myawesomepkg 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- myawesomepkg/TSAPY1/1 (A) Working with Numpy Arrays.py +1146 -0
- myawesomepkg/TSAPY1/1(B)Aggregation (1).py +319 -0
- myawesomepkg/TSAPY1/1(C) Broadcasting .py +328 -0
- myawesomepkg/TSAPY1/10-A_Load_stringr.py +77 -0
- myawesomepkg/TSAPY1/10-B_Forcats.py +70 -0
- myawesomepkg/TSAPY1/2(a) Comparison, Masking And Boolean Logic (1).py +497 -0
- myawesomepkg/TSAPY1/2(b)Fancy Indexing.py +594 -0
- myawesomepkg/TSAPY1/2(c) Sorting Arrays.py +528 -0
- myawesomepkg/TSAPY1/2(d) Structured Array.py +350 -0
- myawesomepkg/TSAPY1/3 (A) Handling Missing Data.py +1013 -0
- myawesomepkg/TSAPY1/4A_Merge_Joins.py +1209 -0
- myawesomepkg/TSAPY1/9A_Dplyr.py +85 -0
- myawesomepkg/TSAPY1/9B_Tidyr.py +71 -0
- myawesomepkg/TSAPY1/Aggregation_Groupin_Pivot_Filter_Vectorice_Time_Series.py +1999 -0
- myawesomepkg/TSAPY1/Combining_Joins.py +1209 -0
- myawesomepkg/TSAPY1/Pract3_C.py +482 -0
- myawesomepkg/TSAPY1/Pract5_Data_Visualization.py +481 -0
- myawesomepkg/TSAPY1/Practical 6.py +860 -0
- myawesomepkg/TSAPY1/Print_R.py +123 -0
- myawesomepkg/TSAPY1/R_Graph.py +32 -0
- myawesomepkg/TSAPY1/Working_Ggplot.py +53 -0
- myawesomepkg/TSAPY1/pract3A-B.py +3212 -0
- {myawesomepkg-0.1.4.dist-info → myawesomepkg-0.1.6.dist-info}/METADATA +1 -1
- myawesomepkg-0.1.6.dist-info/RECORD +47 -0
- myawesomepkg-0.1.4.dist-info/RECORD +0 -25
- {myawesomepkg-0.1.4.dist-info → myawesomepkg-0.1.6.dist-info}/WHEEL +0 -0
- {myawesomepkg-0.1.4.dist-info → myawesomepkg-0.1.6.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,1999 @@
|
|
|
1
|
+
{
|
|
2
|
+
"cells": [
|
|
3
|
+
{
|
|
4
|
+
"cell_type": "code",
|
|
5
|
+
"execution_count": 6,
|
|
6
|
+
"id": "4f69a04d-f81c-4de7-9fcd-9e8e53dde5d2",
|
|
7
|
+
"metadata": {},
|
|
8
|
+
"outputs": [
|
|
9
|
+
{
|
|
10
|
+
"data": {
|
|
11
|
+
"text/plain": [
|
|
12
|
+
"(1035, 6)"
|
|
13
|
+
]
|
|
14
|
+
},
|
|
15
|
+
"execution_count": 6,
|
|
16
|
+
"metadata": {},
|
|
17
|
+
"output_type": "execute_result"
|
|
18
|
+
}
|
|
19
|
+
],
|
|
20
|
+
"source": [
|
|
21
|
+
" # Aggregation and Grouping\n",
|
|
22
|
+
" import seaborn as sns\n",
|
|
23
|
+
" import numpy as np\n",
|
|
24
|
+
" import pandas as pd\n",
|
|
25
|
+
"\n",
|
|
26
|
+
" planets = sns.load_dataset('planets')\n",
|
|
27
|
+
" planets.shape"
|
|
28
|
+
]
|
|
29
|
+
},
|
|
30
|
+
{
|
|
31
|
+
"cell_type": "code",
|
|
32
|
+
"execution_count": 2,
|
|
33
|
+
"id": "d0a85e69-4dee-4a89-af0b-0b1619214246",
|
|
34
|
+
"metadata": {},
|
|
35
|
+
"outputs": [
|
|
36
|
+
{
|
|
37
|
+
"data": {
|
|
38
|
+
"text/html": [
|
|
39
|
+
"<div>\n",
|
|
40
|
+
"<style scoped>\n",
|
|
41
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
42
|
+
" vertical-align: middle;\n",
|
|
43
|
+
" }\n",
|
|
44
|
+
"\n",
|
|
45
|
+
" .dataframe tbody tr th {\n",
|
|
46
|
+
" vertical-align: top;\n",
|
|
47
|
+
" }\n",
|
|
48
|
+
"\n",
|
|
49
|
+
" .dataframe thead th {\n",
|
|
50
|
+
" text-align: right;\n",
|
|
51
|
+
" }\n",
|
|
52
|
+
"</style>\n",
|
|
53
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
54
|
+
" <thead>\n",
|
|
55
|
+
" <tr style=\"text-align: right;\">\n",
|
|
56
|
+
" <th></th>\n",
|
|
57
|
+
" <th>method</th>\n",
|
|
58
|
+
" <th>number</th>\n",
|
|
59
|
+
" <th>orbital_period</th>\n",
|
|
60
|
+
" <th>mass</th>\n",
|
|
61
|
+
" <th>distance</th>\n",
|
|
62
|
+
" <th>year</th>\n",
|
|
63
|
+
" </tr>\n",
|
|
64
|
+
" </thead>\n",
|
|
65
|
+
" <tbody>\n",
|
|
66
|
+
" <tr>\n",
|
|
67
|
+
" <th>0</th>\n",
|
|
68
|
+
" <td>Radial Velocity</td>\n",
|
|
69
|
+
" <td>1</td>\n",
|
|
70
|
+
" <td>269.300</td>\n",
|
|
71
|
+
" <td>7.10</td>\n",
|
|
72
|
+
" <td>77.40</td>\n",
|
|
73
|
+
" <td>2006</td>\n",
|
|
74
|
+
" </tr>\n",
|
|
75
|
+
" <tr>\n",
|
|
76
|
+
" <th>1</th>\n",
|
|
77
|
+
" <td>Radial Velocity</td>\n",
|
|
78
|
+
" <td>1</td>\n",
|
|
79
|
+
" <td>874.774</td>\n",
|
|
80
|
+
" <td>2.21</td>\n",
|
|
81
|
+
" <td>56.95</td>\n",
|
|
82
|
+
" <td>2008</td>\n",
|
|
83
|
+
" </tr>\n",
|
|
84
|
+
" <tr>\n",
|
|
85
|
+
" <th>2</th>\n",
|
|
86
|
+
" <td>Radial Velocity</td>\n",
|
|
87
|
+
" <td>1</td>\n",
|
|
88
|
+
" <td>763.000</td>\n",
|
|
89
|
+
" <td>2.60</td>\n",
|
|
90
|
+
" <td>19.84</td>\n",
|
|
91
|
+
" <td>2011</td>\n",
|
|
92
|
+
" </tr>\n",
|
|
93
|
+
" <tr>\n",
|
|
94
|
+
" <th>3</th>\n",
|
|
95
|
+
" <td>Radial Velocity</td>\n",
|
|
96
|
+
" <td>1</td>\n",
|
|
97
|
+
" <td>326.030</td>\n",
|
|
98
|
+
" <td>19.40</td>\n",
|
|
99
|
+
" <td>110.62</td>\n",
|
|
100
|
+
" <td>2007</td>\n",
|
|
101
|
+
" </tr>\n",
|
|
102
|
+
" <tr>\n",
|
|
103
|
+
" <th>4</th>\n",
|
|
104
|
+
" <td>Radial Velocity</td>\n",
|
|
105
|
+
" <td>1</td>\n",
|
|
106
|
+
" <td>516.220</td>\n",
|
|
107
|
+
" <td>10.50</td>\n",
|
|
108
|
+
" <td>119.47</td>\n",
|
|
109
|
+
" <td>2009</td>\n",
|
|
110
|
+
" </tr>\n",
|
|
111
|
+
" </tbody>\n",
|
|
112
|
+
"</table>\n",
|
|
113
|
+
"</div>"
|
|
114
|
+
],
|
|
115
|
+
"text/plain": [
|
|
116
|
+
" method number orbital_period mass distance year\n",
|
|
117
|
+
"0 Radial Velocity 1 269.300 7.10 77.40 2006\n",
|
|
118
|
+
"1 Radial Velocity 1 874.774 2.21 56.95 2008\n",
|
|
119
|
+
"2 Radial Velocity 1 763.000 2.60 19.84 2011\n",
|
|
120
|
+
"3 Radial Velocity 1 326.030 19.40 110.62 2007\n",
|
|
121
|
+
"4 Radial Velocity 1 516.220 10.50 119.47 2009"
|
|
122
|
+
]
|
|
123
|
+
},
|
|
124
|
+
"execution_count": 2,
|
|
125
|
+
"metadata": {},
|
|
126
|
+
"output_type": "execute_result"
|
|
127
|
+
}
|
|
128
|
+
],
|
|
129
|
+
"source": [
|
|
130
|
+
"planets.head()"
|
|
131
|
+
]
|
|
132
|
+
},
|
|
133
|
+
{
|
|
134
|
+
"cell_type": "code",
|
|
135
|
+
"execution_count": 7,
|
|
136
|
+
"id": "a3af591e-4d36-421f-9193-a531fbf71daf",
|
|
137
|
+
"metadata": {},
|
|
138
|
+
"outputs": [
|
|
139
|
+
{
|
|
140
|
+
"data": {
|
|
141
|
+
"text/plain": [
|
|
142
|
+
"0 0.374540\n",
|
|
143
|
+
"1 0.950714\n",
|
|
144
|
+
"2 0.731994\n",
|
|
145
|
+
"3 0.598658\n",
|
|
146
|
+
"4 0.156019\n",
|
|
147
|
+
"dtype: float64"
|
|
148
|
+
]
|
|
149
|
+
},
|
|
150
|
+
"execution_count": 7,
|
|
151
|
+
"metadata": {},
|
|
152
|
+
"output_type": "execute_result"
|
|
153
|
+
}
|
|
154
|
+
],
|
|
155
|
+
"source": [
|
|
156
|
+
"rng = np.random.RandomState(42)\n",
|
|
157
|
+
"ser = pd.Series(rng.rand(5))\n",
|
|
158
|
+
"ser"
|
|
159
|
+
]
|
|
160
|
+
},
|
|
161
|
+
{
|
|
162
|
+
"cell_type": "code",
|
|
163
|
+
"execution_count": 8,
|
|
164
|
+
"id": "e1551693-5459-4fda-ad83-6bf8983da04e",
|
|
165
|
+
"metadata": {},
|
|
166
|
+
"outputs": [
|
|
167
|
+
{
|
|
168
|
+
"data": {
|
|
169
|
+
"text/plain": [
|
|
170
|
+
"np.float64(2.811925491708157)"
|
|
171
|
+
]
|
|
172
|
+
},
|
|
173
|
+
"execution_count": 8,
|
|
174
|
+
"metadata": {},
|
|
175
|
+
"output_type": "execute_result"
|
|
176
|
+
}
|
|
177
|
+
],
|
|
178
|
+
"source": [
|
|
179
|
+
"ser.sum()"
|
|
180
|
+
]
|
|
181
|
+
},
|
|
182
|
+
{
|
|
183
|
+
"cell_type": "code",
|
|
184
|
+
"execution_count": 9,
|
|
185
|
+
"id": "4229b069-a49f-4a35-a2a4-4c72665c3f15",
|
|
186
|
+
"metadata": {},
|
|
187
|
+
"outputs": [
|
|
188
|
+
{
|
|
189
|
+
"data": {
|
|
190
|
+
"text/plain": [
|
|
191
|
+
"np.float64(0.5623850983416314)"
|
|
192
|
+
]
|
|
193
|
+
},
|
|
194
|
+
"execution_count": 9,
|
|
195
|
+
"metadata": {},
|
|
196
|
+
"output_type": "execute_result"
|
|
197
|
+
}
|
|
198
|
+
],
|
|
199
|
+
"source": [
|
|
200
|
+
"ser.mean()"
|
|
201
|
+
]
|
|
202
|
+
},
|
|
203
|
+
{
|
|
204
|
+
"cell_type": "code",
|
|
205
|
+
"execution_count": 11,
|
|
206
|
+
"id": "09eb4bfb-5496-4e30-9c93-c50663b5466d",
|
|
207
|
+
"metadata": {},
|
|
208
|
+
"outputs": [
|
|
209
|
+
{
|
|
210
|
+
"data": {
|
|
211
|
+
"text/html": [
|
|
212
|
+
"<div>\n",
|
|
213
|
+
"<style scoped>\n",
|
|
214
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
215
|
+
" vertical-align: middle;\n",
|
|
216
|
+
" }\n",
|
|
217
|
+
"\n",
|
|
218
|
+
" .dataframe tbody tr th {\n",
|
|
219
|
+
" vertical-align: top;\n",
|
|
220
|
+
" }\n",
|
|
221
|
+
"\n",
|
|
222
|
+
" .dataframe thead th {\n",
|
|
223
|
+
" text-align: right;\n",
|
|
224
|
+
" }\n",
|
|
225
|
+
"</style>\n",
|
|
226
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
227
|
+
" <thead>\n",
|
|
228
|
+
" <tr style=\"text-align: right;\">\n",
|
|
229
|
+
" <th></th>\n",
|
|
230
|
+
" <th>A</th>\n",
|
|
231
|
+
" <th>B</th>\n",
|
|
232
|
+
" </tr>\n",
|
|
233
|
+
" </thead>\n",
|
|
234
|
+
" <tbody>\n",
|
|
235
|
+
" <tr>\n",
|
|
236
|
+
" <th>0</th>\n",
|
|
237
|
+
" <td>0.183405</td>\n",
|
|
238
|
+
" <td>0.611853</td>\n",
|
|
239
|
+
" </tr>\n",
|
|
240
|
+
" <tr>\n",
|
|
241
|
+
" <th>1</th>\n",
|
|
242
|
+
" <td>0.304242</td>\n",
|
|
243
|
+
