Spaces:
Running
Running
Joram Mutenge
commited on
Commit
·
4c17152
1
Parent(s):
cbef791
notebook on basic operations in polars
Browse files- polars/04_basic_operations.py +623 -0
polars/04_basic_operations.py
ADDED
@@ -0,0 +1,623 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import marimo
|
2 |
+
|
3 |
+
__generated_with = "0.11.13"
|
4 |
+
app = marimo.App(width="medium")
|
5 |
+
|
6 |
+
|
7 |
+
@app.cell
|
8 |
+
def _():
|
9 |
+
import marimo as mo
|
10 |
+
return (mo,)
|
11 |
+
|
12 |
+
|
13 |
+
@app.cell(hide_code=True)
|
14 |
+
def _(mo):
|
15 |
+
mo.md(
|
16 |
+
r"""
|
17 |
+
# Basic operations on data
|
18 |
+
_By [Joram Mutenge](https://www.udemy.com/user/joram-mutenge/)._
|
19 |
+
|
20 |
+
In this notebook, you'll learn how to perform arithmetic operations, comparisons, and conditionals on a Polars dataframe. We'll work with a DataFrame that tracks software usage by year, categorized as either Vintage (old) or Modern (new).
|
21 |
+
"""
|
22 |
+
)
|
23 |
+
return
|
24 |
+
|
25 |
+
|
26 |
+
@app.cell
|
27 |
+
def _():
|
28 |
+
import polars as pl
|
29 |
+
|
30 |
+
df = pl.DataFrame(
|
31 |
+
{
|
32 |
+
"software": [
|
33 |
+
"Lotus-123",
|
34 |
+
"WordStar",
|
35 |
+
"dBase III",
|
36 |
+
"VisiCalc",
|
37 |
+
"WinZip",
|
38 |
+
"MS-DOS",
|
39 |
+
"HyperCard",
|
40 |
+
"WordPerfect",
|
41 |
+
"Excel",
|
42 |
+
"Photoshop",
|
43 |
+
"Visual Studio",
|
44 |
+
"Slack",
|
45 |
+
"Zoom",
|
46 |
+
"Notion",
|
47 |
+
"Figma",
|
48 |
+
"Spotify",
|
49 |
+
"VSCode",
|
50 |
+
"Docker",
|
51 |
+
],
|
52 |
+
"users": [
|
53 |
+
10000,
|
54 |
+
4500,
|
55 |
+
2500,
|
56 |
+
3000,
|
57 |
+
1800,
|
58 |
+
17000,
|
59 |
+
2200,
|
60 |
+
1900,
|
61 |
+
500000,
|
62 |
+
12000000,
|
63 |
+
1500000,
|
64 |
+
3000000,
|
65 |
+
4000000,
|
66 |
+
2000000,
|
67 |
+
2500000,
|
68 |
+
4500000,
|
69 |
+
6000000,
|
70 |
+
3500000,
|
71 |
+
],
|
72 |
+
"category": ["Vintage"] * 8 + ["Modern"] * 10,
|
73 |
+
"year": [
|
74 |
+
1985,
|
75 |
+
1980,
|
76 |
+
1984,
|
77 |
+
1979,
|
78 |
+
1991,
|
79 |
+
1981,
|
80 |
+
1987,
|
81 |
+
1982,
|
82 |
+
1987,
|
83 |
+
1990,
|
84 |
+
1997,
|
85 |
+
2013,
|
86 |
+
2011,
|
87 |
+
2016,
|
88 |
+
2016,
|
89 |
+
2008,
|
90 |
+
2015,
|
91 |
+
2013,
|
92 |
+
],
|
93 |
+
}
|
94 |
+
)
|
95 |
+
|
96 |
+
df
|
97 |
+
return df, pl
|
98 |
+
|
99 |
+
|
100 |
+
@app.cell(hide_code=True)
|
101 |
+
def _(mo):
|
102 |
+
mo.md(
|
103 |
+
r"""
|
104 |
+
## Arithmetic
|
105 |
+
### Addition
|
106 |
+
Let's add 42 users to each piece of software. This means adding 42 to each value under **users**.
