myawesomepkg 0.1.5__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/TSAPY1/2(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/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/pract3A-B.py +3212 -0
- {myawesomepkg-0.1.5.dist-info → myawesomepkg-0.1.6.dist-info}/METADATA +1 -1
- {myawesomepkg-0.1.5.dist-info → myawesomepkg-0.1.6.dist-info}/RECORD +19 -4
- {myawesomepkg-0.1.5.dist-info → myawesomepkg-0.1.6.dist-info}/WHEEL +0 -0
- {myawesomepkg-0.1.5.dist-info → myawesomepkg-0.1.6.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,3212 @@
|
|
|
1
|
+
{
|
|
2
|
+
"cells": [
|
|
3
|
+
{
|
|
4
|
+
"cell_type": "code",
|
|
5
|
+
"execution_count": 1,
|
|
6
|
+
"id": "822792da-dbb3-4ec7-a179-480020ac004b",
|
|
7
|
+
"metadata": {},
|
|
8
|
+
"outputs": [],
|
|
9
|
+
"source": [
|
|
10
|
+
"# Missing Data in Pandas\n",
|
|
11
|
+
"import numpy as np\n",
|
|
12
|
+
"import pandas as pd"
|
|
13
|
+
]
|
|
14
|
+
},
|
|
15
|
+
{
|
|
16
|
+
"cell_type": "code",
|
|
17
|
+
"execution_count": 2,
|
|
18
|
+
"id": "a7aebbf3-0776-4371-9775-aaa82496ac2a",
|
|
19
|
+
"metadata": {},
|
|
20
|
+
"outputs": [
|
|
21
|
+
{
|
|
22
|
+
"data": {
|
|
23
|
+
"text/plain": [
|
|
24
|
+
"array([1, None, 3, 4], dtype=object)"
|
|
25
|
+
]
|
|
26
|
+
},
|
|
27
|
+
"execution_count": 2,
|
|
28
|
+
"metadata": {},
|
|
29
|
+
"output_type": "execute_result"
|
|
30
|
+
}
|
|
31
|
+
],
|
|
32
|
+
"source": [
|
|
33
|
+
"vals1 = np.array([1, None, 3, 4])\n",
|
|
34
|
+
"vals1"
|
|
35
|
+
]
|
|
36
|
+
},
|
|
37
|
+
{
|
|
38
|
+
"cell_type": "code",
|
|
39
|
+
"execution_count": 3,
|
|
40
|
+
"id": "42e9d234-98ea-40ef-b808-e149dec83b46",
|
|
41
|
+
"metadata": {},
|
|
42
|
+
"outputs": [
|
|
43
|
+
{
|
|
44
|
+
"data": {
|
|
45
|
+
"text/plain": [
|
|
46
|
+
"0 False\n",
|
|
47
|
+
"1 True\n",
|
|
48
|
+
"2 False\n",
|
|
49
|
+
"3 True\n",
|
|
50
|
+
"dtype: bool"
|
|
51
|
+
]
|
|
52
|
+
},
|
|
53
|
+
"execution_count": 3,
|
|
54
|
+
"metadata": {},
|
|
55
|
+
"output_type": "execute_result"
|
|
56
|
+
}
|
|
57
|
+
],
|
|
58
|
+
"source": [
|
|
59
|
+
"# Detecting null values\n",
|
|
60
|
+
"data = pd.Series([1, np.nan, 'hello', None])\n",
|
|
61
|
+
"data.isnull()"
|
|
62
|
+
]
|
|
63
|
+
},
|
|
64
|
+
{
|
|
65
|
+
"cell_type": "code",
|
|
66
|
+
"execution_count": 4,
|
|
67
|
+
"id": "d6078385-1b04-4c3b-b3c2-1f0cc7219a33",
|
|
68
|
+
"metadata": {},
|
|
69
|
+
"outputs": [
|
|
70
|
+
{
|
|
71
|
+
"data": {
|
|
72
|
+
"text/plain": [
|
|
73
|
+
"0 1\n",
|
|
74
|
+
"2 hello\n",
|
|
75
|
+
"dtype: object"
|
|
76
|
+
]
|
|
77
|
+
},
|
|
78
|
+
"execution_count": 4,
|
|
79
|
+
"metadata": {},
|
|
80
|
+
"output_type": "execute_result"
|
|
81
|
+
}
|
|
82
|
+
],
|
|
83
|
+
"source": [
|
|
84
|
+
"data[data.notnull()]"
|
|
85
|
+
]
|
|
86
|
+
},
|
|
87
|
+
{
|
|
88
|
+
"cell_type": "code",
|
|
89
|
+
"execution_count": 5,
|
|
90
|
+
"id": "26ed180e-d636-4eda-bb6c-6aef597e3189",
|
|
91
|
+
"metadata": {},
|
|
92
|
+
"outputs": [
|
|
93
|
+
{
|
|
94
|
+
"name": "stdout",
|
|
95
|
+
"output_type": "stream",
|
|
96
|
+
"text": [
|
|
97
|
+
"dtype = object\n",
|
|
98
|
+
"120 ms ± 21.6 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n",
|
|
99
|
+
"\n",
|
|
100
|
+
"dtype = int\n",
|
|
101
|
+
"5.37 ms ± 184 μs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n",
|
|
102
|
+
"\n"
|
|
103
|
+
]
|
|
104
|
+
}
|
|
105
|
+
],
|
|
106
|
+
"source": [
|
|
107
|
+
"for dtype in ['object', 'int']:\n",
|
|
108
|
+
" print(\"dtype =\", dtype)\n",
|
|
109
|
+
" %timeit np.arange(1E6, dtype=dtype).sum()\n",
|
|
110
|
+
" print()"
|
|
111
|
+
]
|
|
112
|
+
},
|
|
113
|
+
{
|
|
114
|
+
"cell_type": "code",
|
|
115
|
+
"execution_count": 7,
|
|
116
|
+
"id": "60a94109-d9bc-4781-9ef5-152f458c9133",
|
|
117
|
+
"metadata": {},
|
|
118
|
+
"outputs": [
|
|
119
|
+
{
|
|
120
|
+
"name": "stdout",
|
|
121
|
+
"output_type": "stream",
|
|
122
|
+
"text": [
|
|
123
|
+
"30.0\n"
|
|
124
|
+
]
|
|
125
|
+
}
|
|
126
|
+
],
|
|
127
|
+
"source": [
|
|
128
|
+
"vals1 = np.array([10, 20, np.nan])\n",
|
|
129
|
+
"print(np.nansum(vals1))"
|
|
130
|
+
]
|
|
131
|
+
},
|
|
132
|
+
{
|
|
133
|
+
"cell_type": "code",
|
|
134
|
+
"execution_count": 8,
|
|
135
|
+
"id": "29e48dea-555c-4a3a-b7d1-6af63234b7a9",
|
|
136
|
+
"metadata": {},
|
|
137
|
+
"outputs": [
|
|
138
|
+
{
|
|
139
|
+
"data": {
|
|
140
|
+
"text/plain": [
|
|
141
|
+
"dtype('float64')"
|
|
142
|
+
]
|
|
143
|
+
},
|
|
144
|
+
"execution_count": 8,
|
|
145
|
+
"metadata": {},
|
|
146
|
+
"output_type": "execute_result"
|
|
147
|
+
}
|
|
148
|
+
],
|
|
149
|
+
"source": [
|
|
150
|
+
"vals2 = np.array([1, np.nan, 3, 4])\n",
|
|
151
|
+
"vals2.dtype"
|
|
152
|
+
]
|
|
153
|
+
},
|
|
154
|
+
{
|
|
155
|
+
"cell_type": "code",
|
|
156
|
+
"execution_count": 9,
|
|
157
|
+
"id": "1c9053b8-8790-4bc8-b8f5-7617a1248b5e",
|
|
158
|
+
"metadata": {},
|
|
159
|
+
"outputs": [
|
|
160
|
+
{
|
|
161
|
+
"data": {
|
|
162
|
+
"text/plain": [
|
|
163
|
+
"nan"
|
|
164
|
+
]
|
|
165
|
+
},
|
|
166
|
+
"execution_count": 9,
|
|
167
|
+
"metadata": {},
|
|
168
|
+
"output_type": "execute_result"
|
|
169
|
+
}
|
|
170
|
+
],
|
|
171
|
+
"source": [
|
|
172
|
+
"1 + np.nan"
|
|
173
|
+
]
|
|
174
|
+
},
|
|
175
|
+
{
|
|
176
|
+
"cell_type": "code",
|
|
177
|
+
"execution_count": 10,
|
|
178
|
+
"id": "4d26e974-d2f9-4aef-bf09-0961429ff7e0",
|
|
179
|
+
"metadata": {},
|
|
180
|
+
"outputs": [
|
|
181
|
+
{
|
|
182
|
+
"data": {
|
|
183
|
+
"text/plain": [
|
|
184
|
+
"nan"
|
|
185
|
+
]
|
|
186
|
+
},
|
|
187
|
+
"execution_count": 10,
|
|
188
|
+
"metadata": {},
|
|
189
|
+
"output_type": "execute_result"
|
|
190
|
+
}
|
|
191
|
+
],
|
|
192
|
+
"source": [
|
|
193
|
+
"0 * np.nan"
|
|
194
|
+
]
|
|
195
|
+
},
|
|
196
|
+
{
|
|
197
|
+
"cell_type": "code",
|
|
198
|
+
"execution_count": 11,
|
|
199
|
+
"id": "ad69d303-24af-4718-8a99-2a063abaa8ce",
|
|
200
|
+
"metadata": {},
|
|
201
|
+
"outputs": [
|
|
202
|
+
{
|
|
203
|
+
"data": {
|
|
204
|
+
"text/plain": [
|
|
205
|
+
"(np.float64(nan), np.float64(nan), np.float64(nan))"
|
|
206
|
+
]
|
|
207
|
+
},
|
|
208
|
+
"execution_count": 11,
|
|
209
|
+
"metadata": {},
|
|
210
|
+
"output_type": "execute_result"
|
|
211
|
+
}
|
|
212
|
+
],
|
|
213
|
+
"source": [
|
|
214
|
+
"vals2.sum(), vals2.min(), vals2.max()"
|
|
215
|
+
]
|
|
216
|
+
},
|
|
217
|
+
{
|
|
218
|
+
"cell_type": "code",
|
|
219
|
+
"execution_count": 12,
|
|
220
|
+
"id": "ae143434-f619-46cd-a43e-ff5a7daf2a28",
|
|
221
|
+
"metadata": {},
|
|
222
|
+
"outputs": [
|
|
223
|
+
{
|
|
224
|
+
"data": {
|
|
225
|
+
"text/plain": [
|
|
226
|
+
"(np.float64(8.0), np.float64(1.0), np.float64(4.0))"
|
|
227
|
+
]
|
|
228
|
+
},
|
|
229
|
+
"execution_count": 12,
|
|
230
|
+
"metadata": {},
|
|
231
|
+
"output_type": "execute_result"
|
|
232
|
+
}
|
|
233
|
+
],
|
|
234
|
+
"source": [
|
|
235
|
+
"np.nansum(vals2), np.nanmin(vals2), np.nanmax(vals2)"
|
|
236
|
+
]
|
|
237
|
+
},
|
|
238
|
+
{
|
|
239
|
+
"cell_type": "code",
|
|
240
|
+
"execution_count": 13,
|
|
241
|
+
"id": "8533305f-78e0-4c3a-b122-23be6b5f73b4",
|
|
242
|
+
"metadata": {},
|
|
243
|
+
"outputs": [
|
|
244
|
+
{
|
|
245
|
+
"data": {
|
|
246
|
+
"text/plain": [
|
|
247
|
+
"0 1.0\n",
|
|
248
|
+
"1 NaN\n",
|
|
249
|
+
"2 2.0\n",
|
|
250
|
+
"3 NaN\n",
|
|
251
|
+
"dtype: float64"
|
|
252
|
+
]
|
|
253
|
+
},
|
|
254
|
+
"execution_count": 13,
|
|
255
|
+
"metadata": {},
|
|
256
|
+
"output_type": "execute_result"
|
|
257
|
+
}
|
|
258
|
+
],
|
|
259
|
+
"source": [
|
|
260
|
+
"pd.Series([1, np.nan, 2, None])"
|
|
261
|
+
]
|
|
262
|
+
},
|
|
263
|
+
{
|
|
264
|
+
"cell_type": "code",
|
|
265
|
+
"execution_count": 14,
|
|
266
|
+
"id": "5317b0d7-a933-4b22-81d6-2fa38a853d5d",
|
|
267
|
+
"metadata": {},
|
|
268
|
+
"outputs": [
|
|
269
|
+
{
|
|
270
|
+
"data": {
|
|
271
|
+
"text/plain": [
|
|
272
|
+
"0 0\n",
|
|
273
|
+
"1 1\n",
|
|
274
|
+
"dtype: int64"
|
|
275
|
+
]
|
|
276
|
+
},
|
|
277
|
+
"execution_count": 14,
|
|
278
|
+
"metadata": {},
|
|
279
|
+
"output_type": "execute_result"
|
|
280
|
+
}
|
|
281
|
+
],
|
|
282
|
+
"source": [
|
|
283
|
+
"x = pd.Series(range(2), dtype=int)\n",
|
|
284
|
+
"x"
|
|
285
|
+
]
|
|
286
|
+
},
|
|
287
|
+
{
|
|
288
|
+
"cell_type": "code",
|
|
289
|
+
"execution_count": 15,
|
|
290
|
+
"id": "10c2aa25-109e-4678-9f17-82965c0d8d2d",
|
|
291
|
+
"metadata": {},
|
|
292
|
+
"outputs": [
|
|
293
|
+
{
|
|
294
|
+
"data": {
|
|
295
|
+
"text/plain": [
|
|
296
|
+
"0 NaN\n",
|
|
297
|
+
"1 1.0\n",
|
|
298
|
+
"dtype: float64"
|
|
299
|
+
]
|
|
300
|
+
},
|
|
301
|
+
"execution_count": 15,
|
|
302
|
+
"metadata": {},
|
|
303
|
+
"output_type": "execute_result"
|
|
304
|
+
}
|
|
305
|
+
],
|
|
306
|
+
"source": [
|
|
307
|
+
"x[0] = None\n",
|
|
308
|
+
"x"
|
|
309
|
+
]
|
|
310
|
+
},
|
|
311
|
+
{
|
|
312
|
+
"cell_type": "code",
|
|
313
|
+
"execution_count": 16,
|
|
314
|
+
"id": "97a73881-49ba-445a-b0f2-670a03f9b562",
|
|
315
|
+
"metadata": {},
|
|
316
|
+
"outputs": [
|
|
317
|
+
{
|
|
318
|
+
"data": {
|
|
319
|
+
"text/plain": [
|
|
320
|
+
"0 False\n",
|
|
321
|
+
"1 True\n",
|
|
322
|
+
"2 False\n",
|
|
323
|
+
"3 True\n",
|
|
324
|
+
"dtype: bool"
|
|
325
|
+
]
|
|
326
|
+
},
|
|
327
|
+
"execution_count": 16,
|
|
328
|
+
"metadata": {},
|
|
329
|
+
"output_type": "execute_result"
|
|
330
|
+
}
|
|
331
|
+
],
|
|
332
|
+
"source": [
|
|
333
|
+
"data = pd.Series([1, np.nan, 'hello', None])\n",
|
|
334
|
+
"data.isnull()"
|
|
335
|
+
]
|
|
336
|
+
},
|
|
337
|
+
{
|
|
338
|
+
"cell_type": "code",
|
|
339
|
+
"execution_count": 17,
|
|
340
|
+
"id": "62c1d7ce-93e6-4fb2-acb2-ecc606a3b14d",
|
|
341
|
+
"metadata": {},
|
|
342
|
+
"outputs": [
|
|
343
|
+
{
|
|
344
|
+
"data": {
|
|
345
|
+
"text/plain": [
|
|
346
|
+
"0 1\n",
|
|
347
|
+
"2 hello\n",
|
|
348
|
+
"dtype: object"
|
|
349
|
+
]
|
|
350
|
+
},
|
|
351
|
+
"execution_count": 17,
|
|
352
|
+
"metadata": {},
|
|
353
|
+
"output_type": "execute_result"
|
|
354
|
+
}
|
|
355
|
+
],
|
|
356
|
+
"source": [
|
|
357
|
+
"data[data.notnull()]"
|
|
358
|
+
]
|
|
359
|
+
},
|
|
360
|
+
{
|
|
361
|
+
"cell_type": "code",
|
|
362
|
+
"execution_count": 18,
|
|
363
|
+
"id": "ccdd04f5-7093-4761-97ed-523295ac42f5",
|
|
364
|
+
"metadata": {},
|
|
365
|
+
"outputs": [
|
|
366
|
+
{
|
|
367
|
+
"data": {
|
|
368
|
+
"text/plain": [
|
|
369
|
+
"0 1\n",
|
|
370
|
+
"2 hello\n",
|
|
371
|
+
"dtype: object"
|
|
372
|
+
]
|
|
373
|
+
},
|
|
374
|
+
"execution_count": 18,
|
|
375
|
+
"metadata": {},
|
|
376
|
+
"output_type": "execute_result"
|
|
377
|
+
}
|
|
378
|
+
],
|
|
379
|
+
"source": [
|
|
380
|
+
"data.dropna()"
|
|
381
|
+
]
|
|
382
|
+
},
|
|
383
|
+
{
|
|
384
|
+
"cell_type": "code",
|
|
385
|
+
"execution_count": 19,
|
|
386
|
+
"id": "8411cb90-03c7-4c26-9fe9-d81b996d45cb",
|
|
387
|
+
"metadata": {},
|
|
388
|
+
"outputs": [
|
|
389
|
+
{
|
|
390
|
+
"data": {
|
|
391
|
+
"text/html": [
|
|
392
|
+
"<div>\n",
|
|
393
|
+
"<style scoped>\n",
|
|
394
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
395
|
+
" vertical-align: middle;\n",
|
|
396
|
+
" }\n",
|
|
397
|
+
"\n",
|
|
398
|
+
" .dataframe tbody tr th {\n",
|
|
399
|
+
" vertical-align: top;\n",
|
|
400
|
+
" }\n",
|
|
401
|
+
"\n",
|
|
402
|
+
" .dataframe thead th {\n",
|
|
403
|
+
" text-align: right;\n",
|
|
404
|
+
" }\n",
|
|
405
|
+
"</style>\n",
|
|
406
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
407
|
+
" <thead>\n",
|
|
408
|
+
" <tr style=\"text-align: right;\">\n",
|
|
409
|
+
" <th></th>\n",
|
|
410
|
+
" <th>0</th>\n",
|
|
411
|
+
" <th>1</th>\n",
|
|
412
|
+
" <th>2</th>\n",
|
|
413
|
+
" </tr>\n",
|
|
414
|
+
" </thead>\n",
|
|
415
|
+
" <tbody>\n",
|
|
416
|
+
" <tr>\n",
|
|
417
|
+
" <th>0</th>\n",
|
|
418
|
+
" <td>1.0</td>\n",
|
|
419
|
+
" <td>NaN</td>\n",
|
|
420
|
+
" <td>2</td>\n",
|
|
421
|
+
" </tr>\n",
|
|
422
|
+
" <tr>\n",
|
|
423
|
+
" <th>1</th>\n",
|
|
424
|
+
" <td>2.0</td>\n",
|
|
425
|
+
" <td>3.0</td>\n",
|
|
426
|
+
" <td>5</td>\n",
|
|
427
|
+
" </tr>\n",
|
|
428
|
+
" <tr>\n",
|
|
429
|
+
" <th>2</th>\n",
|
|
430
|
+
