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 +1,1013 @@
|
|
|
1
|
+
{
|
|
2
|
+
"cells": [
|
|
3
|
+
{
|
|
4
|
+
"cell_type": "code",
|
|
5
|
+
"execution_count": 1,
|
|
6
|
+
"id": "1fd1dba2",
|
|
7
|
+
"metadata": {},
|
|
8
|
+
"outputs": [],
|
|
9
|
+
"source": [
|
|
10
|
+
"import numpy as np\n",
|
|
11
|
+
"import pandas as pd\n"
|
|
12
|
+
]
|
|
13
|
+
},
|
|
14
|
+
{
|
|
15
|
+
"cell_type": "code",
|
|
16
|
+
"execution_count": 2,
|
|
17
|
+
"id": "2b7ac399",
|
|
18
|
+
"metadata": {},
|
|
19
|
+
"outputs": [
|
|
20
|
+
{
|
|
21
|
+
"data": {
|
|
22
|
+
"text/plain": [
|
|
23
|
+
"array([1, None, 3, 4], dtype=object)"
|
|
24
|
+
]
|
|
25
|
+
},
|
|
26
|
+
"execution_count": 2,
|
|
27
|
+
"metadata": {},
|
|
28
|
+
"output_type": "execute_result"
|
|
29
|
+
}
|
|
30
|
+
],
|
|
31
|
+
"source": [
|
|
32
|
+
"vals1 = np.array([1, None, 3, 4])\n",
|
|
33
|
+
"vals1"
|
|
34
|
+
]
|
|
35
|
+
},
|
|
36
|
+
{
|
|
37
|
+
"cell_type": "code",
|
|
38
|
+
"execution_count": 4,
|
|
39
|
+
"id": "50393a54",
|
|
40
|
+
"metadata": {},
|
|
41
|
+
"outputs": [
|
|
42
|
+
{
|
|
43
|
+
"name": "stdout",
|
|
44
|
+
"output_type": "stream",
|
|
45
|
+
"text": [
|
|
46
|
+
"dtype = object\n",
|
|
47
|
+
"63.4 ms ± 4.21 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n",
|
|
48
|
+
"\n",
|
|
49
|
+
"dtype = int\n",
|
|
50
|
+
"2.24 ms ± 134 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n",
|
|
51
|
+
"\n"
|
|
52
|
+
]
|
|
53
|
+
}
|
|
54
|
+
],
|
|
55
|
+
"source": [
|
|
56
|
+
"for dtype in ['object', 'int']:\n",
|
|
57
|
+
" print(\"dtype =\", dtype)\n",
|
|
58
|
+
" %timeit np.arange(1E6, dtype=dtype).sum()\n",
|
|
59
|
+
" print()"
|
|
60
|
+
]
|
|
61
|
+
},
|
|
62
|
+
{
|
|
63
|
+
"cell_type": "code",
|
|
64
|
+
"execution_count": 6,
|
|
65
|
+
"id": "ef13ae07",
|
|
66
|
+
"metadata": {},
|
|
67
|
+
"outputs": [
|
|
68
|
+
{
|
|
69
|
+
"data": {
|
|
70
|
+
"text/plain": [
|
|
71
|
+
"dtype('float64')"
|
|
72
|
+
]
|
|
73
|
+
},
|
|
74
|
+
"execution_count": 6,
|
|
75
|
+
"metadata": {},
|
|
76
|
+
"output_type": "execute_result"
|
|
77
|
+
}
|
|
78
|
+
],
|
|
79
|
+
"source": [
|
|
80
|
+
"vals2 = np.array([1, np.nan, 3, 4])\n",
|
|
81
|
+
"vals2.dtype\n",
|
|
82
|
+
"\n"
|
|
83
|
+
]
|
|
84
|
+
},
|
|
85
|
+
{
|
|
86
|
+
"cell_type": "code",
|
|
87
|
+
"execution_count": 7,
|
|
88
|
+
"id": "a608bfd2",
|
|
89
|
+
"metadata": {},
|
|
90
|
+
"outputs": [
|
|
91
|
+
{
|
|
92
|
+
"data": {
|
|
93
|
+
"text/plain": [
|
|
94
|
+
"nan"
|
|
95
|
+
]
|
|
96
|
+
},
|
|
97
|
+
"execution_count": 7,
|
|
98
|
+
"metadata": {},
|
|
99
|
+
"output_type": "execute_result"
|
|
100
|
+
}
|
|
101
|
+
],
|
|
102
|
+
"source": [
|
|
103
|
+
"1 + np.nan"
|
|
104
|
+
]
|
|
105
|
+
},
|
|
106
|
+
{
|
|
107
|
+
"cell_type": "code",
|
|
108
|
+
"execution_count": 8,
|
|
109
|
+
"id": "ee1ea156",
|
|
110
|
+
"metadata": {},
|
|
111
|
+
"outputs": [
|
|
112
|
+
{
|
|
113
|
+
"data": {
|
|
114
|
+
"text/plain": [
|
|
115
|
+
"nan"
|
|
116
|
+
]
|
|
117
|
+
},
|
|
118
|
+
"execution_count": 8,
|
|
119
|
+
"metadata": {},
|
|
120
|
+
"output_type": "execute_result"
|
|
121
|
+
}
|
|
122
|
+
],
|
|
123
|
+
"source": [
|
|
124
|
+
"0 * np.nan"
|
|
125
|
+
]
|
|
126
|
+
},
|
|
127
|
+
{
|
|
128
|
+
"cell_type": "code",
|
|
129
|
+
"execution_count": 9,
|
|
130
|
+
"id": "710ab0fa",
|
|
131
|
+
"metadata": {},
|
|
132
|
+
"outputs": [
|
|