|
107 |
+
"""
|
108 |
+
)
|
109 |
+
return
|
110 |
+
|
111 |
+
|
112 |
+
@app.cell
|
113 |
+
def _(df, pl):
|
114 |
+
df.with_columns(pl.col("users") + 42)
|
115 |
+
return
|
116 |
+
|
117 |
+
|
118 |
+
@app.cell(hide_code=True)
|
119 |
+
def _(mo):
|
120 |
+
mo.md(r"""Another way to perform the above operation is using the built-in function.""")
|
121 |
+
return
|
122 |
+
|
123 |
+
|
124 |
+
@app.cell
|
125 |
+
def _(df, pl):
|
126 |
+
df.with_columns(pl.col("users").add(42))
|
127 |
+
return
|
128 |
+
|
129 |
+
|
130 |
+
@app.cell(hide_code=True)
|
131 |
+
def _(mo):
|
132 |
+
mo.md(
|
133 |
+
r"""
|
134 |
+
### Subtraction
|
135 |
+
Let's subtract 42 users to each piece of software.
|
136 |
+
"""
|
137 |
+
)
|
138 |
+
return
|
139 |
+
|
140 |
+
|
141 |
+
@app.cell
|
142 |
+
def _(df, pl):
|
143 |
+
df.with_columns(pl.col("users") - 42)
|
144 |
+
return
|
145 |
+
|
146 |
+
|
147 |
+
@app.cell(hide_code=True)
|
148 |
+
def _(mo):
|
149 |
+
mo.md(r"""Alternatively, you could subtract like this:""")
|
150 |
+
return
|
151 |
+
|
152 |
+
|
153 |
+
@app.cell
|
154 |
+
def _(df, pl):
|
155 |
+
df.with_columns(pl.col("users").sub(42))
|
156 |
+
return
|
157 |
+
|
158 |
+
|
159 |
+
@app.cell(hide_code=True)
|
160 |
+
def _(mo):
|
161 |
+
mo.md(
|
162 |
+
r"""
|
163 |
+
### Division
|
164 |
+
Suppose the **users** values are inflated, we can reduce them by dividing by 1000. Here's how to do it.
|
165 |
+
"""
|
166 |
+
)
|
167 |
+
return
|
168 |
+
|
169 |
+
|
170 |
+
@app.cell
|
171 |
+
def _(df, pl):
|
172 |
+
df.with_columns(pl.col("users") / 1000)
|
173 |
+
return
|
174 |
+
|
175 |
+
|
176 |
+
@app.cell(hide_code=True)
|
177 |
+
def _(mo):
|
178 |
+
mo.md(r"""Or we could do it with a built-in expression.""")
|
179 |
+
return
|
180 |
+
|
181 |
+
|
182 |
+
@app.cell
|
183 |
+
def _(df, pl):
|
184 |
+
df.with_columns(pl.col("users").truediv(1000))
|
185 |
+
return
|
186 |
+
|
187 |
+
|
188 |
+
@app.cell(hide_code=True)
|
189 |
+
def _(mo):
|
190 |
+
mo.md(r"""If we didn't care about the remainder after division (i.e remove numbers after decimal point) we could do it like this.""")
|
191 |
+
return
|
192 |
+
|
193 |
+
|
194 |
+
@app.cell
|
195 |
+
def _(df, pl):
|
196 |
+
df.with_columns(pl.col("users").floordiv(1000))
|
197 |
+
return
|
198 |
+
|
199 |
+
|
200 |
+
@app.cell(hide_code=True)
|
201 |
+
def _(mo):
|
202 |
+
mo.md(
|
203 |
+
r"""
|
204 |
+
### Multiplication
|
205 |
+
Let's pretend the *user* values are deflated and increase them by multiplying by 100.
|
206 |
+
"""
|
207 |
+
)
|
208 |
+
return
|
209 |
+
|
210 |
+
|
211 |
+
@app.cell
|
212 |
+
def _(df, pl):
|
213 |
+
(df.with_columns(pl.col("users") * 100))
|
214 |
+
return
|
215 |
+
|
216 |
+
|
217 |
+
@app.cell(hide_code=True)
|
218 |
+
def _(mo):
|
219 |
+
mo.md(r"""Polars also has a built-in function for multiplication.""")