" <td>NaN</td>\n",
|
|
431
|
+
" <td>4.0</td>\n",
|
|
432
|
+
" <td>6</td>\n",
|
|
433
|
+
" </tr>\n",
|
|
434
|
+
" </tbody>\n",
|
|
435
|
+
"</table>\n",
|
|
436
|
+
"</div>"
|
|
437
|
+
],
|
|
438
|
+
"text/plain": [
|
|
439
|
+
" 0 1 2\n",
|
|
440
|
+
"0 1.0 NaN 2\n",
|
|
441
|
+
"1 2.0 3.0 5\n",
|
|
442
|
+
"2 NaN 4.0 6"
|
|
443
|
+
]
|
|
444
|
+
},
|
|
445
|
+
"execution_count": 19,
|
|
446
|
+
"metadata": {},
|
|
447
|
+
"output_type": "execute_result"
|
|
448
|
+
}
|
|
449
|
+
],
|
|
450
|
+
"source": [
|
|
451
|
+
"df = pd.DataFrame([[1, np.nan, 2],\n",
|
|
452
|
+
"[2, 3, 5],\n",
|
|
453
|
+
"[np.nan, 4, 6]])\n",
|
|
454
|
+
"df"
|
|
455
|
+
]
|
|
456
|
+
},
|
|
457
|
+
{
|
|
458
|
+
"cell_type": "code",
|
|
459
|
+
"execution_count": 20,
|
|
460
|
+
"id": "db960192-bdc5-4ca1-8b25-d15a75038c09",
|
|
461
|
+
"metadata": {},
|
|
462
|
+
"outputs": [
|
|
463
|
+
{
|
|
464
|
+
"data": {
|
|
465
|
+
"text/html": [
|
|
466
|
+
"<div>\n",
|
|
467
|
+
"<style scoped>\n",
|
|
468
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
469
|
+
" vertical-align: middle;\n",
|
|
470
|
+
" }\n",
|
|
471
|
+
"\n",
|
|
472
|
+
" .dataframe tbody tr th {\n",
|
|
473
|
+
" vertical-align: top;\n",
|
|
474
|
+
" }\n",
|
|
475
|
+
"\n",
|
|
476
|
+
" .dataframe thead th {\n",
|
|
477
|
+
" text-align: right;\n",
|
|
478
|
+
" }\n",
|
|
479
|
+
"</style>\n",
|
|
480
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
481
|
+
" <thead>\n",
|
|
482
|
+
" <tr style=\"text-align: right;\">\n",
|
|
483
|
+
" <th></th>\n",
|
|
484
|
+
" <th>0</th>\n",
|
|
485
|
+
" <th>1</th>\n",
|
|
486
|
+
" <th>2</th>\n",
|
|
487
|
+
" </tr>\n",
|
|
488
|
+
" </thead>\n",
|
|
489
|
+
" <tbody>\n",
|
|
490
|
+
" <tr>\n",
|
|
491
|
+
" <th>1</th>\n",
|
|
492
|
+
" <td>2.0</td>\n",
|
|
493
|
+
" <td>3.0</td>\n",
|
|
494
|
+
" <td>5</td>\n",
|
|
495
|
+
" </tr>\n",
|
|
496
|
+
" </tbody>\n",
|
|
497
|
+
"</table>\n",
|
|
498
|
+
"</div>"
|
|
499
|
+
],
|
|
500
|
+
"text/plain": [
|
|
501
|
+
" 0 1 2\n",
|
|
502
|
+
"1 2.0 3.0 5"
|
|
503
|
+
]
|
|
504
|
+
},
|
|
505
|
+
"execution_count": 20,
|
|
506
|
+
"metadata": {},
|
|
507
|
+
"output_type": "execute_result"
|
|
508
|
+
}
|
|
509
|
+
],
|
|
510
|
+
"source": [
|
|
511
|
+
"df.dropna()"
|
|
512
|
+
]
|
|
513
|
+
},
|
|
514
|
+
{
|
|
515
|
+
"cell_type": "code",
|
|
516
|
+
"execution_count": 21,
|
|
517
|
+
"id": "192591c6-cdf0-4d9b-9974-ecd6313b7a13",
|
|
518
|
+
"metadata": {},
|
|
519
|
+
"outputs": [
|
|
520
|
+
{
|
|
521
|
+
"data": {
|
|
522
|
+
"text/html": [
|
|
523
|
+
"<div>\n",
|
|
524
|
+
"<style scoped>\n",
|
|
525
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
526
|
+
" vertical-align: middle;\n",
|
|
527
|
+
" }\n",
|
|
528
|
+
"\n",
|
|
529
|
+
" .dataframe tbody tr th {\n",
|
|
530
|
+
" vertical-align: top;\n",
|
|
531
|
+
" }\n",
|
|
532
|
+
"\n",
|
|
533
|
+
" .dataframe thead th {\n",
|
|
534
|
+
" text-align: right;\n",
|
|
535
|
+
" }\n",
|
|
536
|
+
"</style>\n",
|
|
537
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
538
|
+
" <thead>\n",
|
|
539
|
+
" <tr style=\"text-align: right;\">\n",
|
|
540
|
+
" <th></th>\n",
|
|
541
|
+
" <th>2</th>\n",
|
|
542
|
+
" </tr>\n",
|
|
543
|
+
" </thead>\n",
|
|
544
|
+
" <tbody>\n",
|
|
545
|
+
" <tr>\n",
|
|
546
|
+
" <th>0</th>\n",
|
|
547
|
+
" <td>2</td>\n",
|
|
548
|
+
" </tr>\n",
|
|
549
|
+
" <tr>\n",
|
|
550
|
+
" <th>1</th>\n",
|
|
551
|
+
" <td>5</td>\n",
|
|
552
|
+
" </tr>\n",
|
|
553
|
+
" <tr>\n",
|
|
554
|
+
" <th>2</th>\n",
|
|
555
|
+
" <td>6</td>\n",
|
|
556
|
+
" </tr>\n",
|
|
557
|
+
" </tbody>\n",
|
|
558
|
+
"</table>\n",
|
|
559
|
+
"</div>"
|
|
560
|
+
],
|
|
561
|
+
"text/plain": [
|
|
562
|
+
" 2\n",
|
|
563
|
+
"0 2\n",
|
|
564
|
+
"1 5\n",
|
|
565
|
+
"2 6"
|
|
566
|
+
]
|
|
567
|
+
},
|
|
568
|
+
"execution_count": 21,
|
|
569
|
+
"metadata": {},
|
|
570
|
+
"output_type": "execute_result"
|
|
571
|
+
}
|
|
572
|
+
],
|
|
573
|
+
"source": [
|
|
574
|
+
"df.dropna(axis='columns')"
|
|
575
|
+
]
|
|
576
|
+
},
|
|
577
|
+
{
|
|
578
|
+
"cell_type": "code",
|
|
579
|
+
"execution_count": 22,
|
|
580
|
+
"id": "7f404f2c-7825-4be1-9df0-6af94dc64127",
|
|
581
|
+
"metadata": {},
|
|
582
|
+
"outputs": [
|
|
583
|
+
{
|
|
584
|
+
"data": {
|
|
585
|
+
"text/html": [
|
|
586
|
+
"<div>\n",
|
|
587
|
+
"<style scoped>\n",
|
|
588
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
589
|
+
" vertical-align: middle;\n",
|
|
590
|
+
" }\n",
|
|
591
|
+
"\n",
|
|
592
|
+
" .dataframe tbody tr th {\n",
|
|
593
|
+
" vertical-align: top;\n",
|
|
594
|
+
" }\n",
|
|
595
|
+
"\n",
|
|
596
|
+
" .dataframe thead th {\n",
|
|
597
|
+
" text-align: right;\n",
|
|
598
|
+
" }\n",
|
|
599
|
+
"</style>\n",
|
|
600
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
601
|
+
" <thead>\n",
|
|
602
|
+
" <tr style=\"text-align: right;\">\n",
|
|
603
|
+
" <th></th>\n",
|
|
604
|
+
" <th>0</th>\n",
|
|
605
|
+
" <th>1</th>\n",
|
|
606
|
+
" <th>2</th>\n",
|
|
607
|
+
" <th>3</th>\n",
|
|
608
|
+
" </tr>\n",
|
|
609
|
+
" </thead>\n",
|
|
610
|
+
" <tbody>\n",
|
|
611
|
+
" <tr>\n",
|
|
612
|
+
" <th>0</th>\n",
|
|
613
|
+
" <td>1.0</td>\n",
|
|
614
|
+
" <td>NaN</td>\n",
|
|
615
|
+
" <td>2</td>\n",
|
|
616
|
+
" <td>NaN</td>\n",
|
|
617
|
+
" </tr>\n",
|
|
618
|
+
" <tr>\n",
|
|
619
|
+
" <th>1</th>\n",
|
|
620
|
+
" <td>2.0</td>\n",
|
|
621
|
+
" <td>3.0</td>\n",
|
|
622
|
+
" <td>5</td>\n",
|
|
623
|
+
" <td>NaN</td>\n",
|
|
624
|
+
" </tr>\n",
|
|
625
|
+
" <tr>\n",
|
|
626
|
+
" <th>2</th>\n",
|
|
627
|
+
" <td>NaN</td>\n",
|
|
628
|
+
" <td>4.0</td>\n",
|
|
629
|
+
" <td>6</td>\n",
|
|
630
|
+
" <td>NaN</td>\n",
|
|
631
|
+
" </tr>\n",
|
|
632
|
+
" </tbody>\n",
|
|
633
|
+
"</table>\n",
|
|
634
|
+
"</div>"
|
|
635
|
+
],
|
|
636
|
+
"text/plain": [
|
|
637
|
+
" 0 1 2 3\n",
|
|
638
|
+
"0 1.0 NaN 2 NaN\n",
|
|
639
|
+
"1 2.0 3.0 5 NaN\n",
|
|
640
|
+
"2 NaN 4.0 6 NaN"
|
|
641
|
+
]
|
|
642
|
+
},
|
|
643
|
+
"execution_count": 22,
|
|
644
|
+
"metadata": {},
|
|
645
|
+
"output_type": "execute_result"
|
|
646
|
+
}
|
|
647
|
+
],
|
|
648
|
+
"source": [
|
|
649
|
+
"df[3] = np.nan\n",
|
|
650
|
+
"df"
|
|
651
|
+
]
|
|
652
|
+
},
|
|
653
|
+
{
|
|
654
|
+
"cell_type": "code",
|
|
655
|
+
"execution_count": 23,
|
|
656
|
+
"id": "bce0355e-bf7a-488b-9b83-7d8d3d6d11d1",
|
|
657
|
+
"metadata": {},
|
|
658
|
+
"outputs": [
|
|
659
|
+
{
|
|
660
|
+
"data": {
|
|
661
|
+
"text/html": [
|
|
662
|
+
"<div>\n",
|
|
663
|
+
"<style scoped>\n",
|
|
664
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
665
|
+
" vertical-align: middle;\n",
|
|
666
|
+
" }\n",
|
|
667
|
+
"\n",
|
|
668
|
+
" .dataframe tbody tr th {\n",
|
|
669
|
+
" vertical-align: top;\n",
|
|
670
|
+
" }\n",
|
|
671
|
+
"\n",
|
|
672
|
+
" .dataframe thead th {\n",
|
|
673
|
+
" text-align: right;\n",
|
|
674
|
+
" }\n",
|
|
675
|
+
"</style>\n",
|
|
676
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
677
|
+
" <thead>\n",
|
|
678
|
+
" <tr style=\"text-align: right;\">\n",
|
|
679
|
+
" <th></th>\n",
|
|
680
|
+
" <th>0</th>\n",
|
|
681
|
+
" <th>1</th>\n",
|
|
682
|
+
" <th>2</th>\n",
|
|
683
|
+
" </tr>\n",
|
|
684
|
+
" </thead>\n",
|
|
685
|
+
" <tbody>\n",
|
|
686
|
+
" <tr>\n",
|
|
687
|
+
" <th>0</th>\n",
|
|
688
|
+
" <td>1.0</td>\n",
|
|
689
|
+
" <td>NaN</td>\n",
|
|
690
|
+
" <td>2</td>\n",
|
|
691
|
+
" </tr>\n",
|
|
692
|
+
" <tr>\n",
|
|
693
|
+
" <th>1</th>\n",
|
|
694
|
+
" <td>2.0</td>\n",
|
|
695
|
+
" <td>3.0</td>\n",
|
|
696
|
+
" <td>5</td>\n",
|
|
697
|
+
" </tr>\n",
|
|
698
|
+
" <tr>\n",
|
|
699
|
+
" <th>2</th>\n",
|
|
700
|
+
" <td>NaN</td>\n",
|
|
701
|
+
" <td>4.0</td>\n",
|
|
702
|
+
" <td>6</td>\n",
|
|
703
|
+
" </tr>\n",
|
|
704
|
+
" </tbody>\n",
|
|
705
|
+
"</table>\n",
|
|
706
|
+
"</div>"
|
|
707
|
+
],
|
|
708
|
+
"text/plain": [
|
|
709
|
+
" 0 1 2\n",
|
|
710
|
+
"0 1.0 NaN 2\n",
|
|
711
|
+
"1 2.0 3.0 5\n",
|
|
712
|
+
"2 NaN 4.0 6"
|
|
713
|
+
]
|
|
714
|
+
},
|
|
715
|
+
"execution_count": 23,
|
|
716
|
+
"metadata": {},
|
|
717
|
+
"output_type": "execute_result"
|
|
718
|
+
}
|
|
719
|
+
],
|
|
720
|
+
"source": [
|
|
721
|
+
"df.dropna(axis='columns', how='all')"
|
|
722
|
+
]
|
|
723
|
+
},
|
|
724
|
+
{
|
|
725
|
+
"cell_type": "code",
|
|
726
|
+
"execution_count": 24,
|
|
727
|
+
"id": "c1c69f9f-84d9-4259-9b82-bf19948374b0",
|
|
728
|
+
"metadata": {},
|
|
729
|
+
"outputs": [
|
|
730
|
+
{
|
|
731
|
+
"data": {
|
|
732
|
+
"text/html": [
|
|
733
|
+
"<div>\n",
|
|
734
|
+
"<style scoped>\n",
|
|
735
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
736
|
+
" vertical-align: middle;\n",
|
|
737
|
+
" }\n",
|
|
738
|
+
"\n",
|
|
739
|
+
" .dataframe tbody tr th {\n",
|
|
740
|
+
" vertical-align: top;\n",
|
|
741
|
+
" }\n",
|
|
742
|
+
"\n",
|
|
743
|
+
" .dataframe thead th {\n",
|
|
744
|
+
" text-align: right;\n",
|
|
745
|
+
" }\n",
|
|
746
|
+
"</style>\n",
|
|
747
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
748
|
+
" <thead>\n",
|
|
749
|
+
" <tr style=\"text-align: right;\">\n",
|
|
750
|
+
" <th></th>\n",
|
|
751
|
+
" <th>0</th>\n",
|
|
752
|
+
" <th>1</th>\n",
|
|
753
|
+
" <th>2</th>\n",
|
|
754
|
+
" <th>3</th>\n",
|
|
755
|
+
" </tr>\n",
|
|
756
|
+
" </thead>\n",
|
|
757
|
+
" <tbody>\n",
|
|
758
|
+
" <tr>\n",
|
|
759
|
+
" <th>1</th>\n",
|
|
760
|
+
" <td>2.0</td>\n",
|
|
761
|
+
" <td>3.0</td>\n",
|
|
762
|
+
" <td>5</td>\n",
|
|
763
|
+
" <td>NaN</td>\n",
|
|
764
|
+
" </tr>\n",
|
|
765
|
+
" </tbody>\n",
|
|
766
|
+
"</table>\n",
|
|
767
|
+
"</div>"
|
|
768
|
+
],
|
|
769
|
+
"text/plain": [
|
|
770
|
+
" 0 1 2 3\n",
|
|
771
|
+
"1 2.0 3.0 5 NaN"
|
|
772
|
+
]
|
|
773
|
+
},
|
|
774
|
+
"execution_count": 24,
|
|
775
|
+
"metadata": {},
|
|
776
|
+
"output_type": "execute_result"
|
|
777
|
+
}
|
|
778
|
+
],
|
|
779
|
+
"source": [
|
|
780
|
+
"df.dropna(axis='rows', thresh=3)\n"
|
|
781
|
+
]
|
|
782
|
+
},
|
|
783
|
+
{
|
|
784
|
+
"cell_type": "code",
|
|
785
|
+
"execution_count": 25,
|
|
786
|
+
"id": "02274d77-117a-4346-b0cd-25a11e195ea1",
|
|
787
|
+
"metadata": {},
|
|
788
|
+
"outputs": [
|
|
789
|
+
{
|
|
790
|
+
"data": {
|
|
791
|
+
"text/plain": [
|
|
792
|
+
"a 1.0\n",
|
|
793
|
+
"b NaN\n",
|
|
794
|
+
"c 2.0\n",
|
|
795
|
+
"d NaN\n",
|
|
796
|
+
"e 3.0\n",
|
|
797
|
+
"dtype: float64"
|
|
798
|
+
]
|
|
799
|
+
},
|
|
800
|
+
"execution_count": 25,
|
|
801
|
+
"metadata": {},
|
|
802
|
+
"output_type": "execute_result"
|
|
803
|
+
}
|
|
804
|
+
],
|
|
805
|
+
"source": [
|
|
806
|
+
"#Filling null values\n",
|
|
807
|
+
"data = pd.Series([1, np.nan, 2, None, 3], index=list('abcde'))\n",
|
|
808
|
+
"data"
|
|
809
|
+
]
|
|
810
|
+
},
|
|
811
|
+
{
|
|
812
|
+
"cell_type": "code",
|
|
813
|
+
"execution_count": 26,
|
|
814
|
+
"id": "ff7c66b4-8886-4d12-82a9-e033e13bf3f9",
|
|
815
|
+
"metadata": {},
|
|
816
|
+
"outputs": [
|
|
817
|
+
{
|
|
818
|
+
"data": {
|
|
819
|
+
"text/plain": [
|
|
820
|
+
"a 1.0\n",
|
|
821
|
+
"b 0.0\n",
|
|
822
|
+
"c 2.0\n",
|
|
823
|
+
"d 0.0\n",
|
|
824
|
+
"e 3.0\n",
|
|
825
|
+
"dtype: float64"
|
|
826
|
+
]
|
|
827
|
+
},
|
|
828
|
+
"execution_count": 26,
|
|
829
|
+
"metadata": {},
|
|
830
|
+
"output_type": "execute_result"
|
|
831
|
+
}
|
|
832
|
+
],
|
|
833
|
+
"source": [
|
|
834
|
+
"data.fillna(0)"
|
|
835
|
+
]
|
|
836
|
+
},
|
|
837
|
+
{
|
|
838
|
+
"cell_type": "code",
|
|
839
|
+
"execution_count": 27,
|
|
840
|
+
"id": "855559ab-1428-4555-a2b0-6818f0e4be25",
|
|
841
|
+
"metadata": {},
|
|
842
|
+
"outputs": [
|
|
843
|
+
{
|
|
844
|
+
"name": "stderr",
|
|
845
|
+
"output_type": "stream",
|
|
846
|
+
"text": [
|
|
847
|
+
"C:\\Users\\darsh\\AppData\\Local\\Temp\\ipykernel_18940\\3316037056.py:2: FutureWarning: Series.fillna with 'method' is deprecated and will raise in a future version. Use obj.ffill() or obj.bfill() instead.\n",
|
|
848
|
+
" data.fillna(method='ffill')\n"
|
|
849
|
+
]
|
|
850
|
+
},
|
|
851
|
+
{
|
|
852
|
+
"data": {
|
|
853
|
+
"text/plain": [
|
|
854
|
+
"a 1.0\n",
|
|
855
|
+
"b 1.0\n",
|
|
856
|
+
"c 2.0\n",
|
|
857
|
+
"d 2.0\n",
|
|
858
|
+
"e 3.0\n",
|
