-
Notifications
You must be signed in to change notification settings - Fork 1
/
xG_xR_Model_Explained.ipynb
3110 lines (3110 loc) · 126 KB
/
xG_xR_Model_Explained.ipynb
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
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import scrape_functions\n",
"from datetime import date, timedelta\n",
"import json_pbp\n",
"import html_pbp\n",
"import seaborn as sbs\n",
"import espn_pbp\n",
"import json_shifts\n",
"import html_shifts\n",
"import playing_roster\n",
"import json_schedule\n",
"import pandas as pd\n",
"import time\n",
"import numpy as np\n",
"import datetime\n",
"import warnings\n",
"import shared\n",
"import pickle\n",
"#pip install mysql-connector-python-rf\n",
"import mysql.connector\n",
"from mysql.connector import Error\n",
"from sqlalchemy import create_engine\n",
"\n",
"pd.set_option('display.max_columns', None)\n",
"pd.set_option('display.max_colwidth', 999)\n",
"pd.set_option('display.max_rows', None)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create Rink Adjust Object"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"\n",
"import thinkbayes2 as tb\n",
"import thinkbayes as tb0\n",
"\n",
"\n",
"class RinkAdjust(object):\n",
" \n",
" def __init__( self ):\n",
" self.teamxcdf, self.teamycdf, self.otherxcdf, self.otherycdf = {}, {}, {}, {}\n",
"\n",
" \n",
" def addCDFs( self, team, this_x_cdf, this_y_cdf, other_x_cdf, other_y_cdf ):\n",
" self.teamxcdf[team] = this_x_cdf \n",
" self.teamycdf[team] = this_y_cdf \n",
" self.otherxcdf[team] = other_x_cdf \n",
" self.otherycdf[team] = other_y_cdf\n",
"\n",
"\n",
" def addTeam( self, team, this_team, rest_of_league ):\n",
" this_x_cdf = tb.MakeCdfFromPmf( tb.MakePmfFromList( this_team.X_unadj ) )\n",
" this_y_cdf = tb.MakeCdfFromPmf( tb.MakePmfFromList( this_team.Y_unadj ) )\n",
" other_x_cdf = tb.MakeCdfFromPmf( tb.MakePmfFromList( rest_of_league.X_unadj ) )\n",
" other_y_cdf = tb.MakeCdfFromPmf( tb.MakePmfFromList( rest_of_league.Y_unadj ) )\n",
" self.addCDFs( team, this_x_cdf, this_y_cdf, other_x_cdf, other_y_cdf )\n",
"\n",
"\n",
" def PlotTeamCDFs( self, team, savefig=False ):\n",
" this_x_cdf = self.teamxcdf[team]\n",
" this_y_cdf = self.teamycdf[team]\n",
" other_x_cdf = self.otherxcdf[team] \n",
" other_y_cdf = self.otherycdf[team]\n",
"\n",
" f, axx = plt.subplots( 1, 2, sharey='col' )\n",
" f.set_size_inches( 14, 8 )\n",
" \n",
" xx1, yx1 = this_x_cdf.Render()\n",
" xx2, yx2 = other_x_cdf.Render()\n",
"\n",
" axx[0].plot( xx1, yx1, color='blue', label='@%s' % team )\n",
" axx[0].plot( xx2, yx2, color='brown', label='@Rest of League' )\n",
" axx[0].set_xlabel( 'CDF of X' )\n",
" axx[0].legend()\n",
" \n",
" xy1, yy1 = this_y_cdf.Render()\n",
" xy2, yy2 = other_y_cdf.Render()\n",
" \n",
" axx[1].plot( xy1, yy1, color='blue', label='@%s' % team )\n",
" axx[1].plot( xy2, yy2, color='brown', label='@Rest of League' )\n",
" axx[1].set_xlabel( 'CDF of Y' )\n",
" axx[1].legend()\n",
" \n",
" f.suptitle( 'Cumulative Density Function for Shot Location Rink Bias Adjustment' )\n",
" \n",
" plt.show()\n",
" \n",
" if savefig:\n",
" #f.set_tight_layout( True )\n",
" plt.savefig( 'Rink bias CDF chart %s.png' % team )\n",
"\n",
"\n",
" def rink_bias_adjust( self, x, y, team ):\n",
" \"\"\" this method implements the actual location conversion from biased to \"unbiased\" shot location\n",
" \n",
" the way it works for rink bias adjustment is that for a given shot location in a specific rink,\n",
" you find the cumulative probabilities for that x and y in that rink. Then you calculate the league \n",
" equivalent x and y that have the same probabilities as the one measured in the specific rink\n",
" \n",
" The equivalency CDFs are calculated using only visiting teams, which ensures that both single rink and\n",
" league wide rinks have as wide a sample of teams as possible but avoid any possible home team bias.\n",
" All of which lets us assume that they are then unbiased enough to be representative (at least enough \n",
" for standardization purposes)\n",
" \n",
" This is (my adaption of my understanding of) Shuckers' method for rink bias adjustment as described in Appendix A here:\n",
