-
Notifications
You must be signed in to change notification settings - Fork 1
Expand file tree
/
Copy pathhandling_null_weather.py
More file actions
514 lines (331 loc) · 15.2 KB
/
handling_null_weather.py
File metadata and controls
514 lines (331 loc) · 15.2 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
# -*- coding: utf-8 -*-
"""handling_null_weather.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1E3ubASFuOlNQpiZ6wnhLiaVKIohE5Usm
"""
import pandas as pd
from google.colab import files
uploaded=files.upload()
weather= pd.read_csv('weather_data.csv')
print(weather)
#delete all entries beyong 2023 week 10, as we do not need them
# Filter the DataFrame to keep entries up to year 2023, week 10
filtered_df = weather.loc[(weather['Season'] < 2023) | ((weather['Season'] == 2023) & (weather['Week'] <= 10))]
# Update the original DataFrame with the filtered data
weather = filtered_df.copy()
# Display the updated DataFrame if needed
print(weather)
# Loop through all columns and check for null values
for column in weather.columns:
null_count = weather[column].isnull().sum()
print(f"Column '{column}' has {null_count} null values.")
# Find and return rows where 'Weather' column has null values
null_weather_rows = weather[weather['Weather'].isnull()]
# Display the rows with null values in the 'Weather' column
print(null_weather_rows)
# Replace null values in the 'Weather' column with 'Na'
weather['Weather'].fillna('Na', inplace=True)
"""**UPDATING WEATHER COLUMN**"""
# Find and return all unique values in the 'Weather' column
unique_weather_values = weather['Weather'].unique()
# Display the unique weather values
print(unique_weather_values)
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""Since there are not many values, i can find the weather for these days
season 2012 week 3 falcons vs chargers -->
* GAME PLAYED ON :sept 23 2012,
* GAME PLAYED IN: san diego HOME
* STADIUM: sdccu stadium
* OUTDOOR/INDOOR: outdoor
https://www.espn.com/nfl/game/_/gameId/320923024
https://www.timeanddate.com/weather/usa/san-diego/historic?month=9&year=2012
* WEATHER -- PARTLY CLOUDY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2012) & (weather['Week'] == 3) & (weather['Team1'] == 'Falcons') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Partly Cloudy'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2012 week 11 bears vs 49ers
* GAME PLAYED ON:November 19 2012
* GAME PLAYED IN: san francisco
* ARENA: Candle stick park
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/321119025
https://www.timeanddate.com/weather/usa/san-francisco/historic?month=11&year=2012
* WEATHER: PARTLY CLOUDY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2012) & (weather['Week'] == 11) & (weather['Team1'] == 'Bears') & (weather['Team2'] == '49ers'), 'Weather'] = 'Partly Cloudy'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2012 week 15 panthers vs chargers
* GAME PLAYED ON:December 16 2012
* GAME PLAYED IN: san diego
* ARENA: SDCCU
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/321216024
https://www.timeanddate.com/weather/usa/san-diego/historic?month=12&year=2012
* WEATHER: PARTLY CLOUDY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2012) & (weather['Week'] == 15) & (weather['Team1'] == 'Panthers') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Partly Cloudy'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2012 week 15 Seahawks vs Bills
* GAME PLAYED ON:December 16 2012
* GAME PLAYED IN: toronto
* ARENA: rogers center
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/321216024
https://www.timeanddate.com/weather/usa/san-diego/historic?month=12&year=2012
* WEATHER: RAINING
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2012) & (weather['Week'] == 15) & (weather['Team1'] == 'Seahawks') & (weather['Team2'] == 'Bills'), 'Weather'] = 'Raining'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2012 week 17 raiders vs chargers
* GAME PLAYED ON:Jan 1 2012
* GAME PLAYED IN: Oakland
* ARENA: Oakland Coliseum
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/320101013
https://www.timeanddate.com/weather/usa/oakland/historic?month=1&year=2012
* WEATHER: PARTLY CLOUDY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2012) & (weather['Week'] == 17) & (weather['Team1'] == 'Raiders') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Partly Cloudy'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2012 week 17 Cardinals vs 49ers
* GAME PLAYED ON: 8:30 PM, October 29, 2012
* GAME PLAYED IN: glendale arizona
* ARENA: State farm stadium RETRACTABLE ROOF
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/321216024
https://www.timeanddate.com/weather/usa/san-diego/historic?month=12&year=2012
* WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2012) & (weather['Week'] == 17) & (weather['Team1'] == 'Cardinals') & (weather['Team2'] == '49ers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2013 week 1 Packers vs 49ers
* GAME PLAYED ON:Sept 8 2013
* GAME PLAYED IN: san francisco
* ARENA: candlestick park
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/330908025
https://www.timeanddate.com/weather/usa/san-francisco/historic?month=9&year=2013
* WEATHER: Sunny
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2013) & (weather['Week'] == 1) & (weather['Team1'] == 'Packers') & (weather['Team2'] == '49ers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2013 week 1 Texans vs Chargers
* GAME PLAYED ON:Sept 9 2013
* GAME PLAYED IN: san diego
* ARENA: sdccu
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/330909024