|
859
|
+
"dtype: float64"
|
|
860
|
+
]
|
|
861
|
+
},
|
|
862
|
+
"execution_count": 27,
|
|
863
|
+
"metadata": {},
|
|
864
|
+
"output_type": "execute_result"
|
|
865
|
+
}
|
|
866
|
+
],
|
|
867
|
+
"source": [
|
|
868
|
+
"# forward-fill\n",
|
|
869
|
+
"data.fillna(method='ffill')"
|
|
870
|
+
]
|
|
871
|
+
},
|
|
872
|
+
{
|
|
873
|
+
"cell_type": "code",
|
|
874
|
+
"execution_count": 28,
|
|
875
|
+
"id": "cf65f8ea-cce8-4198-bce6-665ade36070c",
|
|
876
|
+
"metadata": {},
|
|
877
|
+
"outputs": [
|
|
878
|
+
{
|
|
879
|
+
"name": "stderr",
|
|
880
|
+
"output_type": "stream",
|
|
881
|
+
"text": [
|
|
882
|
+
"C:\\Users\\darsh\\AppData\\Local\\Temp\\ipykernel_18940\\2650514875.py:2: FutureWarning: Series.fillna with 'method' is deprecated and will raise in a future version. Use obj.ffill() or obj.bfill() instead.\n",
|
|
883
|
+
" data.fillna(method='bfill')\n"
|
|
884
|
+
]
|
|
885
|
+
},
|
|
886
|
+
{
|
|
887
|
+
"data": {
|
|
888
|
+
"text/plain": [
|
|
889
|
+
"a 1.0\n",
|
|
890
|
+
"b 2.0\n",
|
|
891
|
+
"c 2.0\n",
|
|
892
|
+
"d 3.0\n",
|
|
893
|
+
"e 3.0\n",
|
|
894
|
+
"dtype: float64"
|
|
895
|
+
]
|
|
896
|
+
},
|
|
897
|
+
"execution_count": 28,
|
|
898
|
+
"metadata": {},
|
|
899
|
+
"output_type": "execute_result"
|
|
900
|
+
}
|
|
901
|
+
],
|
|
902
|
+
"source": [
|
|
903
|
+
"# back-fill\n",
|
|
904
|
+
"data.fillna(method='bfill')\n"
|
|
905
|
+
]
|
|
906
|
+
},
|
|
907
|
+
{
|
|
908
|
+
"cell_type": "code",
|
|
909
|
+
"execution_count": 29,
|
|
910
|
+
"id": "242b6c7a-20b1-45ae-bcb4-f898d0f60213",
|
|
911
|
+
"metadata": {},
|
|
912
|
+
"outputs": [
|
|
913
|
+
{
|
|
914
|
+
"data": {
|
|
915
|
+
"text/html": [
|
|
916
|
+
"<div>\n",
|
|
917
|
+
"<style scoped>\n",
|
|
918
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
919
|
+
" vertical-align: middle;\n",
|
|
920
|
+
" }\n",
|
|
921
|
+
"\n",
|
|
922
|
+
" .dataframe tbody tr th {\n",
|
|
923
|
+
" vertical-align: top;\n",
|
|
924
|
+
" }\n",
|
|
925
|
+
"\n",
|
|
926
|
+
" .dataframe thead th {\n",
|
|
927
|
+
" text-align: right;\n",
|
|
928
|
+
" }\n",
|
|
929
|
+
"</style>\n",
|
|
930
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
931
|
+
" <thead>\n",
|
|
932
|
+
" <tr style=\"text-align: right;\">\n",
|
|
933
|
+
" <th></th>\n",
|
|
934
|
+
" <th>0</th>\n",
|
|
935
|
+
" <th>1</th>\n",
|
|
936
|
+
" <th>2</th>\n",
|
|
937
|
+
" <th>3</th>\n",
|
|
938
|
+
" </tr>\n",
|
|
939
|
+
" </thead>\n",
|
|
940
|
+
" <tbody>\n",
|
|
941
|
+
" <tr>\n",
|
|
942
|
+
" <th>0</th>\n",
|
|
943
|
+
" <td>1.0</td>\n",
|
|
944
|
+
" <td>NaN</td>\n",
|
|
945
|
+
" <td>2</td>\n",
|
|
946
|
+
" <td>NaN</td>\n",
|
|
947
|
+
" </tr>\n",
|
|
948
|
+
" <tr>\n",
|
|
949
|
+
" <th>1</th>\n",
|
|
950
|
+
" <td>2.0</td>\n",
|
|
951
|
+
" <td>3.0</td>\n",
|
|
952
|
+
" <td>5</td>\n",
|
|
953
|
+
" <td>NaN</td>\n",
|
|
954
|
+
" </tr>\n",
|
|
955
|
+
" <tr>\n",
|
|
956
|
+
" <th>2</th>\n",
|
|
957
|
+
" <td>NaN</td>\n",
|
|
958
|
+
" <td>4.0</td>\n",
|
|
959
|
+
" <td>6</td>\n",
|
|
960
|
+
" <td>NaN</td>\n",
|
|
961
|
+
" </tr>\n",
|
|
962
|
+
" </tbody>\n",
|
|
963
|
+
"</table>\n",
|
|
964
|
+
"</div>"
|
|
965
|
+
],
|
|
966
|
+
"text/plain": [
|
|
967
|
+
" 0 1 2 3\n",
|
|
968
|
+
"0 1.0 NaN 2 NaN\n",
|
|
969
|
+
"1 2.0 3.0 5 NaN\n",
|
|
970
|
+
"2 NaN 4.0 6 NaN"
|
|
971
|
+
]
|
|
972
|
+
},
|
|
973
|
+
"execution_count": 29,
|
|
974
|
+
"metadata": {},
|
|
975
|
+
"output_type": "execute_result"
|
|
976
|
+
}
|
|
977
|
+
],
|
|
978
|
+
"source": [
|
|
979
|
+
"df"
|
|
980
|
+
]
|
|
981
|
+
},
|
|
982
|
+
{
|
|
983
|
+
"cell_type": "code",
|
|
984
|
+
"execution_count": 30,
|
|
985
|
+
"id": "fab1a27d-5762-4c61-ba7f-57eeb9577b99",
|
|
986
|
+
"metadata": {},
|
|
987
|
+
"outputs": [
|
|
988
|
+
{
|
|
989
|
+
"name": "stderr",
|
|
990
|
+
"output_type": "stream",
|
|
991
|
+
"text": [
|
|
992
|
+
"C:\\Users\\darsh\\AppData\\Local\\Temp\\ipykernel_18940\\3455056665.py:1: FutureWarning: DataFrame.fillna with 'method' is deprecated and will raise in a future version. Use obj.ffill() or obj.bfill() instead.\n",
|
|
993
|
+
" df.fillna(method='ffill', axis=1)\n"
|
|
994
|
+
]
|
|
995
|
+
},
|
|
996
|
+
{
|
|
997
|
+
"data": {
|
|
998
|
+
"text/html": [
|
|
999
|
+
"<div>\n",
|
|
1000
|
+
"<style scoped>\n",
|
|
1001
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1002
|
+
" vertical-align: middle;\n",
|
|
1003
|
+
" }\n",
|
|
1004
|
+
"\n",
|
|
1005
|
+
" .dataframe tbody tr th {\n",
|
|
1006
|
+
" vertical-align: top;\n",
|
|
1007
|
+
" }\n",
|
|
1008
|
+
"\n",
|
|
1009
|
+
" .dataframe thead th {\n",
|
|
1010
|
+
" text-align: right;\n",
|
|
1011
|
+
" }\n",
|
|
1012
|
+
"</style>\n",
|
|
1013
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1014
|
+
" <thead>\n",
|
|
1015
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1016
|
+
" <th></th>\n",
|
|
1017
|
+
" <th>0</th>\n",
|
|
1018
|
+
" <th>1</th>\n",
|
|
1019
|
+
" <th>2</th>\n",
|
|
1020
|
+
" <th>3</th>\n",
|
|
1021
|
+
" </tr>\n",
|
|
1022
|
+
" </thead>\n",
|
|
1023
|
+
" <tbody>\n",
|
|
1024
|
+
" <tr>\n",
|
|
1025
|
+
" <th>0</th>\n",
|
|
1026
|
+
" <td>1.0</td>\n",
|
|
1027
|
+
" <td>1.0</td>\n",
|
|
1028
|
+
" <td>2.0</td>\n",
|
|
1029
|
+
" <td>2.0</td>\n",
|
|
1030
|
+
" </tr>\n",
|
|
1031
|
+
" <tr>\n",
|
|
1032
|
+
" <th>1</th>\n",
|
|
1033
|
+
" <td>2.0</td>\n",
|
|
1034
|
+
" <td>3.0</td>\n",
|
|
1035
|
+
" <td>5.0</td>\n",
|
|
1036
|
+
" <td>5.0</td>\n",
|
|
1037
|
+
" </tr>\n",
|
|
1038
|
+
" <tr>\n",
|
|
1039
|
+
" <th>2</th>\n",
|
|
1040
|
+
" <td>NaN</td>\n",
|
|
1041
|
+
" <td>4.0</td>\n",
|
|
1042
|
+
" <td>6.0</td>\n",
|
|
1043
|
+
" <td>6.0</td>\n",
|
|
1044
|
+
" </tr>\n",
|
|
1045
|
+
" </tbody>\n",
|
|
1046
|
+
"</table>\n",
|
|
1047
|
+
"</div>"
|
|
1048
|
+
],
|
|
1049
|
+
"text/plain": [
|
|
1050
|
+
" 0 1 2 3\n",
|
|
1051
|
+
"0 1.0 1.0 2.0 2.0\n",
|
|
1052
|
+
"1 2.0 3.0 5.0 5.0\n",
|
|
1053
|
+
"2 NaN 4.0 6.0 6.0"
|
|
1054
|
+
]
|
|
1055
|
+
},
|
|
1056
|
+
"execution_count": 30,
|
|
1057
|
+
"metadata": {},
|
|
1058
|
+
"output_type": "execute_result"
|
|
1059
|
+
}
|
|
1060
|
+
],
|
|
1061
|
+
"source": [
|
|
1062
|
+
"\n",
|
|
1063
|
+
"df.fillna(method='ffill', axis=1)"
|
|
1064
|
+
]
|
|
1065
|
+
},
|
|
1066
|
+
{
|
|
1067
|
+
"cell_type": "code",
|
|
1068
|
+
"execution_count": 31,
|
|
1069
|
+
"id": "721bd85e-4b3e-4b34-bcfc-ccc683be017c",
|
|
1070
|
+
"metadata": {},
|
|
1071
|
+
"outputs": [
|
|
1072
|
+
{
|
|
1073
|
+
"data": {
|
|
1074
|
+
"text/plain": [
|
|
1075
|
+
"(California, 2000) 33871648\n",
|
|
1076
|
+
"(California, 2010) 37253956\n",
|
|
1077
|
+
"(New York, 2000) 18976457\n",
|
|
1078
|
+
"(New York, 2010) 19378102\n",
|
|
1079
|
+
"(Texas, 2000) 20851820\n",
|
|
1080
|
+
"(Texas, 2010) 25145561\n",
|
|
1081
|
+
"dtype: int64"
|
|
1082
|
+
]
|
|
1083
|
+
},
|
|
1084
|
+
"execution_count": 31,
|
|
1085
|
+
"metadata": {},
|
|
1086
|
+
"output_type": "execute_result"
|
|
1087
|
+
}
|
|
1088
|
+
],
|
|
1089
|
+
"source": [
|
|
1090
|
+
"import pandas as pd\n",
|
|
1091
|
+
"import numpy as np\n",
|
|
1092
|
+
"index = [('California', 2000), ('California', 2010),\n",
|
|
1093
|
+
"('New York', 2000), ('New York', 2010),\n",
|
|
1094
|
+
"('Texas', 2000), ('Texas', 2010)]\n",
|
|
1095
|
+
"populations = [33871648, 37253956,\n",
|
|
1096
|
+
"18976457, 19378102,\n",
|
|
1097
|
+
"20851820, 25145561]\n",
|
|
1098
|
+
"pop = pd.Series(populations, index=index)\n",
|
|
1099
|
+
"pop"
|
|
1100
|
+
]
|
|
1101
|
+
},
|
|
1102
|
+
{
|
|
1103
|
+
"cell_type": "code",
|
|
1104
|
+
"execution_count": 32,
|
|
1105
|
+
"id": "cd4522c5-a2de-473a-a2e0-509485b3941a",
|
|
1106
|
+
"metadata": {},
|
|
1107
|
+
"outputs": [
|
|
1108
|
+
{
|
|
1109
|
+
"data": {
|
|
1110
|
+
"text/plain": [
|
|
1111
|
+
"(California, 2010) 37253956\n",
|
|
1112
|
+
"(New York, 2000) 18976457\n",
|
|
1113
|
+
"(New York, 2010) 19378102\n",
|
|
1114
|
+
"(Texas, 2000) 20851820\n",
|
|
1115
|
+
"dtype: int64"
|
|
1116
|
+
]
|
|
1117
|
+
},
|
|
1118
|
+
"execution_count": 32,
|
|
1119
|
+
"metadata": {},
|
|
1120
|
+
"output_type": "execute_result"
|
|
1121
|
+
}
|
|
1122
|
+
],
|
|
1123
|
+
"source": [
|
|
1124
|
+
"pop[('California', 2010):('Texas', 2000)]"
|
|
1125
|
+
]
|
|
1126
|
+
},
|
|
1127
|
+
{
|
|
1128
|
+
"cell_type": "code",
|
|
1129
|
+
"execution_count": 33,
|
|
1130
|
+
"id": "f42bb21b-6345-4084-a210-fa6464c084a4",
|
|
1131
|
+
"metadata": {},
|
|
1132
|
+
"outputs": [
|
|
1133
|
+
{
|
|
1134
|
+
"data": {
|
|
1135
|
+
"text/plain": [
|
|
1136
|
+
"MultiIndex([('California', 2000),\n",
|
|
1137
|
+
" ('California', 2010),\n",
|
|
1138
|
+
" ( 'New York', 2000),\n",
|
|
1139
|
+
" ( 'New York', 2010),\n",
|
|
1140
|
+
" ( 'Texas', 2000),\n",
|
|
1141
|
+
" ( 'Texas', 2010)],\n",
|
|
1142
|
+
" )"
|
|
1143
|
+
]
|
|
1144
|
+
},
|
|
1145
|
+
"execution_count": 33,
|
|
1146
|
+
"metadata": {},
|
|
1147
|
+
"output_type": "execute_result"
|
|
1148
|
+
}
|
|
1149
|
+
],
|
|
1150
|
+
"source": [
|
|
1151
|
+
"index = pd.MultiIndex.from_tuples(index)\n",
|
|
1152
|
+
"index"
|
|
1153
|
+
]
|
|
1154
|
+
},
|
|
1155
|
+
{
|
|
1156
|
+
"cell_type": "code",
|
|
1157
|
+
"execution_count": 34,
|
|
1158
|
+
"id": "e1129e15-b746-4822-8f82-e95c1943fef5",
|
|
1159
|
+
"metadata": {},
|
|
1160
|
+
"outputs": [
|
|
1161
|
+
{
|
|
1162
|
+
"data": {
|
|
1163
|
+
"text/plain": [
|
|
1164
|
+
"California 2000 33871648\n",
|
|
1165
|
+
" 2010 37253956\n",
|
|
1166
|
+
"New York 2000 18976457\n",
|
|
1167
|
+
" 2010 19378102\n",
|
|
1168
|
+
"Texas 2000 20851820\n",
|
|
1169
|
+
" 2010 25145561\n",
|
|
1170
|
+
"dtype: int64"
|
|
1171
|
+
]
|
|
1172
|
+
},
|
|
1173
|
+
"execution_count": 34,
|
|
1174
|
+
"metadata": {},
|
|
1175
|
+
"output_type": "execute_result"
|
|
1176
|
+
}
|
|
1177
|
+
],
|
|
1178
|
+
"source": [
|
|
1179
|
+
"pop = pop.reindex(index)\n",
|
|
1180
|
+
"pop"
|
|
1181
|
+
]
|
|
1182
|
+
},
|
|
1183
|
+
{
|
|
1184
|
+
"cell_type": "code",
|
|
1185
|
+
"execution_count": 35,
|
|
1186
|
+
"id": "c8e3ab93-a611-48de-b950-517b9b3af9ed",
|
|
1187
|
+
"metadata": {},
|
|
1188
|
+
"outputs": [
|
|
1189
|
+
{
|
|
1190
|
+
"data": {
|
|
1191
|
+
"text/plain": [
|
|
1192
|
+
"California 37253956\n",
|
|
1193
|
+
"New York 19378102\n",
|
|
1194
|
+
"Texas 25145561\n",
|
|
1195
|
+
"dtype: int64"
|
|
1196
|
+
]
|
|
1197
|
+
},
|
|
1198
|
+
"execution_count": 35,
|
|
1199
|
+
"metadata": {},
|
|
1200
|
+
"output_type": "execute_result"
|
|
1201
|
+
}
|
|
1202
|
+
],
|
|
1203
|
+
"source": [
|
|
1204
|
+
"pop[:, 2010]"
|
|
1205
|
+
]
|
|
1206
|
+
},
|
|
1207
|
+
{
|
|
1208
|
+
"cell_type": "code",
|
|
1209
|
+
"execution_count": 36,
|
|
1210
|
+
"id": "cd13cdf1-25f0-4663-833a-210d91a985db",
|
|
1211
|
+
"metadata": {},
|
|
1212
|
+
"outputs": [
|
|
1213
|
+
{
|
|
1214
|
+
"data": {
|
|
1215
|
+
"text/html": [
|
|
1216
|
+
"<div>\n",
|
|
1217
|
+
"<style scoped>\n",
|
|
1218
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1219
|
+
" vertical-align: middle;\n",
|
|
1220
|
+
" }\n",
|
|
1221
|
+
"\n",
|
|
1222
|
+
" .dataframe tbody tr th {\n",
|
|
1223
|
+
" vertical-align: top;\n",
|
|
1224
|
+
" }\n",
|
|
1225
|
+
"\n",
|
|
1226
|
+
" .dataframe thead th {\n",
|
|
1227
|
+
" text-align: right;\n",
|
|
1228
|
+
" }\n",
|
|
1229
|
+
"</style>\n",
|
|
1230
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1231
|
+
" <thead>\n",
|
|
1232
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1233
|
+
" <th></th>\n",
|
|
1234
|
+
" <th>2000</th>\n",
|
|
1235
|
+
" <th>2010</th>\n",
|
|
1236
|
+
" </tr>\n",
|
|
1237
|
+
" </thead>\n",
|
|
1238
|
+
" <tbody>\n",
|
|
1239
|
+
" <tr>\n",
|
|
1240
|
+
" <th>California</th>\n",
|
|
1241
|
+
" <td>33871648</td>\n",
|
|
1242
|
+
" <td>37253956</td>\n",
|
|
1243
|
+
" </tr>\n",
|
|
1244
|
+
" <tr>\n",
|
|
1245
|
+
" <th>New York</th>\n",
|
|
1246
|
+
" <td>18976457</td>\n",
|
|
1247
|
+
" <td>19378102</td>\n",
|
|
1248
|
+
" </tr>\n",
|
|
1249
|
+
" <tr>\n",
|
|
1250
|
+
" <th>Texas</th>\n",
|
|
1251
|
+
" <td>20851820</td>\n",
|
|
1252
|
+
" <td>25145561</td>\n",
|
|
1253
|
+
" </tr>\n",
|
|
1254
|
+
" </tbody>\n",
|