" http://www.sloansportsconference.com/wp-content/uploads/2013/Total%20Hockey%20Rating%20(THoR)%20A%20comprehensive%20statistical%20rating%20of%20National%20Hockey%20League%20forwards%20and%20defensemen%20based%20upon%20all%20on-ice%20events.pdf\n",
" \n",
" for example, if a shot x coordinate is measured as xmeas in a rink\n",
" \n",
" xprob = this_x_cdf.Prob( xmeas ) # cum prob of seeing xmeas in this rink\n",
" xadj = other_x_cdf.Value( xprob ) # value associated with same prob in rest of league \n",
" \n",
" analogous process for y\n",
" \n",
" The code for Cdf/Pmf creation and manipulation is taken directly from Allan Downey's code for \"Think Bayes\"\n",
" \"\"\"\n",
" \n",
" xprob = self.teamxcdf[team].Prob( x )\n",
" newx = self.otherxcdf[team].Value( xprob )\n",
" \n",
" yprob = self.teamycdf[team].Prob( y )\n",
" newy = self.otherycdf[team].Value( yprob )\n",
" \n",
" return newx, newy"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Create Function to Transform Raw NHL PBP Data\n",
"\n",
"NHL PBP Data from scraper: https://github.com/HarryShomer/Hockey-Scraper"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true,
"scrolled": true
},
"outputs": [],
"source": [
"def transform_data(data):\n",
"\n",
" import warnings\n",
" warnings.simplefilter(\"ignore\")\n",
" \n",
" from sqlalchemy import create_engine\n",
" \n",
" pbp_df = data\n",
"\n",
" print(\"All events and columns: \" + str(pbp_df.shape))\n",
" \n",
" ## Remove shootouts\n",
" pbp_df['season'] = pbp_df.apply( lambda x: str(pd.to_datetime(x.Date).year-1) + str(pd.to_datetime(x.Date).year) if pd.to_datetime(x.Date).month < 9 else str(pd.to_datetime(x.Date).year) + str(pd.to_datetime(x.Date).year + 1), axis=1 )\n",
" \n",
" \n",
"\n",
" pbp_df['season2'] = pbp_df.apply( lambda x: x.season if x.Game_Id < 30000 else str(x.season) + \"p\", axis=1 )\n",
"\n",
" pbp_df['Season_Type'] = pbp_df.apply( lambda x: 'RS' if x.Game_Id < 30000 else 'PO', axis=1 )\n",
"\n",
" pbp_df['season_model'] = pbp_df.apply(lambda x: '2011_2012' if x.season in ['20102011','20112012'] else\n",
" '2013_2014' if x.season in ['20122013','20132014'] else\n",
" '2015_2016' if x.season in ['20142015','20152016'] else\n",
" '2017_2018' if x.season in ['20162017','20172018'] else 0, axis = 1)\n",
"\n",
" pbp_df = pbp_df.drop_duplicates(['season','Game_Id','Period','Ev_Team','Seconds_Elapsed'])\n",
"\n",
" pbp_df = pbp_df.sort_values(['season','Game_Id','Period','Seconds_Elapsed'], ascending=True)\n",
"\n",
" # Remove SOs\n",
" pbp_df = pbp_df.loc[((pbp_df.Period == 5) & (pbp_df.Season_Type == \"RS\")) != True,:]\n",
"\n",
" # Group Give/Take together\n",
" pbp_df['Event'] = pbp_df['Event'].apply( lambda x: 'TURN' if x in [\"GIVE\",\"TAKE\"] else x )\n",
"\n",
" pbp_df['Type'] = pbp_df['Type'].apply( lambda x: 'DEFLECTED' if x in [\"DEFLECTED\",\"TIP-IN\"] else \\\n",
" 'WRIST SHOT' if x in [\"WRIST SHOT\",\"SNAP SHOT\"] else x )\n",
"\n",
" ## Check Lag Time doesn't Cross Periods\n",
" pbp_df = pbp_df.sort_values(['season','Game_Id','Period','Seconds_Elapsed'], ascending=True)\n",
"\n",
" pbp_df['lagged_Event'] = pbp_df.groupby(['Game_Id','Period'])['Event'].shift(1)\n",
" pbp_df['lagged_Ev_Zone'] = pbp_df.groupby(['Game_Id','Period'])['Ev_Zone'].shift(1)\n",
" pbp_df['lagged_Seconds_Elapsed'] = pbp_df.groupby(['Game_Id','Period'])['Seconds_Elapsed'].shift(1)\n",
" \n",
" #############################################\n",
" ### Subset to just shots\n",
" #############################################\n",
" pbp_df = pbp_df.loc[pbp_df.Event.isin([\"SHOT\",\"GOAL\",\"MISS\",\"BLOCK\"]),:]\n",
"\n",
" print(\"All shots/blocks and columns: \" + str(pbp_df.shape))\n",
"\n",
" ## Binary\n",
" pbp_df['Goal'] = pbp_df.apply( lambda x: 1 if x.Event == \"GOAL\" else 0, axis = 1 )\n",
" \n",
" pbp_df['EmptyNet_SA'] = pbp_df.apply( lambda x: 1 if ((pd.isnull(x.Home_Goalie)) & (x.Ev_Team == x.Away_Team)) | \\\n",
" ((pd.isnull(x.Away_Goalie)) & (x.Ev_Team == x.Home_Team)) else 0, axis = 1)\n",
"\n",
" pbp_df['is_Rebound'] = pbp_df.apply( lambda x: 1 if (x.lagged_Event in [\"SHOT\"]) & \\\n",
" ((x.Seconds_Elapsed - x.lagged_Seconds_Elapsed) <= 2) else 0, axis = 1 ) \n",
" \n",
" pbp_df['is_Bounce'] = pbp_df.apply( lambda x: 1 if (x.lagged_Event in [\"BLOCK\",\"MISS\"]) & \\\n",