133
|
+
{
|
|
134
|
+
"data": {
|
|
135
|
+
"text/plain": [
|
|
136
|
+
"(nan, nan, nan)"
|
|
137
|
+
]
|
|
138
|
+
},
|
|
139
|
+
"execution_count": 9,
|
|
140
|
+
"metadata": {},
|
|
141
|
+
"output_type": "execute_result"
|
|
142
|
+
}
|
|
143
|
+
],
|
|
144
|
+
"source": [
|
|
145
|
+
"vals2.sum(), vals2.min(), vals2.max()\n"
|
|
146
|
+
]
|
|
147
|
+
},
|
|
148
|
+
{
|
|
149
|
+
"cell_type": "code",
|
|
150
|
+
"execution_count": 10,
|
|
151
|
+
"id": "57cd4e3a",
|
|
152
|
+
"metadata": {},
|
|
153
|
+
"outputs": [
|
|
154
|
+
{
|
|
155
|
+
"data": {
|
|
156
|
+
"text/plain": [
|
|
157
|
+
"(8.0, 1.0, 4.0)"
|
|
158
|
+
]
|
|
159
|
+
},
|
|
160
|
+
"execution_count": 10,
|
|
161
|
+
"metadata": {},
|
|
162
|
+
"output_type": "execute_result"
|
|
163
|
+
}
|
|
164
|
+
],
|
|
165
|
+
"source": [
|
|
166
|
+
"np.nansum(vals2), np.nanmin(vals2), np.nanmax(vals2)\n"
|
|
167
|
+
]
|
|
168
|
+
},
|
|
169
|
+
{
|
|
170
|
+
"cell_type": "code",
|
|
171
|
+
"execution_count": 12,
|
|
172
|
+
"id": "648ccea3",
|
|
173
|
+
"metadata": {},
|
|
174
|
+
"outputs": [
|
|
175
|
+
{
|
|
176
|
+
"data": {
|
|
177
|
+
"text/plain": [
|
|
178
|
+
"0 1.0\n",
|
|
179
|
+
"1 NaN\n",
|
|
180
|
+
"2 2.0\n",
|
|
181
|
+
"3 NaN\n",
|
|
182
|
+
"dtype: float64"
|
|
183
|
+
]
|
|
184
|
+
},
|
|
185
|
+
"execution_count": 12,
|
|
186
|
+
"metadata": {},
|
|
187
|
+
"output_type": "execute_result"
|
|
188
|
+
}
|
|
189
|
+
],
|
|
190
|
+
"source": [
|
|
191
|
+
"pd.Series([1, np.nan, 2, None])\n"
|
|
192
|
+
]
|
|
193
|
+
},
|
|
194
|
+
{
|
|
195
|
+
"cell_type": "code",
|
|
196
|
+
"execution_count": 13,
|
|
197
|
+
"id": "8ecef540",
|
|
198
|
+
"metadata": {},
|
|
199
|
+
"outputs": [
|
|
200
|
+
{
|
|
201
|
+
"data": {
|
|
202
|
+
"text/plain": [
|
|
203
|
+
"0 0\n",
|
|
204
|
+
"1 1\n",
|
|
205
|
+
"dtype: int32"
|
|
206
|
+
]
|
|
207
|
+
},
|
|
208
|
+
"execution_count": 13,
|
|
209
|
+
"metadata": {},
|
|
210
|
+
"output_type": "execute_result"
|
|
211
|
+
}
|
|
212
|
+
],
|
|
213
|
+
"source": [
|
|
214
|
+
"x = pd.Series(range(2), dtype=int)\n",
|
|
215
|
+
"x"
|
|
216
|
+
]
|
|
217
|
+
},
|
|
218
|
+
{
|
|
219
|
+
"cell_type": "code",
|
|
220
|
+
"execution_count": 14,
|
|
221
|
+
"id": "097233c1",
|
|
222
|
+
"metadata": {},
|
|
223
|
+
"outputs": [
|
|
224
|
+
{
|
|
225
|
+
"data": {
|
|
226
|
+
"text/plain": [
|
|
227
|
+
"0 NaN\n",
|
|
228
|
+
"1 1.0\n",
|
|
229
|
+
"dtype: float64"
|
|
230
|
+
]
|
|
231
|
+
},
|
|
232
|
+
"execution_count": 14,
|
|
233
|
+
"metadata": {},
|
|
234
|
+
"output_type": "execute_result"
|
|
235
|
+
}
|
|
236
|
+
],
|
|
237
|
+
"source": [
|
|
238
|
+
"x[0] = None\n",
|
|
239
|
+
"x"
|
|
240
|
+
]
|
|
241
|
+
},
|
|
242
|
+
{
|
|
243
|
+
"cell_type": "code",
|
|
244
|
+
"execution_count": 15,
|
|
245
|
+
"id": "f2b81620",
|
|
246
|
+
"metadata": {},
|
|
247
|
+
"outputs": [],
|
|
248
|
+
"source": [
|
|
249
|
+
"#Detecting null values\n",
|
|
250
|
+
"data = pd.Series([1, np.nan, 'hello', None])\n"
|
|
251
|
+
]
|
|
252
|
+
},
|
|
253
|
+
{
|
|
254
|
+
"cell_type": "code",
|
|
255
|
+
"execution_count": 16,
|
|
256
|
+
"id": "11a5c988",
|
|
257
|
+
"metadata": {},
|
|
258
|
+
"outputs": [
|
|
259
|
+
{
|
|
260
|
+
"data": {
|
|
261
|
+
"text/plain": [
|
|
262
|
+
"0 False\n",
|
|
263
|
+
"1 True\n",
|
|
264
|
+
"2 False\n",
|
|
265
|
+
"3 True\n",
|
|
266
|
+
"dtype: bool"
|
|
267
|
+
]
|
|
268
|
+
},