|
1255
|
+
"</table>\n",
|
|
1256
|
+
"</div>"
|
|
1257
|
+
],
|
|
1258
|
+
"text/plain": [
|
|
1259
|
+
" 2000 2010\n",
|
|
1260
|
+
"California 33871648 37253956\n",
|
|
1261
|
+
"New York 18976457 19378102\n",
|
|
1262
|
+
"Texas 20851820 25145561"
|
|
1263
|
+
]
|
|
1264
|
+
},
|
|
1265
|
+
"execution_count": 36,
|
|
1266
|
+
"metadata": {},
|
|
1267
|
+
"output_type": "execute_result"
|
|
1268
|
+
}
|
|
1269
|
+
],
|
|
1270
|
+
"source": [
|
|
1271
|
+
"pop_df = pop.unstack()\n",
|
|
1272
|
+
"pop_df"
|
|
1273
|
+
]
|
|
1274
|
+
},
|
|
1275
|
+
{
|
|
1276
|
+
"cell_type": "code",
|
|
1277
|
+
"execution_count": 37,
|
|
1278
|
+
"id": "9155ecaf-2a85-4731-8f71-0353eb83a3fb",
|
|
1279
|
+
"metadata": {},
|
|
1280
|
+
"outputs": [
|
|
1281
|
+
{
|
|
1282
|
+
"data": {
|
|
1283
|
+
"text/plain": [
|
|
1284
|
+
"California 2000 33871648\n",
|
|
1285
|
+
" 2010 37253956\n",
|
|
1286
|
+
"New York 2000 18976457\n",
|
|
1287
|
+
" 2010 19378102\n",
|
|
1288
|
+
"Texas 2000 20851820\n",
|
|
1289
|
+
" 2010 25145561\n",
|
|
1290
|
+
"dtype: int64"
|
|
1291
|
+
]
|
|
1292
|
+
},
|
|
1293
|
+
"execution_count": 37,
|
|
1294
|
+
"metadata": {},
|
|
1295
|
+
"output_type": "execute_result"
|
|
1296
|
+
}
|
|
1297
|
+
],
|
|
1298
|
+
"source": [
|
|
1299
|
+
"pop_df.stack()"
|
|
1300
|
+
]
|
|
1301
|
+
},
|
|
1302
|
+
{
|
|
1303
|
+
"cell_type": "code",
|
|
1304
|
+
"execution_count": 38,
|
|
1305
|
+
"id": "6be0213d-b75a-49fc-846b-082cf43be9e9",
|
|
1306
|
+
"metadata": {},
|
|
1307
|
+
"outputs": [
|
|
1308
|
+
{
|
|
1309
|
+
"data": {
|
|
1310
|
+
"text/html": [
|
|
1311
|
+
"<div>\n",
|
|
1312
|
+
"<style scoped>\n",
|
|
1313
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1314
|
+
" vertical-align: middle;\n",
|
|
1315
|
+
" }\n",
|
|
1316
|
+
"\n",
|
|
1317
|
+
" .dataframe tbody tr th {\n",
|
|
1318
|
+
" vertical-align: top;\n",
|
|
1319
|
+
" }\n",
|
|
1320
|
+
"\n",
|
|
1321
|
+
" .dataframe thead th {\n",
|
|
1322
|
+
" text-align: right;\n",
|
|
1323
|
+
" }\n",
|
|
1324
|
+
"</style>\n",
|
|
1325
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1326
|
+
" <thead>\n",
|
|
1327
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1328
|
+
" <th></th>\n",
|
|
1329
|
+
" <th></th>\n",
|
|
1330
|
+
" <th>total</th>\n",
|
|
1331
|
+
" <th>under18</th>\n",
|
|
1332
|
+
" </tr>\n",
|
|
1333
|
+
" </thead>\n",
|
|
1334
|
+
" <tbody>\n",
|
|
1335
|
+
" <tr>\n",
|
|
1336
|
+
" <th rowspan=\"2\" valign=\"top\">California</th>\n",
|
|
1337
|
+
" <th>2000</th>\n",
|
|
1338
|
+
" <td>33871648</td>\n",
|
|
1339
|
+
" <td>9267089</td>\n",
|
|
1340
|
+
" </tr>\n",
|
|
1341
|
+
" <tr>\n",
|
|
1342
|
+
" <th>2010</th>\n",
|
|
1343
|
+
" <td>37253956</td>\n",
|
|
1344
|
+
" <td>9284094</td>\n",
|
|
1345
|
+
" </tr>\n",
|
|
1346
|
+
" <tr>\n",
|
|
1347
|
+
" <th rowspan=\"2\" valign=\"top\">New York</th>\n",
|
|
1348
|
+
" <th>2000</th>\n",
|
|
1349
|
+
" <td>18976457</td>\n",
|
|
1350
|
+
" <td>4687374</td>\n",
|
|
1351
|
+
" </tr>\n",
|
|
1352
|
+
" <tr>\n",
|
|
1353
|
+
" <th>2010</th>\n",
|
|
1354
|
+
" <td>19378102</td>\n",
|
|
1355
|
+
" <td>4318033</td>\n",
|
|
1356
|
+
" </tr>\n",
|
|
1357
|
+
" <tr>\n",
|
|
1358
|
+
" <th rowspan=\"2\" valign=\"top\">Texas</th>\n",
|
|
1359
|
+
" <th>2000</th>\n",
|
|
1360
|
+
" <td>20851820</td>\n",
|
|
1361
|
+
" <td>5906301</td>\n",
|
|
1362
|
+
" </tr>\n",
|
|
1363
|
+
" <tr>\n",
|
|
1364
|
+
" <th>2010</th>\n",
|
|
1365
|
+
" <td>25145561</td>\n",
|
|
1366
|
+
" <td>6879014</td>\n",
|
|
1367
|
+
" </tr>\n",
|
|
1368
|
+
" </tbody>\n",
|
|
1369
|
+
"</table>\n",
|
|
1370
|
+
"</div>"
|
|
1371
|
+
],
|
|
1372
|
+
"text/plain": [
|
|
1373
|
+
" total under18\n",
|
|
1374
|
+
"California 2000 33871648 9267089\n",
|
|
1375
|
+
" 2010 37253956 9284094\n",
|
|
1376
|
+
"New York 2000 18976457 4687374\n",
|
|
1377
|
+
" 2010 19378102 4318033\n",
|
|
1378
|
+
"Texas 2000 20851820 5906301\n",
|
|
1379
|
+
" 2010 25145561 6879014"
|
|
1380
|
+
]
|
|
1381
|
+
},
|
|
1382
|
+
"execution_count": 38,
|
|
1383
|
+
"metadata": {},
|
|
1384
|
+
"output_type": "execute_result"
|
|
1385
|
+
}
|
|
1386
|
+
],
|
|
1387
|
+
"source": [
|
|
1388
|
+
"pop_df = pd.DataFrame({'total': pop,\n",
|
|
1389
|
+
"'under18': [9267089, 9284094,\n",
|
|
1390
|
+
"4687374, 4318033,\n",
|
|
1391
|
+
"5906301, 6879014]})\n",
|
|
1392
|
+
"pop_df"
|
|
1393
|
+
]
|
|
1394
|
+
},
|
|
1395
|
+
{
|
|
1396
|
+
"cell_type": "code",
|
|
1397
|
+
"execution_count": 39,
|
|
1398
|
+
"id": "37df56a1-bbb4-46aa-8508-e32a3e65304a",
|
|
1399
|
+
"metadata": {},
|
|
1400
|
+
"outputs": [
|
|
1401
|
+
{
|
|
1402
|
+
"data": {
|
|
1403
|
+
"text/html": [
|
|
1404
|
+
"<div>\n",
|
|
1405
|
+
"<style scoped>\n",
|
|
1406
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1407
|
+
" vertical-align: middle;\n",
|
|
1408
|
+
" }\n",
|
|
1409
|
+
"\n",
|
|
1410
|
+
" .dataframe tbody tr th {\n",
|
|
1411
|
+
" vertical-align: top;\n",
|
|
1412
|
+
" }\n",
|
|
1413
|
+
"\n",
|
|
1414
|
+
" .dataframe thead th {\n",
|
|
1415
|
+
" text-align: right;\n",
|
|
1416
|
+
" }\n",
|
|
1417
|
+
"</style>\n",
|
|
1418
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1419
|
+
" <thead>\n",
|
|
1420
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1421
|
+
" <th></th>\n",
|
|
1422
|
+
" <th>2000</th>\n",
|
|
1423
|
+
" <th>2010</th>\n",
|
|
1424
|
+
" </tr>\n",
|
|
1425
|
+
" </thead>\n",
|
|
1426
|
+
" <tbody>\n",
|
|
1427
|
+
" <tr>\n",
|
|
1428
|
+
" <th>California</th>\n",
|
|
1429
|
+
" <td>0.273594</td>\n",
|
|
1430
|
+
" <td>0.249211</td>\n",
|
|
1431
|
+
" </tr>\n",
|
|
1432
|
+
" <tr>\n",
|
|
1433
|
+
" <th>New York</th>\n",
|
|
1434
|
+
" <td>0.247010</td>\n",
|
|
1435
|
+
" <td>0.222831</td>\n",
|
|
1436
|
+
" </tr>\n",
|
|
1437
|
+
" <tr>\n",
|
|
1438
|
+
" <th>Texas</th>\n",
|
|
1439
|
+
" <td>0.283251</td>\n",
|
|
1440
|
+
" <td>0.273568</td>\n",
|
|
1441
|
+
" </tr>\n",
|
|
1442
|
+
" </tbody>\n",
|
|
1443
|
+
"</table>\n",
|
|
1444
|
+
"</div>"
|
|
1445
|
+
],
|
|
1446
|
+
"text/plain": [
|
|
1447
|
+
" 2000 2010\n",
|
|
1448
|
+
"California 0.273594 0.249211\n",
|
|
1449
|
+
"New York 0.247010 0.222831\n",
|
|
1450
|
+
"Texas 0.283251 0.273568"
|
|
1451
|
+
]
|
|
1452
|
+
},
|
|
1453
|
+
"execution_count": 39,
|
|
1454
|
+
"metadata": {},
|
|
1455
|
+
"output_type": "execute_result"
|
|
1456
|
+
}
|
|
1457
|
+
],
|
|
1458
|
+
"source": [
|
|
1459
|
+
"f_u18 = pop_df['under18'] / pop_df['total']\n",
|
|
1460
|
+
"f_u18.unstack()"
|
|
1461
|
+
]
|
|
1462
|
+
},
|
|
1463
|
+
{
|
|
1464
|
+
"cell_type": "code",
|
|
1465
|
+
"execution_count": 40,
|
|
1466
|
+
"id": "84c056c9-db9d-4f1c-bbe9-73770c491c33",
|
|
1467
|
+
"metadata": {},
|
|
1468
|
+
"outputs": [
|
|
1469
|
+
{
|
|
1470
|
+
"data": {
|
|
1471
|
+
"text/html": [
|
|
1472
|
+
"<div>\n",
|
|
1473
|
+
"<style scoped>\n",
|
|
1474
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1475
|
+
" vertical-align: middle;\n",
|
|
1476
|
+
" }\n",
|
|
1477
|
+
"\n",
|
|
1478
|
+
" .dataframe tbody tr th {\n",
|
|
1479
|
+
" vertical-align: top;\n",
|
|
1480
|
+
" }\n",
|
|
1481
|
+
"\n",
|
|
1482
|
+
" .dataframe thead th {\n",
|
|
1483
|
+
" text-align: right;\n",
|
|
1484
|
+
" }\n",
|
|
1485
|
+
"</style>\n",
|
|
1486
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1487
|
+
" <thead>\n",
|
|
1488
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1489
|
+
" <th></th>\n",
|
|
1490
|
+
" <th></th>\n",
|
|
1491
|
+
" <th>data1</th>\n",
|
|
1492
|
+
" <th>data2</th>\n",
|
|
1493
|
+
" </tr>\n",
|
|
1494
|
+
" </thead>\n",
|
|
1495
|
+
" <tbody>\n",
|
|
1496
|
+
" <tr>\n",
|
|
1497
|
+
" <th rowspan=\"2\" valign=\"top\">a</th>\n",
|
|
1498
|
+
" <th>1</th>\n",
|
|
1499
|
+
" <td>0.478627</td>\n",
|
|
1500
|
+
" <td>0.628762</td>\n",
|
|
1501
|
+
" </tr>\n",
|
|
1502
|
+
" <tr>\n",
|
|
1503
|
+
" <th>2</th>\n",
|
|
1504
|
+
" <td>0.327155</td>\n",
|
|
1505
|
+
" <td>0.747383</td>\n",
|
|
1506
|
+
" </tr>\n",
|
|
1507
|
+
" <tr>\n",
|
|
1508
|
+
" <th rowspan=\"2\" valign=\"top\">b</th>\n",
|
|
1509
|
+
" <th>1</th>\n",
|
|
1510
|
+
" <td>0.997522</td>\n",
|
|
1511
|
+
" <td>0.443755</td>\n",
|
|
1512
|
+
" </tr>\n",
|
|
1513
|
+
" <tr>\n",
|
|
1514
|
+
" <th>2</th>\n",
|
|
1515
|
+
" <td>0.428418</td>\n",
|
|
1516
|
+
" <td>0.415810</td>\n",
|
|
1517
|
+
" </tr>\n",
|
|
1518
|
+
" </tbody>\n",
|
|
1519
|
+
"</table>\n",
|
|
1520
|
+
"</div>"
|
|
1521
|
+
],
|
|
1522
|
+
"text/plain": [
|
|
1523
|
+
" data1 data2\n",
|
|
1524
|
+
"a 1 0.478627 0.628762\n",
|
|
1525
|
+
" 2 0.327155 0.747383\n",
|
|
1526
|
+
"b 1 0.997522 0.443755\n",
|
|
1527
|
+
" 2 0.428418 0.415810"
|
|
1528
|
+
]
|
|
1529
|
+
},
|
|
1530
|
+
"execution_count": 40,
|
|
1531
|
+
"metadata": {},
|
|
1532
|
+
"output_type": "execute_result"
|
|
1533
|
+
}
|
|
1534
|
+
],
|
|
1535
|
+
"source": [
|
|
1536
|
+
"df = pd.DataFrame(np.random.rand(4, 2),\n",
|
|
1537
|
+
"index=[['a', 'a', 'b', 'b'], [1, 2, 1, 2]],\n",
|
|
1538
|
+
"columns=['data1', 'data2'])\n",
|
|
1539
|
+
"df"
|
|
1540
|
+
]
|
|
1541
|
+
},
|
|
1542
|
+
{
|
|
1543
|
+
"cell_type": "code",
|
|
1544
|
+
"execution_count": 41,
|
|
1545
|
+
"id": "87b94068-cad8-47df-a350-e67d083d60cd",
|
|
1546
|
+
"metadata": {},
|
|
1547
|
+
"outputs": [
|
|
1548
|
+
{
|
|
1549
|
+
"data": {
|
|
1550
|
+
"text/plain": [
|
|
1551
|
+
"California 2000 33871648\n",
|
|
1552
|
+
" 2010 37253956\n",
|
|
1553
|
+
"Texas 2000 20851820\n",
|
|
1554
|
+
" 2010 25145561\n",
|
|
1555
|
+
"New York 2000 18976457\n",
|
|
1556
|
+
" 2010 19378102\n",
|
|
1557
|
+
"dtype: int64"
|
|
1558
|
+
]
|
|
1559
|
+
},
|
|
1560
|
+
"execution_count": 41,
|
|
1561
|
+
"metadata": {},
|
|
1562
|
+
"output_type": "execute_result"
|
|
1563
|
+
}
|
|
1564
|
+
],
|
|
1565
|
+
"source": [
|
|
1566
|
+
"data = {('California', 2000): 33871648,\n",
|
|
1567
|
+
"('California', 2010): 37253956,\n",
|
|
1568
|
+
"('Texas', 2000): 20851820,\n",
|
|
1569
|
+
"('Texas', 2010): 25145561,\n",
|
|
1570
|
+
"('New York', 2000): 18976457,\n",
|
|
1571
|
+
"('New York', 2010): 19378102}\n",
|
|
1572
|
+
"pd.Series(data)"
|
|
1573
|
+
]
|
|
1574
|
+
},
|
|
1575
|
+
{
|
|
1576
|
+
"cell_type": "code",
|
|
1577
|
+
"execution_count": 42,
|
|
1578
|
+
"id": "2357c39e-189d-49d8-a652-0cc60fd0549d",
|
|
1579
|
+
"metadata": {},
|
|
1580
|
+
"outputs": [
|
|
1581
|
+
{
|
|
1582
|
+
"data": {
|
|
1583
|
+
"text/plain": [
|
|
1584
|
+
"MultiIndex([('a', 1),\n",
|
|
1585
|
+
" ('a', 2),\n",
|
|
1586
|
+
" ('b', 1),\n",
|
|
1587
|
+
" ('b', 2)],\n",
|
|
1588
|
+
" )"
|
|
1589
|
+
]
|
|
1590
|
+
},
|
|
1591
|
+
"execution_count": 42,
|
|
1592
|
+
"metadata": {},
|
|
1593
|
+
"output_type": "execute_result"
|
|
1594
|
+
}
|
|
1595
|
+
],
|
|
1596
|
+
"source": [
|
|
1597
|
+
"pd.MultiIndex.from_arrays([['a', 'a', 'b', 'b'], [1, 2, 1, 2]])"
|
|
1598
|
+
]
|
|
1599
|
+
},
|
|
1600
|
+
{
|
|
1601
|
+
"cell_type": "code",
|
|
1602
|
+
"execution_count": 43,
|
|
1603
|
+
"id": "1dc18ebb-fe8a-4bac-9fbf-ea38e7d11e16",
|
|
1604
|
+
"metadata": {},
|
|
1605
|
+
"outputs": [
|
|
1606
|
+
{
|
|
1607
|
+
"data": {
|
|
1608
|
+
"text/plain": [
|
|
1609
|
+
"MultiIndex([('a', 1),\n",
|
|
1610
|
+
" ('a', 2),\n",
|
|
1611
|
+
" ('b', 1),\n",
|
|
1612
|
+
" ('b', 2)],\n",
|
|
1613
|
+
" )"
|
|
1614
|
+
]
|
|
1615
|
+
},
|
|
1616
|
+
"execution_count": 43,
|
|
1617
|
+
"metadata": {},
|
|
1618
|
+
"output_type": "execute_result"
|
|
1619
|
+
}
|
|
1620
|
+
],
|
|
1621
|
+
"source": [
|
|
1622
|
+
"pd.MultiIndex.from_tuples([('a', 1), ('a', 2), ('b', 1), ('b', 2)])"
|
|
1623
|
+
]
|
|
1624
|
+
},
|
|
1625
|
+
{
|
|
1626
|
+
"cell_type": "code",
|
|
1627
|
+
"execution_count": 44,
|
|
1628
|
+
"id": "13bff348-d67d-49ba-b16c-16f31032c1f2",
|
|
1629
|
+
"metadata": {},
|
|
1630
|
+
"outputs": [
|
|
1631
|
+
{
|
|
1632
|
+
"data": {
|
|
1633
|
+
"text/plain": [
|
|
1634
|
+
"MultiIndex([('a', 1),\n",
|
|
1635
|
+
" ('a', 2),\n",
|
|
1636
|
+
" ('b', 1),\n",
|
|
1637
|
+
" ('b', 2)],\n",
|
|
1638
|
+
" )"
|
|
1639
|
+
]
|
|
1640
|
+
},
|
|
1641
|
+
"execution_count": 44,
|
|
1642
|
+
"metadata": {},
|
|
1643
|
+
"output_type": "execute_result"