|
220 |
+
return
|
221 |
+
|
222 |
+
|
223 |
+
@app.cell
|
224 |
+
def _(df, pl):
|
225 |
+
df.with_columns(pl.col("users").mul(100))
|
226 |
+
return
|
227 |
+
|
228 |
+
|
229 |
+
@app.cell(hide_code=True)
|
230 |
+
def _(mo):
|
231 |
+
mo.md(r"""So far, we've only modified the values in an existing column. Let's create a column **decade** that will represent the years as decades. Thus 1985 will be 1980 and 2008 will be 2000.""")
|
232 |
+
return
|
233 |
+
|
234 |
+
|
235 |
+
@app.cell
|
236 |
+
def _(df, pl):
|
237 |
+
(df.with_columns(decade=pl.col("year").floordiv(10).mul(10)))
|
238 |
+
return
|
239 |
+
|
240 |
+
|
241 |
+
@app.cell(hide_code=True)
|
242 |
+
def _(mo):
|
243 |
+
mo.md(r"""We could create a new column another way as follows:""")
|
244 |
+
return
|
245 |
+
|
246 |
+
|
247 |
+
@app.cell
|
248 |
+
def _(df, pl):
|
249 |
+
df.with_columns((pl.col("year").floordiv(10).mul(10)).alias("decade"))
|
250 |
+
return
|
251 |
+
|
252 |
+
|
253 |
+
@app.cell(hide_code=True)
|
254 |
+
def _(mo):
|
255 |
+
mo.md(
|
256 |
+
r"""
|
257 |
+
**Tip**
|
258 |
+
Polars encounrages you to perform your operations as a chain. This enables you to take advantage of the query optimizer. We'll build upon the above code as a chain.
|
259 |
+
|
260 |
+
## Comparison
|
261 |
+
### Equal
|
262 |
+
Let's get all the software categorized as Vintage.
|
263 |
+
"""
|
264 |
+
)
|
265 |
+
return
|
266 |
+
|
267 |
+
|
268 |
+
@app.cell
|
269 |
+
def _(df, pl):
|
270 |
+
(
|
271 |
+
df.with_columns(decade=pl.col("year").floordiv(10).mul(10))
|
272 |
+
.filter(pl.col("category") == "Vintage")
|
273 |
+
)
|
274 |
+
return
|
275 |
+
|
276 |
+
|
277 |
+
@app.cell(hide_code=True)
|
278 |
+
def _(mo):
|
279 |
+
mo.md(r"""We could also do a double comparison. VisiCal is the only software that's vintage and in the decade 1970s. Let's perform this comparison operation.""")
|
280 |
+
return
|
281 |
+
|
282 |
+
|
283 |
+
@app.cell
|
284 |
+
def _(df, pl):
|
285 |
+
(
|
286 |
+
df.with_columns(decade=pl.col("year").floordiv(10).mul(10))
|
287 |
+
.filter(pl.col("category") == "Vintage")
|
288 |
+
.filter(pl.col("decade") == 1970)
|
289 |
+
)
|
290 |
+
return
|
291 |
+
|
292 |
+
|
293 |
+
@app.cell(hide_code=True)
|
294 |
+
def _(mo):
|
295 |
+
mo.md(
|
296 |
+
r"""
|
297 |
+
We could also do this comparison in one line, if readability is not a concern
|
298 |
+
|
299 |
+
**Notice** that we must enclose the two expressions between the `&` with parenthesis.
|
300 |
+
"""
|
301 |
+
)
|
302 |
+
return
|
303 |
+
|
304 |
+
|
305 |
+
@app.cell
|
306 |
+
def _(df, pl):
|
307 |
+
(
|
308 |
+
df.with_columns(decade=pl.col("year").floordiv(10).mul(10))
|
309 |
+
.filter((pl.col("category") == "Vintage") & (pl.col("decade") == 1970))
|
310 |
+
)
|
311 |
+
return
|
312 |
+
|
313 |
+
|
314 |
+
@app.cell(hide_code=True)
|
315 |
+
def _(mo):
|
316 |
+
mo.md(r"""We can also use the built-in function for equal to comparisons.""")