" ((x.Seconds_Elapsed - x.lagged_Seconds_Elapsed) <= 2) else 0, axis = 1 ) \n",
"\n",
" pbp_df['is_Rush'] = pbp_df.apply( lambda x: 1 if (x.Ev_Zone != x.lagged_Ev_Zone) & \\\n",
" ((x.Seconds_Elapsed - x.lagged_Seconds_Elapsed) <= 6) else 0, axis = 1 ) \n",
"\n",
"\n",
" # Replace every occurrence of PHX with ARI\n",
" pbp_df['Home_Team'] = pbp_df.apply( lambda x: x.Home_Team if x.Home_Team !='PHX' else 'ARI', axis=1 )\n",
" pbp_df['Away_Team'] = pbp_df.apply( lambda x: x.Away_Team if x.Away_Team !='PHX' else 'ARI', axis=1 )\n",
" pbp_df['Ev_Team'] = pbp_df.apply( lambda x: x.Ev_Team if x.Ev_Team !='PHX' else 'ARI', axis=1 )\n",
" # Replace every occurrence of ATL with WPG\n",
" pbp_df['Home_Team'] = pbp_df.apply( lambda x: x.Home_Team if x.Home_Team !='ATL' else 'WPG', axis=1 )\n",
" pbp_df['Away_Team'] = pbp_df.apply( lambda x: x.Away_Team if x.Away_Team !='ATL' else 'WPG', axis=1 )\n",
" pbp_df['Ev_Team'] = pbp_df.apply( lambda x: x.Ev_Team if x.Ev_Team !='ATL' else 'WPG', axis=1 )\n",
" \n",
" # add a 'Direction' column to indicate the primary direction for shots. The heuristic to determine\n",
" # direction is the sign of the median of the X coordinate of shots in each period. This then lets us filter\n",
" # out shots that originate from back in the defensive zone when the signs don't match\n",
" pbp_df['Home_Shooter'] = pbp_df.apply( lambda x: 1 if x.Ev_Team == x.Home_Team else 0, axis = 1)\n",
"\n",
" game_period_locations = pbp_df.groupby( by=['season', 'Game_Id', 'Period','Home_Shooter'] )['xC','yC']\n",
" \n",
" game_period_medians = game_period_locations.transform(np.median)\n",
"\n",
" pbp_df['Direction'] = np.sign( game_period_medians['xC'] )\n",
"\n",
" # should actually write this to a CSV as up to here is the performance intensive part\n",
" pbp_df['X_unadj'], pbp_df['Y_unadj'] = zip( *pbp_df.apply( lambda x: (x.xC, x.yC) if x.Direction > 0 else (-x.xC,-x.yC), axis = 1 ) )\n",
"\n",
" pbp_df['LS_Shot'] = pbp_df.apply( lambda x: 1 if x.Y_unadj < 0 else 0, axis = 1)\n",
"\n",
" ## Logged Last Event Time\n",
" pbp_df['LN_Last_Event_Time'] = pbp_df.apply( lambda x: 0 if (x.Seconds_Elapsed - x.lagged_Seconds_Elapsed) <= 0 \\\n",
" else np.log(x.Seconds_Elapsed - x.lagged_Seconds_Elapsed + 0.001), axis = 1)\n",
"\n",
" # Last Event\n",
" pbp_df['LastEV_Off_Faceoff'] = pbp_df.apply( lambda x: x.LN_Last_Event_Time if (x.Ev_Zone == 'Off') & (x.lagged_Event == 'FAC') else 0, axis = 1)\n",
" pbp_df['LastEV_Def_Faceoff'] = pbp_df.apply( lambda x: x.LN_Last_Event_Time if (x.Ev_Zone == 'Def') & (x.lagged_Event == 'FAC') else 0, axis = 1)\n",
" pbp_df['LastEV_Neu_Faceoff'] = pbp_df.apply( lambda x: x.LN_Last_Event_Time if (x.Ev_Zone == 'Neu') & (x.lagged_Event == 'FAC') else 0, axis = 1)\n",
" pbp_df['LastEV_Off_Shot'] = pbp_df.apply( lambda x: x.LN_Last_Event_Time if (x.Ev_Zone == 'Off') & (x.lagged_Event in [\"SHOT\",\"MISS\",\"BLOCK\"]) else 0, axis = 1)\n",
" pbp_df['LastEV_Def_Shot'] = pbp_df.apply( lambda x: x.LN_Last_Event_Time if (x.Ev_Zone == 'Def') & (x.lagged_Event in [\"SHOT\",\"MISS\",\"BLOCK\"]) else 0, axis = 1)\n",
" pbp_df['LastEV_Neu_Shot'] = pbp_df.apply( lambda x: x.LN_Last_Event_Time if (x.Ev_Zone == 'Neu') & (x.lagged_Event in [\"SHOT\",\"MISS\",\"BLOCK\"]) else 0, axis = 1)\n",
" pbp_df['LastEV_Off_Give'] = pbp_df.apply( lambda x: x.LN_Last_Event_Time if (x.Ev_Zone == 'Off') & (x.lagged_Event == 'TURN') else 0, axis = 1)\n",
" pbp_df['LastEV_Def_Give'] = pbp_df.apply( lambda x: x.LN_Last_Event_Time if (x.Ev_Zone == 'Def') & (x.lagged_Event == 'TURN') else 0, axis = 1)\n",
" pbp_df['LastEV_Neu_Give'] = pbp_df.apply( lambda x: x.LN_Last_Event_Time if (x.Ev_Zone == 'Neu') & (x.lagged_Event == 'TURN') else 0, axis = 1)\n",
"\n",
" ## Adjust X, Y coordinates by Rink, using CDF of shot attempts only (remove blocks since they skew data)\n",
" pbp_df = pbp_df.loc[pbp_df.Event.isin([\"SHOT\",\"GOAL\",\"MISS\"]),:]\n",
"\n",
" ## Call RinkAdjust class\n",
" adjuster = RinkAdjust()\n",
"\n",
" ## New dataframe of adjusted shots for each home rink\n",
" pbp_df_adj = pd.DataFrame()\n",
"\n",
" ## For each home rink\n",
" for team in sorted(pbp_df.Home_Team.unique()):\n",
"\n",