|
|
1644
|
+
}
|
|
1645
|
+
],
|
|
1646
|
+
"source": [
|
|
1647
|
+
"pd.MultiIndex.from_product([['a', 'b'], [1, 2]])"
|
|
1648
|
+
]
|
|
1649
|
+
},
|
|
1650
|
+
{
|
|
1651
|
+
"cell_type": "code",
|
|
1652
|
+
"execution_count": 45,
|
|
1653
|
+
"id": "7ce4bd44-6979-4413-84cd-6195fd5440d1",
|
|
1654
|
+
"metadata": {},
|
|
1655
|
+
"outputs": [
|
|
1656
|
+
{
|
|
1657
|
+
"data": {
|
|
1658
|
+
"text/plain": [
|
|
1659
|
+
"MultiIndex([('a', 1),\n",
|
|
1660
|
+
" ('a', 2),\n",
|
|
1661
|
+
" ('b', 1),\n",
|
|
1662
|
+
" ('b', 2)],\n",
|
|
1663
|
+
" )"
|
|
1664
|
+
]
|
|
1665
|
+
},
|
|
1666
|
+
"execution_count": 45,
|
|
1667
|
+
"metadata": {},
|
|
1668
|
+
"output_type": "execute_result"
|
|
1669
|
+
}
|
|
1670
|
+
],
|
|
1671
|
+
"source": [
|
|
1672
|
+
"pd.MultiIndex(levels=[['a', 'b'], [1, 2]],\n",
|
|
1673
|
+
" codes=[[0, 0, 1, 1], [0, 1, 0, 1]])"
|
|
1674
|
+
]
|
|
1675
|
+
},
|
|
1676
|
+
{
|
|
1677
|
+
"cell_type": "code",
|
|
1678
|
+
"execution_count": 46,
|
|
1679
|
+
"id": "745e2c13-b099-4901-b277-074796dcd5b0",
|
|
1680
|
+
"metadata": {},
|
|
1681
|
+
"outputs": [
|
|
1682
|
+
{
|
|
1683
|
+
"data": {
|
|
1684
|
+
"text/plain": [
|
|
1685
|
+
"state year\n",
|
|
1686
|
+
"California 2000 33871648\n",
|
|
1687
|
+
" 2010 37253956\n",
|
|
1688
|
+
"New York 2000 18976457\n",
|
|
1689
|
+
" 2010 19378102\n",
|
|
1690
|
+
"Texas 2000 20851820\n",
|
|
1691
|
+
" 2010 25145561\n",
|
|
1692
|
+
"dtype: int64"
|
|
1693
|
+
]
|
|
1694
|
+
},
|
|
1695
|
+
"execution_count": 46,
|
|
1696
|
+
"metadata": {},
|
|
1697
|
+
"output_type": "execute_result"
|
|
1698
|
+
}
|
|
1699
|
+
],
|
|
1700
|
+
"source": [
|
|
1701
|
+
"pop.index.names = ['state', 'year']\n",
|
|
1702
|
+
"pop"
|
|
1703
|
+
]
|
|
1704
|
+
},
|
|
1705
|
+
{
|
|
1706
|
+
"cell_type": "code",
|
|
1707
|
+
"execution_count": 47,
|
|
1708
|
+
"id": "0676dea4-4f80-4165-81ea-3869b9ab1f15",
|
|
1709
|
+
"metadata": {},
|
|
1710
|
+
"outputs": [
|
|
1711
|
+
{
|
|
1712
|
+
"data": {
|
|
1713
|
+
"text/html": [
|
|
1714
|
+
"<div>\n",
|
|
1715
|
+
"<style scoped>\n",
|
|
1716
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1717
|
+
" vertical-align: middle;\n",
|
|
1718
|
+
" }\n",
|
|
1719
|
+
"\n",
|
|
1720
|
+
" .dataframe tbody tr th {\n",
|
|
1721
|
+
" vertical-align: top;\n",
|
|
1722
|
+
" }\n",
|
|
1723
|
+
"\n",
|
|
1724
|
+
" .dataframe thead tr th {\n",
|
|
1725
|
+
" text-align: left;\n",
|
|
1726
|
+
" }\n",
|
|
1727
|
+
"\n",
|
|
1728
|
+
" .dataframe thead tr:last-of-type th {\n",
|
|
1729
|
+
" text-align: right;\n",
|
|
1730
|
+
" }\n",
|
|
1731
|
+
"</style>\n",
|
|
1732
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1733
|
+
" <thead>\n",
|
|
1734
|
+
" <tr>\n",
|
|
1735
|
+
" <th></th>\n",
|
|
1736
|
+
" <th>subject</th>\n",
|
|
1737
|
+
" <th colspan=\"2\" halign=\"left\">Bob</th>\n",
|
|
1738
|
+
" <th colspan=\"2\" halign=\"left\">Guido</th>\n",
|
|
1739
|
+
" <th colspan=\"2\" halign=\"left\">Sue</th>\n",
|
|
1740
|
+
" </tr>\n",
|
|
1741
|
+
" <tr>\n",
|
|
1742
|
+
" <th></th>\n",
|
|
1743
|
+
" <th>type</th>\n",
|
|
1744
|
+
" <th>HR</th>\n",
|
|
1745
|
+
" <th>Temp</th>\n",
|
|
1746
|
+
" <th>HR</th>\n",
|
|
1747
|
+
" <th>Temp</th>\n",
|
|
1748
|
+
" <th>HR</th>\n",
|
|
1749
|
+
" <th>Temp</th>\n",
|
|
1750
|
+
" </tr>\n",
|
|
1751
|
+
" <tr>\n",
|
|
1752
|
+
" <th>year</th>\n",
|
|
1753
|
+
" <th>visit</th>\n",
|
|
1754
|
+
" <th></th>\n",
|
|
1755
|
+
" <th></th>\n",
|
|
1756
|
+
" <th></th>\n",
|
|
1757
|
+
" <th></th>\n",
|
|
1758
|
+
" <th></th>\n",
|
|
1759
|
+
" <th></th>\n",
|
|
1760
|
+
" </tr>\n",
|
|
1761
|
+
" </thead>\n",
|
|
1762
|
+
" <tbody>\n",
|
|
1763
|
+
" <tr>\n",
|
|
1764
|
+
" <th rowspan=\"2\" valign=\"top\">2013</th>\n",
|
|
1765
|
+
" <th>1</th>\n",
|
|
1766
|
+
" <td>49.0</td>\n",
|
|
1767
|
+
" <td>38.5</td>\n",
|
|
1768
|
+
" <td>37.0</td>\n",
|
|
1769
|
+
" <td>38.2</td>\n",
|
|
1770
|
+
" <td>33.0</td>\n",
|
|
1771
|
+
" <td>38.3</td>\n",
|
|
1772
|
+
" </tr>\n",
|
|
1773
|
+
" <tr>\n",
|
|
1774
|
+
" <th>2</th>\n",
|
|
1775
|
+
" <td>43.0</td>\n",
|
|
1776
|
+
" <td>38.6</td>\n",
|
|
1777
|
+
" <td>23.0</td>\n",
|
|
1778
|
+
" <td>37.5</td>\n",
|
|
1779
|
+
" <td>42.0</td>\n",
|
|
1780
|
+
" <td>35.2</td>\n",
|
|
1781
|
+
" </tr>\n",
|
|
1782
|
+
" <tr>\n",
|
|
1783
|
+
" <th rowspan=\"2\" valign=\"top\">2014</th>\n",
|
|
1784
|
+
" <th>1</th>\n",
|
|
1785
|
+
" <td>22.0</td>\n",
|
|
1786
|
+
" <td>37.3</td>\n",
|
|
1787
|
+
" <td>46.0</td>\n",
|
|
1788
|
+
" <td>36.5</td>\n",
|
|
1789
|
+
" <td>35.0</td>\n",
|
|
1790
|
+
" <td>37.3</td>\n",
|
|
1791
|
+
" </tr>\n",
|
|
1792
|
+
" <tr>\n",
|
|
1793
|
+
" <th>2</th>\n",
|
|
1794
|
+
" <td>40.0</td>\n",
|
|
1795
|
+
" <td>36.9</td>\n",
|
|
1796
|
+
" <td>58.0</td>\n",
|
|
1797
|
+
" <td>37.1</td>\n",
|
|
1798
|
+
" <td>48.0</td>\n",
|
|
1799
|
+
" <td>35.8</td>\n",
|
|
1800
|
+
" </tr>\n",
|
|
1801
|
+
" </tbody>\n",
|
|
1802
|
+
"</table>\n",
|
|
1803
|
+
"</div>"
|
|
1804
|
+
],
|
|
1805
|
+
"text/plain": [
|
|
1806
|
+
"subject Bob Guido Sue \n",
|
|
1807
|
+
"type HR Temp HR Temp HR Temp\n",
|
|
1808
|
+
"year visit \n",
|
|
1809
|
+
"2013 1 49.0 38.5 37.0 38.2 33.0 38.3\n",
|
|
1810
|
+
" 2 43.0 38.6 23.0 37.5 42.0 35.2\n",
|
|
1811
|
+
"2014 1 22.0 37.3 46.0 36.5 35.0 37.3\n",
|
|
1812
|
+
" 2 40.0 36.9 58.0 37.1 48.0 35.8"
|
|
1813
|
+
]
|
|
1814
|
+
},
|
|
1815
|
+
"execution_count": 47,
|
|
1816
|
+
"metadata": {},
|
|
1817
|
+
"output_type": "execute_result"
|
|
1818
|
+
}
|
|
1819
|
+
],
|
|
1820
|
+
"source": [
|
|
1821
|
+
"index = pd.MultiIndex.from_product([[2013, 2014], [1, 2]],\n",
|
|
1822
|
+
"names=['year', 'visit'])\n",
|
|
1823
|
+
"columns = pd.MultiIndex.from_product([['Bob', 'Guido', 'Sue'], ['HR', 'Temp']],\n",
|
|
1824
|
+
"names=['subject', 'type'])\n",
|
|
1825
|
+
"\n",
|
|
1826
|
+
"data = np.round(np.random.randn(4, 6), 1)\n",
|
|
1827
|
+
"data[:, ::2] *= 10\n",
|
|
1828
|
+
"data += 37\n",
|
|
1829
|
+
"\n",
|
|
1830
|
+
"health_data = pd.DataFrame(data, index=index, columns=columns)\n",
|
|
1831
|
+
"health_data"
|
|
1832
|
+
]
|
|
1833
|
+
},
|
|
1834
|
+
{
|
|
1835
|
+
"cell_type": "code",
|
|
1836
|
+
"execution_count": 48,
|
|
1837
|
+
"id": "93319435-e56e-4939-b56c-eb8b3bd97163",
|
|
1838
|
+
"metadata": {},
|
|
1839
|
+
"outputs": [
|
|
1840
|
+
{
|
|
1841
|
+
"data": {
|
|
1842
|
+
"text/html": [
|
|
1843
|
+
"<div>\n",
|
|
1844
|
+
"<style scoped>\n",
|
|
1845
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
1846
|
+
" vertical-align: middle;\n",
|
|
1847
|
+
" }\n",
|
|
1848
|
+
"\n",
|
|
1849
|
+
" .dataframe tbody tr th {\n",
|
|
1850
|
+
" vertical-align: top;\n",
|
|
1851
|
+
" }\n",
|
|
1852
|
+
"\n",
|
|
1853
|
+
" .dataframe thead th {\n",
|
|
1854
|
+
" text-align: right;\n",
|
|
1855
|
+
" }\n",
|
|
1856
|
+
"</style>\n",
|
|
1857
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
1858
|
+
" <thead>\n",
|
|
1859
|
+
" <tr style=\"text-align: right;\">\n",
|
|
1860
|
+
" <th></th>\n",
|
|
1861
|
+
" <th>type</th>\n",
|
|
1862
|
+
" <th>HR</th>\n",
|
|
1863
|
+
" <th>Temp</th>\n",
|
|
1864
|
+
" </tr>\n",
|
|
1865
|
+
" <tr>\n",
|
|
1866
|
+
" <th>year</th>\n",
|
|
1867
|
+
" <th>visit</th>\n",
|
|
1868
|
+
" <th></th>\n",
|
|
1869
|
+
" <th></th>\n",
|
|
1870
|
+
" </tr>\n",
|
|
1871
|
+
" </thead>\n",
|
|
1872
|
+
" <tbody>\n",
|
|
1873
|
+
" <tr>\n",
|
|
1874
|
+
" <th rowspan=\"2\" valign=\"top\">2013</th>\n",
|
|
1875
|
+
" <th>1</th>\n",
|
|
1876
|
+
" <td>37.0</td>\n",
|
|
1877
|
+
" <td>38.2</td>\n",
|
|
1878
|
+
" </tr>\n",
|
|
1879
|
+
" <tr>\n",
|
|
1880
|
+
" <th>2</th>\n",
|
|
1881
|
+
" <td>23.0</td>\n",
|
|
1882
|
+
" <td>37.5</td>\n",
|
|
1883
|
+
" </tr>\n",
|
|
1884
|
+
" <tr>\n",
|
|
1885
|
+
" <th rowspan=\"2\" valign=\"top\">2014</th>\n",
|
|
1886
|
+
" <th>1</th>\n",
|
|
1887
|
+
" <td>46.0</td>\n",
|
|
1888
|
+
" <td>36.5</td>\n",
|
|
1889
|
+
" </tr>\n",
|
|
1890
|
+
" <tr>\n",
|
|
1891
|
+
" <th>2</th>\n",
|
|
1892
|
+
" <td>58.0</td>\n",
|
|
1893
|
+
" <td>37.1</td>\n",
|
|
1894
|
+
" </tr>\n",
|
|
1895
|
+
" </tbody>\n",
|
|
1896
|
+
"</table>\n",
|
|
1897
|
+
"</div>"
|
|
1898
|
+
],
|
|
1899
|
+
"text/plain": [
|
|
1900
|
+
"type HR Temp\n",
|
|
1901
|
+
"year visit \n",
|
|
1902
|
+
"2013 1 37.0 38.2\n",
|
|
1903
|
+
" 2 23.0 37.5\n",
|
|
1904
|
+
"2014 1 46.0 36.5\n",
|
|
1905
|
+
" 2 58.0 37.1"
|
|
1906
|
+
]
|
|
1907
|
+
},
|
|
1908
|
+
"execution_count": 48,
|
|
1909
|
+
"metadata": {},
|
|
1910
|
+
"output_type": "execute_result"
|
|
1911
|
+
}
|
|
1912
|
+
],
|
|
1913
|
+
"source": [
|
|
1914
|
+
"health_data['Guido']"
|
|
1915
|
+
]
|
|
1916
|
+
},
|
|
1917
|
+
{
|
|
1918
|
+
"cell_type": "code",
|
|
1919
|
+
"execution_count": 49,
|
|
1920
|
+
"id": "aa5d6ddb-581f-4d7e-b148-602f94749e1b",
|
|
1921
|
+
"metadata": {},
|
|
1922
|
+
"outputs": [
|
|
1923
|
+
{
|
|
1924
|
+
"data": {
|
|
1925
|
+
"text/plain": [
|
|
1926
|
+
"state year\n",
|
|
1927
|
+
"California 2000 33871648\n",
|
|
1928
|
+
" 2010 37253956\n",
|
|
1929
|
+
"New York 2000 18976457\n",
|
|
1930
|
+
" 2010 19378102\n",
|
|
1931
|
+
"Texas 2000 20851820\n",
|
|
1932
|
+
" 2010 25145561\n",
|
|
1933
|
+
"dtype: int64"
|
|
1934
|
+
]
|
|
1935
|
+
},
|
|
1936
|
+
"execution_count": 49,
|
|
1937
|
+
"metadata": {},
|
|
1938
|
+
"output_type": "execute_result"
|
|
1939
|
+
}
|
|
1940
|
+
],
|
|
1941
|
+
"source": [
|
|
1942
|
+
"pop"
|
|
1943
|
+
]
|
|
1944
|
+
},
|
|
1945
|
+
{
|
|
1946
|
+
"cell_type": "code",
|
|
1947
|
+
"execution_count": 50,
|
|
1948
|
+
"id": "6e2a0550-b4f7-4e1a-9c9e-e6a537554179",
|
|
1949
|
+
"metadata": {},
|
|
1950
|
+
"outputs": [
|
|
1951
|
+
{
|
|
1952
|
+
"data": {
|
|
1953
|
+
"text/plain": [
|
|
1954
|
+
"np.int64(33871648)"
|
|
1955
|
+
]
|
|
1956
|
+
},
|
|
1957
|
+
"execution_count": 50,
|
|
1958
|
+
"metadata": {},
|
|
1959
|
+
"output_type": "execute_result"
|
|
1960
|
+
}
|
|
1961
|
+
],
|
|
1962
|
+
"source": [
|
|
1963
|
+
"pop['California', 2000]"
|
|
1964
|
+
]
|
|
1965
|
+
},
|
|
1966
|
+
{
|
|
1967
|
+
"cell_type": "code",
|
|
1968
|
+
"execution_count": 51,
|
|
1969
|
+
"id": "d07b7114-56b8-4609-b749-c1e0c8c9fa64",
|
|
1970
|
+
"metadata": {},
|
|
1971
|
+
"outputs": [
|
|
1972
|
+
{
|
|
1973
|
+
"data": {
|
|
1974
|
+
"text/plain": [
|
|
1975
|
+
"year\n",
|
|
1976
|
+
"2000 33871648\n",
|
|
1977
|
+
"2010 37253956\n",
|
|
1978
|
+
"dtype: int64"
|
|
1979
|
+
]
|
|
1980
|
+
},
|
|
1981
|
+
"execution_count": 51,
|
|
1982
|
+
"metadata": {},
|
|
1983
|
+
"output_type": "execute_result"
|
|
1984
|
+
}
|
|
1985
|
+
],
|
|
1986
|
+
"source": [
|
|
1987
|
+
"pop['California']"
|
|
1988
|
+
]
|
|
1989
|
+
},
|
|
1990
|
+
{
|
|
1991
|
+
"cell_type": "code",
|
|
1992
|
+
"execution_count": 52,
|
|
1993
|
+
"id": "be5249e4-9244-4145-82a9-6ead97ef95ec",
|
|
1994
|
+
"metadata": {},
|
|
1995
|
+
"outputs": [
|
|
1996
|
+
{
|
|
1997
|
+
"data": {
|
|
1998
|
+
"text/plain": [
|
|
1999
|
+
"state year\n",
|
|
2000
|
+
"California 2000 33871648\n",
|
|
2001
|
+
" 2010 37253956\n",
|
|
2002
|
+
"New York 2000 18976457\n",
|
|
2003
|
+
" 2010 19378102\n",
|
|
2004
|
+
"dtype: int64"
|
|
2005
|
+
]
|
|
2006
|
+
},
|
|
2007
|
+
"execution_count": 52,
|
|
2008
|
+
"metadata": {},
|
|
2009
|
+
"output_type": "execute_result"
|
|
2010
|
+
}
|
|
2011
|
+
],
|
|
2012
|
+
"source": [
|
|
2013
|
+
"pop.loc['California':'New York']"
|
|
2014
|
+
]
|
|
2015
|
+
},
|
|
2016
|
+
{
|
|
2017
|
+
"cell_type": "code",
|
|
2018
|
+
"execution_count": 53,
|
|
2019
|
+
"id": "3f02298e-195e-4f18-a8c6-5352e1fc5c14",
|
|
2020
|
+
"metadata": {},
|
|
2021
|
+
"outputs": [
|
|
2022
|
+
{
|
|
2023
|
+
"data": {
|
|
2024
|
+
"text/plain": [
|
|
2025
|
+
"state\n",
|
|
2026
|
+
"California 33871648\n",
|
|
2027
|
+
"New York 18976457\n",
|
|
2028
|
+
"Texas 20851820\n",
|
|
2029
|
+
"dtype: int64"
|
|
2030
|
+
]
|
|
2031
|
+
},
|
|
2032
|
+
"execution_count": 53,
|
|
2033
|
+
"metadata": {},
|
|
2034
|
+
"output_type": "execute_result"
|
|
2035
|
+
}
|
|
2036
|
+
],
|
|
2037
|
+
"source": [
|
|
2038
|
+
"pop[:, 2000]"
|
|
2039
|
+
]
|
|
2040
|