|
317 |
+
return
|
318 |
+
|
319 |
+
|
320 |
+
@app.cell
|
321 |
+
def _(df, pl):
|
322 |
+
(df
|
323 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
324 |
+
.filter(pl.col('category').eq('Vintage'))
|
325 |
+
)
|
326 |
+
return
|
327 |
+
|
328 |
+
|
329 |
+
@app.cell(hide_code=True)
|
330 |
+
def _(mo):
|
331 |
+
mo.md(
|
332 |
+
r"""
|
333 |
+
### Not equal
|
334 |
+
We can also compare if something is `not` equal to something. In this case, category is not vintage.
|
335 |
+
"""
|
336 |
+
)
|
337 |
+
return
|
338 |
+
|
339 |
+
|
340 |
+
@app.cell
|
341 |
+
def _(df, pl):
|
342 |
+
(df
|
343 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
344 |
+
.filter(pl.col('category') != 'Vintage')
|
345 |
+
)
|
346 |
+
return
|
347 |
+
|
348 |
+
|
349 |
+
@app.cell(hide_code=True)
|
350 |
+
def _(mo):
|
351 |
+
mo.md(r"""Or with the built-in function.""")
|
352 |
+
return
|
353 |
+
|
354 |
+
|
355 |
+
@app.cell
|
356 |
+
def _(df, pl):
|
357 |
+
(df
|
358 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
359 |
+
.filter(pl.col('category').ne('Vintage'))
|
360 |
+
)
|
361 |
+
return
|
362 |
+
|
363 |
+
|
364 |
+
@app.cell(hide_code=True)
|
365 |
+
def _(mo):
|
366 |
+
mo.md(r"""Or if you want to be extra clever, you can use the negation symbol `~` used in logic.""")
|
367 |
+
return
|
368 |
+
|
369 |
+
|
370 |
+
@app.cell
|
371 |
+
def _(df, pl):
|
372 |
+
(df
|
373 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
374 |
+
.filter(~pl.col('category').eq('Vintage'))
|
375 |
+
)
|
376 |
+
return
|
377 |
+
|
378 |
+
|
379 |
+
@app.cell(hide_code=True)
|
380 |
+
def _(mo):
|
381 |
+
mo.md(
|
382 |
+
r"""
|
383 |
+
### Greater than
|
384 |
+
Let's get the software where the year is greater than 2008 from the above dataframe.
|
385 |
+
"""
|
386 |
+
)
|
387 |
+
return
|
388 |
+
|
389 |
+
|
390 |
+
@app.cell
|
391 |
+
def _(df, pl):
|
392 |
+
(df
|
393 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
394 |
+
.filter(~pl.col('category').eq('Vintage'))
|
395 |
+
.filter(pl.col('year') > 2008)
|
396 |
+
)
|
397 |
+
return
|
398 |
+
|
399 |
+
|
400 |
+
@app.cell(hide_code=True)
|
401 |
+
def _(mo):
|
402 |
+
mo.md(r"""Or if we wanted the year 2008 to be included, we could use great or equal to.""")
|
403 |
+
return
|
404 |
+
|
405 |
+
|
406 |
+
@app.cell
|
407 |
+
def _(df, pl):
|
408 |
+
(df
|
409 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
410 |
+
.filter(~pl.col('category').eq('Vintage'))
|
411 |
+
.filter(pl.col('year') >= 2008)
|
412 |
+
)
|
413 |
+
return
|
414 |
+
|
415 |
+
|
416 |
+
@app.cell(hide_code=True)
|
417 |
+
def _(mo):
|
418 |
+
mo.md(r"""We could do the previous two operations with built-in functions. Here's with greater than.""")