|
|
269
|
+
"execution_count": 16,
|
|
270
|
+
"metadata": {},
|
|
271
|
+
"output_type": "execute_result"
|
|
272
|
+
}
|
|
273
|
+
],
|
|
274
|
+
"source": [
|
|
275
|
+
"data.isnull()\n"
|
|
276
|
+
]
|
|
277
|
+
},
|
|
278
|
+
{
|
|
279
|
+
"cell_type": "code",
|
|
280
|
+
"execution_count": 17,
|
|
281
|
+
"id": "9ecaa9a5",
|
|
282
|
+
"metadata": {},
|
|
283
|
+
"outputs": [
|
|
284
|
+
{
|
|
285
|
+
"data": {
|
|
286
|
+
"text/plain": [
|
|
287
|
+
"0 1\n",
|
|
288
|
+
"2 hello\n",
|
|
289
|
+
"dtype: object"
|
|
290
|
+
]
|
|
291
|
+
},
|
|
292
|
+
"execution_count": 17,
|
|
293
|
+
"metadata": {},
|
|
294
|
+
"output_type": "execute_result"
|
|
295
|
+
}
|
|
296
|
+
],
|
|
297
|
+
"source": [
|
|
298
|
+
"data[data.notnull()]\n"
|
|
299
|
+
]
|
|
300
|
+
},
|
|
301
|
+
{
|
|
302
|
+
"cell_type": "code",
|
|
303
|
+
"execution_count": 18,
|
|
304
|
+
"id": "d7c214eb",
|
|
305
|
+
"metadata": {},
|
|
306
|
+
"outputs": [
|
|
307
|
+
{
|
|
308
|
+
"data": {
|
|
309
|
+
"text/plain": [
|
|
310
|
+
"0 1\n",
|
|
311
|
+
"2 hello\n",
|
|
312
|
+
"dtype: object"
|
|
313
|
+
]
|
|
314
|
+
},
|
|
315
|
+
"execution_count": 18,
|
|
316
|
+
"metadata": {},
|
|
317
|
+
"output_type": "execute_result"
|
|
318
|
+
}
|
|
319
|
+
],
|
|
320
|
+
"source": [
|
|
321
|
+
"#Dropping null values\n",
|
|
322
|
+
"data.dropna()\n"
|
|
323
|
+
]
|
|
324
|
+
},
|
|
325
|
+
{
|
|
326
|
+
"cell_type": "code",
|
|
327
|
+
"execution_count": 20,
|
|
328
|
+
"id": "8d7e21ef",
|
|
329
|
+
"metadata": {},
|
|
330
|
+
"outputs": [
|
|
331
|
+
{
|
|
332
|
+
"data": {
|
|
333
|
+
"text/html": [
|
|
334
|
+
"<div>\n",
|
|
335
|
+
"<style scoped>\n",
|
|
336
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
337
|
+
" vertical-align: middle;\n",
|
|
338
|
+
" }\n",
|
|
339
|
+
"\n",
|
|
340
|
+
" .dataframe tbody tr th {\n",
|
|
341
|
+
" vertical-align: top;\n",
|
|
342
|
+
" }\n",
|
|
343
|
+
"\n",
|
|
344
|
+
" .dataframe thead th {\n",
|
|
345
|
+
" text-align: right;\n",
|
|
346
|
+
" }\n",
|
|
347
|
+
"</style>\n",
|
|
348
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
349
|
+
" <thead>\n",
|
|
350
|
+
" <tr style=\"text-align: right;\">\n",
|
|
351
|
+
" <th></th>\n",
|
|
352
|
+
" <th>0</th>\n",
|
|
353
|
+
" <th>1</th>\n",
|
|
354
|
+
" <th>2</th>\n",
|
|
355
|
+
" </tr>\n",
|
|
356
|
+
" </thead>\n",
|
|
357
|
+
" <tbody>\n",
|
|
358
|
+
" <tr>\n",
|
|
359
|
+
" <th>0</th>\n",
|
|
360
|
+
" <td>1.0</td>\n",
|
|
361
|
+
" <td>NaN</td>\n",
|
|
362
|
+
" <td>2</td>\n",
|
|
363
|
+
" </tr>\n",
|
|
364
|
+
" <tr>\n",
|
|
365
|
+
" <th>1</th>\n",
|
|
366
|
+
" <td>2.0</td>\n",
|
|
367
|
+
" <td>3.0</td>\n",
|
|
368
|
+
" <td>5</td>\n",
|
|
369
|
+
" </tr>\n",
|
|
370
|
+
" <tr>\n",
|
|
371
|
+
" <th>2</th>\n",
|
|
372
|
+
" <td>NaN</td>\n",
|
|
373
|
+
" <td>4.0</td>\n",
|
|
374
|
+
" <td>6</td>\n",
|
|
375
|
+
" </tr>\n",
|
|
376
|
+
" </tbody>\n",
|
|
377
|
+
"</table>\n",
|
|
378
|
+
"</div>"
|
|
379
|
+
],
|
|
380
|
+
"text/plain": [
|
|
381
|
+
" 0 1 2\n",
|
|
382
|
+
"0 1.0 NaN 2\n",
|
|
383
|
+
"1 2.0 3.0 5\n",
|
|
384
|
+
"2 NaN 4.0 6"
|
|
385
|
+
]
|
|
386
|
+
},
|
|
387
|
+
"execution_count": 20,
|
|
388
|
+
"metadata": {},
|
|
389
|
+
"output_type": "execute_result"
|
|
390
|
+
}
|
|
391
|
+
],
|
|
392
|
+
"source": [
|
|
393
|
+
"df = pd.DataFrame([[1, np.nan, 2],\n",
|
|
394
|
+
" [2, 3, 5],\n",
|
|
395
|
+