" <td>0.139494</td>\n",
|
|
244
|
+
" </tr>\n",
|
|
245
|
+
" <tr>\n",
|
|
246
|
+
" <th>2</th>\n",
|
|
247
|
+
" <td>0.524756</td>\n",
|
|
248
|
+
" <td>0.292145</td>\n",
|
|
249
|
+
" </tr>\n",
|
|
250
|
+
" <tr>\n",
|
|
251
|
+
" <th>3</th>\n",
|
|
252
|
+
" <td>0.431945</td>\n",
|
|
253
|
+
" <td>0.366362</td>\n",
|
|
254
|
+
" </tr>\n",
|
|
255
|
+
" <tr>\n",
|
|
256
|
+
" <th>4</th>\n",
|
|
257
|
+
" <td>0.291229</td>\n",
|
|
258
|
+
" <td>0.456070</td>\n",
|
|
259
|
+
" </tr>\n",
|
|
260
|
+
" </tbody>\n",
|
|
261
|
+
"</table>\n",
|
|
262
|
+
"</div>"
|
|
263
|
+
],
|
|
264
|
+
"text/plain": [
|
|
265
|
+
" A B\n",
|
|
266
|
+
"0 0.183405 0.611853\n",
|
|
267
|
+
"1 0.304242 0.139494\n",
|
|
268
|
+
"2 0.524756 0.292145\n",
|
|
269
|
+
"3 0.431945 0.366362\n",
|
|
270
|
+
"4 0.291229 0.456070"
|
|
271
|
+
]
|
|
272
|
+
},
|
|
273
|
+
"execution_count": 11,
|
|
274
|
+
"metadata": {},
|
|
275
|
+
"output_type": "execute_result"
|
|
276
|
+
}
|
|
277
|
+
],
|
|
278
|
+
"source": [
|
|
279
|
+
"df = pd.DataFrame({'A': rng.rand(5),\n",
|
|
280
|
+
" 'B': rng.rand(5)})\n",
|
|
281
|
+
"df"
|
|
282
|
+
]
|
|
283
|
+
},
|
|
284
|
+
{
|
|
285
|
+
"cell_type": "code",
|
|
286
|
+
"execution_count": 12,
|
|
287
|
+
"id": "dd941315-2e2b-42a4-80a9-a50dc81a291d",
|
|
288
|
+
"metadata": {},
|
|
289
|
+
"outputs": [
|
|
290
|
+
{
|
|
291
|
+
"data": {
|
|
292
|
+
"text/plain": [
|
|
293
|
+
"A 0.347115\n",
|
|
294
|
+
"B 0.373185\n",
|
|
295
|
+
"dtype: float64"
|
|
296
|
+
]
|
|
297
|
+
},
|
|
298
|
+
"execution_count": 12,
|
|
299
|
+
"metadata": {},
|
|
300
|
+
"output_type": "execute_result"
|
|
301
|
+
}
|
|
302
|
+
],
|
|
303
|
+
"source": [
|
|
304
|
+
"df.mean()"
|
|
305
|
+
]
|
|
306
|
+
},
|
|
307
|
+
{
|
|
308
|
+
"cell_type": "code",
|
|
309
|
+
"execution_count": 13,
|
|
310
|
+
"id": "b1c5221c-fd2f-44aa-a2a7-64cf11940039",
|
|
311
|
+
"metadata": {},
|
|
312
|
+
"outputs": [
|
|
313
|
+
{
|
|
314
|
+
"data": {
|
|
315
|
+
"text/plain": [
|
|
316
|
+
"0 0.397629\n",
|
|
317
|
+
"1 0.221868\n",
|
|
318
|
+
"2 0.408451\n",
|
|
319
|
+
"3 0.399153\n",
|
|
320
|
+
"4 0.373650\n",
|
|
321
|
+
"dtype: float64"
|
|
322
|
+
]
|
|
323
|
+
},
|
|
324
|
+
"execution_count": 13,
|
|
325
|
+
"metadata": {},
|
|
326
|
+
"output_type": "execute_result"
|
|
327
|
+
}
|
|
328
|
+
],
|
|
329
|
+
"source": [
|
|
330
|
+
"df.mean(axis='columns')"
|
|
331
|
+
]
|
|
332
|
+
},
|
|
333
|
+
{
|
|
334
|
+
"cell_type": "code",
|
|
335
|
+
"execution_count": 14,
|
|
336
|
+
"id": "3c3c9815-5ff7-4522-9b78-f79b7d2749c2",
|
|
337
|
+
"metadata": {},
|
|
338
|
+
"outputs": [
|
|
339
|
+
{
|
|
340
|
+
"data": {
|
|
341
|
+
"text/html": [
|
|
342
|
+
"<div>\n",
|
|
343
|
+
"<style scoped>\n",
|
|
344
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
345
|
+
" vertical-align: middle;\n",
|
|
346
|
+
" }\n",
|
|
347
|
+
"\n",
|
|
348
|
+
" .dataframe tbody tr th {\n",
|
|
349
|
+
" vertical-align: top;\n",
|
|
350
|
+
" }\n",
|
|
351
|
+
"\n",
|
|
352
|
+
" .dataframe thead th {\n",
|
|
353
|
+
" text-align: right;\n",
|
|
354
|
+
" }\n",
|
|
355
|
+
"</style>\n",
|
|
356
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
357
|
+
" <thead>\n",
|
|
358
|
+
" <tr style=\"text-align: right;\">\n",
|
|
359
|
+
" <th></th>\n",
|
|
360
|
+
" <th>number</th>\n",
|
|
361
|
+
" <th>orbital_period</th>\n",
|
|
362
|
+
" <th>mass</th>\n",
|
|
363
|
+
" <th>distance</th>\n",
|
|
364
|
+
" <th>year</th>\n",
|
|
365
|
+
" </tr>\n",
|
|
366
|
+
" </thead>\n",
|
|
367
|
+
" <tbody>\n",
|
|
368
|
+
" <tr>\n",
|
|
369
|
+
" <th>count</th>\n",
|
|
370
|
+
" <td>498.00000</td>\n",
|
|
371
|
+
" <td>498.000000</td>\n",
|
|
372
|
+
" <td>498.000000</td>\n",
|
|
373
|
+
" <td>498.000000</td>\n",
|
|
374
|
+
" <td>498.000000</td>\n",
|
|
375
|
+
" </tr>\n",
|
|
376
|
+
" <tr>\n",
|
|
377
|
+
" <th>mean</th>\n",
|
|
378
|
+
" <td>1.73494</td>\n",
|
|
379
|
+
" <td>835.778671</td>\n",
|
|
380
|
+
" <td>2.509320</td>\n",
|
|
381
|
+
" <td>52.068213</td>\n",
|
|
382
|
+
" <td>2007.377510</td>\n",
|
|
383
|
+
" </tr>\n",
|
|
384
|
+
" <tr>\n",
|
|
385
|
+
" <th>std</th>\n",
|
|
386
|
+
" <td>1.17572</td>\n",
|
|
387
|
+
" <td>1469.128259</td>\n",
|
|
388
|
+
" <td>3.636274</td>\n",
|
|
389
|
+
" <td>46.596041</td>\n",
|
|
390
|
+
" <td>4.167284</td>\n",
|
|
391
|
+
" </tr>\n",
|
|
392
|
+
" <tr>\n",
|
|
393
|
+
" <th>min</th>\n",
|
|
394
|
+
" <td>1.00000</td>\n",
|
|
395
|
+
" <td>1.328300</td>\n",
|
|
396
|
+
" <td>0.003600</td>\n",
|
|
397
|
+
" <td>1.350000</td>\n",
|
|
398
|
+
" <td>1989.000000</td>\n",
|
|
399
|
+
" </tr>\n",
|
|
400
|
+
" <tr>\n",
|
|
401
|
+
" <th>25%</th>\n",
|
|
402
|
+
" <td>1.00000</td>\n",
|
|
403
|
+
" <td>38.272250</td>\n",
|
|
404
|
+
" <td>0.212500</td>\n",
|
|
405
|
+
" <td>24.497500</td>\n",
|
|
406
|
+
" <td>2005.000000</td>\n",
|
|
407
|
+
" </tr>\n",
|
|
408
|
+
" <tr>\n",
|
|
409
|
+
" <th>50%</th>\n",
|
|
410
|
+
" <td>1.00000</td>\n",
|
|
411
|
+
" <td>357.000000</td>\n",
|
|
412
|
+
" <td>1.245000</td>\n",
|
|
413
|
+
" <td>39.940000</td>\n",
|
|
414
|
+
" <td>2009.000000</td>\n",
|
|
415
|
+
" </tr>\n",
|
|
416
|
+
" <tr>\n",
|
|
417
|
+
" <th>75%</th>\n",
|
|
418
|
+
" <td>2.00000</td>\n",
|
|
419
|
+
" <td>999.600000</td>\n",
|
|
420
|
+
" <td>2.867500</td>\n",
|
|
421
|
+
" <td>59.332500</td>\n",
|
|
422
|
+
" <td>2011.000000</td>\n",
|
|
423
|
+
" </tr>\n",
|
|
424
|
+
" <tr>\n",
|
|
425
|
+
" <th>max</th>\n",
|
|
426
|
+
" <td>6.00000</td>\n",
|
|
427
|
+
" <td>17337.500000</td>\n",
|
|
428
|
+
" <td>25.000000</td>\n",
|
|
429
|
+
" <td>354.000000</td>\n",
|
|
430
|
+
" <td>2014.000000</td>\n",
|
|
431
|
+
" </tr>\n",
|
|
432
|
+
" </tbody>\n",
|
|
433
|
+
"</table>\n",
|
|
434
|
+
"</div>"
|
|
435
|
+
],
|
|
436
|
+
"text/plain": [
|
|
437
|
+
" number orbital_period mass distance year\n",
|
|
438
|
+
"count 498.00000 498.000000 498.000000 498.000000 498.000000\n",
|
|
439
|
+
"mean 1.73494 835.778671 2.509320 52.068213 2007.377510\n",
|
|
440
|
+
"std 1.17572 1469.128259 3.636274 46.596041 4.167284\n",
|
|
441
|
+
"min 1.00000 1.328300 0.003600 1.350000 1989.000000\n",
|
|
442
|
+
"25% 1.00000 38.272250 0.212500 24.497500 2005.000000\n",
|
|
443
|
+
"50% 1.00000 357.000000 1.245000 39.940000 2009.000000\n",
|
|
444
|
+
"75% 2.00000 999.600000 2.867500 59.332500 2011.000000\n",
|
|
445
|
+
"max 6.00000 17337.500000 25.000000 354.000000 2014.000000"
|
|
446
|
+
]
|
|
447
|
+
},
|
|
448
|
+
"execution_count": 14,
|
|
449
|
+
"metadata": {},
|
|
450
|
+
"output_type": "execute_result"
|
|
451
|
+
}
|
|
452
|
+
],
|
|
453
|
+
"source": [
|
|
454
|
+
"planets.dropna().describe()"
|
|
455
|
+
]
|
|
456
|
+
},
|
|
457
|
+
{
|
|
458
|
+
"cell_type": "code",
|
|
459
|
+
"execution_count": 18,
|
|
460
|
+
"id": "443f472b-83a4-4468-a104-5fc39c327453",
|
|
461
|
+
"metadata": {},
|
|
462
|
+
"outputs": [
|
|
463
|
+
{
|
|
464
|
+
"name": "stdout",
|
|
465
|
+
"output_type": "stream",
|
|
466
|
+
"text": [
|
|
467
|
+
" A B\n",
|
|
468
|
+
"0 0.183405 0.611853\n",
|
|
469
|
+
"1 0.304242 0.139494\n",
|
|
470
|
+
"2 0.524756 0.292145\n",
|
|
471
|
+
"3 0.431945 0.366362\n",
|
|
472
|
+
"4 0.291229 0.456070\n"
|
|
473
|
+
]
|
|
474
|
+
},
|
|
475
|
+
{
|
|
476
|
+
"ename": "KeyError",
|
|
477
|
+
"evalue": "'key'",
|
|
478
|
+
"output_type": "error",
|
|
479
|
+
"traceback": [
|
|
480
|
+
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
|
481
|
+
"\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
|
|
482
|
+
"Cell \u001b[1;32mIn[18], line 3\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mfilter_func\u001b[39m(x):\n\u001b[0;32m 2\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m x[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mdata2\u001b[39m\u001b[38;5;124m'\u001b[39m]\u001b[38;5;241m.\u001b[39mstd() \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m4\u001b[39m\n\u001b[1;32m----> 3\u001b[0m \u001b[38;5;28mprint\u001b[39m(df); \u001b[38;5;28mprint\u001b[39m(df\u001b[38;5;241m.\u001b[39mgroupby(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mkey\u001b[39m\u001b[38;5;124m'\u001b[39m)\u001b[38;5;241m.\u001b[39mstd());\n\u001b[0;32m 4\u001b[0m \u001b[38;5;28mprint\u001b[39m(df\u001b[38;5;241m.\u001b[39mgroupby(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mkey\u001b[39m\u001b[38;5;124m'\u001b[39m)\u001b[38;5;241m.\u001b[39mfilter(filter_func))\n",
|
|
483
|
+