https://www.timeanddate.com/weather/usa/san-francisco/historic?month=9&year=2013
* WEATHER: Sunny
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2013) & (weather['Week'] == 1) & (weather['Team1'] == 'Texans') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2013 week 3 colts vs 49ers
* GAME PLAYED ON: September 22, 2013
* GAME PLAYED IN: san francisco
* ARENA: candlestick aprk
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/330922025
https://www.timeanddate.com/weather/usa/san-francisco/historic?month=9&year=2013
* WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2013) & (weather['Week'] == 3) & (weather['Team1'] == 'Colts') & (weather['Team2'] == '49ers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2013 week 4 cowboys chargers
* GAME PLAYED ON: sept 29 2013
* GAME PLAYED IN: san diego
* ARENA: SDCCU
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/330929024
https://www.timeanddate.com/weather/usa/san-diego/historic?month=12&year=2012
* WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2013) & (weather['Week'] == 4) & (weather['Team1'] == 'Cowboys') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2013 week 6 Colts chargers
* GAME PLAYED ON: oct 14 2013
* GAME PLAYED IN: san diego
* ARENA: SDCCU
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/330929024
https://www.timeanddate.com/weather/usa/san-diego/historic?month=12&year=2012
* WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2013) & (weather['Week'] == 6) & (weather['Team1'] == 'Colts') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2013 week 10 Panthers 49ers
* GAME PLAYED ON: nov 10 2013
* GAME PLAYED IN: san francisco
* ARENA: candlestick park
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/331110025
https://www.timeanddate.com/weather/usa/san-francisco/historic?month=11&year=2013
* WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2013) & (weather['Week'] == 10) & (weather['Team1'] == 'Panthers') & (weather['Team2'] == '49ers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2013 week 10 Broncos chargers
* GAME PLAYED ON: nov 10 2013
* GAME PLAYED IN: san diego
* ARENA: sdccu
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/331110025
https://www.timeanddate.com/weather/usa/san-francisco/historic?month=11&year=2013
WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2013) & (weather['Week'] == 10) & (weather['Team1'] == 'Broncos') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2014 week 4 Jaguars chargers
* GAME PLAYED ON: sept 28 2014
* GAME PLAYED IN: san diego
* ARENA: sdccu
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/400554290
https://www.timeanddate.com/weather/usa/san-diego/historic?month=9&year=2014
WEATHER: PARTLY CLOUDY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2014) & (weather['Week'] == 4) & (weather['Team1'] == 'Jaguars') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Partly Cloudy'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2014 week 5 Jets chargers
* GAME PLAYED ON: oct 5 2014
* GAME PLAYED IN: san diego
* ARENA: sdccu
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/400554275
https://www.timeanddate.com/weather/usa/san-diego/historic?month=9&year=2014
WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2014) & (weather['Week'] == 5) & (weather['Team1'] == 'Jets') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2014 week 7 Chiefs chargers
* GAME PLAYED ON: December 28, 2014
* GAME PLAYED IN: kansas city MO
* ARENA: geha field at arrowhead stadium
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/400554413
https://www.timeanddate.com/weather/usa/kansas-city-kansas/historic?month=12&year=2014
WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2014) & (weather['Week'] == 7) & (weather['Team1'] == 'Chiefs') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2014 week 11 Raiders chargers
* GAME PLAYED ON: November 16, 2014
* GAME PLAYED IN: san diego
* ARENA: sdccu
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/400554391
https://www.timeanddate.com/weather/usa/san-diego/historic?month=9&year=2014
WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2014) & (weather['Week'] == 11) & (weather['Team1'] == 'Raiders') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2014 week 12 Rams chargers
* GAME PLAYED ON: November 23, 2014
* GAME PLAYED IN: san diego
* ARENA: sdccu
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/400554360
https://www.timeanddate.com/weather/usa/san-diego/historic?month=9&year=2014
WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2014) & (weather['Week'] == 12) & (weather['Team1'] == 'Rams') & (weather['Team2'] == 'Chargers'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""2023 week 4 Falcons Jaguars
* GAME PLAYED ON: oct 1, 2023
* GAME PLAYED IN: london
* ARENA: wembley stadium
* OUTDOOR/INDOOR : OUTDOOR
https://www.espn.com/nfl/game/_/gameId/400554391
https://www.timeanddate.com/weather/usa/san-diego/historic?month=9&year=2014
WEATHER: SUNNY
"""
# Replace 'Na' with 'partly cloudy' for the specified entity
weather.loc[(weather['Season'] == 2023) & (weather['Week'] == 4) & (weather['Team1'] == 'Falcons') & (weather['Team2'] == 'Jaguars'), 'Weather'] = 'Sunny'
# Find and return all rows where 'Wather' column has the value 'na'
na_weather_rows = weather[weather['Weather'] == 'Na']
# Display the rows with 'Weather' value equal to 'na'
print(na_weather_rows)
"""
---
"""
weather.to_csv('updated_weatherr.csv', index=False)
from google.colab import files
uploaded=files.upload()
nfl_teams= pd.read_csv('nfl_teams.csv')
print(nfl_teams)