" ## Split shots into team arena and all other rinks\n",
" shot_data = pbp_df\n",
" rink_shots = shot_data[ shot_data.Home_Team == team ]\n",
" rest_of_league = shot_data[ shot_data.Home_Team != team ]\n",
"\n",
" ## Create teamxcdf and otherxcdf for rink adjustment\n",
" adjuster.addTeam( team, rink_shots, rest_of_league )\n",
" \n",
" ## Adjusted coordinates\n",
" Xadj = []\n",
" Yadj = []\n",
"\n",
" ## For each shot in rink adjust coordinates based on other rinks\n",
" for row in rink_shots.itertuples():\n",
" newx, newy = adjuster.rink_bias_adjust( row.X_unadj, row.Y_unadj, row.Home_Team )\n",
"\n",
" Xadj.append(newx)\n",
" Yadj.append(newy)\n",
"\n",
" rink_shots['X'] = Xadj\n",
" rink_shots['Y'] = Yadj\n",
"\n",
" pbp_df_adj = pbp_df_adj.append(rink_shots)\n",
"\n",
" print (\"All shots columns, rink adjusted: \" + str(pbp_df_adj.shape))\n",
"\n",
" ## Apply only to season level data after x,y CDF adjustment\n",
" pbp_df_adj['Shot_Distance_Unadj'] = pbp_df_adj.apply( lambda x: ((89 - x.X_unadj)**2 + (x.Y_unadj ** 2)) ** 0.5, axis = 1 )\n",
" pbp_df_adj['Shot_Distance'] = pbp_df_adj.apply( lambda x: ((89 - x.X)**2 + (x.Y ** 2)) ** 0.5, axis = 1 )\n",
" pbp_df_adj['Shot_Angle'] = pbp_df_adj.apply( lambda x: np.arctan(abs(89 - x.X) / abs(0 - x.Y)) * (180 / np.pi) if x.Y != 0 \\\n",
" else 90, axis = 1 ) \n",
"\n",
" pbp_df_adj['Last_Shot_Distance'] = pbp_df_adj.groupby(['Game_Id','Period','Home_Shooter'])['Shot_Distance'].shift(1)\n",
" pbp_df_adj['Last_Shot_Angle'] = pbp_df_adj.groupby(['Game_Id','Period','Home_Shooter'])['Shot_Angle'].shift(1)\n",
" pbp_df_adj['Last_LS_Shot'] = pbp_df_adj.groupby(['Game_Id','Period','Home_Shooter'])['LS_Shot'].shift(1)\n",
"\n",
" pbp_df_adj['Rebound_Distance_Change'] = pbp_df_adj.apply( lambda x: x.Last_Shot_Distance + x.Shot_Distance if x.is_Rebound == 1 else 0, axis = 1 )\n",
" pbp_df_adj['Rebound_Angle_Change'] = pbp_df_adj.apply( lambda x: 0 if x.is_Rebound == 0 \\\n",
" else abs(x.Last_Shot_Angle - x.Shot_Angle) \\\n",
" if x.is_Rebound == 1 & (x.Last_LS_Shot == x.LS_Shot) else \\\n",
" (180 - x.Last_Shot_Angle - x.Shot_Angle), axis = 1 )\n",
"\n",
" pbp_df_adj['Rebound_Distance_Traveled_byAngle'] = pbp_df_adj. \\\n",
" apply( lambda x: x.Rebound_Distance_Change / x.Rebound_Angle_Change \\\n",
" if x.Rebound_Angle_Change > 0 else 0, axis = 1)\n",
"\n",
" pbp_df_adj['LN_Rebound_Distance_Traveled_byAngle'] = pbp_df_adj. \\\n",
" apply(lambda x: np.log(x.Rebound_Distance_Traveled_byAngle) \\\n",
" if x.Rebound_Distance_Traveled_byAngle > 0 else 0, axis = 1)\n",
"\n",
" print (\"All shots columns, final calcuations: \" + str(pbp_df_adj.shape))\n",
" \n",
" return pbp_df_adj\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Read-in and Stack"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"types = {'xC': np.float64,\n",
"'yC': np.float64,\n",
"'X': np.float64,\n",
"'X_unadj': np.float64,\n",
"'Y': np.float64,\n",
"'Y_unadj': np.float64,\n",
"'Game_Id': int}"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {
"scrolled": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style>\n",
" .dataframe thead tr:only-child th {\n",
" text-align: right;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Away_Coach</th>\n",
" <th>Away_Goalie</th>\n",
" <th>Away_Goalie_Id</th>\n",
" <th>Away_Players</th>\n",
" <th>Away_Score</th>\n",
" <th>Away_Team</th>\n",
" <th>Date</th>\n",
" <th>Description</th>\n",
" <th>Ev_Team</th>\n",
" <th>Ev_Zone</th>\n",
" <th>Event</th>\n",
" <th>Game_Id</th>\n",
" <th>Home_Coach</th>\n",
" <th>Home_Goalie</th>\n",
" <th>Home_Goalie_Id</th>\n",
" <th>Home_Players</th>\n",
" <th>Home_Score</th>\n",
" <th>Home_Team</th>\n",
" <th>Home_Zone</th>\n",
" <th>Period</th>\n",
" <th>Seconds_Elapsed</th>\n",
" <th>Strength</th>\n",
" <th>Time_Elapsed</th>\n",
" <th>Type</th>\n",
" <th>awayPlayer1</th>\n",
" <th>awayPlayer1_id</th>\n",
" <th>awayPlayer2</th>\n",
" <th>awayPlayer2_id</th>\n",
" <th>awayPlayer3</th>\n",
" <th>awayPlayer3_id</th>\n",
" <th>awayPlayer4</th>\n",
" <th>awayPlayer4_id</th>\n",
" <th>awayPlayer5</th>\n",
" <th>awayPlayer5_id</th>\n",
" <th>awayPlayer6</th>\n",
" <th>awayPlayer6_id</th>\n",
" <th>homePlayer1</th>\n",
" <th>homePlayer1_id</th>\n",