"File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\pandas\\core\\frame.py:9183\u001b[0m, in \u001b[0;36mDataFrame.groupby\u001b[1;34m(self, by, axis, level, as_index, sort, group_keys, observed, dropna)\u001b[0m\n\u001b[0;32m 9180\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m level \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m by \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m 9181\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou have to supply one of \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mby\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m and \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlevel\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m-> 9183\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mDataFrameGroupBy\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 9184\u001b[0m \u001b[43m \u001b[49m\u001b[43mobj\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9185\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mby\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9186\u001b[0m \u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9187\u001b[0m \u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlevel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9188\u001b[0m \u001b[43m \u001b[49m\u001b[43mas_index\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mas_index\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9189\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9190\u001b[0m \u001b[43m \u001b[49m\u001b[43mgroup_keys\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgroup_keys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9191\u001b[0m \u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mobserved\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9192\u001b[0m \u001b[43m \u001b[49m\u001b[43mdropna\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdropna\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 9193\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
|
|
484
|
+
"File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\pandas\\core\\groupby\\groupby.py:1329\u001b[0m, in \u001b[0;36mGroupBy.__init__\u001b[1;34m(self, obj, keys, axis, level, grouper, exclusions, selection, as_index, sort, group_keys, observed, dropna)\u001b[0m\n\u001b[0;32m 1326\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdropna \u001b[38;5;241m=\u001b[39m dropna\n\u001b[0;32m 1328\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m grouper \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m-> 1329\u001b[0m grouper, exclusions, obj \u001b[38;5;241m=\u001b[39m \u001b[43mget_grouper\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 1330\u001b[0m \u001b[43m \u001b[49m\u001b[43mobj\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1331\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeys\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1332\u001b[0m \u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1333\u001b[0m \u001b[43m \u001b[49m\u001b[43mlevel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlevel\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1334\u001b[0m \u001b[43m \u001b[49m\u001b[43msort\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msort\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1335\u001b[0m \u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mis\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mlib\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mno_default\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mobserved\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1336\u001b[0m \u001b[43m \u001b[49m\u001b[43mdropna\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdropna\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 1337\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 1339\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m observed \u001b[38;5;129;01mis\u001b[39;00m lib\u001b[38;5;241m.\u001b[39mno_default:\n\u001b[0;32m 1340\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28many\u001b[39m(ping\u001b[38;5;241m.\u001b[39m_passed_categorical \u001b[38;5;28;01mfor\u001b[39;00m ping \u001b[38;5;129;01min\u001b[39;00m grouper\u001b[38;5;241m.\u001b[39mgroupings):\n",
|
|
485
|
+
"File \u001b[1;32m~\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\pandas\\core\\groupby\\grouper.py:1043\u001b[0m, in \u001b[0;36mget_grouper\u001b[1;34m(obj, key, axis, level, sort, observed, validate, dropna)\u001b[0m\n\u001b[0;32m 1041\u001b[0m in_axis, level, gpr \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m, gpr, \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m 1042\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1043\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(gpr)\n\u001b[0;32m 1044\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(gpr, Grouper) \u001b[38;5;129;01mand\u001b[39;00m gpr\u001b[38;5;241m.\u001b[39mkey \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m 1045\u001b[0m \u001b[38;5;66;03m# Add key to exclusions\u001b[39;00m\n\u001b[0;32m 1046\u001b[0m exclusions\u001b[38;5;241m.\u001b[39madd(gpr\u001b[38;5;241m.\u001b[39mkey)\n",
|
|
486
|
+
"\u001b[1;31mKeyError\u001b[0m: 'key'"
|
|
487
|
+
]
|
|
488
|
+
}
|
|
489
|
+
],
|
|
490
|
+
"source": [
|
|
491
|
+
" def filter_func(x):\n",
|
|
492
|
+
" return x['data2'].std() > 4\n",
|
|
493
|
+
" print(df); print(df.groupby('key').std());\n",
|
|
494
|
+
" print(df.groupby('key').filter(filter_func))\n",
|
|
495
|
+
" "
|
|
496
|
+
]
|
|
497
|
+
},
|
|
498
|
+
{
|
|
499
|
+
"cell_type": "code",
|
|
500
|
+
"execution_count": 22,
|
|
501
|
+
"id": "40071505-de3c-4940-89ea-d38b0f1212b8",
|
|
502
|
+
"metadata": {},
|
|
503
|
+
"outputs": [
|
|
504
|
+
{
|
|
505
|
+
"data": {
|
|
506
|
+
"text/html": [
|
|
507
|
+
"<div>\n",
|
|
508
|
+
"<style scoped>\n",
|
|
509
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
510
|
+
" vertical-align: middle;\n",
|
|
511
|
+
" }\n",
|
|
512
|
+
"\n",
|
|
513
|
+
" .dataframe tbody tr th {\n",
|
|
514
|
+
" vertical-align: top;\n",
|
|
515
|
+
" }\n",
|
|
516
|
+
"\n",
|
|
517
|
+
" .dataframe thead th {\n",
|
|
518
|
+
" text-align: right;\n",
|
|
519
|
+
" }\n",
|
|
520
|
+
"</style>\n",
|
|
521
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
522
|
+
" <thead>\n",
|
|
523
|
+
" <tr style=\"text-align: right;\">\n",
|
|
524
|
+
" <th></th>\n",
|
|
525
|
+
" <th>key</th>\n",
|
|
526
|
+
" <th>data1</th>\n",
|
|
527
|
+
" <th>data2</th>\n",
|
|
528
|
+
" </tr>\n",
|
|
529
|
+
" </thead>\n",
|
|
530
|
+
" <tbody>\n",
|
|
531
|
+
" <tr>\n",
|
|
532
|
+
" <th>0</th>\n",
|
|
533
|
+
" <td>A</td>\n",
|
|
534
|
+
" <td>0</td>\n",
|
|
535
|
+
" <td>5</td>\n",
|
|
536
|
+
" </tr>\n",
|
|
537
|
+
" <tr>\n",
|
|
538
|
+
" <th>1</th>\n",
|
|
539
|
+
" <td>B</td>\n",
|
|
540
|
+
" <td>1</td>\n",
|
|
541
|
+
" <td>0</td>\n",
|
|
542
|
+
" </tr>\n",
|
|
543
|
+
" <tr>\n",
|
|
544
|
+
" <th>2</th>\n",
|
|
545
|
+
" <td>C</td>\n",
|
|
546
|
+
" <td>2</td>\n",
|
|
547
|
+
" <td>3</td>\n",
|
|
548
|
+
" </tr>\n",
|
|
549
|
+
" <tr>\n",
|
|
550
|
+
" <th>3</th>\n",
|
|
551
|
+
" <td>A</td>\n",
|
|
552
|
+
" <td>3</td>\n",
|
|
553
|
+
" <td>3</td>\n",
|
|
554
|
+
" </tr>\n",
|
|
555
|
+
" <tr>\n",
|
|
556
|
+
" <th>4</th>\n",
|
|
557
|
+
" <td>B</td>\n",
|
|
558
|
+
" <td>4</td>\n",
|
|
559
|
+
" <td>7</td>\n",
|
|
560
|
+
" </tr>\n",
|
|
561
|
+
" <tr>\n",
|
|
562
|
+
" <th>5</th>\n",
|
|
563
|
+
" <td>C</td>\n",
|
|
564
|
+
" <td>5</td>\n",
|
|
565
|
+
" <td>9</td>\n",
|
|
566
|
+
" </tr>\n",
|
|
567
|
+
" </tbody>\n",
|
|
568
|
+
"</table>\n",
|
|
569
|
+
"</div>"
|
|
570
|
+
],
|
|
571
|
+
"text/plain": [
|
|
572
|
+
" key data1 data2\n",
|
|
573
|
+
"0 A 0 5\n",
|
|
574
|
+
"1 B 1 0\n",
|
|
575
|
+
"2 C 2 3\n",
|
|
576
|
+
"3 A 3 3\n",
|
|
577
|
+
"4 B 4 7\n",
|
|
578
|
+
"5 C 5 9"
|
|
579
|
+
]
|
|
580
|
+
},
|
|
581
|
+
"execution_count": 22,
|
|
582
|
+
"metadata": {},
|
|
583
|
+
"output_type": "execute_result"
|
|
584
|
+
}
|
|
585
|
+
],
|
|
586
|
+
"source": [
|
|
587
|
+
"#Aggregate, ilter, transform, apply\n",
|
|
588
|
+
"rng = np.random.RandomState(0)\n",
|
|
589
|
+
"df = pd.DataFrame({'key': ['A', 'B', 'C', 'A', 'B', 'C'],\n",
|
|
590
|
+
" 'data1': range(6),\n",
|
|
591
|
+
" 'data2': rng.randint(0, 10, 6)},\n",
|
|
592
|
+
" columns = ['key', 'data1', 'data2'])\n",
|
|
593
|
+
"df"
|
|
594
|
+
]
|
|
595
|
+
},
|
|
596
|
+
{
|
|
597
|
+
"cell_type": "code",
|
|
598
|
+
"execution_count": 23,
|
|
599
|
+
"id": "2c3e28cc-a33e-4567-8b3c-84f243692d1c",
|
|
600
|
+
"metadata": {},
|
|
601
|
+
"outputs": [
|
|
602
|
+
{
|
|
603
|
+
"name": "stderr",
|
|
604
|
+
"output_type": "stream",
|
|
605
|
+
"text": [
|
|
606
|
+
"C:\\Users\\darsh\\AppData\\Local\\Temp\\ipykernel_1940\\968873422.py:1: FutureWarning: The provided callable <function median at 0x00000235EACE3060> is currently using SeriesGroupBy.median. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"median\" instead.\n",
