@base.should_validate?(attribute.to_sym) || attribute == :base) : true add_without_validation_group(attribute, msg, *args, &block) if add_error end...end
Now provide the response and nothing else.
| That'd be ActiveModel::Errors . Things such as validations and error handling have been moved over to Active Model to provide a common API for all ORM Railties such as Active Record, Data Mapper, Mongoid etc. to hook into Rails with. It would appear the wizardly plugin needs to check for ActiveModel first and if it exists, then include the error handling there rather than ActiveRecord::Errors . A trivial change. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/3433106', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/135850/']} | jdg_382935 |
stackexchange | llm_judgeable_groundtruth_similarity | 31687442 |
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 structure and protocol aside, I was wondering where JWT fits into client/server communication? Is it here to replace authentication and session cookies? Is it here to relieve servers of storing session tokens in a database or memory? Is it for clients to make sure they are receiving data from the expected server and if that's not a concern I wouldn't need JWT? Is it necessary or a good practice for server to server communication when the connection is HTTPS/SSL?
Now provide the response and nothing else.
| What JWT is exactly? It is a token that only the server can generate, and can contain a payload of data. What's the point of it? A JWT payload can contain things like user ID so that when the client sends you a JWT, you can be sure that it is issued by you , and you can see to whom it was issued. Where can it be useful? Usually, in RESTful APIs, where the server must not use any sort of sessions. How does it differ from using sessions? In a typical session flow, the browser sends a cookie containing a token , which is then matched at the server to some data which the server makes use of to authenticate the user. In a JWT flow, the token itself contains the data. The server decodes the token to authenticate the user only. No data stored on the server. What is a typical authentication flow using JWT? User credentials sent to /signin /signin returns a JWT (signed with a key) JWT is stored in localStorage JWT is sent on every request (to API) The server can read the JWT and extract user ID out of it Jwt contains the encoded form of the algorithm.data.signature and so if the user tries to fiddle with the user ID or any other data held in the jwt, then the jwt signature becomes invalid. Jwt is encoded (not encrypted), so any one can read the data component of the jwt (see jwt.io for example). Therefore it is recommended not to store any secrets like password in the jwt. It is also recommended to use an encrypted connection (SSL/TLS) when making the web request that contains the jwt because otherwise an attacker can steal the jwt and use it to impersonate you. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/31687442', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/383515/']} | jdg_382936 |
stackexchange | llm_judgeable_groundtruth_similarity | 24629247 |
Below is a question asked on the forum Stackoverflow.com. Provide a good and informational response to it like a helpful human would.
Question:
Here's my understanding of the Stream framework of Java 8: Something creates a source Stream The implementation is responsible for providing a BaseStream#parallel() method, which in turns returns a Stream that can run it's operations in parallel. While someone has already found a way to use a custom thread pool with Stream framework's parallel executions, I cannot for the life of me find any mention in the Java 8 API that the default Java 8 parallel Stream implementations would use ForkJoinPool#commonPool() . ( Collection#parallelStream() , the methods in StreamSupport class, and others possible sources of parallel-enabled streams in the API that I don't know about). Only tidbits that I could gleam off search results were these: State of the Lambda: Libraries Edition ("Parallelism under the hood") Vaguely mentions the Stream framework and the Fork/Join machinery. The Fork/Join machinery is designed to automate this process. JEP 107: Bulk Data Operations for Collections Almost directly states that the the Collection interface's default method #parallelStream() implements itself using Fork/Join. But still nothing about common pool. The parallel implementation builds upon the java.util.concurrency Fork/Join implementation introduced in Java 7. and hence: Collection#parallelStream() . Class Arrays (Javadoc) Directly states multiple times that the common pool is used. The ForkJoin common pool is used to execute any parallel tasks. So my question is: Where is it said that the ForkJoinPool#commonPool() is used for parallel operations on streams that are obtained from the Java 8 API?
Now provide the response and nothing else.
| W.r.t. where is it documented that Java 8 parallel streams use FJ Framework? Afaik (Java 1.8u5) it is not mentioned in the JavaDoc of parallel streams that a common ForkJoinPool is used. But it is mentioned in the ForkJoin documentation at the bottom of http://docs.oracle.com/javase/tutorial/essential/concurrency/forkjoin.html W.r.t. replacing the Thread pool My understanding is that you can use a custom ForkJoinPool (instead of the common one)- see Custom thread pool in Java 8 parallel stream -, but not a custom ThreadPool which is different from the ForkJoin implementation (I have an open question here: How to (globally) replace the common thread pool backend of Java parallel streams? ) W.r.t. replacing the Streams api You may checkout https://github.com/nurkiewicz/LazySeq which is a more Scala like streams implementation - very nice, very interesting PS (w.r.t. ForkJoin and Streams) If you are interested, I would like to note that I stumbled across some issues with the use of the FJ pool, see, e.g. Nested Java 8 parallel forEach loop perform poor. Is this behavior expected? Using a semaphore inside a nested Java 8 parallel stream action may DEADLOCK. Is this a bug? | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/24629247', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/961517/']} | jdg_382937 |
stackexchange | llm_judgeable_groundtruth_similarity | 4366904 |
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 making a logger and I wish to have some kind of stream-like happenings going on, ideally doing CLogger << "Testing, " << 1 << ",2,3\n"; instead of CLogger->log("Testing, %i,2,3", 1); My question is how would I do this? I don't want to directly create a stream to stdout as I want to use my own method which includes writing files and such. I've considered overloading with a certain struct that'd flush the current stream buffer to a method, but I'd have to do CLogger << flush << "Test!\n"; which is kind of odd. Does anybody know how to do this?