+
},
|
|
2041
|
+
{
|
|
2042
|
+
"cell_type": "code",
|
|
2043
|
+
"execution_count": 54,
|
|
2044
|
+
"id": "a95754cd-af47-42df-b021-4a3f7acf8be0",
|
|
2045
|
+
"metadata": {},
|
|
2046
|
+
"outputs": [
|
|
2047
|
+
{
|
|
2048
|
+
"data": {
|
|
2049
|
+
"text/plain": [
|
|
2050
|
+
"state year\n",
|
|
2051
|
+
"California 2000 33871648\n",
|
|
2052
|
+
" 2010 37253956\n",
|
|
2053
|
+
"Texas 2010 25145561\n",
|
|
2054
|
+
"dtype: int64"
|
|
2055
|
+
]
|
|
2056
|
+
},
|
|
2057
|
+
"execution_count": 54,
|
|
2058
|
+
"metadata": {},
|
|
2059
|
+
"output_type": "execute_result"
|
|
2060
|
+
}
|
|
2061
|
+
],
|
|
2062
|
+
"source": [
|
|
2063
|
+
"pop[pop > 22000000]"
|
|
2064
|
+
]
|
|
2065
|
+
},
|
|
2066
|
+
{
|
|
2067
|
+
"cell_type": "code",
|
|
2068
|
+
"execution_count": 55,
|
|
2069
|
+
"id": "ca7b8ea9-951b-46e5-bebf-d47ac2f15bf3",
|
|
2070
|
+
"metadata": {},
|
|
2071
|
+
"outputs": [
|
|
2072
|
+
{
|
|
2073
|
+
"data": {
|
|
2074
|
+
"text/plain": [
|
|
2075
|
+
"state year\n",
|
|
2076
|
+
"California 2000 33871648\n",
|
|
2077
|
+
" 2010 37253956\n",
|
|
2078
|
+
"Texas 2000 20851820\n",
|
|
2079
|
+
" 2010 25145561\n",
|
|
2080
|
+
"dtype: int64"
|
|
2081
|
+
]
|
|
2082
|
+
},
|
|
2083
|
+
"execution_count": 55,
|
|
2084
|
+
"metadata": {},
|
|
2085
|
+
"output_type": "execute_result"
|
|
2086
|
+
}
|
|
2087
|
+
],
|
|
2088
|
+
"source": [
|
|
2089
|
+
"pop[['California', 'Texas']]"
|
|
2090
|
+
]
|
|
2091
|
+
},
|
|
2092
|
+
{
|
|
2093
|
+
"cell_type": "code",
|
|
2094
|
+
"execution_count": 56,
|
|
2095
|
+
"id": "3aefb9d1-98c2-4749-b926-a4691b41de28",
|
|
2096
|
+
"metadata": {},
|
|
2097
|
+
"outputs": [
|
|
2098
|
+
{
|
|
2099
|
+
"data": {
|
|
2100
|
+
"text/html": [
|
|
2101
|
+
"<div>\n",
|
|
2102
|
+
"<style scoped>\n",
|
|
2103
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
2104
|
+
" vertical-align: middle;\n",
|
|
2105
|
+
" }\n",
|
|
2106
|
+
"\n",
|
|
2107
|
+
" .dataframe tbody tr th {\n",
|
|
2108
|
+
" vertical-align: top;\n",
|
|
2109
|
+
" }\n",
|
|
2110
|
+
"\n",
|
|
2111
|
+
" .dataframe thead tr th {\n",
|
|
2112
|
+
" text-align: left;\n",
|
|
2113
|
+
" }\n",
|
|
2114
|
+
"\n",
|
|
2115
|
+
" .dataframe thead tr:last-of-type th {\n",
|
|
2116
|
+
" text-align: right;\n",
|
|
2117
|
+
" }\n",
|
|
2118
|
+
"</style>\n",
|
|
2119
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
2120
|
+
" <thead>\n",
|
|
2121
|
+
" <tr>\n",
|
|
2122
|
+
" <th></th>\n",
|
|
2123
|
+
" <th>subject</th>\n",
|
|
2124
|
+
" <th colspan=\"2\" halign=\"left\">Bob</th>\n",
|
|
2125
|
+
" <th colspan=\"2\" halign=\"left\">Guido</th>\n",
|
|
2126
|
+
" <th colspan=\"2\" halign=\"left\">Sue</th>\n",
|
|
2127
|
+
" </tr>\n",
|
|
2128
|
+
" <tr>\n",
|
|
2129
|
+
" <th></th>\n",
|
|
2130
|
+
" <th>type</th>\n",
|
|
2131
|
+
" <th>HR</th>\n",
|
|
2132
|
+
" <th>Temp</th>\n",
|
|
2133
|
+
" <th>HR</th>\n",
|
|
2134
|
+
" <th>Temp</th>\n",
|
|
2135
|
+
" <th>HR</th>\n",
|
|
2136
|
+
" <th>Temp</th>\n",
|
|
2137
|
+
" </tr>\n",
|
|
2138
|
+
" <tr>\n",
|
|
2139
|
+
" <th>year</th>\n",
|
|
2140
|
+
" <th>visit</th>\n",
|
|
2141
|
+
" <th></th>\n",
|
|
2142
|
+
" <th></th>\n",
|
|
2143
|
+
" <th></th>\n",
|
|
2144
|
+
" <th></th>\n",
|
|
2145
|
+
" <th></th>\n",
|
|
2146
|
+
" <th></th>\n",
|
|
2147
|
+
" </tr>\n",
|
|
2148
|
+
" </thead>\n",
|
|
2149
|
+
" <tbody>\n",
|
|
2150
|
+
" <tr>\n",
|
|
2151
|
+
" <th rowspan=\"2\" valign=\"top\">2013</th>\n",
|
|
2152
|
+
" <th>1</th>\n",
|
|
2153
|
+
" <td>49.0</td>\n",
|
|
2154
|
+
" <td>38.5</td>\n",
|
|
2155
|
+
" <td>37.0</td>\n",
|
|
2156
|
+
" <td>38.2</td>\n",
|
|
2157
|
+
" <td>33.0</td>\n",
|
|
2158
|
+
" <td>38.3</td>\n",
|
|
2159
|
+
" </tr>\n",
|
|
2160
|
+
" <tr>\n",
|
|
2161
|
+
" <th>2</th>\n",
|
|
2162
|
+
" <td>43.0</td>\n",
|
|
2163
|
+
" <td>38.6</td>\n",
|
|
2164
|
+
" <td>23.0</td>\n",
|
|
2165
|
+
" <td>37.5</td>\n",
|
|
2166
|
+
" <td>42.0</td>\n",
|
|
2167
|
+
" <td>35.2</td>\n",
|
|
2168
|
+
" </tr>\n",
|
|
2169
|
+
" <tr>\n",
|
|
2170
|
+
" <th rowspan=\"2\" valign=\"top\">2014</th>\n",
|
|
2171
|
+
" <th>1</th>\n",
|
|
2172
|
+
" <td>22.0</td>\n",
|
|
2173
|
+
" <td>37.3</td>\n",
|
|
2174
|
+
" <td>46.0</td>\n",
|
|
2175
|
+
" <td>36.5</td>\n",
|
|
2176
|
+
" <td>35.0</td>\n",
|
|
2177
|
+
" <td>37.3</td>\n",
|
|
2178
|
+
" </tr>\n",
|
|
2179
|
+
" <tr>\n",
|
|
2180
|
+
" <th>2</th>\n",
|
|
2181
|
+
" <td>40.0</td>\n",
|
|
2182
|
+
" <td>36.9</td>\n",
|
|
2183
|
+
" <td>58.0</td>\n",
|
|
2184
|
+
" <td>37.1</td>\n",
|
|
2185
|
+
" <td>48.0</td>\n",
|
|
2186
|
+
" <td>35.8</td>\n",
|
|
2187
|
+
" </tr>\n",
|
|
2188
|
+
" </tbody>\n",
|
|
2189
|
+
"</table>\n",
|
|
2190
|
+
"</div>"
|
|
2191
|
+
],
|
|
2192
|
+
"text/plain": [
|
|
2193
|
+
"subject Bob Guido Sue \n",
|
|
2194
|
+
"type HR Temp HR Temp HR Temp\n",
|
|
2195
|
+
"year visit \n",
|
|
2196
|
+
"2013 1 49.0 38.5 37.0 38.2 33.0 38.3\n",
|
|
2197
|
+
" 2 43.0 38.6 23.0 37.5 42.0 35.2\n",
|
|
2198
|
+
"2014 1 22.0 37.3 46.0 36.5 35.0 37.3\n",
|
|
2199
|
+
" 2 40.0 36.9 58.0 37.1 48.0 35.8"
|
|
2200
|
+
]
|
|
2201
|
+
},
|
|
2202
|
+
"execution_count": 56,
|
|
2203
|
+
"metadata": {},
|
|
2204
|
+
"output_type": "execute_result"
|
|
2205
|
+
}
|
|
2206
|
+
],
|
|
2207
|
+
"source": [
|
|
2208
|
+
"health_data"
|
|
2209
|
+
]
|
|
2210
|
+
},
|
|
2211
|
+
{
|
|
2212
|
+
"cell_type": "code",
|
|
2213
|
+
"execution_count": 57,
|
|
2214
|
+
"id": "c7d0357c-1b12-4eed-8bb9-4f689921749e",
|
|
2215
|
+
"metadata": {},
|
|
2216
|
+
"outputs": [
|
|
2217
|
+
{
|
|
2218
|
+
"data": {
|
|
2219
|
+
"text/plain": [
|
|
2220
|
+
"year visit\n",
|
|
2221
|
+
"2013 1 37.0\n",
|
|
2222
|
+
" 2 23.0\n",
|
|
2223
|
+
"2014 1 46.0\n",
|
|
2224
|
+
" 2 58.0\n",
|
|
2225
|
+
"Name: (Guido, HR), dtype: float64"
|
|
2226
|
+
]
|
|
2227
|
+
},
|
|
2228
|
+
"execution_count": 57,
|
|
2229
|
+
"metadata": {},
|
|
2230
|
+
"output_type": "execute_result"
|
|
2231
|
+
}
|
|
2232
|
+
],
|
|
2233
|
+
"source": [
|
|
2234
|
+
"health_data['Guido', 'HR']"
|
|
2235
|
+
]
|
|
2236
|
+
},
|
|
2237
|
+
{
|
|
2238
|
+
"cell_type": "code",
|
|
2239
|
+
"execution_count": 58,
|
|
2240
|
+
"id": "78e41138-b1f1-45de-9fd5-5d4e2434e5da",
|
|
2241
|
+
"metadata": {},
|
|
2242
|
+
"outputs": [
|
|
2243
|
+
{
|
|
2244
|
+
"data": {
|
|
2245
|
+
"text/html": [
|
|
2246
|
+
"<div>\n",
|
|
2247
|
+
"<style scoped>\n",
|
|
2248
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
2249
|
+
" vertical-align: middle;\n",
|
|
2250
|
+
" }\n",
|
|
2251
|
+
"\n",
|
|
2252
|
+
" .dataframe tbody tr th {\n",
|
|
2253
|
+
" vertical-align: top;\n",
|
|
2254
|
+
" }\n",
|
|
2255
|
+
"\n",
|
|
2256
|
+
" .dataframe thead tr th {\n",
|
|
2257
|
+
" text-align: left;\n",
|
|
2258
|
+
" }\n",
|
|
2259
|
+
"\n",
|
|
2260
|
+
" .dataframe thead tr:last-of-type th {\n",
|
|
2261
|
+
" text-align: right;\n",
|
|
2262
|
+
" }\n",
|
|
2263
|
+
"</style>\n",
|
|
2264
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
2265
|
+
" <thead>\n",
|
|
2266
|
+
" <tr>\n",
|
|
2267
|
+
" <th></th>\n",
|
|
2268
|
+
" <th>subject</th>\n",
|
|
2269
|
+
" <th colspan=\"2\" halign=\"left\">Bob</th>\n",
|
|
2270
|
+
" </tr>\n",
|
|
2271
|
+
" <tr>\n",
|
|
2272
|
+
" <th></th>\n",
|
|
2273
|
+
" <th>type</th>\n",
|
|
2274
|
+
" <th>HR</th>\n",
|
|
2275
|
+
" <th>Temp</th>\n",
|
|
2276
|
+
" </tr>\n",
|
|
2277
|
+
" <tr>\n",
|
|
2278
|
+
" <th>year</th>\n",
|
|
2279
|
+
" <th>visit</th>\n",
|
|
2280
|
+
" <th></th>\n",
|
|
2281
|
+
" <th></th>\n",
|
|
2282
|
+
" </tr>\n",
|
|
2283
|
+
" </thead>\n",
|
|
2284
|
+
" <tbody>\n",
|
|
2285
|
+
" <tr>\n",
|
|
2286
|
+
" <th rowspan=\"2\" valign=\"top\">2013</th>\n",
|
|
2287
|
+
" <th>1</th>\n",
|
|
2288
|
+
" <td>49.0</td>\n",
|
|
2289
|
+
" <td>38.5</td>\n",
|
|
2290
|
+
" </tr>\n",
|
|
2291
|
+
" <tr>\n",
|
|
2292
|
+
" <th>2</th>\n",
|
|
2293
|
+
" <td>43.0</td>\n",
|
|
2294
|
+
" <td>38.6</td>\n",
|
|
2295
|
+
" </tr>\n",
|
|
2296
|
+
" </tbody>\n",
|
|
2297
|
+
"</table>\n",
|
|
2298
|
+
"</div>"
|
|
2299
|
+
],
|
|
2300
|
+
"text/plain": [
|
|
2301
|
+
"subject Bob \n",
|
|
2302
|
+
"type HR Temp\n",
|
|
2303
|
+
"year visit \n",
|
|
2304
|
+
"2013 1 49.0 38.5\n",
|
|
2305
|
+
" 2 43.0 38.6"
|
|
2306
|
+
]
|
|
2307
|
+
},
|
|
2308
|
+
"execution_count": 58,
|
|
2309
|
+
"metadata": {},
|
|
2310
|
+
"output_type": "execute_result"
|
|
2311
|
+
}
|
|
2312
|
+
],
|
|
2313
|
+
"source": [
|
|
2314
|
+
"health_data.iloc[:2, :2]"
|
|
2315
|
+
]
|
|
2316
|
+
},
|
|
2317
|
+
{
|
|
2318
|
+
"cell_type": "code",
|
|
2319
|
+
"execution_count": 59,
|
|
2320
|
+
"id": "b7b91354-56af-4970-b9eb-d7226b01eed8",
|
|
2321
|
+
"metadata": {},
|
|
2322
|
+
"outputs": [
|
|
2323
|
+
{
|
|
2324
|
+
"data": {
|
|
2325
|
+
"text/plain": [
|
|
2326
|
+
"year visit\n",
|
|
2327
|
+
"2013 1 49.0\n",
|
|
2328
|
+
" 2 43.0\n",
|
|
2329
|
+
"2014 1 22.0\n",
|
|
2330
|
+
" 2 40.0\n",
|
|
2331
|
+
"Name: (Bob, HR), dtype: float64"
|
|
2332
|
+
]
|
|
2333
|
+
},
|
|
2334
|
+
"execution_count": 59,
|
|
2335
|
+
"metadata": {},
|
|
2336
|
+
"output_type": "execute_result"
|
|
2337
|
+
}
|
|
2338
|
+
],
|
|
2339
|
+
"source": [
|
|
2340
|
+
"health_data.loc[:, ('Bob', 'HR')]"
|
|
2341
|
+
]
|
|
2342
|
+
},
|
|
2343
|
+
{
|
|
2344
|
+
"cell_type": "code",
|
|
2345
|
+
"execution_count": 62,
|
|
2346
|
+
"id": "da061035-ee51-4c68-a801-c32ca6d40d8b",
|
|
2347
|
+
"metadata": {},
|
|
2348
|
+
"outputs": [
|
|
2349
|
+
{
|
|
2350
|
+
"data": {
|
|
2351
|
+
"text/html": [
|
|
2352
|
+
"<div>\n",
|
|
2353
|
+
"<style scoped>\n",
|
|
2354
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
2355
|
+
" vertical-align: middle;\n",
|
|
2356
|
+
" }\n",
|
|
2357
|
+
"\n",
|
|
2358
|
+
" .dataframe tbody tr th {\n",
|
|
2359
|
+
" vertical-align: top;\n",
|
|
2360
|
+
" }\n",
|
|
2361
|
+
"\n",
|
|
2362
|
+
" .dataframe thead tr th {\n",
|
|
2363
|
+
" text-align: left;\n",
|
|
2364
|
+
" }\n",
|
|
2365
|
+
"\n",
|
|
2366
|
+
" .dataframe thead tr:last-of-type th {\n",
|
|
2367
|
+
" text-align: right;\n",
|
|
2368
|
+
" }\n",
|
|
2369
|
+
"</style>\n",
|
|
2370
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
2371
|
+
" <thead>\n",
|
|
2372
|
+
" <tr>\n",
|
|
2373
|
+
" <th></th>\n",
|
|
2374
|
+
" <th>subject</th>\n",
|
|
2375
|
+
" <th>Bob</th>\n",
|
|
2376
|
+
" <th>Guido</th>\n",
|
|
2377
|
+
" <th>Sue</th>\n",
|
|
2378
|
+
" </tr>\n",
|
|
2379
|
+
" <tr>\n",
|
|
2380
|
+
" <th></th>\n",
|
|
2381
|
+
" <th>type</th>\n",
|
|
2382
|
+
" <th>HR</th>\n",
|
|
2383
|
+
" <th>HR</th>\n",
|
|
2384
|
+
" <th>HR</th>\n",
|
|
2385
|
+
" </tr>\n",
|
|
2386
|
+
" <tr>\n",
|
|
2387
|
+
" <th>year</th>\n",
|
|
2388
|
+
" <th>visit</th>\n",
|
|
2389
|
+
" <th></th>\n",
|
|
2390
|
+
" <th></th>\n",
|
|
2391
|
+
" <th></th>\n",
|
|
2392
|
+
" </tr>\n",
|
|
2393
|
+
" </thead>\n",
|
|
2394
|
+
" <tbody>\n",
|
|
2395
|
+
" <tr>\n",
|
|
2396
|
+
" <th>2013</th>\n",
|
|
2397
|
+
" <th>1</th>\n",
|
|
2398
|
+
" <td>49.0</td>\n",
|
|
2399
|
+
" <td>37.0</td>\n",
|
|
2400
|
+
" <td>33.0</td>\n",
|
|
2401
|
+
" </tr>\n",
|
|
2402
|
+
" <tr>\n",
|
|
2403
|
+
" <th>2014</th>\n",
|
|
2404
|
+
" <th>1</th>\n",
|
|
2405
|
+
" <td>22.0</td>\n",
|
|
2406
|
+
" <td>46.0</td>\n",
|
|
2407
|
+
" <td>35.0</td>\n",
|
|
2408
|
+
" </tr>\n",
|
|
2409
|
+
" </tbody>\n",
|
|
2410
|
+
"</table>\n",
|
|
2411
|
+
"</div>"
|
|
2412
|
+
],
|
|
2413
|
+
"text/plain": [
|
|
2414
|
+
"subject Bob Guido Sue\n",
|
|
2415
|
+
"type HR HR HR\n",
|
|
2416
|
+
"year visit \n",
|
|
2417
|
+
"2013 1 49.0 37.0 33.0\n",
|
|
2418
|
+
"2014 1 22.0 46.0 35.0"
|
|
2419
|
+
]
|
|
2420
|
+
},
|
|
2421
|
+
"execution_count": 62,
|
|
2422
|
+
"metadata": {},
|
|
2423
|
+
"output_type": "execute_result"
|
|
2424
|
+
}
|
|
2425
|
+
],
|
|
2426
|
+
"source": [
|
|
2427
|
+
"idx = pd.IndexSlice\n",
|
|
2428
|
+
"health_data.loc[idx[:, 1], idx[:, 'HR']]"
|
|
2429
|
+
]
|
|
2430
|
+
},
|
|
2431
|
+
{
|
|
2432
|
+
"cell_type": "code",
|
|
2433
|
+
"execution_count": 63,
|
|
2434
|
+
"id": "6186ea7f-0b22-494e-a5bc-f897223b289a",
|
|
2435
|
+
"metadata": {},
|
|
2436
|
+
"outputs": [
|
|
2437
|
+
{
|
|
2438
|
+