|
|
607
|
+
" df.groupby('key').aggregate(['min', np.median, max])\n",
|
|
608
|
+
"C:\\Users\\darsh\\AppData\\Local\\Temp\\ipykernel_1940\\968873422.py:1: FutureWarning: The provided callable <built-in function max> is currently using SeriesGroupBy.max. In a future version of pandas, the provided callable will be used directly. To keep current behavior pass the string \"max\" instead.\n",
|
|
609
|
+
" df.groupby('key').aggregate(['min', np.median, max])\n"
|
|
610
|
+
]
|
|
611
|
+
},
|
|
612
|
+
{
|
|
613
|
+
"data": {
|
|
614
|
+
"text/html": [
|
|
615
|
+
"<div>\n",
|
|
616
|
+
"<style scoped>\n",
|
|
617
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
618
|
+
" vertical-align: middle;\n",
|
|
619
|
+
" }\n",
|
|
620
|
+
"\n",
|
|
621
|
+
" .dataframe tbody tr th {\n",
|
|
622
|
+
" vertical-align: top;\n",
|
|
623
|
+
" }\n",
|
|
624
|
+
"\n",
|
|
625
|
+
" .dataframe thead tr th {\n",
|
|
626
|
+
" text-align: left;\n",
|
|
627
|
+
" }\n",
|
|
628
|
+
"\n",
|
|
629
|
+
" .dataframe thead tr:last-of-type th {\n",
|
|
630
|
+
" text-align: right;\n",
|
|
631
|
+
" }\n",
|
|
632
|
+
"</style>\n",
|
|
633
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
634
|
+
" <thead>\n",
|
|
635
|
+
" <tr>\n",
|
|
636
|
+
" <th></th>\n",
|
|
637
|
+
" <th colspan=\"3\" halign=\"left\">data1</th>\n",
|
|
638
|
+
" <th colspan=\"3\" halign=\"left\">data2</th>\n",
|
|
639
|
+
" </tr>\n",
|
|
640
|
+
" <tr>\n",
|
|
641
|
+
" <th></th>\n",
|
|
642
|
+
" <th>min</th>\n",
|
|
643
|
+
" <th>median</th>\n",
|
|
644
|
+
" <th>max</th>\n",
|
|
645
|
+
" <th>min</th>\n",
|
|
646
|
+
" <th>median</th>\n",
|
|
647
|
+
" <th>max</th>\n",
|
|
648
|
+
" </tr>\n",
|
|
649
|
+
" <tr>\n",
|
|
650
|
+
" <th>key</th>\n",
|
|
651
|
+
" <th></th>\n",
|
|
652
|
+
" <th></th>\n",
|
|
653
|
+
" <th></th>\n",
|
|
654
|
+
" <th></th>\n",
|
|
655
|
+
" <th></th>\n",
|
|
656
|
+
" <th></th>\n",
|
|
657
|
+
" </tr>\n",
|
|
658
|
+
" </thead>\n",
|
|
659
|
+
" <tbody>\n",
|
|
660
|
+
" <tr>\n",
|
|
661
|
+
" <th>A</th>\n",
|
|
662
|
+
" <td>0</td>\n",
|
|
663
|
+
" <td>1.5</td>\n",
|
|
664
|
+
" <td>3</td>\n",
|
|
665
|
+
" <td>3</td>\n",
|
|
666
|
+
" <td>4.0</td>\n",
|
|
667
|
+
" <td>5</td>\n",
|
|
668
|
+
" </tr>\n",
|
|
669
|
+
" <tr>\n",
|
|
670
|
+
" <th>B</th>\n",
|
|
671
|
+
" <td>1</td>\n",
|
|
672
|
+
" <td>2.5</td>\n",
|
|
673
|
+
" <td>4</td>\n",
|
|
674
|
+
" <td>0</td>\n",
|
|
675
|
+
" <td>3.5</td>\n",
|
|
676
|
+
" <td>7</td>\n",
|
|
677
|
+
" </tr>\n",
|
|
678
|
+
" <tr>\n",
|
|
679
|
+
" <th>C</th>\n",
|
|
680
|
+
" <td>2</td>\n",
|
|
681
|
+
" <td>3.5</td>\n",
|
|
682
|
+
" <td>5</td>\n",
|
|
683
|
+
" <td>3</td>\n",
|
|
684
|
+
" <td>6.0</td>\n",
|
|
685
|
+
" <td>9</td>\n",
|
|
686
|
+
" </tr>\n",
|
|
687
|
+
" </tbody>\n",
|
|
688
|
+
"</table>\n",
|
|
689
|
+
"</div>"
|
|
690
|
+
],
|
|
691
|
+
"text/plain": [
|
|
692
|
+
" data1 data2 \n",
|
|
693
|
+
" min median max min median max\n",
|
|
694
|
+
"key \n",
|
|
695
|
+
"A 0 1.5 3 3 4.0 5\n",
|
|
696
|
+
"B 1 2.5 4 0 3.5 7\n",
|
|
697
|
+
"C 2 3.5 5 3 6.0 9"
|
|
698
|
+
]
|
|
699
|
+
},
|
|
700
|
+
"execution_count": 23,
|
|
701
|
+
"metadata": {},
|
|
702
|
+
"output_type": "execute_result"
|
|
703
|
+
}
|
|
704
|
+
],
|
|
705
|
+
"source": [
|
|
706
|
+
"df.groupby('key').aggregate(['min', np.median, max])"
|
|
707
|
+
]
|
|
708
|
+
},
|
|
709
|
+
{
|
|
710
|
+
"cell_type": "code",
|
|
711
|
+
"execution_count": 24,
|
|
712
|
+
"id": "c05f9979-f316-4c52-8398-7b4db4623523",
|
|
713
|
+
"metadata": {},
|
|
714
|
+
"outputs": [
|
|
715
|
+
{
|
|
716
|
+
"data": {
|
|
717
|
+
"text/html": [
|
|
718
|
+
"<div>\n",
|
|
719
|
+
"<style scoped>\n",
|
|
720
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
721
|
+
" vertical-align: middle;\n",
|
|
722
|
+
" }\n",
|
|
723
|
+
"\n",
|
|
724
|
+
" .dataframe tbody tr th {\n",
|
|
725
|
+
" vertical-align: top;\n",
|
|
726
|
+
" }\n",
|
|
727
|
+
"\n",
|
|
728
|
+
" .dataframe thead th {\n",
|
|
729
|
+
" text-align: right;\n",
|
|
730
|
+
" }\n",
|
|
731
|
+
"</style>\n",
|
|
732
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
733
|
+
" <thead>\n",
|
|
734
|
+
" <tr style=\"text-align: right;\">\n",
|
|
735
|
+
" <th></th>\n",
|
|
736
|
+
" <th>data1</th>\n",
|
|
737
|
+
" <th>data2</th>\n",
|
|
738
|
+
" </tr>\n",
|
|
739
|
+
" <tr>\n",
|
|
740
|
+
" <th>key</th>\n",
|
|
741
|
+
" <th></th>\n",
|
|
742
|
+
" <th></th>\n",
|
|
743
|
+
" </tr>\n",
|
|
744
|
+
" </thead>\n",
|
|
745
|
+
" <tbody>\n",
|
|
746
|
+
" <tr>\n",
|
|
747
|
+
" <th>A</th>\n",
|
|
748
|
+
" <td>0</td>\n",
|
|
749
|
+
" <td>5</td>\n",
|
|
750
|
+
" </tr>\n",
|
|
751
|
+
" <tr>\n",
|
|
752
|
+
" <th>B</th>\n",
|
|
753
|
+
" <td>1</td>\n",
|
|
754
|
+
" <td>7</td>\n",
|
|
755
|
+
" </tr>\n",
|
|
756
|
+
" <tr>\n",
|
|
757
|
+
" <th>C</th>\n",
|
|
758
|
+
" <td>2</td>\n",
|
|
759
|
+
" <td>9</td>\n",
|
|
760
|
+
" </tr>\n",
|
|
761
|
+
" </tbody>\n",
|
|
762
|
+
"</table>\n",
|
|
763
|
+
"</div>"
|
|
764
|
+
],
|
|
765
|
+
"text/plain": [
|
|
766
|
+
" data1 data2\n",
|
|
767
|
+
"key \n",
|
|
768
|
+
"A 0 5\n",
|
|
769
|
+
"B 1 7\n",
|
|
770
|
+
"C 2 9"
|
|
771
|
+
]
|
|
772
|
+
},
|
|
773
|
+
"execution_count": 24,
|
|
774
|
+
"metadata": {},
|
|
775
|
+
"output_type": "execute_result"
|
|
776
|
+
}
|
|
777
|
+
],
|
|
778
|
+
"source": [
|
|
779
|
+
" df.groupby('key').aggregate({'data1': 'min',\n",
|
|
780
|
+
" 'data2': 'max'})"
|
|
781
|
+
]
|
|
782
|
+
},
|
|
783
|
+
{
|
|
784
|
+
"cell_type": "code",
|
|
785
|
+
"execution_count": 25,
|
|
786
|
+
"id": "c065e650-3fe4-46a3-b1c0-a12c2b854bf3",
|
|
787
|
+
"metadata": {},
|
|
788
|
+
"outputs": [
|
|
789
|
+
{
|
|
790
|
+
"name": "stdout",
|
|
791
|
+
"output_type": "stream",
|
|
792
|
+
"text": [
|
|
793
|
+
" key data1 data2\n",
|
|
794
|
+
"0 A 0 5\n",
|
|
795
|
+
"1 B 1 0\n",
|
|
796
|
+
"2 C 2 3\n",
|
|
797
|
+
"3 A 3 3\n",
|
|
798
|
+
"4 B 4 7\n",
|
|
799
|
+
"5 C 5 9\n",
|
|
800
|
+
" data1 data2\n",
|
|
801
|
+
"key \n",
|
|
802
|
+
"A 2.12132 1.414214\n",
|
|
803
|
+
"B 2.12132 4.949747\n",
|
|
804
|
+
"C 2.12132 4.242641\n",
|
|
805
|
+
" key data1 data2\n",
|
|
806
|
+
"1 B 1 0\n",
|
|
807
|
+
"2 C 2 3\n",
|
|
808
|
+
"4 B 4 7\n",
|
|
809
|
+
"5 C 5 9\n"
|
|
810
|
+
]
|
|
811
|
+
}
|
|
812
|
+
],
|
|
813
|
+
"source": [
|
|
814
|
+
"# Filtering. \n",
|
|
815
|
+
"def filter_func(x):\n",
|
|
816
|
+
" return x['data2'].std() > 4\n",
|
|
817
|
+
"print(df); print(df.groupby('key').std());\n",
|
|
818
|
+
"print(df.groupby('key').filter(filter_func))"
|
|
819
|
+
]
|
|
820
|
+
},
|
|
821
|
+
{
|
|
822
|
+
"cell_type": "code",
|
|
823
|
+
"execution_count": 28,
|
|
824
|
+
"id": "a0f958e6-d237-45df-b85b-483bcb13dfee",
|
|
825
|
+
"metadata": {},
|
|
826
|
+
"outputs": [
|
|
827
|
+
{
|
|
828
|
+
"data": {
|
|
829
|
+
"text/html": [
|
|
830
|
+
"<div>\n",
|
|
831
|
+
"<style scoped>\n",
|
|
832
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
833
|
+
" vertical-align: middle;\n",
|
|
834
|
+
" }\n",
|
|
835
|
+
"\n",
|
|
836
|
+
" .dataframe tbody tr th {\n",
|
|
837
|
+
" vertical-align: top;\n",
|
|
838
|
+
" }\n",
|
|
839
|
+
"\n",
|
|
840
|
+
" .dataframe thead th {\n",
|
|
841
|
+
" text-align: right;\n",
|
|
842
|
+
" }\n",
|
|
843
|
+
"</style>\n",
|
|
844
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
845
|
+
" <thead>\n",
|
|
846
|
+
" <tr style=\"text-align: right;\">\n",
|
|
847
|
+
" <th></th>\n",
|
|
848
|
+
" <th>key</th>\n",
|
|
849
|
+
" <th>data1</th>\n",
|
|
850
|
+
" <th>data2</th>\n",
|
|
851
|
+
" </tr>\n",
|
|
852
|
+
" </thead>\n",
|
|
853
|
+
" <tbody>\n",
|
|
854
|
+
" <tr>\n",
|
|
855
|
+
" <th>1</th>\n",
|
|
856
|
+
" <td>B</td>\n",
|
|
857
|
+
" <td>1</td>\n",
|
|
858
|
+
" <td>0</td>\n",
|
|
859
|
+
" </tr>\n",
|
|
860
|
+
" <tr>\n",
|
|
861
|
+
" <th>2</th>\n",
|
|
862
|
+
" <td>C</td>\n",
|
|
863
|
+
" <td>2</td>\n",
|
|
864
|
+
" <td>3</td>\n",
|
|
865
|
+
" </tr>\n",
|
|
866
|
+
" <tr>\n",
|
|
867
|
+
" <th>4</th>\n",
|
|
868
|
+
" <td>B</td>\n",
|
|
869
|
+
" <td>4</td>\n",
|
|
870
|
+
" <td>7</td>\n",
|
|
871
|
+
" </tr>\n",
|
|
872
|
+
" <tr>\n",
|
|
873
|
+
" <th>5</th>\n",
|
|
874
|
+
" <td>C</td>\n",
|
|
875
|
+
" <td>5</td>\n",
|
|
876
|
+
" <td>9</td>\n",
|
|
877
|
+
" </tr>\n",
|
|
878
|
+
" </tbody>\n",
|
|
879
|
+
"</table>\n",
|
|
880
|
+
"</div>"
|
|
881
|
+
],
|
|
882
|
+
"text/plain": [
|
|
883
|
+
" key data1 data2\n",
|
|
884
|
+
"1 B 1 0\n",
|
|
885
|
+
"2 C 2 3\n",
|
|
886
|
+
"4 B 4 7\n",
|
|
887
|
+
"5 C 5 9"
|
|
888
|
+
]
|
|
889
|
+
},
|
|
890
|
+
"execution_count": 28,
|
|
891
|
+
"metadata": {},
|
|
892
|