" [np.nan, 4, 6]])\n",
|
|
396
|
+
"df\n"
|
|
397
|
+
]
|
|
398
|
+
},
|
|
399
|
+
{
|
|
400
|
+
"cell_type": "code",
|
|
401
|
+
"execution_count": 21,
|
|
402
|
+
"id": "3355043d",
|
|
403
|
+
"metadata": {},
|
|
404
|
+
"outputs": [
|
|
405
|
+
{
|
|
406
|
+
"data": {
|
|
407
|
+
"text/html": [
|
|
408
|
+
"<div>\n",
|
|
409
|
+
"<style scoped>\n",
|
|
410
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
411
|
+
" vertical-align: middle;\n",
|
|
412
|
+
" }\n",
|
|
413
|
+
"\n",
|
|
414
|
+
" .dataframe tbody tr th {\n",
|
|
415
|
+
" vertical-align: top;\n",
|
|
416
|
+
" }\n",
|
|
417
|
+
"\n",
|
|
418
|
+
" .dataframe thead th {\n",
|
|
419
|
+
" text-align: right;\n",
|
|
420
|
+
" }\n",
|
|
421
|
+
"</style>\n",
|
|
422
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
423
|
+
" <thead>\n",
|
|
424
|
+
" <tr style=\"text-align: right;\">\n",
|
|
425
|
+
" <th></th>\n",
|
|
426
|
+
" <th>0</th>\n",
|
|
427
|
+
" <th>1</th>\n",
|
|
428
|
+
" <th>2</th>\n",
|
|
429
|
+
" </tr>\n",
|
|
430
|
+
" </thead>\n",
|
|
431
|
+
" <tbody>\n",
|
|
432
|
+
" <tr>\n",
|
|
433
|
+
" <th>1</th>\n",
|
|
434
|
+
" <td>2.0</td>\n",
|
|
435
|
+
" <td>3.0</td>\n",
|
|
436
|
+
" <td>5</td>\n",
|
|
437
|
+
" </tr>\n",
|
|
438
|
+
" </tbody>\n",
|
|
439
|
+
"</table>\n",
|
|
440
|
+
"</div>"
|
|
441
|
+
],
|
|
442
|
+
"text/plain": [
|
|
443
|
+
" 0 1 2\n",
|
|
444
|
+
"1 2.0 3.0 5"
|
|
445
|
+
]
|
|
446
|
+
},
|
|
447
|
+
"execution_count": 21,
|
|
448
|
+
"metadata": {},
|
|
449
|
+
"output_type": "execute_result"
|
|
450
|
+
}
|
|
451
|
+
],
|
|
452
|
+
"source": [
|
|
453
|
+
"df.dropna()"
|
|
454
|
+
]
|
|
455
|
+
},
|
|
456
|
+
{
|
|
457
|
+
"cell_type": "code",
|
|
458
|
+
"execution_count": 22,
|
|
459
|
+
"id": "c3c7920b",
|
|
460
|
+
"metadata": {},
|
|
461
|
+
"outputs": [
|
|
462
|
+
{
|
|
463
|
+
"data": {
|
|
464
|
+
"text/html": [
|
|
465
|
+
"<div>\n",
|
|
466
|
+
"<style scoped>\n",
|
|
467
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
468
|
+
" vertical-align: middle;\n",
|
|
469
|
+
" }\n",
|
|
470
|
+
"\n",
|
|
471
|
+
" .dataframe tbody tr th {\n",
|
|
472
|
+
" vertical-align: top;\n",
|
|
473
|
+
" }\n",
|
|
474
|
+
"\n",
|
|
475
|
+
" .dataframe thead th {\n",
|
|
476
|
+
" text-align: right;\n",
|
|
477
|
+
" }\n",
|
|
478
|
+
"</style>\n",
|
|
479
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
480
|
+
" <thead>\n",
|
|
481
|
+
" <tr style=\"text-align: right;\">\n",
|
|
482
|
+
" <th></th>\n",
|
|
483
|
+
" <th>2</th>\n",
|
|
484
|
+
" </tr>\n",
|
|
485
|
+
" </thead>\n",
|
|
486
|
+
" <tbody>\n",
|
|
487
|
+
" <tr>\n",
|
|
488
|
+
" <th>0</th>\n",
|
|
489
|
+
" <td>2</td>\n",
|
|
490
|
+
" </tr>\n",
|
|
491
|
+
" <tr>\n",
|
|
492
|
+
" <th>1</th>\n",
|
|
493
|
+
" <td>5</td>\n",
|
|
494
|
+
" </tr>\n",
|
|
495
|
+
" <tr>\n",
|
|
496
|
+
" <th>2</th>\n",
|
|
497
|
+
" <td>6</td>\n",
|
|
498
|
+
" </tr>\n",
|
|
499
|
+
" </tbody>\n",
|
|
500
|
+
"</table>\n",
|
|
501
|
+
"</div>"
|
|
502
|
+
],
|
|
503
|
+
"text/plain": [
|
|
504
|
+
" 2\n",
|
|
505
|
+
"0 2\n",
|
|
506
|
+
"1 5\n",
|
|
507
|
+
"2 6"
|
|
508
|
+
]
|
|
509
|
+
},
|
|
510
|
+
"execution_count": 22,
|
|
511
|
+
"metadata": {},
|
|
512
|
+
"output_type": "execute_result"
|
|
513
|
+
}
|
|
514
|
+
],
|
|
515
|
+
"source": [
|
|
516
|
+
"df.dropna(axis='columns')"
|
|
517
|
+
]
|
|
518
|
+
},
|
|
519
|
+
{
|
|
520
|
+
"cell_type": "code",