|
419 |
+
return
|
420 |
+
|
421 |
+
|
422 |
+
@app.cell
|
423 |
+
def _(df, pl):
|
424 |
+
(df
|
425 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
426 |
+
.filter(~pl.col('category').eq('Vintage'))
|
427 |
+
.filter(pl.col('year').gt(2008))
|
428 |
+
)
|
429 |
+
return
|
430 |
+
|
431 |
+
|
432 |
+
@app.cell(hide_code=True)
|
433 |
+
def _(mo):
|
434 |
+
mo.md(r"""And here's with greater or equal to""")
|
435 |
+
return
|
436 |
+
|
437 |
+
|
438 |
+
@app.cell
|
439 |
+
def _(df, pl):
|
440 |
+
(df
|
441 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
442 |
+
.filter(~pl.col('category').eq('Vintage'))
|
443 |
+
.filter(pl.col('year').ge(2008))
|
444 |
+
)
|
445 |
+
return
|
446 |
+
|
447 |
+
|
448 |
+
@app.cell(hide_code=True)
|
449 |
+
def _(mo):
|
450 |
+
mo.md(
|
451 |
+
r"""
|
452 |
+
**Note**: For "less than", and "less or equal to" you can use the operators `<` or `<=`. Alternatively, you can use built-in functions `lt` or `le` respectively.
|
453 |
+
|
454 |
+
### Is between
|
455 |
+
Polars also allows us to filter between a range of values. Let's get the modern software were the year is between 2013 and 2016. This is inclusive on both ends (i.e. both years are part of the result).
|
456 |
+
"""
|
457 |
+
)
|
458 |
+
return
|
459 |
+
|
460 |
+
|
461 |
+
@app.cell
|
462 |
+
def _(df, pl):
|
463 |
+
(df
|
464 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
465 |
+
.filter(pl.col('category').eq('Modern'))
|
466 |
+
.filter(pl.col('year').is_between(2013, 2016))
|
467 |
+
)
|
468 |
+
return
|
469 |
+
|
470 |
+
|
471 |
+
@app.cell(hide_code=True)
|
472 |
+
def _(mo):
|
473 |
+
mo.md(
|
474 |
+
r"""
|
475 |
+
### Or operator
|
476 |
+
If we only want either one of the conditions in the comparison to be met, we could use `|`, which is the `or` operator.
|
477 |
+
|
478 |
+
Let's get software that is either modern or used in the decade 1980s.
|
479 |
+
"""
|
480 |
+
)
|
481 |
+
return
|
482 |
+
|
483 |
+
|
484 |
+
@app.cell
|
485 |
+
def _(df, pl):
|
486 |
+
(df
|
487 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
488 |
+
.filter((pl.col('category') == 'Modern') | (pl.col('decade') == 1980))
|
489 |
+
)
|
490 |
+
return
|
491 |
+
|
492 |
+
|
493 |
+
@app.cell(hide_code=True)
|
494 |
+
def _(mo):
|
495 |
+
mo.md(
|
496 |
+
r"""
|
497 |
+
## Conditionals
|
498 |
+
Polars also allows you create new columns based on a condition. Let's create a column *status* that will indicate if the software is "discontinued" or "in use".
|
499 |
+
|
500 |
+
Here's a list of products that are no longer in use.
|
501 |
+
"""
|
502 |
+
)
|
503 |
+
return
|
504 |
+
|
505 |
+
|
506 |
+
@app.cell
|
507 |
+
def _():
|
508 |
+
discontinued_list = ['Lotus-123', 'WordStar', 'dBase III', 'VisiCalc', 'MS-DOS', 'HyperCard']
|
509 |
+
return (discontinued_list,)
|
510 |
+
|
511 |
+
|
512 |
+
@app.cell(hide_code=True)
|
513 |
+
def _(mo):
|
514 |
+
mo.md(r"""Here's how we can get a dataframe of the products that are discontinued.""")