+
"output_type": "execute_result"
|
|
893
|
+
}
|
|
894
|
+
],
|
|
895
|
+
"source": [
|
|
896
|
+
"df.groupby('key').filter(filter_func)"
|
|
897
|
+
]
|
|
898
|
+
},
|
|
899
|
+
{
|
|
900
|
+
"cell_type": "code",
|
|
901
|
+
"execution_count": 29,
|
|
902
|
+
"id": "6357cbab-c99d-470c-83b3-22a8edcbd7ac",
|
|
903
|
+
"metadata": {},
|
|
904
|
+
"outputs": [
|
|
905
|
+
{
|
|
906
|
+
"data": {
|
|
907
|
+
"text/html": [
|
|
908
|
+
"<div>\n",
|
|
909
|
+
"<style scoped>\n",
|
|
910
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
911
|
+
" vertical-align: middle;\n",
|
|
912
|
+
" }\n",
|
|
913
|
+
"\n",
|
|
914
|
+
" .dataframe tbody tr th {\n",
|
|
915
|
+
" vertical-align: top;\n",
|
|
916
|
+
" }\n",
|
|
917
|
+
"\n",
|
|
918
|
+
" .dataframe thead th {\n",
|
|
919
|
+
" text-align: right;\n",
|
|
920
|
+
" }\n",
|
|
921
|
+
"</style>\n",
|
|
922
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
923
|
+
" <thead>\n",
|
|
924
|
+
" <tr style=\"text-align: right;\">\n",
|
|
925
|
+
" <th></th>\n",
|
|
926
|
+
" <th>data1</th>\n",
|
|
927
|
+
" <th>data2</th>\n",
|
|
928
|
+
" </tr>\n",
|
|
929
|
+
" </thead>\n",
|
|
930
|
+
" <tbody>\n",
|
|
931
|
+
" <tr>\n",
|
|
932
|
+
" <th>0</th>\n",
|
|
933
|
+
" <td>-1.5</td>\n",
|
|
934
|
+
" <td>1.0</td>\n",
|
|
935
|
+
" </tr>\n",
|
|
936
|
+
" <tr>\n",
|
|
937
|
+
" <th>1</th>\n",
|
|
938
|
+
" <td>-1.5</td>\n",
|
|
939
|
+
" <td>-3.5</td>\n",
|
|
940
|
+
" </tr>\n",
|
|
941
|
+
" <tr>\n",
|
|
942
|
+
" <th>2</th>\n",
|
|
943
|
+
" <td>-1.5</td>\n",
|
|
944
|
+
" <td>-3.0</td>\n",
|
|
945
|
+
" </tr>\n",
|
|
946
|
+
" <tr>\n",
|
|
947
|
+
" <th>3</th>\n",
|
|
948
|
+
" <td>1.5</td>\n",
|
|
949
|
+
" <td>-1.0</td>\n",
|
|
950
|
+
" </tr>\n",
|
|
951
|
+
" <tr>\n",
|
|
952
|
+
" <th>4</th>\n",
|
|
953
|
+
" <td>1.5</td>\n",
|
|
954
|
+
" <td>3.5</td>\n",
|
|
955
|
+
" </tr>\n",
|
|
956
|
+
" <tr>\n",
|
|
957
|
+
" <th>5</th>\n",
|
|
958
|
+
" <td>1.5</td>\n",
|
|
959
|
+
" <td>3.0</td>\n",
|
|
960
|
+
" </tr>\n",
|
|
961
|
+
" </tbody>\n",
|
|
962
|
+
"</table>\n",
|
|
963
|
+
"</div>"
|
|
964
|
+
],
|
|
965
|
+
"text/plain": [
|
|
966
|
+
" data1 data2\n",
|
|
967
|
+
"0 -1.5 1.0\n",
|
|
968
|
+
"1 -1.5 -3.5\n",
|
|
969
|
+
"2 -1.5 -3.0\n",
|
|
970
|
+
"3 1.5 -1.0\n",
|
|
971
|
+
"4 1.5 3.5\n",
|
|
972
|
+
"5 1.5 3.0"
|
|
973
|
+
]
|
|
974
|
+
},
|
|
975
|
+
"execution_count": 29,
|
|
976
|
+
"metadata": {},
|
|
977
|
+
"output_type": "execute_result"
|
|
978
|
+
}
|
|
979
|
+
],
|
|
980
|
+
"source": [
|
|
981
|
+
" df.groupby('key').transform(lambda x: x - x.mean())"
|
|
982
|
+
]
|
|
983
|
+
},
|
|
984
|
+
{
|
|
985
|
+
"cell_type": "code",
|
|
986
|
+
"execution_count": 30,
|
|
987
|
+
"id": "eace356a-087d-4376-84ad-70096afc5f8a",
|
|
988
|
+
"metadata": {},
|
|
989
|
+
"outputs": [
|
|
990
|
+
{
|
|
991
|
+
"name": "stdout",
|
|
992
|
+
"output_type": "stream",
|
|
993
|
+
"text": [
|
|
994
|
+
" key data1 data2\n",
|
|
995
|
+
"0 A 0 5\n",
|
|
996
|
+
"1 B 1 0\n",
|
|
997
|
+
"2 C 2 3\n",
|
|
998
|
+
"3 A 3 3\n",
|
|
999
|
+
"4 B 4 7\n",
|
|
1000
|
+
"5 C 5 9\n",
|
|
1001
|
+
" key data1 data2\n",
|
|
1002
|
+
"key \n",
|
|
1003
|
+
"A 0 A 0.000000 5\n",
|
|
1004
|
+
" 3 A 0.375000 3\n",
|
|
1005
|
+
"B 1 B 0.142857 0\n",
|
|
1006
|
+
" 4 B 0.571429 7\n",
|
|
1007
|
+
"C 2 C 0.166667 3\n",
|
|
1008
|
+
" 5 C 0.416667 9\n"
|
|
1009
|
+
]
|
|
1010
|
+
},
|
|
1011
|
+
{
|
|
1012
|
+
"name": "stderr",
|
|
1013
|
+
"output_type": "stream",
|
|
1014
|
+
"text": [
|
|
1015
|
+
"C:\\Users\\darsh\\AppData\\Local\\Temp\\ipykernel_1940\\3133374050.py:6: DeprecationWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.\n",
|
|
1016
|
+
" print(df); print(df.groupby('key').apply(norm_by_data2))\n"
|
|
1017
|
+
]
|
|
1018
|
+
}
|
|
1019
|
+
],
|
|
1020
|
+
"source": [
|
|
1021
|
+
" # The apply() method.\n",
|
|
1022
|
+
" def norm_by_data2(x):\n",
|
|
1023
|
+
" # x is a DataFrame of group values\n",
|
|
1024
|
+
" x['data1'] /= x['data2'].sum()\n",
|
|
1025
|
+
" return x\n",
|
|
1026
|
+
" print(df); print(df.groupby('key').apply(norm_by_data2))"
|
|
1027
|
+
]
|
|
1028
|
+
},
|
|
1029
|
+
{
|
|
1030
|
+
"cell_type": "code",
|
|
1031
|
+
"execution_count": 31,
|
|
1032
|
+
"id": "ba028303-402d-4141-b284-e15df4855ff3",
|
|
1033
|
+
"metadata": {},
|
|
1034
|
+
"outputs": [
|
|
1035
|
+
{
|
|
1036
|
+
"name": "stdout",
|
|
1037
|
+
"output_type": "stream",
|
|
1038
|
+
"text": [
|
|
1039
|
+
" key data1 data2\n",
|
|
1040
|
+
"0 A 0 5\n",
|
|
1041
|
+
"1 B 1 0\n",
|
|
1042
|
+
"2 C 2 3\n",
|
|
1043
|
+
"3 A 3 3\n",
|
|
1044
|
+
"4 B 4 7\n",
|
|
1045
|
+
"5 C 5 9\n",
|
|
1046
|
+
" key data1 data2\n",
|
|
1047
|
+
"0 ACC 7 17\n",
|
|
1048
|
+
"1 BA 4 3\n",
|
|
1049
|
+
"2 B 4 7\n"
|
|
1050
|
+
]
|
|
1051
|
+
}
|
|
1052
|
+
],
|
|
1053
|
+
"source": [
|
|
1054
|
+
"#Specifying the split key\n",
|
|
1055
|
+
"L = [0, 1, 0, 1, 2, 0]\n",
|
|
1056
|
+
"print(df); print(df.groupby(L).sum())"
|
|
1057
|
+
]
|
|
1058
|
+
},
|
|
1059
|
+
{
|
|
1060
|
+
"cell_type": "code",
|
|
1061
|
+
"execution_count": 33,
|
|
1062
|
+
"id": "cd2e7ff6-2aaa-4fe4-9efd-d852e2de7cfd",
|
|
1063
|
+
"metadata": {},
|
|
1064
|
+
"outputs": [
|
|
1065
|
+
{
|
|
1066
|
+
"data": {
|
|
1067
|
+
"text/html": [
|
|
1068
|
+
"<div>\n",
|
|
1069
|
+
"<style scoped>\n",
|
|
1070
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1071
|
+
" vertical-align: middle;\n",
|
|
1072
|
+
" }\n",
|
|
1073
|
+
"\n",
|
|
1074
|
+
" .dataframe tbody tr th {\n",
|
|
1075
|
+
" vertical-align: top;\n",
|
|
1076
|
+
" }\n",
|
|
1077
|
+
"\n",
|
|
1078
|
+
" .dataframe thead th {\n",
|
|
1079
|
+
" text-align: right;\n",
|
|
1080
|
+
" }\n",
|
|
1081
|
+
"</style>\n",
|
|
1082
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1083
|
+
" <thead>\n",
|
|
1084
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1085
|
+
" <th>decade</th>\n",
|
|
1086
|
+
" <th>1980s</th>\n",
|
|
1087
|
+
" <th>1990s</th>\n",
|
|
1088
|
+
" <th>2000s</th>\n",
|
|
1089
|
+
" <th>2010s</th>\n",
|
|
1090
|
+
" </tr>\n",
|
|
1091
|
+
" <tr>\n",
|
|
1092
|
+
" <th>method</th>\n",
|
|
1093
|
+
" <th></th>\n",
|
|
1094
|
+
" <th></th>\n",
|
|
1095
|
+
" <th></th>\n",
|
|
1096
|
+
" <th></th>\n",
|
|
1097
|
+
" </tr>\n",
|
|
1098
|
+
" </thead>\n",
|
|
1099
|
+
" <tbody>\n",
|
|
1100
|
+
" <tr>\n",
|
|
1101
|
+
" <th>Astrometry</th>\n",
|
|
1102
|
+
" <td>0.0</td>\n",
|
|
1103
|
+
" <td>0.0</td>\n",
|
|
1104
|
+
" <td>0.0</td>\n",
|
|
1105
|
+
" <td>2.0</td>\n",
|
|
1106
|
+
" </tr>\n",
|
|
1107
|
+
" <tr>\n",
|
|
1108
|
+
" <th>Eclipse Timing Variations</th>\n",
|
|
1109
|
+
" <td>0.0</td>\n",
|
|
1110
|
+
" <td>0.0</td>\n",
|
|
1111
|
+
" <td>5.0</td>\n",
|
|
1112
|
+
" <td>10.0</td>\n",
|
|
1113
|
+
" </tr>\n",
|
|
1114
|
+
" <tr>\n",
|
|
1115
|
+
" <th>Imaging</th>\n",
|
|
1116
|
+
" <td>0.0</td>\n",
|
|
1117
|
+
" <td>0.0</td>\n",
|
|
1118
|
+
" <td>29.0</td>\n",
|
|
1119
|
+
" <td>21.0</td>\n",
|
|
1120
|
+
" </tr>\n",
|
|
1121
|
+
" <tr>\n",
|
|
1122
|
+
" <th>Microlensing</th>\n",
|
|
1123
|
+
" <td>0.0</td>\n",
|
|
1124
|
+
" <td>0.0</td>\n",
|
|
1125
|
+
" <td>12.0</td>\n",
|
|
1126
|
+
" <td>15.0</td>\n",
|
|
1127
|
+
" </tr>\n",
|
|
1128
|
+
" <tr>\n",
|
|
1129
|
+
" <th>Orbital Brightness Modulation</th>\n",
|
|
1130
|
+
" <td>0.0</td>\n",
|
|
1131
|
+
" <td>0.0</td>\n",
|
|
1132
|
+
" <td>0.0</td>\n",
|
|
1133
|
+
" <td>5.0</td>\n",
|
|
1134
|
+
" </tr>\n",
|
|
1135
|
+
" <tr>\n",
|
|
1136
|
+
" <th>Pulsar Timing</th>\n",
|
|
1137
|
+
" <td>0.0</td>\n",
|
|
1138
|
+
" <td>9.0</td>\n",
|
|
1139
|
+
" <td>1.0</td>\n",
|
|
1140
|
+
" <td>1.0</td>\n",
|
|
1141
|
+
" </tr>\n",
|
|
1142
|
+
" <tr>\n",
|
|
1143
|
+
" <th>Pulsation Timing Variations</th>\n",
|
|
1144
|
+
" <td>0.0</td>\n",
|
|
1145
|
+
" <td>0.0</td>\n",
|
|
1146
|
+
" <td>1.0</td>\n",
|
|
1147
|
+
" <td>0.0</td>\n",
|
|
1148
|
+
" </tr>\n",
|
|
1149
|
+
" <tr>\n",
|
|
1150
|
+
" <th>Radial Velocity</th>\n",
|
|
1151
|
+
" <td>1.0</td>\n",
|
|
1152
|
+
" <td>52.0</td>\n",
|
|
1153
|
+
" <td>475.0</td>\n",
|
|
1154
|
+
" <td>424.0</td>\n",
|
|
1155
|
+
" </tr>\n",
|
|
1156
|
+
" <tr>\n",
|
|
1157
|
+
" <th>Transit</th>\n",
|
|
1158
|
+
" <td>0.0</td>\n",
|
|
1159
|
+
" <td>0.0</td>\n",
|
|
1160
|
+
" <td>64.0</td>\n",
|
|
1161
|
+
" <td>712.0</td>\n",
|
|
1162
|
+
" </tr>\n",
|
|
1163
|
+
" <tr>\n",
|
|
1164
|
+
" <th>Transit Timing Variations</th>\n",
|
|
1165
|
+
" <td>0.0</td>\n",
|
|
1166
|
+
" <td>0.0</td>\n",
|
|
1167
|
+
" <td>0.0</td>\n",
|
|
1168
|
+
" <td>9.0</td>\n",
|
|
1169
|
+
" </tr>\n",
|
|
1170
|
+
" </tbody>\n",
|
|
1171
|
+
"</table>\n",
|
|
1172
|
+
"</div>"
|
|
1173
|
+
],
|
|
1174
|
+
"text/plain": [
|