"data": {
|
|
2439
|
+
"text/plain": [
|
|
2440
|
+
"char int\n",
|
|
2441
|
+
"a 1 0.617857\n",
|
|
2442
|
+
" 2 0.704381\n",
|
|
2443
|
+
"c 1 0.356883\n",
|
|
2444
|
+
" 2 0.141801\n",
|
|
2445
|
+
"b 1 0.622593\n",
|
|
2446
|
+
" 2 0.786514\n",
|
|
2447
|
+
"dtype: float64"
|
|
2448
|
+
]
|
|
2449
|
+
},
|
|
2450
|
+
"execution_count": 63,
|
|
2451
|
+
"metadata": {},
|
|
2452
|
+
"output_type": "execute_result"
|
|
2453
|
+
}
|
|
2454
|
+
],
|
|
2455
|
+
"source": [
|
|
2456
|
+
"index = pd.MultiIndex.from_product([['a', 'c', 'b'], [1, 2]])\n",
|
|
2457
|
+
"data = pd.Series(np.random.rand(6), index=index)\n",
|
|
2458
|
+
"data.index.names = ['char', 'int']\n",
|
|
2459
|
+
"data"
|
|
2460
|
+
]
|
|
2461
|
+
},
|
|
2462
|
+
{
|
|
2463
|
+
"cell_type": "code",
|
|
2464
|
+
"execution_count": 64,
|
|
2465
|
+
"id": "ebd32db3-50dc-48e9-9715-6b4c36603daa",
|
|
2466
|
+
"metadata": {},
|
|
2467
|
+
"outputs": [
|
|
2468
|
+
{
|
|
2469
|
+
"name": "stdout",
|
|
2470
|
+
"output_type": "stream",
|
|
2471
|
+
"text": [
|
|
2472
|
+
"<class 'pandas.errors.UnsortedIndexError'>\n",
|
|
2473
|
+
"'Key length (1) was greater than MultiIndex lexsort depth (0)'\n"
|
|
2474
|
+
]
|
|
2475
|
+
}
|
|
2476
|
+
],
|
|
2477
|
+
"source": [
|
|
2478
|
+
"try:\n",
|
|
2479
|
+
" data['a':'b']\n",
|
|
2480
|
+
"except KeyError as e:\n",
|
|
2481
|
+
" print(type(e))\n",
|
|
2482
|
+
" print(e)"
|
|
2483
|
+
]
|
|
2484
|
+
},
|
|
2485
|
+
{
|
|
2486
|
+
"cell_type": "code",
|
|
2487
|
+
"execution_count": 65,
|
|
2488
|
+
"id": "2591b9e1-398e-4ad8-b6c6-f4d2fc9998e3",
|
|
2489
|
+
"metadata": {},
|
|
2490
|
+
"outputs": [
|
|
2491
|
+
{
|
|
2492
|
+
"data": {
|
|
2493
|
+
"text/plain": [
|
|
2494
|
+
"char int\n",
|
|
2495
|
+
"a 1 0.617857\n",
|
|
2496
|
+
" 2 0.704381\n",
|
|
2497
|
+
"b 1 0.622593\n",
|
|
2498
|
+
" 2 0.786514\n",
|
|
2499
|
+
"c 1 0.356883\n",
|
|
2500
|
+
" 2 0.141801\n",
|
|
2501
|
+
"dtype: float64"
|
|
2502
|
+
]
|
|
2503
|
+
},
|
|
2504
|
+
"execution_count": 65,
|
|
2505
|
+
"metadata": {},
|
|
2506
|
+
"output_type": "execute_result"
|
|
2507
|
+
}
|
|
2508
|
+
],
|
|
2509
|
+
"source": [
|
|
2510
|
+
"data = data.sort_index()\n",
|
|
2511
|
+
"data"
|
|
2512
|
+
]
|
|
2513
|
+
},
|
|
2514
|
+
{
|
|
2515
|
+
"cell_type": "code",
|
|
2516
|
+
"execution_count": 66,
|
|
2517
|
+
"id": "a476b952-f359-4e97-9161-3a663d50d376",
|
|
2518
|
+
"metadata": {},
|
|
2519
|
+
"outputs": [
|
|
2520
|
+
{
|
|
2521
|
+
"data": {
|
|
2522
|
+
"text/plain": [
|
|
2523
|
+
"char int\n",
|
|
2524
|
+
"a 1 0.617857\n",
|
|
2525
|
+
" 2 0.704381\n",
|
|
2526
|
+
"b 1 0.622593\n",
|
|
2527
|
+
" 2 0.786514\n",
|
|
2528
|
+
"dtype: float64"
|
|
2529
|
+
]
|
|
2530
|
+
},
|
|
2531
|
+
"execution_count": 66,
|
|
2532
|
+
"metadata": {},
|
|
2533
|
+
"output_type": "execute_result"
|
|
2534
|
+
}
|
|
2535
|
+
],
|
|
2536
|
+
"source": [
|
|
2537
|
+
"data['a':'b']"
|
|
2538
|
+
]
|
|
2539
|
+
},
|
|
2540
|
+
{
|
|
2541
|
+
"cell_type": "code",
|
|
2542
|
+
"execution_count": 67,
|
|
2543
|
+
"id": "2ca63cfa-b281-436d-b2d2-5e1e3b649655",
|
|
2544
|
+
"metadata": {},
|
|
2545
|
+
"outputs": [
|
|
2546
|
+
{
|
|
2547
|
+
"data": {
|
|
2548
|
+
"text/html": [
|
|
2549
|
+
"<div>\n",
|
|
2550
|
+
"<style scoped>\n",
|
|
2551
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
2552
|
+
" vertical-align: middle;\n",
|
|
2553
|
+
" }\n",
|
|
2554
|
+
"\n",
|
|
2555
|
+
" .dataframe tbody tr th {\n",
|
|
2556
|
+
" vertical-align: top;\n",
|
|
2557
|
+
" }\n",
|
|
2558
|
+
"\n",
|
|
2559
|
+
" .dataframe thead th {\n",
|
|
2560
|
+
" text-align: right;\n",
|
|
2561
|
+
" }\n",
|
|
2562
|
+
"</style>\n",
|
|
2563
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
2564
|
+
" <thead>\n",
|
|
2565
|
+
" <tr style=\"text-align: right;\">\n",
|
|
2566
|
+
" <th>state</th>\n",
|
|
2567
|
+
" <th>California</th>\n",
|
|
2568
|
+
" <th>New York</th>\n",
|
|
2569
|
+
" <th>Texas</th>\n",
|
|
2570
|
+
" </tr>\n",
|
|
2571
|
+
" <tr>\n",
|
|
2572
|
+
" <th>year</th>\n",
|
|
2573
|
+
" <th></th>\n",
|
|
2574
|
+
" <th></th>\n",
|
|
2575
|
+
" <th></th>\n",
|
|
2576
|
+
" </tr>\n",
|
|
2577
|
+
" </thead>\n",
|
|
2578
|
+
" <tbody>\n",
|
|
2579
|
+
" <tr>\n",
|
|
2580
|
+
" <th>2000</th>\n",
|
|
2581
|
+
" <td>33871648</td>\n",
|
|
2582
|
+
" <td>18976457</td>\n",
|
|
2583
|
+
" <td>20851820</td>\n",
|
|
2584
|
+
" </tr>\n",
|
|
2585
|
+
" <tr>\n",
|
|
2586
|
+
" <th>2010</th>\n",
|
|
2587
|
+
" <td>37253956</td>\n",
|
|
2588
|
+
" <td>19378102</td>\n",
|
|
2589
|
+
" <td>25145561</td>\n",
|
|
2590
|
+
" </tr>\n",
|
|
2591
|
+
" </tbody>\n",
|
|
2592
|
+
"</table>\n",
|
|
2593
|
+
"</div>"
|
|
2594
|
+
],
|
|
2595
|
+
"text/plain": [
|
|
2596
|
+
"state California New York Texas\n",
|
|
2597
|
+
"year \n",
|
|
2598
|
+
"2000 33871648 18976457 20851820\n",
|
|
2599
|
+
"2010 37253956 19378102 25145561"
|
|
2600
|
+
]
|
|
2601
|
+
},
|
|
2602
|
+
"execution_count": 67,
|
|
2603
|
+
"metadata": {},
|
|
2604
|
+
"output_type": "execute_result"
|
|
2605
|
+
}
|
|
2606
|
+
],
|
|
2607
|
+
"source": [
|
|
2608
|
+
"pop.unstack(level=0)"
|
|
2609
|
+
]
|
|
2610
|
+
},
|
|
2611
|
+
{
|
|
2612
|
+
"cell_type": "code",
|
|
2613
|
+
"execution_count": 68,
|
|
2614
|
+
"id": "8057f14d-7163-4e8b-8adb-020a9837577a",
|
|
2615
|
+
"metadata": {},
|
|
2616
|
+
"outputs": [
|
|
2617
|
+
{
|
|
2618
|
+
"data": {
|
|
2619
|
+
"text/html": [
|
|
2620
|
+
"<div>\n",
|
|
2621
|
+
"<style scoped>\n",
|
|
2622
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
2623
|
+
" vertical-align: middle;\n",
|
|
2624
|
+
" }\n",
|
|
2625
|
+
"\n",
|
|
2626
|
+
" .dataframe tbody tr th {\n",
|
|
2627
|
+
" vertical-align: top;\n",
|
|
2628
|
+
" }\n",
|
|
2629
|
+
"\n",
|
|
2630
|
+
" .dataframe thead th {\n",
|
|
2631
|
+
" text-align: right;\n",
|
|
2632
|
+
" }\n",
|
|
2633
|
+
"</style>\n",
|
|
2634
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
2635
|
+
" <thead>\n",
|
|
2636
|
+
" <tr style=\"text-align: right;\">\n",
|
|
2637
|
+
" <th>year</th>\n",
|
|
2638
|
+
" <th>2000</th>\n",
|
|
2639
|
+
" <th>2010</th>\n",
|
|
2640
|
+
" </tr>\n",
|
|
2641
|
+
" <tr>\n",
|
|
2642
|
+
" <th>state</th>\n",
|
|
2643
|
+
" <th></th>\n",
|
|
2644
|
+
" <th></th>\n",
|
|
2645
|
+
" </tr>\n",
|
|
2646
|
+
" </thead>\n",
|
|
2647
|
+
" <tbody>\n",
|
|
2648
|
+
" <tr>\n",
|
|
2649
|
+
" <th>California</th>\n",
|
|
2650
|
+
" <td>33871648</td>\n",
|
|
2651
|
+
" <td>37253956</td>\n",
|
|
2652
|
+
" </tr>\n",
|
|
2653
|
+
" <tr>\n",
|
|
2654
|
+
" <th>New York</th>\n",
|
|
2655
|
+
" <td>18976457</td>\n",
|
|
2656
|
+
" <td>19378102</td>\n",
|
|
2657
|
+
" </tr>\n",
|
|
2658
|
+
" <tr>\n",
|
|
2659
|
+
" <th>Texas</th>\n",
|
|
2660
|
+
" <td>20851820</td>\n",
|
|
2661
|
+
" <td>25145561</td>\n",
|
|
2662
|
+
" </tr>\n",
|
|
2663
|
+
" </tbody>\n",
|
|
2664
|
+
"</table>\n",
|
|
2665
|
+
"</div>"
|
|
2666
|
+
],
|
|
2667
|
+
"text/plain": [
|
|
2668
|
+
"year 2000 2010\n",
|
|
2669
|
+
"state \n",
|
|
2670
|
+
"California 33871648 37253956\n",
|
|
2671
|
+
"New York 18976457 19378102\n",
|
|
2672
|
+
"Texas 20851820 25145561"
|
|
2673
|
+
]
|
|
2674
|
+
},
|
|
2675
|
+
"execution_count": 68,
|
|
2676
|
+
"metadata": {},
|
|
2677
|
+
"output_type": "execute_result"
|
|
2678
|
+
}
|
|
2679
|
+
],
|
|
2680
|
+
"source": [
|
|
2681
|
+
"pop.unstack(level=1)"
|
|
2682
|
+
]
|
|
2683
|
+
},
|
|
2684
|
+
{
|
|
2685
|
+
"cell_type": "code",
|
|
2686
|
+
"execution_count": 69,
|
|
2687
|
+
"id": "496a65b2-aa0a-4705-95ba-8b3e9cb7e673",
|
|
2688
|
+
"metadata": {},
|
|
2689
|
+
"outputs": [
|
|
2690
|
+
{
|
|
2691
|
+
"data": {
|
|
2692
|
+
"text/plain": [
|
|
2693
|
+
"state year\n",
|
|
2694
|
+
"California 2000 33871648\n",
|
|
2695
|
+
" 2010 37253956\n",
|
|
2696
|
+
"New York 2000 18976457\n",
|
|
2697
|
+
" 2010 19378102\n",
|
|
2698
|
+
"Texas 2000 20851820\n",
|
|
2699
|
+
" 2010 25145561\n",
|
|
2700
|
+
"dtype: int64"
|
|
2701
|
+
]
|
|
2702
|
+
},
|
|
2703
|
+
"execution_count": 69,
|
|
2704
|
+
"metadata": {},
|
|
2705
|
+
"output_type": "execute_result"
|
|
2706
|
+
}
|
|
2707
|
+
],
|
|
2708
|
+
"source": [
|
|
2709
|
+
"pop.unstack().stack()"
|
|
2710
|
+
]
|
|
2711
|
+
},
|
|
2712
|
+
{
|
|
2713
|
+
"cell_type": "code",
|
|
2714
|
+
"execution_count": 70,
|
|
2715
|
+
"id": "0ba9ee6c-f39c-4f7a-b748-9c30b64d52e6",
|
|
2716
|
+
"metadata": {},
|
|
2717
|
+
"outputs": [
|
|
2718
|
+
{
|
|
2719
|
+
"data": {
|
|
2720
|
+
"text/html": [
|
|
2721
|
+
"<div>\n",
|
|
2722
|
+
"<style scoped>\n",
|
|
2723
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
2724
|
+
" vertical-align: middle;\n",
|
|
2725
|
+
" }\n",
|
|
2726
|
+
"\n",
|
|
2727
|
+
" .dataframe tbody tr th {\n",
|
|
2728
|
+
" vertical-align: top;\n",
|
|
2729
|
+
" }\n",
|
|
2730
|
+
"\n",
|
|
2731
|
+
" .dataframe thead th {\n",
|
|
2732
|
+
" text-align: right;\n",
|
|
2733
|
+
" }\n",
|
|
2734
|
+
"</style>\n",
|
|
2735
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
2736
|
+
" <thead>\n",
|
|
2737
|
+
" <tr style=\"text-align: right;\">\n",
|
|
2738
|
+
" <th></th>\n",
|
|
2739
|
+
" <th>state</th>\n",
|
|
2740
|
+
" <th>year</th>\n",
|
|
2741
|
+
" <th>population</th>\n",
|
|
2742
|
+
" </tr>\n",
|
|
2743
|
+
" </thead>\n",
|
|
2744
|
+
" <tbody>\n",
|
|
2745
|
+
" <tr>\n",
|
|
2746
|
+
" <th>0</th>\n",
|
|
2747
|
+
" <td>California</td>\n",
|
|
2748
|
+
" <td>2000</td>\n",
|
|
2749
|
+
" <td>33871648</td>\n",
|
|
2750
|
+
" </tr>\n",
|
|
2751
|
+
" <tr>\n",
|
|
2752
|
+
" <th>1</th>\n",
|
|
2753
|
+
" <td>California</td>\n",
|
|
2754
|
+
" <td>2010</td>\n",
|
|
2755
|
+
" <td>37253956</td>\n",
|
|
2756
|
+
" </tr>\n",
|
|
2757
|
+
" <tr>\n",
|
|
2758
|
+
" <th>2</th>\n",
|
|
2759
|
+
" <td>New York</td>\n",
|
|
2760
|
+
" <td>2000</td>\n",
|
|
2761
|
+
" <td>18976457</td>\n",
|
|
2762
|
+
" </tr>\n",
|
|
2763
|
+
" <tr>\n",
|
|
2764
|
+
" <th>3</th>\n",
|
|
2765
|
+
" <td>New York</td>\n",
|
|
2766
|
+
" <td>2010</td>\n",
|
|
2767
|
+
" <td>19378102</td>\n",
|
|
2768
|
+
" </tr>\n",
|
|
2769
|
+
" <tr>\n",
|
|
2770
|
+
" <th>4</th>\n",
|
|
2771
|
+
" <td>Texas</td>\n",
|
|
2772
|
+
" <td>2000</td>\n",
|
|
2773
|
+
" <td>20851820</td>\n",
|
|
2774
|
+
" </tr>\n",
|
|
2775
|
+
" <tr>\n",
|
|
2776
|
+
" <th>5</th>\n",
|
|
2777
|
+
" <td>Texas</td>\n",
|
|
2778
|
+
" <td>2010</td>\n",
|
|
2779
|
+
" <td>25145561</td>\n",
|
|
2780
|
+
" </tr>\n",
|
|
2781
|
+
" </tbody>\n",
|
|
2782
|
+
"</table>\n",
|
|
2783
|
+
"</div>"
|
|
2784
|
+
],
|
|
2785
|
+
"text/plain": [
|
|
2786
|
+
" state year population\n",
|
|
2787
|
+
"0 California 2000 33871648\n",
|
|
2788
|
+
"1 California 2010 37253956\n",
|
|
2789
|
+
"2 New York 2000 18976457\n",
|
|
2790
|
+
"3 New York 2010 19378102\n",
|
|
2791
|
+
"4 Texas 2000 20851820\n",
|
|
2792
|
+
"5 Texas 2010 25145561"
|
|
2793
|
+
]
|
|
2794
|
+
},
|
|
2795
|
+
"execution_count": 70,
|
|
2796
|
+
"metadata": {},
|
|
2797
|
+
"output_type": "execute_result"
|
|
2798
|
+
}
|
|
2799
|
+
],
|
|
2800
|
+
"source": [
|
|
2801
|
+
"pop_flat = pop.reset_index(name='population')\n",
|
|
2802
|
+
"pop_flat"
|
|
2803
|
+
]
|
|
2804
|
+
},
|
|
2805
|
+
{
|
|
2806
|
+
"cell_type": "code",
|
|
2807
|
+
"execution_count": 71,
|
|
2808
|
+
"id": "4e67b8ea-8331-4ec5-96fd-03101e4a2abb",
|
|
2809
|
+
"metadata": {},
|
|
2810
|
+
"outputs": [
|
|
2811
|
+
{
|
|
2812
|
+
"data": {
|
|
2813
|
+
"text/html": [
|
|
2814
|
+
"<div>\n",
|
|
2815
|
+
"<style scoped>\n",
|
|
2816
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
2817
|
+
" vertical-align: middle;\n",
|
|
2818
|
+
" }\n",
|
|
2819
|
+
"\n",
|
|
2820
|
+
" .dataframe tbody tr th {\n",
|
|
2821
|
+
" vertical-align: top;\n",
|
|
2822
|
+
" }\n",
|
|
2823
|
+
"\n",
|
|
2824
|
+
" .dataframe thead th {\n",
|
|
2825
|
+
" text-align: right;\n",
|
|
2826
|
+
" }\n",
|
|
2827
|
+
"</style>\n",
|
|
2828
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
2829
|
+
" <thead>\n",
|
|
2830
|
+
" <tr style=\"text-align: right;\">\n",
|
|
2831
|
+
" <th></th>\n",
|
|
2832
|
+
" <th></th>\n",
|
|
2833
|
+
" <th>population</th>\n",
|
|
2834
|
+