" <th>homePlayer2</th>\n",
" <th>homePlayer2_id</th>\n",
" <th>homePlayer3</th>\n",
" <th>homePlayer3_id</th>\n",
" <th>homePlayer4</th>\n",
" <th>homePlayer4_id</th>\n",
" <th>homePlayer5</th>\n",
" <th>homePlayer5_id</th>\n",
" <th>homePlayer6</th>\n",
" <th>homePlayer6_id</th>\n",
" <th>p1_ID</th>\n",
" <th>p1_name</th>\n",
" <th>p2_ID</th>\n",
" <th>p2_name</th>\n",
" <th>p3_ID</th>\n",
" <th>p3_name</th>\n",
" <th>xC</th>\n",
" <th>yC</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>PAUL MAURICE</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>CAR</td>\n",
" <td>2010-10-07</td>\n",
" <td>Period Start- Local time: 7:10 EET</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>PSTR</td>\n",
" <td>20003</td>\n",
" <td>TODD RICHARDS</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>MIN</td>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>5x5</td>\n",
" <td>0:00</td>\n",
" <td>NaN</td>\n",
" <td>JEFF SKINNER</td>\n",
" <td>8475784.0</td>\n",
" <td>TUOMO RUUTU</td>\n",
" <td>8469462.0</td>\n",
" <td>JUSSI JOKINEN</td>\n",
" <td>8469638.0</td>\n",
" <td>JONI PITKANEN</td>\n",
" <td>8470137.0</td>\n",
" <td>JOE CORVO</td>\n",
" <td>8466215.0</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>MIKKO KOIVU</td>\n",
" <td>8469459.0</td>\n",
" <td>ANTTI MIETTINEN</td>\n",
" <td>8468704.0</td>\n",
" <td>ANDREW BRUNETTE</td>\n",
" <td>8459596.0</td>\n",
" <td>GREG ZANON</td>\n",
" <td>8468636.0</td>\n",
" <td>CAM BARKER</td>\n",
" <td>8471216.0</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>PAUL MAURICE</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>CAR</td>\n",
" <td>2010-10-07</td>\n",
" <td>MIN won Neu. Zone - CAR #36 JOKINEN vs MIN #9 KOIVU</td>\n",
" <td>MIN</td>\n",
" <td>Neu</td>\n",
" <td>FAC</td>\n",
" <td>20003</td>\n",
" <td>TODD RICHARDS</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>MIN</td>\n",
" <td>Neu</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>5x5</td>\n",
" <td>0:00</td>\n",
" <td>NaN</td>\n",
" <td>JEFF SKINNER</td>\n",
" <td>8475784.0</td>\n",
" <td>TUOMO RUUTU</td>\n",
" <td>8469462.0</td>\n",
" <td>JUSSI JOKINEN</td>\n",
" <td>8469638.0</td>\n",
" <td>JONI PITKANEN</td>\n",
" <td>8470137.0</td>\n",
" <td>JOE CORVO</td>\n",
" <td>8466215.0</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>MIKKO KOIVU</td>\n",
" <td>8469459.0</td>\n",
" <td>ANTTI MIETTINEN</td>\n",
" <td>8468704.0</td>\n",
" <td>ANDREW BRUNETTE</td>\n",
" <td>8459596.0</td>\n",
" <td>GREG ZANON</td>\n",
" <td>8468636.0</td>\n",
" <td>CAM BARKER</td>\n",
" <td>8471216.0</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>8469459.0</td>\n",
" <td>MIKKO KOIVU</td>\n",
" <td>8469638.0</td>\n",
" <td>JUSSI JOKINEN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>PAUL MAURICE</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>CAR</td>\n",
" <td>2010-10-07</td>\n",
" <td>OFFSIDE</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>STOP</td>\n",
" <td>20003</td>\n",
" <td>TODD RICHARDS</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>MIN</td>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>8.0</td>\n",
" <td>5x5</td>\n",
" <td>0:08</td>\n",
" <td>NaN</td>\n",
" <td>JEFF SKINNER</td>\n",
" <td>8475784.0</td>\n",
" <td>TUOMO RUUTU</td>\n",
" <td>8469462.0</td>\n",
" <td>JUSSI JOKINEN</td>\n",
" <td>8469638.0</td>\n",
" <td>JONI PITKANEN</td>\n",
" <td>8470137.0</td>\n",
" <td>JOE CORVO</td>\n",
" <td>8466215.0</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>MIKKO KOIVU</td>\n",
" <td>8469459.0</td>\n",
" <td>ANTTI MIETTINEN</td>\n",
" <td>8468704.0</td>\n",
" <td>ANDREW BRUNETTE</td>\n",
" <td>8459596.0</td>\n",
" <td>GREG ZANON</td>\n",
" <td>8468636.0</td>\n",
" <td>CAM BARKER</td>\n",
" <td>8471216.0</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>PAUL MAURICE</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>CAR</td>\n",
" <td>2010-10-07</td>\n",
" <td>MIN won Neu. Zone - CAR #36 JOKINEN vs MIN #9 KOIVU</td>\n",
" <td>MIN</td>\n",
" <td>Neu</td>\n",
" <td>FAC</td>\n",
" <td>20003</td>\n",
" <td>TODD RICHARDS</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>MIN</td>\n",
" <td>Neu</td>\n",
" <td>1</td>\n",
" <td>8.0</td>\n",
" <td>5x5</td>\n",
" <td>0:08</td>\n",