|
1175
|
+
"decade 1980s 1990s 2000s 2010s\n",
|
|
1176
|
+
"method \n",
|
|
1177
|
+
"Astrometry 0.0 0.0 0.0 2.0\n",
|
|
1178
|
+
"Eclipse Timing Variations 0.0 0.0 5.0 10.0\n",
|
|
1179
|
+
"Imaging 0.0 0.0 29.0 21.0\n",
|
|
1180
|
+
"Microlensing 0.0 0.0 12.0 15.0\n",
|
|
1181
|
+
"Orbital Brightness Modulation 0.0 0.0 0.0 5.0\n",
|
|
1182
|
+
"Pulsar Timing 0.0 9.0 1.0 1.0\n",
|
|
1183
|
+
"Pulsation Timing Variations 0.0 0.0 1.0 0.0\n",
|
|
1184
|
+
"Radial Velocity 1.0 52.0 475.0 424.0\n",
|
|
1185
|
+
"Transit 0.0 0.0 64.0 712.0\n",
|
|
1186
|
+
"Transit Timing Variations 0.0 0.0 0.0 9.0"
|
|
1187
|
+
]
|
|
1188
|
+
},
|
|
1189
|
+
"execution_count": 33,
|
|
1190
|
+
"metadata": {},
|
|
1191
|
+
"output_type": "execute_result"
|
|
1192
|
+
}
|
|
1193
|
+
],
|
|
1194
|
+
"source": [
|
|
1195
|
+
"# Grouping example\n",
|
|
1196
|
+
"decade = 10 * (planets['year'] // 10)\n",
|
|
1197
|
+
"decade = decade.astype(str) + 's'\n",
|
|
1198
|
+
"decade.name = 'decade'\n",
|
|
1199
|
+
"planets.groupby(['method', decade])['number'].sum().unstack().fillna(0)"
|
|
1200
|
+
]
|
|
1201
|
+
},
|
|
1202
|
+
{
|
|
1203
|
+
"cell_type": "code",
|
|
1204
|
+
"execution_count": 34,
|
|
1205
|
+
"id": "68c8eaac-b321-4e5a-bfda-7366061c8ec3",
|
|
1206
|
+
"metadata": {},
|
|
1207
|
+
"outputs": [],
|
|
1208
|
+
"source": [
|
|
1209
|
+
"# Pivot Tables\n",
|
|
1210
|
+
"import numpy as np\n",
|
|
1211
|
+
"import pandas as pd\n",
|
|
1212
|
+
"import seaborn as sns\n",
|
|
1213
|
+
"titanic = sns.load_dataset('titanic')"
|
|
1214
|
+
]
|
|
1215
|
+
},
|
|
1216
|
+
{
|
|
1217
|
+
"cell_type": "code",
|
|
1218
|
+
"execution_count": 35,
|
|
1219
|
+
"id": "fe9c52f9-e461-483f-bfd1-36400787c720",
|
|
1220
|
+
"metadata": {},
|
|
1221
|
+
"outputs": [
|
|
1222
|
+
{
|
|
1223
|
+
"data": {
|
|
1224
|
+
"text/html": [
|
|
1225
|
+
"<div>\n",
|
|
1226
|
+
"<style scoped>\n",
|
|
1227
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1228
|
+
" vertical-align: middle;\n",
|
|
1229
|
+
" }\n",
|
|
1230
|
+
"\n",
|
|
1231
|
+
" .dataframe tbody tr th {\n",
|
|
1232
|
+
" vertical-align: top;\n",
|
|
1233
|
+
" }\n",
|
|
1234
|
+
"\n",
|
|
1235
|
+
" .dataframe thead th {\n",
|
|
1236
|
+
" text-align: right;\n",
|
|
1237
|
+
" }\n",
|
|
1238
|
+
"</style>\n",
|
|
1239
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1240
|
+
" <thead>\n",
|
|
1241
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1242
|
+
" <th></th>\n",
|
|
1243
|
+
" <th>survived</th>\n",
|
|
1244
|
+
" <th>pclass</th>\n",
|
|
1245
|
+
" <th>sex</th>\n",
|
|
1246
|
+
" <th>age</th>\n",
|
|
1247
|
+
" <th>sibsp</th>\n",
|
|
1248
|
+
" <th>parch</th>\n",
|
|
1249
|
+
" <th>fare</th>\n",
|
|
1250
|
+
" <th>embarked</th>\n",
|
|
1251
|
+
" <th>class</th>\n",
|
|
1252
|
+
" <th>who</th>\n",
|
|
1253
|
+
" <th>adult_male</th>\n",
|
|
1254
|
+
" <th>deck</th>\n",
|
|
1255
|
+
" <th>embark_town</th>\n",
|
|
1256
|
+
" <th>alive</th>\n",
|
|
1257
|
+
" <th>alone</th>\n",
|
|
1258
|
+
" </tr>\n",
|
|
1259
|
+
" </thead>\n",
|
|
1260
|
+
" <tbody>\n",
|
|
1261
|
+
" <tr>\n",
|
|
1262
|
+
" <th>0</th>\n",
|
|
1263
|
+
" <td>0</td>\n",
|
|
1264
|
+
" <td>3</td>\n",
|
|
1265
|
+
" <td>male</td>\n",
|
|
1266
|
+
" <td>22.0</td>\n",
|
|
1267
|
+
" <td>1</td>\n",
|
|
1268
|
+
" <td>0</td>\n",
|
|
1269
|
+
" <td>7.2500</td>\n",
|
|
1270
|
+
" <td>S</td>\n",
|
|
1271
|
+
" <td>Third</td>\n",
|
|
1272
|
+
" <td>man</td>\n",
|
|
1273
|
+
" <td>True</td>\n",
|
|
1274
|
+
" <td>NaN</td>\n",
|
|
1275
|
+
" <td>Southampton</td>\n",
|
|
1276
|
+
" <td>no</td>\n",
|
|
1277
|
+
" <td>False</td>\n",
|
|
1278
|
+
" </tr>\n",
|
|
1279
|
+
" <tr>\n",
|
|
1280
|
+
" <th>1</th>\n",
|
|
1281
|
+
" <td>1</td>\n",
|
|
1282
|
+
" <td>1</td>\n",
|
|
1283
|
+
" <td>female</td>\n",
|
|
1284
|
+
" <td>38.0</td>\n",
|
|
1285
|
+
" <td>1</td>\n",
|
|
1286
|
+
" <td>0</td>\n",
|
|
1287
|
+
" <td>71.2833</td>\n",
|
|
1288
|
+
" <td>C</td>\n",
|
|
1289
|
+
" <td>First</td>\n",
|
|
1290
|
+
" <td>woman</td>\n",
|
|
1291
|
+
" <td>False</td>\n",
|
|
1292
|
+
" <td>C</td>\n",
|
|
1293
|
+
" <td>Cherbourg</td>\n",
|
|
1294
|
+
" <td>yes</td>\n",
|
|
1295
|
+
" <td>False</td>\n",
|
|
1296
|
+
" </tr>\n",
|
|
1297
|
+
" <tr>\n",
|
|
1298
|
+
" <th>2</th>\n",
|
|
1299
|
+
" <td>1</td>\n",
|
|
1300
|
+
" <td>3</td>\n",
|
|
1301
|
+
" <td>female</td>\n",
|
|
1302
|
+
" <td>26.0</td>\n",
|
|
1303
|
+
" <td>0</td>\n",
|
|
1304
|
+
" <td>0</td>\n",
|
|
1305
|
+
" <td>7.9250</td>\n",
|
|
1306
|
+
" <td>S</td>\n",
|
|
1307
|
+
" <td>Third</td>\n",
|
|
1308
|
+
" <td>woman</td>\n",
|
|
1309
|
+
" <td>False</td>\n",
|
|
1310
|
+
" <td>NaN</td>\n",
|
|
1311
|
+
" <td>Southampton</td>\n",
|
|
1312
|
+
" <td>yes</td>\n",
|
|
1313
|
+
" <td>True</td>\n",
|
|
1314
|
+
" </tr>\n",
|
|
1315
|
+
" <tr>\n",
|
|
1316
|
+
" <th>3</th>\n",
|
|
1317
|
+
" <td>1</td>\n",
|
|
1318
|
+
" <td>1</td>\n",
|
|
1319
|
+
" <td>female</td>\n",
|
|
1320
|
+
" <td>35.0</td>\n",
|
|
1321
|
+
" <td>1</td>\n",
|
|
1322
|
+
" <td>0</td>\n",
|
|
1323
|
+
" <td>53.1000</td>\n",
|
|
1324
|
+
" <td>S</td>\n",
|
|
1325
|
+
" <td>First</td>\n",
|
|
1326
|
+
" <td>woman</td>\n",
|
|
1327
|
+
" <td>False</td>\n",
|
|
1328
|
+
" <td>C</td>\n",
|
|
1329
|
+
" <td>Southampton</td>\n",
|
|
1330
|
+
" <td>yes</td>\n",
|
|
1331
|
+
" <td>False</td>\n",
|
|
1332
|
+
" </tr>\n",
|
|
1333
|
+
" <tr>\n",
|
|
1334
|
+
" <th>4</th>\n",
|
|
1335
|
+
" <td>0</td>\n",
|
|
1336
|
+
" <td>3</td>\n",
|
|
1337
|
+
" <td>male</td>\n",
|
|
1338
|
+
" <td>35.0</td>\n",
|
|
1339
|
+
" <td>0</td>\n",
|
|
1340
|
+
" <td>0</td>\n",
|
|
1341
|
+
" <td>8.0500</td>\n",
|
|
1342
|
+
" <td>S</td>\n",
|
|
1343
|
+
" <td>Third</td>\n",
|
|
1344
|
+
" <td>man</td>\n",
|
|
1345
|
+
" <td>True</td>\n",
|
|
1346
|
+
" <td>NaN</td>\n",
|
|
1347
|
+
" <td>Southampton</td>\n",
|
|
1348
|
+
" <td>no</td>\n",
|
|
1349
|
+
" <td>True</td>\n",
|
|
1350
|
+
" </tr>\n",
|
|
1351
|
+
" </tbody>\n",
|
|
1352
|
+
"</table>\n",
|
|
1353
|
+
"</div>"
|
|
1354
|
+
],
|
|
1355
|
+
"text/plain": [
|
|
1356
|
+
" survived pclass sex age sibsp parch fare embarked class \\\n",
|
|
1357
|
+
"0 0 3 male 22.0 1 0 7.2500 S Third \n",
|
|
1358
|
+
"1 1 1 female 38.0 1 0 71.2833 C First \n",
|
|
1359
|
+
"2 1 3 female 26.0 0 0 7.9250 S Third \n",
|
|
1360
|
+
"3 1 1 female 35.0 1 0 53.1000 S First \n",
|
|
1361
|
+
"4 0 3 male 35.0 0 0 8.0500 S Third \n",
|
|
1362
|
+
"\n",
|
|
1363
|
+
" who adult_male deck embark_town alive alone \n",
|
|
1364
|
+
"0 man True NaN Southampton no False \n",
|
|
1365
|
+
"1 woman False C Cherbourg yes False \n",
|
|
1366
|
+
"2 woman False NaN Southampton yes True \n",
|
|
1367
|
+
"3 woman False C Southampton yes False \n",
|
|
1368
|
+
"4 man True NaN Southampton no True "
|
|
1369
|
+
]
|
|
1370
|
+
},
|
|
1371
|
+
"execution_count": 35,
|
|
1372
|
+
"metadata": {},
|
|
1373
|
+
"output_type": "execute_result"
|
|
1374
|
+
}
|
|
1375
|
+
],
|
|
1376
|
+
"source": [
|
|
1377
|
+
"titanic.head()"
|
|
1378
|
+
]
|
|
1379
|
+
},
|
|
1380
|
+
{
|
|
1381
|
+
"cell_type": "code",
|
|
1382
|
+
"execution_count": 36,
|
|
1383
|
+
"id": "d9f3b1fc-5125-4058-8448-95f65d8decd6",
|
|
1384
|
+
"metadata": {},
|
|
1385
|
+
"outputs": [
|
|
1386
|
+
{
|
|
1387
|
+
"data": {
|
|
1388
|
+
"text/html": [
|
|
1389
|
+
"<div>\n",
|
|
1390
|
+
"<style scoped>\n",
|
|
1391
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1392
|
+
" vertical-align: middle;\n",
|
|
1393
|
+
" }\n",
|
|
1394
|
+
"\n",
|
|
1395
|
+
" .dataframe tbody tr th {\n",
|
|
1396
|
+
" vertical-align: top;\n",
|
|
1397
|
+
" }\n",
|
|
1398
|
+
"\n",
|
|
1399
|
+
" .dataframe thead th {\n",
|
|
1400
|
+
" text-align: right;\n",
|
|
1401
|
+
" }\n",
|
|
1402
|
+
"</style>\n",
|
|
1403
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1404
|
+
" <thead>\n",
|
|
1405
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1406
|
+
" <th></th>\n",
|
|
1407
|
+
" <th>survived</th>\n",
|
|
1408
|
+
" </tr>\n",
|
|
1409
|
+
" <tr>\n",
|
|
1410
|
+
" <th>sex</th>\n",
|
|
1411
|
+
" <th></th>\n",
|
|
1412
|
+
" </tr>\n",
|
|
1413
|
+
" </thead>\n",
|
|
1414
|
+
" <tbody>\n",
|
|
1415
|
+
" <tr>\n",
|
|
1416
|
+
" <th>female</th>\n",
|
|
1417
|
+
" <td>0.742038</td>\n",
|
|
1418
|
+
" </tr>\n",
|
|
1419
|
+
" <tr>\n",
|
|
1420
|
+
" <th>male</th>\n",
|
|
1421
|
+
" <td>0.188908</td>\n",
|
|
1422
|
+
" </tr>\n",
|
|
1423
|
+
" </tbody>\n",
|
|
1424
|
+
"</table>\n",
|
|
1425
|
+
"</div>"
|
|
1426
|
+
],
|
|
1427
|
+
"text/plain": [
|
|
1428
|
+
" survived\n",
|
|
1429
|
+
"sex \n",
|
|
1430
|
+
"female 0.742038\n",
|
|
1431
|
+
"male 0.188908"
|
|
1432
|
+
]
|
|
1433
|
+
},
|
|
1434
|
+
"execution_count": 36,