" </tr>\n",
|
|
2835
|
+
" <tr>\n",
|
|
2836
|
+
" <th>state</th>\n",
|
|
2837
|
+
" <th>year</th>\n",
|
|
2838
|
+
" <th></th>\n",
|
|
2839
|
+
" </tr>\n",
|
|
2840
|
+
" </thead>\n",
|
|
2841
|
+
" <tbody>\n",
|
|
2842
|
+
" <tr>\n",
|
|
2843
|
+
" <th rowspan=\"2\" valign=\"top\">California</th>\n",
|
|
2844
|
+
" <th>2000</th>\n",
|
|
2845
|
+
" <td>33871648</td>\n",
|
|
2846
|
+
" </tr>\n",
|
|
2847
|
+
" <tr>\n",
|
|
2848
|
+
" <th>2010</th>\n",
|
|
2849
|
+
" <td>37253956</td>\n",
|
|
2850
|
+
" </tr>\n",
|
|
2851
|
+
" <tr>\n",
|
|
2852
|
+
" <th rowspan=\"2\" valign=\"top\">New York</th>\n",
|
|
2853
|
+
" <th>2000</th>\n",
|
|
2854
|
+
" <td>18976457</td>\n",
|
|
2855
|
+
" </tr>\n",
|
|
2856
|
+
" <tr>\n",
|
|
2857
|
+
" <th>2010</th>\n",
|
|
2858
|
+
" <td>19378102</td>\n",
|
|
2859
|
+
" </tr>\n",
|
|
2860
|
+
" <tr>\n",
|
|
2861
|
+
" <th rowspan=\"2\" valign=\"top\">Texas</th>\n",
|
|
2862
|
+
" <th>2000</th>\n",
|
|
2863
|
+
" <td>20851820</td>\n",
|
|
2864
|
+
" </tr>\n",
|
|
2865
|
+
" <tr>\n",
|
|
2866
|
+
" <th>2010</th>\n",
|
|
2867
|
+
" <td>25145561</td>\n",
|
|
2868
|
+
" </tr>\n",
|
|
2869
|
+
" </tbody>\n",
|
|
2870
|
+
"</table>\n",
|
|
2871
|
+
"</div>"
|
|
2872
|
+
],
|
|
2873
|
+
"text/plain": [
|
|
2874
|
+
" population\n",
|
|
2875
|
+
"state year \n",
|
|
2876
|
+
"California 2000 33871648\n",
|
|
2877
|
+
" 2010 37253956\n",
|
|
2878
|
+
"New York 2000 18976457\n",
|
|
2879
|
+
" 2010 19378102\n",
|
|
2880
|
+
"Texas 2000 20851820\n",
|
|
2881
|
+
" 2010 25145561"
|
|
2882
|
+
]
|
|
2883
|
+
},
|
|
2884
|
+
"execution_count": 71,
|
|
2885
|
+
"metadata": {},
|
|
2886
|
+
"output_type": "execute_result"
|
|
2887
|
+
}
|
|
2888
|
+
],
|
|
2889
|
+
"source": [
|
|
2890
|
+
"pop_flat.set_index(['state', 'year'])"
|
|
2891
|
+
]
|
|
2892
|
+
},
|
|
2893
|
+
{
|
|
2894
|
+
"cell_type": "code",
|
|
2895
|
+
"execution_count": 72,
|
|
2896
|
+
"id": "76f64c1e-51ab-4675-af1c-e77ddcb160fb",
|
|
2897
|
+
"metadata": {},
|
|
2898
|
+
"outputs": [
|
|
2899
|
+
{
|
|
2900
|
+
"data": {
|
|
2901
|
+
"text/html": [
|
|
2902
|
+
"<div>\n",
|
|
2903
|
+
"<style scoped>\n",
|
|
2904
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
2905
|
+
" vertical-align: middle;\n",
|
|
2906
|
+
" }\n",
|
|
2907
|
+
"\n",
|
|
2908
|
+
" .dataframe tbody tr th {\n",
|
|
2909
|
+
" vertical-align: top;\n",
|
|
2910
|
+
" }\n",
|
|
2911
|
+
"\n",
|
|
2912
|
+
" .dataframe thead tr th {\n",
|
|
2913
|
+
" text-align: left;\n",
|
|
2914
|
+
" }\n",
|
|
2915
|
+
"\n",
|
|
2916
|
+
" .dataframe thead tr:last-of-type th {\n",
|
|
2917
|
+
" text-align: right;\n",
|
|
2918
|
+
" }\n",
|
|
2919
|
+
"</style>\n",
|
|
2920
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
2921
|
+
" <thead>\n",
|
|
2922
|
+
" <tr>\n",
|
|
2923
|
+
" <th></th>\n",
|
|
2924
|
+
" <th>subject</th>\n",
|
|
2925
|
+
" <th colspan=\"2\" halign=\"left\">Bob</th>\n",
|
|
2926
|
+
" <th colspan=\"2\" halign=\"left\">Guido</th>\n",
|
|
2927
|
+
" <th colspan=\"2\" halign=\"left\">Sue</th>\n",
|
|
2928
|
+
" </tr>\n",
|
|
2929
|
+
" <tr>\n",
|
|
2930
|
+
" <th></th>\n",
|
|
2931
|
+
" <th>type</th>\n",
|
|
2932
|
+
" <th>HR</th>\n",
|
|
2933
|
+
" <th>Temp</th>\n",
|
|
2934
|
+
" <th>HR</th>\n",
|
|
2935
|
+
" <th>Temp</th>\n",
|
|
2936
|
+
" <th>HR</th>\n",
|
|
2937
|
+
" <th>Temp</th>\n",
|
|
2938
|
+
" </tr>\n",
|
|
2939
|
+
" <tr>\n",
|
|
2940
|
+
" <th>year</th>\n",
|
|
2941
|
+
" <th>visit</th>\n",
|
|
2942
|
+
" <th></th>\n",
|
|
2943
|
+
" <th></th>\n",
|
|
2944
|
+
" <th></th>\n",
|
|
2945
|
+
" <th></th>\n",
|
|
2946
|
+
" <th></th>\n",
|
|
2947
|
+
" <th></th>\n",
|
|
2948
|
+
" </tr>\n",
|
|
2949
|
+
" </thead>\n",
|
|
2950
|
+
" <tbody>\n",
|
|
2951
|
+
" <tr>\n",
|
|
2952
|
+
" <th rowspan=\"2\" valign=\"top\">2013</th>\n",
|
|
2953
|
+
" <th>1</th>\n",
|
|
2954
|
+
" <td>49.0</td>\n",
|
|
2955
|
+
" <td>38.5</td>\n",
|
|
2956
|
+
" <td>37.0</td>\n",
|
|
2957
|
+
" <td>38.2</td>\n",
|
|
2958
|
+
" <td>33.0</td>\n",
|
|
2959
|
+
" <td>38.3</td>\n",
|
|
2960
|
+
" </tr>\n",
|
|
2961
|
+
" <tr>\n",
|
|
2962
|
+
" <th>2</th>\n",
|
|
2963
|
+
" <td>43.0</td>\n",
|
|
2964
|
+
" <td>38.6</td>\n",
|
|
2965
|
+
" <td>23.0</td>\n",
|
|
2966
|
+
" <td>37.5</td>\n",
|
|
2967
|
+
" <td>42.0</td>\n",
|
|
2968
|
+
" <td>35.2</td>\n",
|
|
2969
|
+
" </tr>\n",
|
|
2970
|
+
" <tr>\n",
|
|
2971
|
+
" <th rowspan=\"2\" valign=\"top\">2014</th>\n",
|
|
2972
|
+
" <th>1</th>\n",
|
|
2973
|
+
" <td>22.0</td>\n",
|
|
2974
|
+
" <td>37.3</td>\n",
|
|
2975
|
+
" <td>46.0</td>\n",
|
|
2976
|
+
" <td>36.5</td>\n",
|
|
2977
|
+
" <td>35.0</td>\n",
|
|
2978
|
+
" <td>37.3</td>\n",
|
|
2979
|
+
" </tr>\n",
|
|
2980
|
+
" <tr>\n",
|
|
2981
|
+
" <th>2</th>\n",
|
|
2982
|
+
" <td>40.0</td>\n",
|
|
2983
|
+
" <td>36.9</td>\n",
|
|
2984
|
+
" <td>58.0</td>\n",
|
|
2985
|
+
" <td>37.1</td>\n",
|
|
2986
|
+
" <td>48.0</td>\n",
|
|
2987
|
+
" <td>35.8</td>\n",
|
|
2988
|
+
" </tr>\n",
|
|
2989
|
+
" </tbody>\n",
|
|
2990
|
+
"</table>\n",
|
|
2991
|
+
"</div>"
|
|
2992
|
+
],
|
|
2993
|
+
"text/plain": [
|
|
2994
|
+
"subject Bob Guido Sue \n",
|
|
2995
|
+
"type HR Temp HR Temp HR Temp\n",
|
|
2996
|
+
"year visit \n",
|
|
2997
|
+
"2013 1 49.0 38.5 37.0 38.2 33.0 38.3\n",
|
|
2998
|
+
" 2 43.0 38.6 23.0 37.5 42.0 35.2\n",
|
|
2999
|
+
"2014 1 22.0 37.3 46.0 36.5 35.0 37.3\n",
|
|
3000
|
+
" 2 40.0 36.9 58.0 37.1 48.0 35.8"
|
|
3001
|
+
]
|
|
3002
|
+
},
|
|
3003
|
+
"execution_count": 72,
|
|
3004
|
+
"metadata": {},
|
|
3005
|
+
"output_type": "execute_result"
|
|
3006
|
+
}
|
|
3007
|
+
],
|
|
3008
|
+
"source": [
|
|
3009
|
+
"health_data"
|
|
3010
|
+
]
|
|
3011
|
+
},
|
|
3012
|
+
{
|
|
3013
|
+
"cell_type": "code",
|
|
3014
|
+
"execution_count": 76,
|
|
3015
|
+
"id": "478121ee-78c0-4f0f-b226-d3c7d47e6eb8",
|
|
3016
|
+
"metadata": {},
|
|
3017
|
+
"outputs": [
|
|
3018
|
+
{
|
|
3019
|
+
"data": {
|
|
3020
|
+
"text/html": [
|
|
3021
|
+
"<div>\n",
|
|
3022
|
+
"<style scoped>\n",
|
|
3023
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
3024
|
+
" vertical-align: middle;\n",
|
|
3025
|
+
" }\n",
|
|
3026
|
+
"\n",
|
|
3027
|
+
" .dataframe tbody tr th {\n",
|
|
3028
|
+
" vertical-align: top;\n",
|
|
3029
|
+
" }\n",
|
|
3030
|
+
"\n",
|
|
3031
|
+
" .dataframe thead tr th {\n",
|
|
3032
|
+
" text-align: left;\n",
|
|
3033
|
+
" }\n",
|
|
3034
|
+
"\n",
|
|
3035
|
+
" .dataframe thead tr:last-of-type th {\n",
|
|
3036
|
+
" text-align: right;\n",
|
|
3037
|
+
" }\n",
|
|
3038
|
+
"</style>\n",
|
|
3039
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
3040
|
+
" <thead>\n",
|
|
3041
|
+
" <tr>\n",
|
|
3042
|
+
" <th>subject</th>\n",
|
|
3043
|
+
" <th colspan=\"2\" halign=\"left\">Bob</th>\n",
|
|
3044
|
+
" <th colspan=\"2\" halign=\"left\">Guido</th>\n",
|
|
3045
|
+
" <th colspan=\"2\" halign=\"left\">Sue</th>\n",
|
|
3046
|
+
" </tr>\n",
|
|
3047
|
+
" <tr>\n",
|
|
3048
|
+
" <th>type</th>\n",
|
|
3049
|
+
" <th>HR</th>\n",
|
|
3050
|
+
" <th>Temp</th>\n",
|
|
3051
|
+
" <th>HR</th>\n",
|
|
3052
|
+
" <th>Temp</th>\n",
|
|
3053
|
+
" <th>HR</th>\n",
|
|
3054
|
+
" <th>Temp</th>\n",
|
|
3055
|
+
" </tr>\n",
|
|
3056
|
+
" <tr>\n",
|
|
3057
|
+
" <th>year</th>\n",
|
|
3058
|
+
" <th></th>\n",
|
|
3059
|
+
" <th></th>\n",
|
|
3060
|
+
" <th></th>\n",
|
|
3061
|
+
" <th></th>\n",
|
|
3062
|
+
" <th></th>\n",
|
|
3063
|
+
" <th></th>\n",
|
|
3064
|
+
" </tr>\n",
|
|
3065
|
+
" </thead>\n",
|
|
3066
|
+
" <tbody>\n",
|
|
3067
|
+
" <tr>\n",
|
|
3068
|
+
" <th>2013</th>\n",
|
|
3069
|
+
" <td>46.0</td>\n",
|
|
3070
|
+
" <td>38.55</td>\n",
|
|
3071
|
+
" <td>30.0</td>\n",
|
|
3072
|
+
" <td>37.85</td>\n",
|
|
3073
|
+
" <td>37.5</td>\n",
|
|
3074
|
+
" <td>36.75</td>\n",
|
|
3075
|
+
" </tr>\n",
|
|
3076
|
+
" <tr>\n",
|
|
3077
|
+
" <th>2014</th>\n",
|
|
3078
|
+
" <td>31.0</td>\n",
|
|
3079
|
+
" <td>37.10</td>\n",
|
|
3080
|
+
" <td>52.0</td>\n",
|
|
3081
|
+
" <td>36.80</td>\n",
|
|
3082
|
+
" <td>41.5</td>\n",
|
|
3083
|
+
" <td>36.55</td>\n",
|
|
3084
|
+
" </tr>\n",
|
|
3085
|
+
" </tbody>\n",
|
|
3086
|
+
"</table>\n",
|
|
3087
|
+
"</div>"
|
|
3088
|
+
],
|
|
3089
|
+
"text/plain": [
|
|
3090
|
+
"subject Bob Guido Sue \n",
|
|
3091
|
+
"type HR Temp HR Temp HR Temp\n",
|
|
3092
|
+
"year \n",
|
|
3093
|
+
"2013 46.0 38.55 30.0 37.85 37.5 36.75\n",
|
|
3094
|
+
"2014 31.0 37.10 52.0 36.80 41.5 36.55"
|
|
3095
|
+
]
|
|
3096
|
+
},
|
|
3097
|
+
"execution_count": 76,
|
|
3098
|
+
"metadata": {},
|
|
3099
|
+
"output_type": "execute_result"
|
|
3100
|
+
}
|
|
3101
|
+
],
|
|
3102
|
+
"source": [
|
|
3103
|
+
"data_mean = health_data.groupby(level='year').mean()\n",
|
|
3104
|
+
"data_mean\n"
|
|
3105
|
+
]
|
|
3106
|
+
},
|
|
3107
|
+
{
|
|
3108
|
+
"cell_type": "code",
|
|
3109
|
+
"execution_count": 78,
|
|
3110
|
+
"id": "02eea5df-9a32-451a-9e77-230df16e8dc4",
|
|
3111
|
+
"metadata": {},
|
|
3112
|
+
"outputs": [
|
|
3113
|
+
{
|
|
3114
|
+
"name": "stderr",
|
|
3115
|
+
"output_type": "stream",
|
|
3116
|
+
"text": [
|
|
3117
|
+
"C:\\Users\\darsh\\AppData\\Local\\Temp\\ipykernel_18940\\900051928.py:1: FutureWarning: DataFrame.groupby with axis=1 is deprecated. Do `frame.T.groupby(...)` without axis instead.\n",
|
|
3118
|
+
" data_mean.groupby(axis=1, level='type').mean()\n"
|
|
3119
|
+
]
|
|
3120
|
+
},
|
|
3121
|
+
{
|
|
3122
|
+
"data": {
|
|
3123
|
+
"text/html": [
|
|
3124
|
+
"<div>\n",
|
|
3125
|
+
"<style scoped>\n",
|
|
3126
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
3127
|
+
" vertical-align: middle;\n",
|
|
3128
|
+
" }\n",
|
|
3129
|
+
"\n",
|
|
3130
|
+
" .dataframe tbody tr th {\n",
|
|
3131
|
+
" vertical-align: top;\n",
|
|
3132
|
+
" }\n",
|
|
3133
|
+
"\n",
|
|
3134
|
+
" .dataframe thead th {\n",
|
|
3135
|
+
" text-align: right;\n",
|
|
3136
|
+
" }\n",
|
|
3137
|
+
"</style>\n",
|
|
3138
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
3139
|
+
" <thead>\n",
|
|
3140
|
+
" <tr style=\"text-align: right;\">\n",
|
|
3141
|
+
" <th>type</th>\n",
|
|
3142
|
+
" <th>HR</th>\n",
|
|
3143
|
+
" <th>Temp</th>\n",
|
|
3144
|
+
" </tr>\n",
|
|
3145
|
+
" <tr>\n",
|
|
3146
|
+
" <th>year</th>\n",
|
|
3147
|
+
" <th></th>\n",
|
|
3148
|
+
" <th></th>\n",
|
|
3149
|
+
" </tr>\n",
|
|
3150
|
+
" </thead>\n",
|
|
3151
|
+
" <tbody>\n",
|
|
3152
|
+
" <tr>\n",
|
|
3153
|
+
" <th>2013</th>\n",
|
|
3154
|
+
" <td>37.833333</td>\n",
|
|
3155
|
+
" <td>37.716667</td>\n",
|
|
3156
|
+
" </tr>\n",
|
|
3157
|
+
" <tr>\n",
|
|
3158
|
+
" <th>2014</th>\n",
|
|
3159
|
+
" <td>41.500000</td>\n",
|
|
3160
|
+
" <td>36.816667</td>\n",
|
|
3161
|
+
" </tr>\n",
|
|
3162
|
+
" </tbody>\n",
|
|
3163
|
+
"</table>\n",
|
|
3164
|
+
"</div>"
|
|
3165
|
+
],
|
|
3166
|
+
"text/plain": [
|
|
3167
|
+
"type HR Temp\n",
|
|
3168
|
+
"year \n",
|
|
3169
|
+
"2013 37.833333 37.716667\n",
|
|
3170
|
+
"2014 41.500000 36.816667"
|
|
3171
|
+
]
|
|
3172
|
+
},
|
|
3173
|
+
"execution_count": 78,
|
|
3174
|
+
"metadata": {},
|
|
3175
|
+
"output_type": "execute_result"
|
|
3176
|
+
}
|
|
3177
|
+
],
|
|
3178
|
+
"source": [
|
|
3179
|
+
"data_mean.groupby(axis=1, level='type').mean()\n"
|
|
3180
|
+
]
|
|
3181
|
+
},
|
|
3182
|
+
{
|
|
3183
|
+
"cell_type": "code",
|
|
3184
|
+
"execution_count": null,
|
|
3185
|
+
"id": "5e820d27-723f-4254-adfb-a55903baa80f",
|
|
3186
|
+
"metadata": {},
|
|
3187
|
+
"outputs": [],
|
|
3188
|
+
"source": []
|
|
3189
|
+
}
|
|
3190
|
+
],
|
|
3191
|
+
"metadata": {
|
|
3192
|
+
"kernelspec": {
|
|
3193
|
+
"display_name": "Python 3 (ipykernel)",
|
|
3194
|
+
"language": "python",
|
|
3195
|
+
"name": "python3"
|
|
3196
|
+
},
|
|
3197
|
+
"language_info": {
|
|
3198
|
+
"codemirror_mode": {
|
|
3199
|
+
"name": "ipython",
|
|
3200
|
+
"version": 3
|
|
3201
|
+
},
|
|
3202
|
+
"file_extension": ".py",
|
|
3203
|
+
"mimetype": "text/x-python",
|
|
3204
|
+
"name": "python",
|
|
3205
|
+
"nbconvert_exporter": "python",
|
|
3206
|
+
"pygments_lexer": "ipython3",
|
|
3207
|
+
"version": "3.12.0"
|
|
3208
|
+
}
|
|
3209
|
+
},
|
|
3210
|
+
"nbformat": 4,
|
|
3211
|
+
"nbformat_minor": 5
|
|
3212
|
+
}
|