" <td>NaN</td>\n",
" <td>JEFF SKINNER</td>\n",
" <td>8475784.0</td>\n",
" <td>TUOMO RUUTU</td>\n",
" <td>8469462.0</td>\n",
" <td>JUSSI JOKINEN</td>\n",
" <td>8469638.0</td>\n",
" <td>JONI PITKANEN</td>\n",
" <td>8470137.0</td>\n",
" <td>JOE CORVO</td>\n",
" <td>8466215.0</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>MIKKO KOIVU</td>\n",
" <td>8469459.0</td>\n",
" <td>ANTTI MIETTINEN</td>\n",
" <td>8468704.0</td>\n",
" <td>ANDREW BRUNETTE</td>\n",
" <td>8459596.0</td>\n",
" <td>GREG ZANON</td>\n",
" <td>8468636.0</td>\n",
" <td>CAM BARKER</td>\n",
" <td>8471216.0</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>8469459.0</td>\n",
" <td>MIKKO KOIVU</td>\n",
" <td>8469638.0</td>\n",
" <td>JUSSI JOKINEN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20.0</td>\n",
" <td>-22.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>PAUL MAURICE</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>CAR</td>\n",
" <td>2010-10-07</td>\n",
" <td>CAR ONGOAL - #12 STAAL, Snap, Off. Zone, 37 ft.</td>\n",
" <td>CAR</td>\n",
" <td>Off</td>\n",
" <td>SHOT</td>\n",
" <td>20003</td>\n",
" <td>TODD RICHARDS</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>6</td>\n",
" <td>0</td>\n",
" <td>MIN</td>\n",
" <td>Def</td>\n",
" <td>1</td>\n",
" <td>65.0</td>\n",
" <td>5x5</td>\n",
" <td>1:05</td>\n",
" <td>SNAP SHOT</td>\n",
" <td>ERIC STAAL</td>\n",
" <td>8470595.0</td>\n",
" <td>CHAD LAROSE</td>\n",
" <td>8469812.0</td>\n",
" <td>ERIK COLE</td>\n",
" <td>8467396.0</td>\n",
" <td>JONI PITKANEN</td>\n",
" <td>8470137.0</td>\n",
" <td>JOE CORVO</td>\n",
" <td>8466215.0</td>\n",
" <td>CAM WARD</td>\n",
" <td>8470320.0</td>\n",
" <td>MATT CULLEN</td>\n",
" <td>8464989.0</td>\n",
" <td>CAL CLUTTERBUCK</td>\n",
" <td>8473504.0</td>\n",
" <td>MARTIN HAVLAT</td>\n",
" <td>8467899.0</td>\n",
" <td>BRENT BURNS</td>\n",
" <td>8470613.0</td>\n",
" <td>NICK SCHULTZ</td>\n",
" <td>8468513.0</td>\n",
" <td>NIKLAS BACKSTROM</td>\n",
" <td>8473404.0</td>\n",
" <td>8470595.0</td>\n",
" <td>ERIC STAAL</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>56.0</td>\n",
" <td>-15.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Away_Coach Away_Goalie Away_Goalie_Id Away_Players Away_Score \\\n",
"0 PAUL MAURICE CAM WARD 8470320.0 6 0 \n",
"1 PAUL MAURICE CAM WARD 8470320.0 6 0 \n",
"2 PAUL MAURICE CAM WARD 8470320.0 6 0 \n",
"3 PAUL MAURICE CAM WARD 8470320.0 6 0 \n",
"4 PAUL MAURICE CAM WARD 8470320.0 6 0 \n",
"\n",
" Away_Team Date Description \\\n",
"0 CAR 2010-10-07 Period Start- Local time: 7:10 EET \n",
"1 CAR 2010-10-07 MIN won Neu. Zone - CAR #36 JOKINEN vs MIN #9 KOIVU \n",
"2 CAR 2010-10-07 OFFSIDE \n",
"3 CAR 2010-10-07 MIN won Neu. Zone - CAR #36 JOKINEN vs MIN #9 KOIVU \n",
"4 CAR 2010-10-07 CAR ONGOAL - #12 STAAL, Snap, Off. Zone, 37 ft. \n",
"\n",
" Ev_Team Ev_Zone Event Game_Id Home_Coach Home_Goalie \\\n",
"0 NaN NaN PSTR 20003 TODD RICHARDS NIKLAS BACKSTROM \n",
"1 MIN Neu FAC 20003 TODD RICHARDS NIKLAS BACKSTROM \n",
"2 NaN NaN STOP 20003 TODD RICHARDS NIKLAS BACKSTROM \n",
"3 MIN Neu FAC 20003 TODD RICHARDS NIKLAS BACKSTROM \n",
"4 CAR Off SHOT 20003 TODD RICHARDS NIKLAS BACKSTROM \n",
"\n",
" Home_Goalie_Id Home_Players Home_Score Home_Team Home_Zone Period \\\n",
"0 8473404.0 6 0 MIN NaN 1 \n",
"1 8473404.0 6 0 MIN Neu 1 \n",
"2 8473404.0 6 0 MIN NaN 1 \n",
"3 8473404.0 6 0 MIN Neu 1 \n",
"4 8473404.0 6 0 MIN Def 1 \n",
"\n",
" Seconds_Elapsed Strength Time_Elapsed Type awayPlayer1 \\\n",
"0 0.0 5x5 0:00 NaN JEFF SKINNER \n",
"1 0.0 5x5 0:00 NaN JEFF SKINNER \n",
"2 8.0 5x5 0:08 NaN JEFF SKINNER \n",
"3 8.0 5x5 0:08 NaN JEFF SKINNER \n",
"4 65.0 5x5 1:05 SNAP SHOT ERIC STAAL \n",
"\n",
" awayPlayer1_id awayPlayer2 awayPlayer2_id awayPlayer3 awayPlayer3_id \\\n",
"0 8475784.0 TUOMO RUUTU 8469462.0 JUSSI JOKINEN 8469638.0 \n",
"1 8475784.0 TUOMO RUUTU 8469462.0 JUSSI JOKINEN 8469638.0 \n",
"2 8475784.0 TUOMO RUUTU 8469462.0 JUSSI JOKINEN 8469638.0 \n",
"3 8475784.0 TUOMO RUUTU 8469462.0 JUSSI JOKINEN 8469638.0 \n",
"4 8470595.0 CHAD LAROSE 8469812.0 ERIK COLE 8467396.0 \n",
"\n",
" awayPlayer4 awayPlayer4_id awayPlayer5 awayPlayer5_id awayPlayer6 \\\n",
"0 JONI PITKANEN 8470137.0 JOE CORVO 8466215.0 CAM WARD \n",