Now provide the response and nothing else.
| If all that you need is directing certain log messages to files, have you considered std::ofstream ? Otherwise, I like to derive my logging class from std::ostream , so I get all of the stream goodness. The trick is to put all of your application-specific code in the associated streambuf class. Consider: #include <iostream>#include <sstream>class CLogger : public std::ostream {private: class CLogBuf : public std::stringbuf { private: // or whatever you need for your application std::string m_marker; public: CLogBuf(const std::string& marker) : m_marker(marker) { } ~CLogBuf() { pubsync(); } int sync() { std::cout << m_marker << ": " << str(); str(""); return std::cout?0:-1; } };public: // Other constructors could specify filename, etc // just remember to pass whatever you need to CLogBuf CLogger(const std::string& marker) : std::ostream(new CLogBuf(marker)) {} ~CLogger() { delete rdbuf(); }};int main(){ CLogger hi("hello"); CLogger bye("goodbye"); hi << "hello, world" << std::endl; hi << "Oops, forgot to flush.\n"; bye << "goodbye, cruel world\n" << std::flush; bye << "Cough, cough.\n";} Notes: The CLogger constructor can take whatever parameters you need to use -- a filename, an output language, a pointer to the underlying log data, whatever. Just pass the data onto the CLogBuf class. The CLogBuf's sync() is automatically called during in response to std::flush. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/4366904', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/292831/']} | jdg_382938 |
stackexchange | llm_judgeable_groundtruth_similarity | 44332290 |
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 the mapbox-gl library with TypeScript, and I've installed its community sourced type definitions with @types/mapbox-gl . When I try to import and set an accessToken to use the library, my TypeScript compiler throws this error: TS2540: Cannot assign to 'accessToken' because it is a constant or a read-only property. So I pulled up the .d.ts file and the variable in question looks extremely assignable (seen here: https://github.com/DefinitelyTyped/DefinitelyTyped/blob/master/types/mapbox-gl/index.d.ts ): declare namespace mapboxgl { let accessToken: string; ... This is my code: import * as mapbox from 'mapbox-gl';mapbox.accessToken = 'token'; Versions! "@types/mapbox-gl": "^0.35.0","typescript": "^2.3.4","mapbox-gl": "^0.37.0", TypeScript hackery says that I can cast mapbox to any and it will work, but I'm very curious what about the typing is going wrong here.
Now provide the response and nothing else.
| Here's a temporary workaround I've been using: Object.getOwnPropertyDescriptor(mapboxgl, "accessToken").set('YOUR_TOKEN'); Explanation Since the object was redefined to use a custom setter which places the token inside an internal closure - we can call the setter function directly as shown in the example. Diving a little deeper, we can see that es6 modules are constants by definition: https://github.com/Microsoft/TypeScript/issues/6751#issuecomment-177114001 we can then do something like: (mapboxgl as any).accessToken = .. . which will work. | {} | {'log_upvote_score': 6, 'links': ['https://Stackoverflow.com/questions/44332290', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1710757/']} | jdg_382939 |
stackexchange | llm_judgeable_groundtruth_similarity | 10861550 |
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 do not understand what I do exactly when I add a CCSpriteFrameCache or CCSpriteBatchNode to my cocos2d application. Can somebody please explain the following points (it would be helpful if you could explain a few; please write the corresponding letter in front of your answer according to which question you are answering): [all questions imply the achievement of best performance and lowest memory-use] a) Is it crucial to create spritesheets for every single layer ? (For example: Menu - own spritesheet, GameLayer - own spritesheet...) b) Can somebody explain why I have to add sprites to the batch node, and what a batch node generally is ? b1)So, why can't I just do something like: [[CCSpriteFrameCache sharedSpriteFrameCache] addSpriteFramesWithFile:@"menusprites.plist"]; CCSpriteBatchNode *spriteSheet = [CCSpriteBatchNode batchNodeWithFile:@"menusprites.png"]; [self addChild:spriteSheet]; And then just add sprites to my layer by calling CCSprite *mySprite = [CCSprite spriteWithSpriteFrameName:@""]; [self addChild:mySprite]; without adding them to the batch node ? Because from what I understand it works like this : I add my spritesheet with all the sprites on it to the screen. My app then goes into the plist and looks for the coordinates of the sprite I want to display and then places it on the screen. So why should I call [spriteSheet addChild:mySprite]; ? c) How do I then get rid of the spritesheet for memory purposes when I do not need it anymore ?
Now provide the response and nothing else.
| a) It is best to create as few spritesheets (CCSpriteBatchNodes) as is possible. Sprite batching reduces draw calls. Draw calls are expensive. Still, every batch node creates one draw call. So you want to use as few as possible because the ultimate goal is to keep draw calls as low as possible. b) The CCSpriteBatchNode renders all of its children in one go, in one batched draw call. That's why you need to add sprites to the batch node so it can render them all together. Only sprites using the same texture as the batch node can be added to a batch node, because you can only batch draw from the same texture. Whenever the engine has to switch from one texture to another, it issues a new draw call. b1) You can't do this because the batch node renders its children. If you add the sprites to any other node, each sprite draws itself, which means one additional draw call per sprite. And the sprite batch node has nothing to do. c) The CCSpriteBatchNode is just a regular node. You can remove it from the scene like any other node. The texture and sprite frames are cached in the CCTextureCache and CCSpriteFrameCache singleton classes. If you want to remove the textures and sprite frames from memory, you have to do it through the cache classes. | {} | {'log_upvote_score': 5, 'links': ['https://Stackoverflow.com/questions/10861550', 'https://Stackoverflow.com', 'https://Stackoverflow.com/users/1066899/']} | jdg_382940 |
Subsets and Splits