|
|
1435
|
+
"metadata": {},
|
|
1436
|
+
"output_type": "execute_result"
|
|
1437
|
+
}
|
|
1438
|
+
],
|
|
1439
|
+
"source": [
|
|
1440
|
+
"titanic.groupby('sex')[['survived']].mean()"
|
|
1441
|
+
]
|
|
1442
|
+
},
|
|
1443
|
+
{
|
|
1444
|
+
"cell_type": "code",
|
|
1445
|
+
"execution_count": 37,
|
|
1446
|
+
"id": "96fc78d1-878a-4418-8b2c-1e6bae80c1f7",
|
|
1447
|
+
"metadata": {},
|
|
1448
|
+
"outputs": [
|
|
1449
|
+
{
|
|
1450
|
+
"name": "stderr",
|
|
1451
|
+
"output_type": "stream",
|
|
1452
|
+
"text": [
|
|
1453
|
+
"C:\\Users\\darsh\\AppData\\Local\\Temp\\ipykernel_1940\\2603839867.py:1: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.\n",
|
|
1454
|
+
" titanic.groupby(['sex', 'class'])['survived'].aggregate('mean').unstack()\n"
|
|
1455
|
+
]
|
|
1456
|
+
},
|
|
1457
|
+
{
|
|
1458
|
+
"data": {
|
|
1459
|
+
"text/html": [
|
|
1460
|
+
"<div>\n",
|
|
1461
|
+
"<style scoped>\n",
|
|
1462
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1463
|
+
" vertical-align: middle;\n",
|
|
1464
|
+
" }\n",
|
|
1465
|
+
"\n",
|
|
1466
|
+
" .dataframe tbody tr th {\n",
|
|
1467
|
+
" vertical-align: top;\n",
|
|
1468
|
+
" }\n",
|
|
1469
|
+
"\n",
|
|
1470
|
+
" .dataframe thead th {\n",
|
|
1471
|
+
" text-align: right;\n",
|
|
1472
|
+
" }\n",
|
|
1473
|
+
"</style>\n",
|
|
1474
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1475
|
+
" <thead>\n",
|
|
1476
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1477
|
+
" <th>class</th>\n",
|
|
1478
|
+
" <th>First</th>\n",
|
|
1479
|
+
" <th>Second</th>\n",
|
|
1480
|
+
" <th>Third</th>\n",
|
|
1481
|
+
" </tr>\n",
|
|
1482
|
+
" <tr>\n",
|
|
1483
|
+
" <th>sex</th>\n",
|
|
1484
|
+
" <th></th>\n",
|
|
1485
|
+
" <th></th>\n",
|
|
1486
|
+
" <th></th>\n",
|
|
1487
|
+
" </tr>\n",
|
|
1488
|
+
" </thead>\n",
|
|
1489
|
+
" <tbody>\n",
|
|
1490
|
+
" <tr>\n",
|
|
1491
|
+
" <th>female</th>\n",
|
|
1492
|
+
" <td>0.968085</td>\n",
|
|
1493
|
+
" <td>0.921053</td>\n",
|
|
1494
|
+
" <td>0.500000</td>\n",
|
|
1495
|
+
" </tr>\n",
|
|
1496
|
+
" <tr>\n",
|
|
1497
|
+
" <th>male</th>\n",
|
|
1498
|
+
" <td>0.368852</td>\n",
|
|
1499
|
+
" <td>0.157407</td>\n",
|
|
1500
|
+
" <td>0.135447</td>\n",
|
|
1501
|
+
" </tr>\n",
|
|
1502
|
+
" </tbody>\n",
|
|
1503
|
+
"</table>\n",
|
|
1504
|
+
"</div>"
|
|
1505
|
+
],
|
|
1506
|
+
"text/plain": [
|
|
1507
|
+
"class First Second Third\n",
|
|
1508
|
+
"sex \n",
|
|
1509
|
+
"female 0.968085 0.921053 0.500000\n",
|
|
1510
|
+
"male 0.368852 0.157407 0.135447"
|
|
1511
|
+
]
|
|
1512
|
+
},
|
|
1513
|
+
"execution_count": 37,
|
|
1514
|
+
"metadata": {},
|
|
1515
|
+
"output_type": "execute_result"
|
|
1516
|
+
}
|
|
1517
|
+
],
|
|
1518
|
+
"source": [
|
|
1519
|
+
"titanic.groupby(['sex', 'class'])['survived'].aggregate('mean').unstack()"
|
|
1520
|
+
]
|
|
1521
|
+
},
|
|
1522
|
+
{
|
|
1523
|
+
"cell_type": "code",
|
|
1524
|
+
"execution_count": 38,
|
|
1525
|
+
"id": "28b5cad3-2411-4cd7-aa24-4a423e03b00b",
|
|
1526
|
+
"metadata": {},
|
|
1527
|
+
"outputs": [
|
|
1528
|
+
{
|
|
1529
|
+
"data": {
|
|
1530
|
+
"text/plain": [
|
|
1531
|
+
"array([ 4, 6, 10, 14, 22, 26])"
|
|
1532
|
+
]
|
|
1533
|
+
},
|
|
1534
|
+
"execution_count": 38,
|
|
1535
|
+
"metadata": {},
|
|
1536
|
+
"output_type": "execute_result"
|
|
1537
|
+
}
|
|
1538
|
+
],
|
|
1539
|
+
"source": [
|
|
1540
|
+
"#Vectorized String Operation\n",
|
|
1541
|
+
"import numpy as np\n",
|
|
1542
|
+
"x = np.array([2, 3, 5, 7, 11, 13])\n",
|
|
1543
|
+
"x * 2"
|
|
1544
|
+
]
|
|
1545
|
+
},
|
|
1546
|
+
{
|
|
1547
|
+
"cell_type": "code",
|
|
1548
|
+
"execution_count": 39,
|
|
1549
|
+
"id": "febdc11c-b284-4b43-a9c0-44001bc9dda3",
|
|
1550
|
+
"metadata": {},
|
|
1551
|
+
"outputs": [
|
|
1552
|
+
{
|
|
1553
|
+
"data": {
|
|
1554
|
+
"text/plain": [
|
|
1555
|
+
"['Peter', 'Paul', 'Mary', 'Guido']"
|
|
1556
|
+
]
|
|
1557
|
+
},
|
|
1558
|
+
"execution_count": 39,
|
|
1559
|
+
"metadata": {},
|
|
1560
|
+
"output_type": "execute_result"
|
|
1561
|
+
}
|
|
1562
|
+
],
|
|
1563
|
+
"source": [
|
|
1564
|
+
"data = ['peter', 'Paul', 'MARY', 'gUIDO']\n",
|
|
1565
|
+
"[s.capitalize() for s in data]"
|
|
1566
|
+
]
|
|
1567
|
+
},
|
|
1568
|
+
{
|
|
1569
|
+
"cell_type": "code",
|
|
1570
|
+
"execution_count": 40,
|
|
1571
|
+
"id": "8d689e1a-ccdc-4916-b665-49cf7b21d02e",
|
|
1572
|
+
"metadata": {},
|
|
1573
|
+
"outputs": [
|
|
1574
|
+
{
|
|
1575
|
+
"ename": "AttributeError",
|
|
1576
|
+
"evalue": "'NoneType' object has no attribute 'capitalize'",
|
|
1577
|
+
"output_type": "error",
|
|
1578
|
+
"traceback": [
|
|
1579
|
+
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
|
1580
|
+
"\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",
|
|
1581
|
+
"Cell \u001b[1;32mIn[40], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m data \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mpeter\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mPaul\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mMARY\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgUIDO\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[1;32m----> 2\u001b[0m [\u001b[43ms\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcapitalize\u001b[49m() \u001b[38;5;28;01mfor\u001b[39;00m s \u001b[38;5;129;01min\u001b[39;00m data]\n",
|
|
1582
|
+
"\u001b[1;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'capitalize'"
|
|
1583
|
+
]
|
|
1584
|
+
}
|
|
1585
|
+
],
|
|
1586
|
+
"source": [
|
|
1587
|
+
"data = ['peter', 'Paul', None, 'MARY', 'gUIDO']\n",
|
|
1588
|
+
"[s.capitalize() for s in data]"
|
|
1589
|
+
]
|
|
1590
|
+
},
|
|
1591
|
+
{
|
|
1592
|
+
"cell_type": "code",
|
|
1593
|
+
"execution_count": 41,
|
|
1594
|
+
"id": "8c2280ab-a3f9-424b-af89-97823534801e",
|
|
1595
|
+
"metadata": {},
|
|
1596
|
+
"outputs": [
|
|
1597
|
+
{
|
|
1598
|
+
"data": {
|
|
1599
|
+
"text/plain": [
|
|
1600
|
+
"0 peter\n",
|
|
1601
|
+
"1 Paul\n",
|
|
1602
|
+
"2 None\n",
|
|
1603
|
+
"3 MARY\n",
|
|
1604
|
+
"4 gUIDO\n",
|
|
1605
|
+
"dtype: object"
|
|
1606
|
+
]
|
|
1607
|
+
},
|
|
1608
|
+
"execution_count": 41,
|
|
1609
|
+
"metadata": {},
|
|
1610
|
+
"output_type": "execute_result"
|
|
1611
|
+
}
|
|
1612
|
+
],
|
|
1613
|
+
"source": [
|
|
1614
|
+
"import pandas as pd\n",
|
|
1615
|
+
"names = pd.Series(data)\n",
|
|
1616
|
+
"names"
|
|
1617
|
+
]
|
|
1618
|
+
},
|
|
1619
|
+
{
|
|
1620
|
+
"cell_type": "code",
|
|
1621
|
+
"execution_count": 42,
|
|
1622
|
+
"id": "c5271eae-68d8-4a39-8b78-e0509e0bdf6a",
|
|
1623
|
+
"metadata": {},
|
|
1624
|
+
"outputs": [
|
|
1625
|
+
{
|
|
1626
|
+
"data": {
|
|
1627
|
+
"text/plain": [
|
|
1628
|
+
"0 Peter\n",
|
|
1629
|
+
"1 Paul\n",
|
|
1630
|
+
"2 None\n",
|
|
1631
|
+
"3 Mary\n",
|
|
1632
|
+
"4 Guido\n",
|
|
1633
|
+
"dtype: object"
|
|
1634
|
+
]
|
|
1635
|
+
},
|
|
1636
|
+
"execution_count": 42,
|
|
1637
|
+
"metadata": {},
|
|
1638
|
+
"output_type": "execute_result"
|
|
1639
|
+
}
|
|
1640
|
+
],
|
|
1641
|
+
"source": [
|
|
1642
|
+
" names.str.capitalize()"
|
|
1643
|
+
]
|
|
1644
|
+
},
|
|
1645
|
+
{
|
|
1646
|
+
"cell_type": "code",
|
|
1647
|
+
"execution_count": 44,
|
|
1648
|
+
"id": "77c5a86f-9cc8-4c2d-9aa2-3901a484c83c",
|
|
1649
|
+
"metadata": {},
|
|
1650
|
+
"outputs": [],
|
|
1651
|
+
"source": [
|
|
1652
|
+
"monte = pd.Series(['Graham Chapman', 'John Cleese', 'Terry Gilliam',\n",
|
|
1653
|
+
" 'Eric Idle', 'Terry Jones', 'Michael Palin'])"
|
|
1654
|
+
]
|
|
1655
|
+
},
|
|
1656
|
+
{
|
|
1657
|
+
"cell_type": "code",
|
|
1658
|
+
"execution_count": 45,
|
|
1659
|
+
"id": "ce34f0ac-171b-4e08-a816-e39e348f2508",
|
|
1660
|
+
"metadata": {},
|
|
1661
|
+
"outputs": [
|
|
1662
|
+
{
|
|
1663
|
+
"data": {
|
|
1664
|
+
"text/plain": [
|
|
1665
|
+
"0 graham chapman\n",
|
|
1666
|
+
"1 john cleese\n",
|
|
1667
|
+
"2 terry gilliam\n",
|
|
1668
|
+
"3 eric idle\n",
|
|
1669
|
+
"4 terry jones\n",
|
|
1670
|
+
"5 michael palin\n",
|
|
1671
|
+
"dtype: object"
|
|
1672
|
+
]
|
|
1673
|
+
},
|
|
1674
|
+
"execution_count": 45,
|
|
1675
|
+
"metadata": {},
|
|
1676
|
+
"output_type": "execute_result"
|
|
1677
|
+
}
|
|
1678
|
+
],
|
|
1679
|
+
"source": [
|
|
1680
|
+
" monte.str.lower()"
|
|
1681
|
+
]
|
|
1682
|
+
},
|
|
1683
|
+
{
|
|
1684
|
+
"cell_type": "code",
|
|
1685
|
+
"execution_count": 46,
|
|
1686
|
+
"id": "b5672c72-c2db-4425-8290-7944ec83c77c",
|
|
1687
|
+
"metadata": {},
|
|
1688
|
+
"outputs": [
|
|
1689
|
+
{
|
|
1690
|
+
"data": {
|
|
1691
|
+
"text/plain": [
|
|
1692
|
+
"0 14\n",
|
|
1693
|
+
"1 11\n",
|
|
1694
|
+
"2 13\n",
|
|
1695
|
+
"3 9\n",
|
|
1696
|
+
"4 11\n",
|
|
1697
|
+
"5 13\n",
|
|
1698
|
+
"dtype: int64"