|
515 |
+
return
|
516 |
+
|
517 |
+
|
518 |
+
@app.cell
|
519 |
+
def _(df, discontinued_list, pl):
|
520 |
+
(df
|
521 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
522 |
+
.filter(pl.col('software').is_in(discontinued_list))
|
523 |
+
)
|
524 |
+
return
|
525 |
+
|
526 |
+
|
527 |
+
@app.cell(hide_code=True)
|
528 |
+
def _(mo):
|
529 |
+
mo.md(r"""Now, let's create the *status* column.""")
|
530 |
+
return
|
531 |
+
|
532 |
+
|
533 |
+
@app.cell
|
534 |
+
def _(df, discontinued_list, pl):
|
535 |
+
(df
|
536 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
537 |
+
.with_columns(pl.when(pl.col('software').is_in(discontinued_list))
|
538 |
+
.then(pl.lit('Discontinued'))
|
539 |
+
.otherwise(pl.lit('In use'))
|
540 |
+
.alias('status')
|
541 |
+
)
|
542 |
+
)
|
543 |
+
return
|
544 |
+
|
545 |
+
|
546 |
+
@app.cell(hide_code=True)
|
547 |
+
def _(mo):
|
548 |
+
mo.md(
|
549 |
+
r"""
|
550 |
+
## Unique counts
|
551 |
+
Sometimes you may want to see only the unique values in a column. Let's check the unique decades we have in our DataFrame.
|
552 |
+
"""
|
553 |
+
)
|
554 |
+
return
|
555 |
+
|
556 |
+
|
557 |
+
@app.cell
|
558 |
+
def _(df, discontinued_list, pl):
|
559 |
+
(df
|
560 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
561 |
+
.with_columns(pl.when(pl.col('software').is_in(discontinued_list))
|
562 |
+
.then(pl.lit('Discontinued'))
|
563 |
+
.otherwise(pl.lit('In use'))
|
564 |
+
.alias('status')
|
565 |
+
)
|
566 |
+
.select('decade').unique()
|
567 |
+
)
|
568 |
+
return
|
569 |
+
|
570 |
+
|
571 |
+
@app.cell(hide_code=True)
|
572 |
+
def _(mo):
|
573 |
+
mo.md(r"""Finally, let's find out the number of software used in each decade.""")
|
574 |
+
return
|
575 |
+
|
576 |
+
|
577 |
+
@app.cell
|
578 |
+
def _(df, discontinued_list, pl):
|
579 |
+
(df
|
580 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
581 |
+
.with_columns(pl.when(pl.col('software').is_in(discontinued_list))
|
582 |
+
.then(pl.lit('Discontinued'))
|
583 |
+
.otherwise(pl.lit('In use'))
|
584 |
+
.alias('status')
|
585 |
+
)
|
586 |
+
['decade'].value_counts()
|
587 |
+
)
|
588 |
+
return
|
589 |
+
|
590 |
+
|
591 |
+
@app.cell(hide_code=True)
|
592 |
+
def _(mo):
|
593 |
+
mo.md(r"""We could also rewrite the above code as follows:""")
|
594 |
+
return
|
595 |
+
|
596 |
+
|
597 |
+
@app.cell
|
598 |
+
def _(df, discontinued_list, pl):
|
599 |
+
(df
|
600 |
+
.with_columns(decade=pl.col('year').floordiv(10).mul(10))
|
601 |
+
.with_columns(pl.when(pl.col('software').is_in(discontinued_list))
|
602 |
+
.then(pl.lit('Discontinued'))
|
603 |
+
.otherwise(pl.lit('In use'))
|
604 |
+
.alias('status')
|
605 |
+
)
|
606 |
+
.select('decade').to_series().value_counts()
|
607 |
+
)
|
608 |
+
return
|
609 |
+
|
610 |
+
|
611 |
+
@app.cell(hide_code=True)
|
612 |
+
def _(mo):
|
613 |
+
mo.md(r"""Hopefully, we've picked your interest to try out Polars the next time you analyze your data.""")
|
614 |
+
return
|
615 |
+
|
616 |
+
|
617 |
+
@app.cell
|
618 |
+
def _():
|
619 |
+
return
|
620 |
+
|
621 |
+
|
622 |
+
if __name__ == "__main__":
|
623 |
+
app.run()
|