"1 JONI PITKANEN 8470137.0 JOE CORVO 8466215.0 CAM WARD \n",
"2 JONI PITKANEN 8470137.0 JOE CORVO 8466215.0 CAM WARD \n",
"3 JONI PITKANEN 8470137.0 JOE CORVO 8466215.0 CAM WARD \n",
"4 JONI PITKANEN 8470137.0 JOE CORVO 8466215.0 CAM WARD \n",
"\n",
" awayPlayer6_id homePlayer1 homePlayer1_id homePlayer2 \\\n",
"0 8470320.0 MIKKO KOIVU 8469459.0 ANTTI MIETTINEN \n",
"1 8470320.0 MIKKO KOIVU 8469459.0 ANTTI MIETTINEN \n",
"2 8470320.0 MIKKO KOIVU 8469459.0 ANTTI MIETTINEN \n",
"3 8470320.0 MIKKO KOIVU 8469459.0 ANTTI MIETTINEN \n",
"4 8470320.0 MATT CULLEN 8464989.0 CAL CLUTTERBUCK \n",
"\n",
" homePlayer2_id homePlayer3 homePlayer3_id homePlayer4 \\\n",
"0 8468704.0 ANDREW BRUNETTE 8459596.0 GREG ZANON \n",
"1 8468704.0 ANDREW BRUNETTE 8459596.0 GREG ZANON \n",
"2 8468704.0 ANDREW BRUNETTE 8459596.0 GREG ZANON \n",
"3 8468704.0 ANDREW BRUNETTE 8459596.0 GREG ZANON \n",
"4 8473504.0 MARTIN HAVLAT 8467899.0 BRENT BURNS \n",
"\n",
" homePlayer4_id homePlayer5 homePlayer5_id homePlayer6 \\\n",
"0 8468636.0 CAM BARKER 8471216.0 NIKLAS BACKSTROM \n",
"1 8468636.0 CAM BARKER 8471216.0 NIKLAS BACKSTROM \n",
"2 8468636.0 CAM BARKER 8471216.0 NIKLAS BACKSTROM \n",
"3 8468636.0 CAM BARKER 8471216.0 NIKLAS BACKSTROM \n",
"4 8470613.0 NICK SCHULTZ 8468513.0 NIKLAS BACKSTROM \n",
"\n",
" homePlayer6_id p1_ID p1_name p2_ID p2_name p3_ID \\\n",
"0 8473404.0 NaN NaN NaN NaN NaN \n",
"1 8473404.0 8469459.0 MIKKO KOIVU 8469638.0 JUSSI JOKINEN NaN \n",
"2 8473404.0 NaN NaN NaN NaN NaN \n",
"3 8473404.0 8469459.0 MIKKO KOIVU 8469638.0 JUSSI JOKINEN NaN \n",
"4 8473404.0 8470595.0 ERIC STAAL NaN NaN NaN \n",
"\n",
" p3_name xC yC \n",
"0 NaN NaN NaN \n",
"1 NaN 0.0 0.0 \n",
"2 NaN NaN NaN \n",
"3 NaN 20.0 -22.0 \n",
"4 NaN 56.0 -15.0 "
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"nhl_pbp20102011 = pd.read_csv('/Users/colander1/Documents/CWA/HockeyScrape/nhl_pbp20102011.csv', dtype=types)\n",
"nhl_pbp20112012 = pd.read_csv('/Users/colander1/Documents/CWA/HockeyScrape/nhl_pbp20112012.csv', dtype=types)\n",
"nhl_pbp20122013 = pd.read_csv('/Users/colander1/Documents/CWA/HockeyScrape/nhl_pbp20122013.csv', dtype=types)\n",
"nhl_pbp20132014 = pd.read_csv('/Users/colander1/Documents/CWA/HockeyScrape/nhl_pbp20132014.csv', dtype=types)\n",
"nhl_pbp20142015 = pd.read_csv('/Users/colander1/Documents/CWA/HockeyScrape/nhl_pbp20142015.csv', dtype=types)\n",
"nhl_pbp20152016 = pd.read_csv('/Users/colander1/Documents/CWA/HockeyScrape/nhl_pbp20152016.csv', dtype=types)\n",
"nhl_pbp20162017 = pd.read_csv('/Users/colander1/Documents/CWA/HockeyScrape/nhl_pbp20162017.csv', dtype=types)\n",
"\n",
"nhl_pbp20172018 = pd.read_csv('/Users/colander1/Documents/CWA/HockeyScrape/nhl_pbp20172018.csv', dtype=types)\n",
"\n",
"nhl_pbp = pd.concat([nhl_pbp20102011, nhl_pbp20112012, nhl_pbp20122013, nhl_pbp20132014,\n",
" nhl_pbp20142015, nhl_pbp20152016, nhl_pbp20162017, nhl_pbp20172018])\n",
"\n",
"unwanted = nhl_pbp.columns[nhl_pbp.columns.str.startswith('Unna')]\n",
"\n",
"nhl_pbp.drop(unwanted, axis=1, inplace=True)\n",
"\n",
"nhl_pbp.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Goalie/Skater Roster with Handedness"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"player_lookup = pd.read_sql(con=engine, sql =\"SELECT * FROM `nhl_all`.`hockey_roster_info` AS B\")\n",
"\n",
"player_lookup = player_lookup.sort_values('gamesPlayed',ascending=False).groupby(['playerId']).first().reset_index(). \\\n",
" loc[:, ['playerBirthDate', 'playerPositionCode', 'playerShootsCatches','playerId']]\n",
" \n",
"skater_lookup = player_lookup.loc[player_lookup.playerPositionCode != \"G\", :]\n",
"skater_lookup.columns = ['shooterDOB','Player_Position','Shoots','p1_ID']\n",
"skater_lookup['p1_ID'] = skater_lookup['p1_ID'].astype(str)\n",
"\n",
"\n",
"goalie_lookup = pd.read_sql(con=engine, sql = \"SELECT DISTINCT playerId as SA_Goalie_Id, playerShootsCatches as Catches, playerBirthDate as goalieDOB FROM `nhl_all`.`hockey_goalies_roster` AS A\") \n",
"goalie_lookup['SA_Goalie_Id'] = goalie_lookup['SA_Goalie_Id'].astype(str)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Lookup Players, Generate More Features"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def lookups_data_clean(data):\n",