|
|
1699
|
+
]
|
|
1700
|
+
},
|
|
1701
|
+
"execution_count": 46,
|
|
1702
|
+
"metadata": {},
|
|
1703
|
+
"output_type": "execute_result"
|
|
1704
|
+
}
|
|
1705
|
+
],
|
|
1706
|
+
"source": [
|
|
1707
|
+
" monte.str.len()"
|
|
1708
|
+
]
|
|
1709
|
+
},
|
|
1710
|
+
{
|
|
1711
|
+
"cell_type": "code",
|
|
1712
|
+
"execution_count": 47,
|
|
1713
|
+
"id": "9c99eabc-b0f4-41d7-8de8-fd550a7e5448",
|
|
1714
|
+
"metadata": {},
|
|
1715
|
+
"outputs": [
|
|
1716
|
+
{
|
|
1717
|
+
"data": {
|
|
1718
|
+
"text/plain": [
|
|
1719
|
+
"0 [Graham, Chapman]\n",
|
|
1720
|
+
"1 [John, Cleese]\n",
|
|
1721
|
+
"2 [Terry, Gilliam]\n",
|
|
1722
|
+
"3 [Eric, Idle]\n",
|
|
1723
|
+
"4 [Terry, Jones]\n",
|
|
1724
|
+
"5 [Michael, Palin]\n",
|
|
1725
|
+
"dtype: object"
|
|
1726
|
+
]
|
|
1727
|
+
},
|
|
1728
|
+
"execution_count": 47,
|
|
1729
|
+
"metadata": {},
|
|
1730
|
+
"output_type": "execute_result"
|
|
1731
|
+
}
|
|
1732
|
+
],
|
|
1733
|
+
"source": [
|
|
1734
|
+
" monte.str.split()"
|
|
1735
|
+
]
|
|
1736
|
+
},
|
|
1737
|
+
{
|
|
1738
|
+
"cell_type": "code",
|
|
1739
|
+
"execution_count": 48,
|
|
1740
|
+
"id": "e751ca4c-b6e3-4f50-a09e-10e1d1915eb4",
|
|
1741
|
+
"metadata": {},
|
|
1742
|
+
"outputs": [
|
|
1743
|
+
{
|
|
1744
|
+
"data": {
|
|
1745
|
+
"text/plain": [
|
|
1746
|
+
"0 Gra\n",
|
|
1747
|
+
"1 Joh\n",
|
|
1748
|
+
"2 Ter\n",
|
|
1749
|
+
"3 Eri\n",
|
|
1750
|
+
"4 Ter\n",
|
|
1751
|
+
"5 Mic\n",
|
|
1752
|
+
"dtype: object"
|
|
1753
|
+
]
|
|
1754
|
+
},
|
|
1755
|
+
"execution_count": 48,
|
|
1756
|
+
"metadata": {},
|
|
1757
|
+
"output_type": "execute_result"
|
|
1758
|
+
}
|
|
1759
|
+
],
|
|
1760
|
+
"source": [
|
|
1761
|
+
"#Vectorized item access and slicing\n",
|
|
1762
|
+
"monte.str[0:3]"
|
|
1763
|
+
]
|
|
1764
|
+
},
|
|
1765
|
+
{
|
|
1766
|
+
"cell_type": "code",
|
|
1767
|
+
"execution_count": 49,
|
|
1768
|
+
"id": "6c7d9ce7-e394-4492-8ed5-8f7f3772bd0f",
|
|
1769
|
+
"metadata": {},
|
|
1770
|
+
"outputs": [
|
|
1771
|
+
{
|
|
1772
|
+
"data": {
|
|
1773
|
+
"text/plain": [
|
|
1774
|
+
"0 Chapman\n",
|
|
1775
|
+
"1 Cleese\n",
|
|
1776
|
+
"2 Gilliam\n",
|
|
1777
|
+
"3 Idle\n",
|
|
1778
|
+
"4 Jones\n",
|
|
1779
|
+
"5 Palin\n",
|
|
1780
|
+
"dtype: object"
|
|
1781
|
+
]
|
|
1782
|
+
},
|
|
1783
|
+
"execution_count": 49,
|
|
1784
|
+
"metadata": {},
|
|
1785
|
+
"output_type": "execute_result"
|
|
1786
|
+
}
|
|
1787
|
+
],
|
|
1788
|
+
"source": [
|
|
1789
|
+
"monte.str.split().str.get(-1)"
|
|
1790
|
+
]
|
|
1791
|
+
},
|
|
1792
|
+
{
|
|
1793
|
+
"cell_type": "code",
|
|
1794
|
+
"execution_count": 50,
|
|
1795
|
+
"id": "82f5029b-0cc0-4122-ab88-db298650a5c2",
|
|
1796
|
+
"metadata": {},
|
|
1797
|
+
"outputs": [
|
|
1798
|
+
{
|
|
1799
|
+
"data": {
|
|
1800
|
+
"text/plain": [
|
|
1801
|
+
"datetime.datetime(2015, 7, 4, 0, 0)"
|
|
1802
|
+
]
|
|
1803
|
+
},
|
|
1804
|
+
"execution_count": 50,
|
|
1805
|
+
"metadata": {},
|
|
1806
|
+
"output_type": "execute_result"
|
|
1807
|
+
}
|
|
1808
|
+
],
|
|
1809
|
+
"source": [
|
|
1810
|
+
" # Working with Time Serie\n",
|
|
1811
|
+
"from datetime import datetime\n",
|
|
1812
|
+
"datetime(year=2015, month=7, day=4)"
|
|
1813
|
+
]
|
|
1814
|
+
},
|
|
1815
|
+
{
|
|
1816
|
+
"cell_type": "code",
|
|
1817
|
+
"execution_count": 51,
|
|
1818
|
+
"id": "60d56a09-8fd3-4168-89fb-04970425fee8",
|
|
1819
|
+
"metadata": {},
|
|
1820
|
+
"outputs": [
|
|
1821
|
+
{
|
|
1822
|
+
"data": {
|
|
1823
|
+
"text/plain": [
|
|
1824
|
+
"datetime.datetime(2015, 7, 4, 0, 0)"
|
|
1825
|
+
]
|
|
1826
|
+
},
|
|
1827
|
+
"execution_count": 51,
|
|
1828
|
+
"metadata": {},
|
|
1829
|
+
"output_type": "execute_result"
|
|
1830
|
+
}
|
|
1831
|
+
],
|
|
1832
|
+
"source": [
|
|
1833
|
+
" from dateutil import parser\n",
|
|
1834
|
+
" date = parser.parse(\"4th of July, 2015\")\n",
|
|
1835
|
+
" date"
|
|
1836
|
+
]
|
|
1837
|
+
},
|
|
1838
|
+
{
|
|
1839
|
+
"cell_type": "code",
|
|
1840
|
+
"execution_count": 52,
|
|
1841
|
+
"id": "5eae15bf-1a75-4565-b1d0-2b10cef44d3b",
|
|
1842
|
+
"metadata": {},
|
|
1843
|
+
"outputs": [
|
|
1844
|
+
{
|
|
1845
|
+
"data": {
|
|
1846
|
+
"text/plain": [
|
|
1847
|
+
"'Saturday'"
|
|
1848
|
+
]
|
|
1849
|
+
},
|
|
1850
|
+
"execution_count": 52,
|
|
1851
|
+
"metadata": {},
|
|
1852
|
+
"output_type": "execute_result"
|
|
1853
|
+
}
|
|
1854
|
+
],
|
|
1855
|
+
"source": [
|
|
1856
|
+
"date.strftime('%A')"
|
|
1857
|
+
]
|
|
1858
|
+
},
|
|
1859
|
+
{
|
|
1860
|
+
"cell_type": "code",
|
|
1861
|
+
"execution_count": 54,
|
|
1862
|
+
"id": "d6cc3148-aeb7-447e-83b6-66037aad2b88",
|
|
1863
|
+
"metadata": {},
|
|
1864
|
+
"outputs": [
|
|
1865
|
+
{
|
|
1866
|
+
"data": {
|
|
1867
|
+
"text/plain": [
|
|
1868
|
+
"array('2015-07-04', dtype='datetime64[D]')"
|
|
1869
|
+
]
|
|
1870
|
+
},
|
|
1871
|
+
"execution_count": 54,
|
|
1872
|
+
"metadata": {},
|
|
1873
|
+
"output_type": "execute_result"
|
|
1874
|
+
}
|
|
1875
|
+
],
|
|
1876
|
+
"source": [
|
|
1877
|
+
"import numpy as np\n",
|
|
1878
|
+
"date = np.array('2015-07-04', dtype=np.datetime64)\n",
|
|
1879
|
+
"date"
|
|
1880
|
+
]
|
|
1881
|
+
},
|
|
1882
|
+
{
|
|
1883
|
+
"cell_type": "code",
|
|
1884
|
+
"execution_count": 55,
|
|
1885
|
+
"id": "a504a4a8-5a0a-4c62-8c17-80d6124e657a",
|
|
1886
|
+
"metadata": {},
|
|
1887
|
+
"outputs": [
|
|
1888
|
+
{
|
|
1889
|
+
"data": {
|
|
1890
|
+
"text/plain": [
|
|
1891
|
+
"array(['2015-07-04', '2015-07-05', '2015-07-06', '2015-07-07',\n",
|
|
1892
|
+
" '2015-07-08', '2015-07-09', '2015-07-10', '2015-07-11',\n",
|
|
1893
|
+
" '2015-07-12', '2015-07-13', '2015-07-14', '2015-07-15'],\n",
|
|
1894
|
+
" dtype='datetime64[D]')"
|
|
1895
|
+
]
|
|
1896
|
+
},
|
|
1897
|
+
"execution_count": 55,
|
|
1898
|
+
"metadata": {},
|
|
1899
|
+
"output_type": "execute_result"
|
|
1900
|
+
}
|
|
1901
|
+
],
|
|
1902
|
+
"source": [
|
|
1903
|
+
"date + np.arange(12)"
|
|
1904
|
+
]
|
|
1905
|
+
},
|
|
1906
|
+
{
|
|
1907
|
+
"cell_type": "code",
|
|
1908
|
+
"execution_count": 56,
|
|
1909
|
+
"id": "1d245780-95e0-480c-bfd3-9d1e2a3673c3",
|
|
1910
|
+
"metadata": {},
|
|
1911
|
+
"outputs": [
|
|
1912
|
+
{
|
|
1913
|
+
"data": {
|
|
1914
|
+
"text/plain": [
|
|
1915
|
+
"np.datetime64('2015-07-04')"
|
|
1916
|
+
]
|
|
1917
|
+
},
|
|
1918
|
+
"execution_count": 56,
|
|
1919
|
+
"metadata": {},
|
|
1920
|
+
"output_type": "execute_result"
|
|
1921
|
+
}
|
|
1922
|
+
],
|
|
1923
|
+
"source": [
|
|
1924
|
+
"np.datetime64('2015-07-04')"
|
|
1925
|
+
]
|
|
1926
|
+
},
|
|
1927
|
+
{
|
|
1928
|
+
"cell_type": "code",
|
|
1929
|
+
"execution_count": 57,
|
|
1930
|
+
"id": "3f94ee5e-43c8-4956-b004-3f9a850a9b19",
|
|
1931
|
+
"metadata": {},
|
|
1932
|
+
"outputs": [
|
|
1933
|
+
{
|
|
1934
|
+
"data": {
|
|
1935
|
+
"text/plain": [
|
|
1936
|
+
"np.datetime64('2015-07-04T12:00')"
|
|
1937
|
+
]
|
|
1938
|
+
},
|
|
1939
|
+
"execution_count": 57,
|
|
1940
|
+
"metadata": {},
|
|
1941
|
+
"output_type": "execute_result"
|
|
1942
|
+
}
|
|
1943
|
+
],
|
|
1944
|
+
"source": [
|
|
1945
|
+
"np.datetime64('2015-07-04 12:00')"
|
|
1946
|
+
]
|
|
1947
|
+
},
|
|
1948
|
+
{
|
|
1949
|
+
"cell_type": "code",
|
|
1950
|
+
"execution_count": 58,
|
|
1951
|
+
"id": "e8b9830a-584d-41c6-b387-d8244e3a012e",
|
|
1952
|
+
"metadata": {},
|
|
1953
|
+
"outputs": [
|
|
1954
|
+
{
|
|
1955
|
+
"data": {
|
|
1956
|
+
"text/plain": [
|
|
1957
|
+
"np.datetime64('2015-07-04T12:59:59.500000000')"
|
|
1958
|
+
]
|
|
1959
|
+
},
|
|
1960
|
+
"execution_count": 58,
|
|
1961
|
+
"metadata": {},
|
|
1962
|
+
"output_type": "execute_result"
|
|
1963
|
+
}
|
|
1964
|
+
],
|
|
1965
|
+
"source": [
|
|
1966
|
+
" np.datetime64('2015-07-04 12:59:59.50', 'ns')"
|
|
1967
|
+
]
|
|
1968
|
+
},
|
|
1969
|
+
{
|
|
1970
|
+
"cell_type": "code",
|
|
1971
|
+
"execution_count": null,
|
|
1972
|
+
"id": "d63b7366-07ee-4baf-84a3-295458571d0f",
|
|
1973
|
+
"metadata": {},
|
|
1974
|
+
"outputs": [],
|
|
1975
|
+
"source": []
|
|
1976
|
+
}
|
|
1977
|
+
],
|
|
1978
|
+
"metadata": {
|
|
1979
|
+
"kernelspec": {
|
|
1980
|
+
"display_name": "Python 3 (ipykernel)",
|
|
1981
|
+
"language": "python",
|
|
1982
|
+
"name": "python3"
|
|
1983
|
+
},
|
|
1984
|
+
"language_info": {
|
|
1985
|
+
"codemirror_mode": {
|
|
1986
|
+
"name": "ipython",
|
|
1987
|
+
"version": 3
|
|
1988
|
+
},
|
|
1989
|
+
"file_extension": ".py",
|
|
1990
|
+
"mimetype": "text/x-python",
|
|
1991
|
+
"name": "python",
|
|
1992
|
+
"nbconvert_exporter": "python",
|
|
1993
|
+
"pygments_lexer": "ipython3",
|
|
1994
|
+
"version": "3.12.0"
|
|
1995
|
+
}
|
|
1996
|
+
},
|
|
1997
|
+
"nbformat": 4,
|
|
1998
|
+
"nbformat_minor": 5
|
|
1999
|
+
}
|