|
|
521
|
+
"execution_count": 23,
|
|
522
|
+
"id": "d987a577",
|
|
523
|
+
"metadata": {},
|
|
524
|
+
"outputs": [
|
|
525
|
+
{
|
|
526
|
+
"data": {
|
|
527
|
+
"text/html": [
|
|
528
|
+
"<div>\n",
|
|
529
|
+
"<style scoped>\n",
|
|
530
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
531
|
+
" vertical-align: middle;\n",
|
|
532
|
+
" }\n",
|
|
533
|
+
"\n",
|
|
534
|
+
" .dataframe tbody tr th {\n",
|
|
535
|
+
" vertical-align: top;\n",
|
|
536
|
+
" }\n",
|
|
537
|
+
"\n",
|
|
538
|
+
" .dataframe thead th {\n",
|
|
539
|
+
" text-align: right;\n",
|
|
540
|
+
" }\n",
|
|
541
|
+
"</style>\n",
|
|
542
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
543
|
+
" <thead>\n",
|
|
544
|
+
" <tr style=\"text-align: right;\">\n",
|
|
545
|
+
" <th></th>\n",
|
|
546
|
+
" <th>0</th>\n",
|
|
547
|
+
" <th>1</th>\n",
|
|
548
|
+
" <th>2</th>\n",
|
|
549
|
+
" <th>3</th>\n",
|
|
550
|
+
" </tr>\n",
|
|
551
|
+
" </thead>\n",
|
|
552
|
+
" <tbody>\n",
|
|
553
|
+
" <tr>\n",
|
|
554
|
+
" <th>0</th>\n",
|
|
555
|
+
" <td>1.0</td>\n",
|
|
556
|
+
" <td>NaN</td>\n",
|
|
557
|
+
" <td>2</td>\n",
|
|
558
|
+
" <td>NaN</td>\n",
|
|
559
|
+
" </tr>\n",
|
|
560
|
+
" <tr>\n",
|
|
561
|
+
" <th>1</th>\n",
|
|
562
|
+
" <td>2.0</td>\n",
|
|
563
|
+
" <td>3.0</td>\n",
|
|
564
|
+
" <td>5</td>\n",
|
|
565
|
+
" <td>NaN</td>\n",
|
|
566
|
+
" </tr>\n",
|
|
567
|
+
" <tr>\n",
|
|
568
|
+
" <th>2</th>\n",
|
|
569
|
+
" <td>NaN</td>\n",
|
|
570
|
+
" <td>4.0</td>\n",
|
|
571
|
+
" <td>6</td>\n",
|
|
572
|
+
" <td>NaN</td>\n",
|
|
573
|
+
" </tr>\n",
|
|
574
|
+
" </tbody>\n",
|
|
575
|
+
"</table>\n",
|
|
576
|
+
"</div>"
|
|
577
|
+
],
|
|
578
|
+
"text/plain": [
|
|
579
|
+
" 0 1 2 3\n",
|
|
580
|
+
"0 1.0 NaN 2 NaN\n",
|
|
581
|
+
"1 2.0 3.0 5 NaN\n",
|
|
582
|
+
"2 NaN 4.0 6 NaN"
|
|
583
|
+
]
|
|
584
|
+
},
|
|
585
|
+
"execution_count": 23,
|
|
586
|
+
"metadata": {},
|
|
587
|
+
"output_type": "execute_result"
|
|
588
|
+
}
|
|
589
|
+
],
|
|
590
|
+
"source": [
|
|
591
|
+
"df[3] = np.nan\n",
|
|
592
|
+
"df"
|
|
593
|
+
]
|
|
594
|
+
},
|
|
595
|
+
{
|
|
596
|
+
"cell_type": "code",
|
|
597
|
+
"execution_count": 24,
|
|
598
|
+
"id": "5fa2e884",
|
|
599
|
+
"metadata": {},
|
|
600
|
+
"outputs": [
|
|
601
|
+
{
|
|
602
|
+
"data": {
|
|
603
|
+
"text/html": [
|
|
604
|
+
"<div>\n",
|
|
605
|
+
"<style scoped>\n",
|
|
606
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
607
|
+
" vertical-align: middle;\n",
|
|
608
|
+
" }\n",
|
|
609
|
+
"\n",
|
|
610
|
+
" .dataframe tbody tr th {\n",
|
|
611
|
+
" vertical-align: top;\n",
|
|
612
|
+
" }\n",
|
|
613
|
+
"\n",
|
|
614
|
+
" .dataframe thead th {\n",
|
|
615
|
+
" text-align: right;\n",
|
|
616
|
+
" }\n",
|
|
617
|
+
"</style>\n",
|
|
618
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
619
|
+
" <thead>\n",
|
|
620
|
+
" <tr style=\"text-align: right;\">\n",
|
|
621
|
+
" <th></th>\n",
|
|
622
|
+
" <th>0</th>\n",
|
|
623
|
+
" <th>1</th>\n",
|
|
624
|
+
" <th>2</th>\n",
|
|
625
|
+
" </tr>\n",
|
|
626
|
+
" </thead>\n",
|
|
627
|
+
" <tbody>\n",
|
|
628
|
+
" <tr>\n",
|
|
629
|
+
" <th>0</th>\n",
|
|
630
|
+
" <td>1.0</td>\n",
|
|
631
|
+
" <td>NaN</td>\n",
|
|
632
|
+
" <td>2</td>\n",
|
|
633
|
+
" </tr>\n",
|
|
634
|
+
" <tr>\n",
|
|
635
|
+
" <th>1</th>\n",
|
|
636
|
+
" <td>2.0</td>\n",
|
|
637
|
+
" <td>3.0</td>\n",
|
|
638
|
+
" <td>5</td>\n",
|
|
639
|
+
" </tr>\n",
|
|
640
|
+
" <tr>\n",
|
|
641
|
+
" <th>2</th>\n",
|
|
642
|
+
" <td>NaN</td>\n",
|
|
643
|
+
" <td>4.0</td>\n",
|
|
644
|
+
" <td>6</td>\n",
|
|
645
|
+
" </tr>\n",
|
|
646
|
+
" </tbody>\n",
|
|
647
|
+
"</table>\n",
|
|
648
|
+
"</div>"
|
|
649
|
+
],
|
|
650
|
+
"text/plain": [
|
|
651
|
+
" 0 1 2\n",
|
|
652
|
+
"0 1.0 NaN 2\n",
|
|
653
|
+
"1 2.0 3.0 5\n",
|
|
654
|
+
"2 NaN 4.0 6"
|
|
655
|
+
]
|
|
656
|
+
},
|
|
657
|
+
"execution_count": 24,
|
|
658
|
+
"metadata": {},
|
|
659
|
+
"output_type": "execute_result"
|
|
660
|
+
}
|
|
661
|
+
],
|
|
662
|
+
"source": [
|
|
663
|
+
"df.dropna(axis='columns', how='all')"
|
|
664
|
+
]
|
|
665
|
+
},
|
|
666
|
+
{
|
|
667
|
+
"cell_type": "code",
|
|
668
|
+
"execution_count": 25,
|
|
669
|
+
"id": "2b62a4d7",
|
|
670
|
+
"metadata": {},
|
|
671
|
+
"outputs": [
|
|
672
|
+
{
|
|
673
|
+
"data": {
|
|
674
|
+
"text/html": [
|
|
675
|
+
"<div>\n",
|
|
676
|
+
"<style scoped>\n",
|
|
677
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
678
|
+
" vertical-align: middle;\n",
|
|
679
|
+
" }\n",
|
|
680
|
+
"\n",
|
|
681
|
+
" .dataframe tbody tr th {\n",
|
|
682
|
+
" vertical-align: top;\n",
|
|
683
|
+
" }\n",
|
|
684
|
+
"\n",
|
|
685
|
+
" .dataframe thead th {\n",
|
|
686
|
+
" text-align: right;\n",
|
|
687
|
+
" }\n",
|
|
688
|
+
"</style>\n",
|
|
689
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
690
|
+
" <thead>\n",
|
|
691
|
+
" <tr style=\"text-align: right;\">\n",
|
|
692
|
+
" <th></th>\n",
|
|
693
|
+
" <th>0</th>\n",
|
|
694
|
+
" <th>1</th>\n",
|
|
695
|
+
" <th>2</th>\n",
|
|
696
|
+
" <th>3</th>\n",
|
|
697
|
+
" </tr>\n",
|
|
698
|
+
" </thead>\n",
|
|
699
|
+
" <tbody>\n",
|
|
700
|
+
" <tr>\n",
|
|
701
|
+
" <th>1</th>\n",
|
|
702
|
+
" <td>2.0</td>\n",
|
|
703
|
+
" <td>3.0</td>\n",
|
|
704
|
+
" <td>5</td>\n",
|
|
705
|
+
" <td>NaN</td>\n",
|
|
706
|
+
" </tr>\n",
|
|
707
|
+
" </tbody>\n",
|
|
708
|
+
"</table>\n",
|
|
709
|
+
"</div>"
|
|
710
|
+
],
|
|
711
|
+
"text/plain": [
|
|
712
|
+
" 0 1 2 3\n",
|
|
713
|
+
"1 2.0 3.0 5 NaN"
|
|
714
|
+
]
|
|
715
|
+
},
|
|
716
|
+
"execution_count": 25,
|
|
717
|
+
"metadata": {},
|
|
718
|
+
"output_type": "execute_result"
|
|
719
|
+
}
|
|
720
|
+
],
|
|
721
|
+
"source": [
|
|
722
|
+
"df.dropna(axis='rows', thresh=3)\n"
|
|
723
|
+
]
|
|
724
|
+
},
|
|
725
|
+
{
|
|
726
|
+
"cell_type": "code",
|
|
727
|
+
"execution_count": 26,
|
|
728
|
+
"id": "ab65fccd",
|
|
729
|
+
"metadata": {},
|
|
730
|
+
"outputs": [
|
|
731
|
+
{
|
|
732
|
+
"data": {
|
|
733
|
+
"text/plain": [
|
|
734
|
+
"a 1.0\n",
|
|
735
|
+
"b NaN\n",
|
|
736
|
+
"c 2.0\n",
|
|
737
|
+
"d NaN\n",
|
|
738
|
+
"e 3.0\n",
|
|
739
|
+
"dtype: float64"
|
|
740
|
+
]
|
|
741
|
+
},
|
|
742
|
+
"execution_count": 26,
|
|
743
|
+
"metadata": {},
|
|
744
|
+
"output_type": "execute_result"
|
|
745
|
+
}
|
|
746
|
+
],
|
|
747
|
+
"source": [
|
|
748
|
+
"#Filling null values\n",
|
|
749
|
+
"data = pd.Series([1, np.nan, 2, None, 3], index=list('abcde'))\n",
|
|
750
|
+
"data"
|
|
751
|
+
]
|
|
752
|
+
},
|
|
753
|
+
{
|
|
754
|
+
"cell_type": "code",
|
|
755
|
+
"execution_count": 27,
|
|
756
|
+
"id": "79701b50",
|
|
757
|
+
"metadata": {},
|
|
758
|
+
"outputs": [
|
|
759
|
+
{
|
|
760
|
+
"data": {
|
|
761
|
+
"text/plain": [
|
|
762
|
+
"a 1.0\n",
|
|
763
|
+
"b 0.0\n",
|
|
764
|
+
"c 2.0\n",
|
|
765
|
+
"d 0.0\n",
|
|
766
|
+
"e 3.0\n",
|
|
767
|
+
"dtype: float64"
|
|
768
|
+
]
|
|
769
|
+
},
|
|
770
|
+
"execution_count": 27,
|
|
771
|
+
"metadata": {},
|
|
772
|
+
"output_type": "execute_result"
|
|
773
|
+
}
|
|
774
|
+
],
|
|
775
|
+
"source": [
|
|
776
|
+
"data.fillna(0)"
|
|
777
|
+
]
|
|
778
|
+
},
|
|
779
|
+
{
|
|
780
|
+
"cell_type": "code",
|
|
781
|
+
"execution_count": 28,
|
|
782
|
+
"id": "e2920e55",
|
|
783
|
+
"metadata": {},
|
|
784
|
+
"outputs": [
|
|
785
|
+
{
|
|
786
|
+
"data": {
|
|
787
|
+
"text/plain": [
|
|
788
|
+
"a 1.0\n",
|
|
789
|
+
"b 1.0\n",
|
|
790
|
+
"c 2.0\n",
|
|
791
|
+
"d 2.0\n",
|
|
792
|
+
"e 3.0\n",
|
|
793
|
+
"dtype: float64"
|
|
794
|
+
]
|
|
795
|
+
},
|
|
796
|
+
"execution_count": 28,
|
|
797
|
+
"metadata": {},
|
|
798
|
+
"output_type": "execute_result"
|
|
799
|
+
}
|
|
800
|
+
],
|
|
801
|
+
"source": [
|
|
802
|
+
"# forward-fill\n",
|
|
803
|
+
"data.fillna(method='ffill')"
|
|
804
|
+
]
|
|
805
|
+
},
|
|
806
|
+
{
|
|
807
|
+
"cell_type": "code",
|
|
808
|
+
"execution_count": 30,
|
|
809
|
+
"id": "057ad778",
|
|
810
|
+
"metadata": {},
|
|
811
|
+
"outputs": [
|
|
812
|
+
{
|
|
813
|
+
"data": {
|
|
814
|
+
"text/plain": [
|
|
815
|
+
"a 1.0\n",
|
|
816
|
+
"b 2.0\n",
|
|
817
|
+
"c 2.0\n",
|
|
818
|
+
"d 3.0\n",
|
|
819
|
+
"e 3.0\n",
|
|
820
|
+
"dtype: float64"
|
|
821
|
+
]
|
|
822
|
+
},
|
|
823
|
+
"execution_count": 30,
|
|
824
|
+
"metadata": {},
|
|
825
|
+
"output_type": "execute_result"
|
|
826
|
+
}
|
|
827
|
+
],
|
|
828
|
+
"source": [
|
|
829
|
+
"# back-fill\n",
|
|
830
|
+
"data.fillna(method='bfill')\n"
|
|
831
|
+
]
|
|
832
|
+
},
|
|
833
|
+
{
|
|
834
|
+
"cell_type": "code",
|
|
835
|
+
"execution_count": 31,
|
|
836
|
+
"id": "1d99ee5b",
|
|
837
|
+
"metadata": {},
|
|
838
|
+
"outputs": [
|
|
839
|
+
{
|
|
840
|
+
"data": {
|
|
841
|
+
"text/html": [
|
|
842
|
+
"<div>\n",
|
|
843
|
+
"<style scoped>\n",
|
|
844
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
845
|
+
" vertical-align: middle;\n",
|
|
846
|
+
" }\n",
|
|
847
|
+
"\n",
|
|
848
|
+
" .dataframe tbody tr th {\n",
|
|
849
|
+
" vertical-align: top;\n",
|
|
850
|
+
" }\n",
|
|
851
|
+
"\n",
|
|
852
|
+
" .dataframe thead th {\n",
|
|
853
|
+
" text-align: right;\n",
|
|
854
|
+
" }\n",
|
|
855
|
+
"</style>\n",
|
|
856
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
857
|
+
" <thead>\n",
|
|
858
|
+
" <tr style=\"text-align: right;\">\n",
|
|
859
|
+
" <th></th>\n",
|
|
860
|
+
" <th>0</th>\n",
|
|
861
|
+
" <th>1</th>\n",
|
|
862
|
+
" <th>2</th>\n",
|
|
863
|
+
" <th>3</th>\n",
|
|
864
|
+
" </tr>\n",
|
|
865
|
+
" </thead>\n",
|
|
866
|
+
" <tbody>\n",
|
|
867
|
+
" <tr>\n",
|
|
868
|
+
" <th>0</th>\n",
|
|
869
|
+
" <td>1.0</td>\n",
|
|
870
|
+
" <td>NaN</td>\n",
|
|
871
|
+
" <td>2</td>\n",
|
|
872
|
+
" <td>NaN</td>\n",
|
|
873
|
+
" </tr>\n",
|
|
874
|
+
" <tr>\n",
|
|
875
|
+
" <th>1</th>\n",
|
|
876
|
+
" <td>2.0</td>\n",
|
|
877
|
+
" <td>3.0</td>\n",
|
|
878
|
+
" <td>5</td>\n",
|
|
879
|
+
" <td>NaN</td>\n",
|
|
880
|
+
" </tr>\n",
|
|
881
|
+
" <tr>\n",
|
|
882
|
+
" <th>2</th>\n",
|
|
883
|
+
" <td>NaN</td>\n",
|
|
884
|
+
" <td>4.0</td>\n",
|
|
885
|
+
" <td>6</td>\n",
|
|
886
|
+
" <td>NaN</td>\n",
|
|
887
|
+
" </tr>\n",
|
|
888
|
+
" </tbody>\n",
|
|
889
|
+
"</table>\n",
|
|
890
|
+
"</div>"
|
|
891
|
+
],
|
|
892
|
+
"text/plain": [
|
|
893
|
+
" 0 1 2 3\n",
|
|
894
|
+
"0 1.0 NaN 2 NaN\n",
|
|
895
|
+
"1 2.0 3.0 5 NaN\n",
|
|
896
|
+
"2 NaN 4.0 6 NaN"
|
|
897
|
+
]
|
|
898
|
+
},
|
|
899
|
+
"execution_count": 31,
|
|
900
|
+
"metadata": {},
|
|
901
|
+
"output_type": "execute_result"
|
|
902
|
+
}
|
|
903
|
+
],
|
|
904
|
+
"source": [
|
|
905
|
+
"df"
|
|
906
|
+
]
|
|
907
|
+
},
|
|
908
|
+
{
|
|
909
|
+
"cell_type": "code",
|
|
910
|
+
"execution_count": 32,
|
|
911
|
+
"id": "a5e51c61",
|
|
912
|
+
"metadata": {},
|
|
913
|
+
"outputs": [
|
|
914
|
+
{
|
|
915
|
+
"data": {
|
|
916
|
+
"text/html": [
|
|
917
|
+
"<div>\n",
|
|
918
|
+
"<style scoped>\n",
|
|
919
|
+
" .dataframe tbody tr th:only-of-type {\n",
|
|
920
|
+
" vertical-align: middle;\n",
|
|
921
|
+
" }\n",
|
|
922
|
+
"\n",
|
|
923
|
+
" .dataframe tbody tr th {\n",
|
|
924
|
+
" vertical-align: top;\n",
|
|
925
|
+
" }\n",
|
|
926
|
+
"\n",
|
|
927
|
+
" .dataframe thead th {\n",
|
|
928
|
+
" text-align: right;\n",
|
|
929
|
+
" }\n",
|
|
930
|
+
"</style>\n",
|
|
931
|
+
"<table border=\"1\" class=\"dataframe\">\n",
|
|
932
|
+
" <thead>\n",
|
|
933
|
+
" <tr style=\"text-align: right;\">\n",
|
|
934
|
+
" <th></th>\n",
|
|
935
|
+
" <th>0</th>\n",
|
|
936
|
+
" <th>1</th>\n",
|
|
937
|
+
" <th>2</th>\n",
|
|
938
|
+
" <th>3</th>\n",
|
|
939
|
+
" </tr>\n",
|
|
940
|
+
" </thead>\n",
|
|
941
|
+
" <tbody>\n",
|
|
942
|
+
" <tr>\n",
|
|
943
|
+
" <th>0</th>\n",
|
|
944
|
+
" <td>1.0</td>\n",
|
|
945
|
+
" <td>1.0</td>\n",
|
|
946
|
+
" <td>2.0</td>\n",
|
|
947
|
+
" <td>2.0</td>\n",
|
|
948
|
+
" </tr>\n",
|
|
949
|
+
" <tr>\n",
|
|
950
|
+
" <th>1</th>\n",
|
|
951
|
+
" <td>2.0</td>\n",
|
|
952
|
+
" <td>3.0</td>\n",
|
|
953
|
+
" <td>5.0</td>\n",
|
|
954
|
+
" <td>5.0</td>\n",
|
|
955
|
+
" </tr>\n",
|
|
956
|
+
" <tr>\n",
|
|
957
|
+
" <th>2</th>\n",
|
|
958
|
+
" <td>NaN</td>\n",
|
|
959
|
+
" <td>4.0</td>\n",
|
|
960
|
+
" <td>6.0</td>\n",
|
|
961
|
+
" <td>6.0</td>\n",
|
|
962
|
+
" </tr>\n",
|
|
963
|
+
" </tbody>\n",
|
|
964
|
+
"</table>\n",
|
|
965
|
+
"</div>"
|
|
966
|
+
],
|
|
967
|
+
"text/plain": [
|
|
968
|
+
" 0 1 2 3\n",
|
|
969
|
+
"0 1.0 1.0 2.0 2.0\n",
|
|
970
|
+
"1 2.0 3.0 5.0 5.0\n",
|
|
971
|
+
"2 NaN 4.0 6.0 6.0"
|
|
972
|
+
]
|
|
973
|
+
},
|
|
974
|
+
"execution_count": 32,
|
|
975
|
+
"metadata": {},
|
|
976
|
+
"output_type": "execute_result"
|
|
977
|
+
}
|
|
978
|
+
],
|
|
979
|
+
"source": [
|
|
980
|
+
"df.fillna(method='ffill', axis=1)"
|
|
981
|
+
]
|
|
982
|
+
},
|
|
983
|
+
{
|
|
984
|
+
"cell_type": "code",
|
|
985
|
+
"execution_count": null,
|
|
986
|
+
"id": "1ae8ebbc",
|
|
987
|
+
"metadata": {},
|
|
988
|
+
"outputs": [],
|
|
989
|
+
"source": []
|
|
990
|
+
}
|
|
991
|
+
],
|
|
992
|
+
"metadata": {
|
|
993
|
+
"kernelspec": {
|
|
994
|
+
"display_name": "Python 3 (ipykernel)",
|
|
995
|
+
"language": "python",
|
|
996
|
+
"name": "python3"
|
|
997
|
+
},
|
|
998
|
+
"language_info": {
|
|
999
|
+
"codemirror_mode": {
|
|
1000
|
+
"name": "ipython",
|
|
1001
|
+
"version": 3
|
|
1002
|
+
},
|
|
1003
|
+
"file_extension": ".py",
|
|
1004
|
+
"mimetype": "text/x-python",
|
|
1005
|
+
"name": "python",
|
|
1006
|
+
"nbconvert_exporter": "python",
|
|
1007
|
+
"pygments_lexer": "ipython3",
|
|
1008
|
+
"version": "3.9.13"
|
|
1009
|
+
}
|
|
1010
|
+
},
|
|
1011
|
+
"nbformat": 4,
|
|
1012
|
+
"nbformat_minor": 5
|
|
1013
|
+
}
|