" \n",
" \n",
" for col in ['Game_Id','Away_Goalie_Id','Home_Goalie_Id','p1_ID','p2_ID','p3_ID',\n",
" 'awayPlayer1_id','awayPlayer2_id','awayPlayer3_id','awayPlayer4_id','awayPlayer5_id','awayPlayer6_id',\n",
" 'homePlayer1_id','homePlayer2_id','homePlayer3_id','homePlayer4_id','homePlayer5_id','homePlayer6_id']:\n",
" data[col] = data[col].fillna(0).astype(int).astype(str)\n",
"\n",
" data['SA_Goalie'] = data.apply( lambda x: x.Away_Goalie if x.Ev_Team == x.Home_Team else x.Home_Goalie, axis=1 )\n",
" data['SA_Goalie_Id'] = data.apply( lambda x: x.Away_Goalie_Id if x.Ev_Team == x.Home_Team else x.Home_Goalie_Id, axis=1 )\n",
" \n",
" data['Away_State'] = data.apply( lambda x: x.Away_Players - 1 if x.Away_Goalie_Id in [x.awayPlayer6_id, x.awayPlayer5_id, x.awayPlayer4_id, x.awayPlayer3_id] else x.Away_Players, axis=1 )\n",
" data['Home_State'] = data.apply( lambda x: x.Home_Players - 1 if x.Home_Goalie_Id in [x.homePlayer6_id, x.homePlayer5_id, x.homePlayer4_id, x.homePlayer3_id] else x.Home_Players, axis=1 )\n",
" \n",
" data['Away_State'] = data.apply( lambda x: x.Away_Players - 1 if x.Away_Goalie_Id in [x.awayPlayer6_id, x.awayPlayer5_id, x.awayPlayer4_id, x.awayPlayer3_id] else x.Away_Players, axis=1 )\n",
" data['Home_State'] = data.apply( lambda x: x.Home_Players - 1 if x.Home_Goalie_Id in [x.homePlayer6_id, x.homePlayer5_id, x.homePlayer4_id, x.homePlayer3_id] else x.Home_Players, axis=1 )\n",
" \n",
" data['Results_inRebound'] = data['is_Rebound'].shift(periods=-1)\n",
" \n",
" data['Shooter_State'] = data.apply( lambda x: x.Away_State if x.Ev_Team != x.Home_Team else x.Home_State, axis=1 )\n",
" data['Goalie_State'] = data.apply( lambda x: x.Away_State if x.Ev_Team == x.Home_Team else x.Home_State, axis=1 )\n",
" \n",
" data['Game_State'] = data.apply( lambda x: str(x.Away_State) + \"v\" + str(x.Home_State) if x.Ev_Team == x.Home_Team else \\\n",
" str(x.Home_State) + \"v\" + str(x.Away_State) , axis=1 )\n",
" data['Game_State'] = data.apply( lambda x: \"SH_SA\" if x.Game_State in [\"3v5\",\"3v4\",\"3v6\",\"4v5\",\"4v6\",\"5v6\"] else \\\n",
" \"PP_2p_SA\" if x.Game_State in [\"6v3\",\"6v4\",\"5v3\"] else \\\n",
" \"5v5\" if x.Game_State in [\"5v5\",\"6v6\"] else x.Game_State, axis=1 )\n",
" \n",
" data['State_Space'] = data['Goalie_State'] + data['Shooter_State']\n",
" data['Shooter_State_Advantage'] = data['Shooter_State'] - data['Goalie_State']\n",
" \n",
" data = data.merge(skater_lookup, on=['p1_ID'], how = 'left')\n",
" data = data.merge(goalie_lookup, on=['SA_Goalie_Id'], how = 'left')\n",
" \n",
"\n",
" data['Shooter_Handedness'] = data.apply( lambda x: \"L\" if x.Shoots == \"L\" else \\\n",
" \"R\" if x.Shoots == \"R\" else \"U\", axis=1 )\n",
" \n",
" data['Handed_Class'] = data['Shoots'].str.cat(data['Catches'], sep='')\n",
" \n",
" data['Handed_Class2'] = data.apply( lambda x: \"Same\" if x.Handed_Class in [\"LL\",\"RR\"] else \\\n",
" \"Opposite\" if x.Handed_Class in [\"LR\",\"RL\"] else \"U\", axis = 1)\n",
" \n",
" data['Player_Position2'] = data.apply( lambda x: \"D\" if x.Player_Position == \"D\" else \"F\", axis=1 )\n",
" \n",
" return data\n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"## Cumulative Shooting Function"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def cumulative_shooting_talent(data):\n",
" \n",
" shooting_percentage = data.groupby(['Player_Position2'])['Goal'].mean()\n",
" \n",
" data['Cum_Goal'] = data.groupby(['p1_ID'])['Goal'].cumsum()\n",
" data['Cum_Shots'] = data.groupby(['p1_ID']).cumcount()\n",
" \n",
" data['Cum_Goal'] = data.apply( lambda x: x.Cum_Goal - 1 if x.Event == \"GOAL\" else x.Cum_Goal, axis = 1)\n",
" \n",
" kr21_stabilizer_F = pd.to_numeric(375.0)\n",
" kr21_stabilizer_D = pd.to_numeric(275.0)\n",
"\n",
" data['Regressed_Shooting_Indexed'] = data.apply( lambda x: ((x.Cum_Goal + (kr21_stabilizer_D * shooting_percentage[0])) /\\\n",
" (x.Cum_Shots + kr21_stabilizer_D)) / shooting_percentage[0]\\\n",
" if x.Player_Position2 == \"D\" else ((x.Cum_Goal + (kr21_stabilizer_F * shooting_percentage[1])) /\\\n",
" (x.Cum_Shots + kr21_stabilizer_F)) / shooting_percentage[1], axis = 1)\n",
" \n",
" return data\n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [