In [1]:
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import sqlite3
import numpy as np
from numpy import random
In [2]:
database = 'database.sqlite'
conn = sqlite3.connect(database)
In [3]:
query = """select * from match where home_player_X1 is not null and 'home_player_Y1' is not null
and home_player_X2 is not null and 'home_player_Y2' is not null
and home_player_X3 is not null and home_player_Y3 is not null
and home_player_X4 is not null and home_player_Y4 is not null
and home_player_X5 is not null and home_player_Y5 is not null
and home_player_X6 is not null and home_player_Y6 is not null
and home_player_X7 is not null and home_player_Y7 is not null
and home_player_X8 is not null and home_player_Y8 is not null
and home_player_X9 is not null and home_player_Y9 is not null
and home_player_X10 is not null and home_player_Y10 is not null
and home_player_X11 is not null and home_player_Y11 is not null
and away_player_X1 is not null and away_player_Y1 is not null
and away_player_X2 is not null and away_player_Y2 is not null
and away_player_X3 is not null and away_player_Y3 is not null
and away_player_X4 is not null and away_player_Y4 is not null
and away_player_X5 is not null and away_player_Y5 is not null
and away_player_X6 is not null and away_player_Y6 is not null
and away_player_X7 is not null and away_player_Y7 is not null
and away_player_X8 is not null and away_player_Y8 is not null
and away_player_X9 is not null and away_player_Y9 is not null
and away_player_X10 is not null and away_player_Y10 is not null
and away_player_X11 is not null and away_player_Y11 is not null
and home_team_goal is not null and away_team_goal is not null
and home_player_1 is not null
and home_player_2 is not null
and home_player_3 is not null
and home_player_4 is not null
and home_player_5 is not null
and home_player_6 is not null
and home_player_7 is not null
and home_player_8 is not null
and home_player_9 is not null
and home_player_10 is not null
and home_player_11 is not null
and away_player_1 is not null
and away_player_2 is not null
and away_player_3 is not null
and away_player_4 is not null
and away_player_5 is not null
and away_player_6 is not null
and away_player_7 is not null
and away_player_8 is not null
and away_player_9 is not null
and away_player_10 is not null
and away_player_11 is not null
and B365H is not null and B365D is not null and B365A is not null;"""
matches = pd.read_sql(query, conn)
matches
Out[3]:
id
country_id
league_id
season
stage
date
match_api_id
home_team_api_id
away_team_api_id
home_team_goal
...
SJA
VCH
VCD
VCA
GBH
GBD
GBA
BSH
BSD
BSA
0
146
1
1
2008/2009
24
2009-02-27 00:00:00
493017
8203
9987
2
...
2.30
2.65
3.25
2.35
2.90
3.25
2.30
2.80
3.20
2.25
1
154
1
1
2008/2009
25
2009-03-08 00:00:00
493025
9984
8342
1
...
2.25
2.65
3.20
2.35
2.90
3.20
2.30
2.62
3.20
2.38
2
156
1
1
2008/2009
25
2009-03-07 00:00:00
493027
8635
10000
2
...
8.50
1.30
4.35
8.00
1.35
4.33
8.50
1.36
4.20
7.00
3
163
1
1
2008/2009
26
2009-03-13 00:00:00
493034
8203
8635
2
...
1.73
4.35
3.30
1.75
4.50
3.40
1.75
4.20
3.30
1.75
4
169
1
1
2008/2009
26
2009-03-14 00:00:00
493040
10000
9999
0
...
5.00
1.65
3.50
4.50
1.65
3.50
5.00
1.70
3.40
4.33
5
174
1
1
2008/2009
27
2009-03-22 00:00:00
493045
9991
10000
1
...
4.75
1.60
3.40
5.00
1.65
3.40
5.00
1.62
3.50
5.00
6
177
1
1
2008/2009
27
2009-03-21 00:00:00
493048
9999
8203
1
...
2.75
2.25
3.25
2.80
2.10
3.25
3.15
2.25
3.20
2.75
7
190
1
1
2008/2009
29
2009-04-12 00:00:00
493061
8635
8342
1
...
4.75
1.65
3.40
5.00
1.70
3.40
4.50
1.73
3.40
4.20
8
191
1
1
2008/2009
29
2009-04-10 00:00:00
493062
9999
9987
1
...
2.15
2.80
3.25
2.25
3.20
3.20
2.10
2.80
3.20
2.25
9
220
1
1
2008/2009
31
2009-04-26 00:00:00
493082
9999
9991
1
...
2.20
3.20
3.20
2.10
3.00
3.25
2.15
2.88
3.25
2.20
10
227
1
1
2008/2009
32
2009-05-02 00:00:00
493089
10000
9985
0
...
1.62
5.00
3.50
1.60
5.25
3.50
1.60
5.00
3.60
1.57
11
230
1
1
2008/2009
32
2009-05-02 00:00:00
493092
9991
9984
2
...
8.50
1.35
4.00
8.50
1.35
4.50
7.00
1.33
4.50
7.50
12
232
1
1
2008/2009
32
2009-05-02 00:00:00
493094
10001
9999
1
...
5.50
1.55
3.50
5.50
1.57
3.60
5.25
1.57
3.60
5.00
13
235
1
1
2008/2009
33
2009-05-09 00:00:00
493097
9985
8342
2
...
7.50
1.45
3.80
6.50
1.47
3.75
6.50
1.50
3.75
5.50
14
241
1
1
2008/2009
33
2009-05-09 00:00:00
493103
8635
9999
3
...
16.00
1.14
6.50
13.00
1.15
6.50
13.00
1.17
6.00
13.00
15
243
1
1
2008/2009
33
2009-05-09 00:00:00
493105
9984
10001
2
...
2.63
2.60
3.25
2.40
2.50
3.30
2.50
2.50
3.20
2.50
16
244
1
1
2008/2009
34
2009-05-16 00:00:00
493106
9987
8635
0
...
1.45
6.50
4.00
1.44
6.50
3.75
1.45
7.00
4.00
1.40
17
245
1
1
2008/2009
34
2009-05-16 00:00:00
493107
9991
9985
0
...
1.70
4.50
3.60
1.65
4.50
3.60
1.65
4.50
3.50
1.67
18
309
1
1
2009/2010
1
2009-08-02 00:00:00
665321
9984
9991
1
...
2.30
2.62
3.25
2.40
2.70
3.20
2.40
2.88
3.10
2.30
19
310
1
1
2009/2010
1
2009-08-01 00:00:00
665322
9994
10000
1
...
3.30
2.00
3.25
3.40
2.10
3.30
3.10
2.25
3.20
2.80
20
311
1
1
2009/2010
1
2009-08-01 00:00:00
665323
8571
8635
0
...
1.57
5.50
3.60
1.57
5.25
3.50
1.60
5.50
3.60
1.53
21
314
1
1
2009/2010
10
2009-10-04 00:00:00
665411
8342
8635
4
...
2.75
2.40
3.25
2.62
2.45
3.20
2.70
2.38
3.20
2.62
22
318
1
1
2009/2010
10
2009-10-03 00:00:00
665417
8203
9994
2
...
4.00
1.85
3.30
3.75
1.95
3.25
3.75
1.91
3.25
3.60
23
320
1
1
2009/2010
10
2009-10-03 00:00:00
665421
9993
10001
3
...
4.50
1.73
3.40
4.33
1.75
3.40
4.50
1.75
3.30
4.20
24
321
1
1
2009/2010
11
2009-10-18 00:00:00
665425
8342
9991
1
...
4.75
1.70
3.50
4.00
1.60
3.50
5.25
1.67
3.40
4.75
25
323
1
1
2009/2010
11
2009-10-18 00:00:00
665427
9987
8203
1
...
4.33
1.75
3.40
4.33
1.83
3.30
4.00
1.83
3.30
3.80
26
324
1
1
2009/2010
11
2009-10-17 00:00:00
665429
10000
9993
4
...
3.60
1.90
3.30
3.60
2.05
3.25
3.30
2.00
3.25
3.30
27
325
1
1
2009/2010
11
2009-10-17 00:00:00
665430
9994
9984
1
...
3.40
2.00
3.25
3.40
2.10
3.20
3.20
2.05
3.25
3.20
28
327
1
1
2009/2010
11
2009-10-17 00:00:00
665435
10001
9985
2
...
1.67
5.50
3.40
1.60
5.00
3.40
1.65
4.75
3.40
1.67
29
328
1
1
2009/2010
12
2009-10-24 00:00:00
665438
9985
10000
1
...
6.50
1.44
3.75
6.50
1.40
4.00
7.50
1.44
3.75
6.50
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
19570
24492
21484
21484
2015/2016
6
2015-09-27 00:00:00
2030140
9783
8558
3
...
NaN
2.10
3.40
3.90
NaN
NaN
NaN
NaN
NaN
NaN
19571
24493
21484
21484
2015/2016
6
2015-09-27 00:00:00
2030141
9869
8603
1
...
NaN
2.30
3.30
3.40
NaN
NaN
NaN
NaN
NaN
NaN
19572
24494
21484
21484
2015/2016
7
2015-10-03 00:00:00
2030142
8302
8634
2
...
NaN
4.10
3.90
1.91
NaN
NaN
NaN
NaN
NaN
NaN
19573
24496
21484
21484
2015/2016
7
2015-10-02 00:00:00
2030144
9910
8305
0
...
NaN
1.50
4.50
7.50
NaN
NaN
NaN
NaN
NaN
NaN
19574
24497
21484
21484
2015/2016
7
2015-10-04 00:00:00
2030145
8581
10205
1
...
NaN
4.40
3.60
1.93
NaN
NaN
NaN
NaN
NaN
NaN
19575
24498
21484
21484
2015/2016
7
2015-10-04 00:00:00
2030146
9906
8633
1
...
NaN
3.13
3.40
2.45
NaN
NaN
NaN
NaN
NaN
NaN
19576
24499
21484
21484
2015/2016
7
2015-10-03 00:00:00
2030147
9864
8560
3
...
NaN
2.40
3.25
3.30
NaN
NaN
NaN
NaN
NaN
NaN
19577
24500
21484
21484
2015/2016
7
2015-10-04 00:00:00
2030148
8315
10267
3
...
NaN
2.38
3.40
3.25
NaN
NaN
NaN
NaN
NaN
NaN
19578
24501
21484
21484
2015/2016
7
2015-10-03 00:00:00
2030149
7878
9783
1
...
NaN
2.63
3.25
3.00
NaN
NaN
NaN
NaN
NaN
NaN
19579
24502
21484
21484
2015/2016
7
2015-10-03 00:00:00
2030150
8558
9869
1
...
NaN
2.00
3.40
4.30
NaN
NaN
NaN
NaN
NaN
NaN
19580
24503
21484
21484
2015/2016
7
2015-10-04 00:00:00
2030151
8370
8603
0
...
NaN
2.20
3.80
3.30
NaN
NaN
NaN
NaN
NaN
NaN
19581
24504
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030152
8634
8370
5
...
NaN
1.15
9.50
19.00
NaN
NaN
NaN
NaN
NaN
NaN
19582
24505
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030153
8372
8302
1
...
NaN
3.60
3.50
2.20
NaN
NaN
NaN
NaN
NaN
NaN
19583
24507
21484
21484
2015/2016
8
2015-10-18 00:00:00
2030155
10205
9910
1
...
NaN
2.05
3.70
3.75
NaN
NaN
NaN
NaN
NaN
NaN
19584
24508
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030156
8633
8581
3
...
NaN
1.08
13.00
34.00
NaN
NaN
NaN
NaN
NaN
NaN
19585
24509
21484
21484
2015/2016
8
2015-10-18 00:00:00
2030157
8560
9906
0
...
NaN
4.30
3.30
2.05
NaN
NaN
NaN
NaN
NaN
NaN
19586
24510
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030158
10267
9864
3
...
NaN
1.62
4.10
6.25
NaN
NaN
NaN
NaN
NaN
NaN
19587
24511
21484
21484
2015/2016
8
2015-10-18 00:00:00
2030159
9783
8315
2
...
NaN
2.70
3.25
2.88
NaN
NaN
NaN
NaN
NaN
NaN
19588
24512
21484
21484
2015/2016
8
2015-10-19 00:00:00
2030160
9869
7878
3
...
NaN
2.00
3.40
4.33
NaN
NaN
NaN
NaN
NaN
NaN
19589
24513
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030161
8603
8558
1
...
NaN
2.05
3.50
4.00
NaN
NaN
NaN
NaN
NaN
NaN
19590
24514
21484
21484
2015/2016
9
2015-10-25 00:00:00
2030162
8634
8372
3
...
NaN
1.11
11.00
31.00
NaN
NaN
NaN
NaN
NaN
NaN
19591
24515
21484
21484
2015/2016
9
2015-10-24 00:00:00
2030163
8302
8305
5
...
NaN
1.50
4.60
7.50
NaN
NaN
NaN
NaN
NaN
NaN
19592
24516
21484
21484
2015/2016
9
2015-10-25 00:00:00
2030164
8306
10205
0
...
NaN
3.60
3.40
2.20
NaN
NaN
NaN
NaN
NaN
NaN
19593
24517
21484
21484
2015/2016
9
2015-10-24 00:00:00
2030165
9910
8633
1
...
NaN
3.90
4.00
1.93
NaN
NaN
NaN
NaN
NaN
NaN
19594
24518
21484
21484
2015/2016
9
2015-10-25 00:00:00
2030166
8581
8560
0
...
NaN
2.75
3.13
2.90
NaN
NaN
NaN
NaN
NaN
NaN
19595
24519
21484
21484
2015/2016
9
2015-10-25 00:00:00
2030167
9906
10267
2
...
NaN
1.57
4.00
7.00
NaN
NaN
NaN
NaN
NaN
NaN
19596
24520
21484
21484
2015/2016
9
2015-10-24 00:00:00
2030168
9864
9783
2
...
NaN
2.30
3.40
3.40
NaN
NaN
NaN
NaN
NaN
NaN
19597
24521
21484
21484
2015/2016
9
2015-10-26 00:00:00
2030169
8315
9869
3
...
NaN
1.55
4.20
7.00
NaN
NaN
NaN
NaN
NaN
NaN
19598
24522
21484
21484
2015/2016
9
2015-10-24 00:00:00
2030170
7878
8603
1
...
NaN
2.30
3.40
3.30
NaN
NaN
NaN
NaN
NaN
NaN
19599
24523
21484
21484
2015/2016
9
2015-10-23 00:00:00
2030171
8370
8558
3
...
NaN
2.20
3.60
3.50
NaN
NaN
NaN
NaN
NaN
NaN
19600 rows × 115 columns
Como podemos observar, temos 19600 jogos com informação sobre a posição dos jogadores e suas informações. Entretanto precisamos refinar as features.
In [4]:
drop = matches.columns.values[-27:-1]
print drop
#Removing other betting houses odds
matches2 = matches.drop(drop,1)
matches2= matches2.drop('BSA',1)
matches2
['BWH' 'BWD' 'BWA' 'IWH' 'IWD' 'IWA' 'LBH' 'LBD' 'LBA' 'PSH' 'PSD' 'PSA'
'WHH' 'WHD' 'WHA' 'SJH' 'SJD' 'SJA' 'VCH' 'VCD' 'VCA' 'GBH' 'GBD' 'GBA'
'BSH' 'BSD']
Out[4]:
id
country_id
league_id
season
stage
date
match_api_id
home_team_api_id
away_team_api_id
home_team_goal
...
shoton
shotoff
foulcommit
card
cross
corner
possession
B365H
B365D
B365A
0
146
1
1
2008/2009
24
2009-02-27 00:00:00
493017
8203
9987
2
...
None
None
None
None
None
None
None
3.00
3.40
2.30
1
154
1
1
2008/2009
25
2009-03-08 00:00:00
493025
9984
8342
1
...
None
None
None
None
None
None
None
2.80
3.20
2.37
2
156
1
1
2008/2009
25
2009-03-07 00:00:00
493027
8635
10000
2
...
None
None
None
None
None
None
None
1.40
4.50
8.00
3
163
1
1
2008/2009
26
2009-03-13 00:00:00
493034
8203
8635
2
...
None
None
None
None
None
None
None
4.50
3.60
1.75
4
169
1
1
2008/2009
26
2009-03-14 00:00:00
493040
10000
9999
0
...
None
None
None
None
None
None
None
1.75
3.50
4.75
5
174
1
1
2008/2009
27
2009-03-22 00:00:00
493045
9991
10000
1
...
None
None
None
None
None
None
None
1.65
3.60
4.75
6
177
1
1
2008/2009
27
2009-03-21 00:00:00
493048
9999
8203
1
...
None
None
None
None
None
None
None
2.20
3.30
3.00
7
190
1
1
2008/2009
29
2009-04-12 00:00:00
493061
8635
8342
1
...
None
None
None
None
None
None
None
1.67
3.50
5.00
8
191
1
1
2008/2009
29
2009-04-10 00:00:00
493062
9999
9987
1
...
None
None
None
None
None
None
None
3.20
3.25
2.25
9
220
1
1
2008/2009
31
2009-04-26 00:00:00
493082
9999
9991
1
...
None
None
None
None
None
None
None
3.20
3.30
2.10
10
227
1
1
2008/2009
32
2009-05-02 00:00:00
493089
10000
9985
0
...
None
None
None
None
None
None
None
5.50
3.60
1.57
11
230
1
1
2008/2009
32
2009-05-02 00:00:00
493092
9991
9984
2
...
None
None
None
None
None
None
None
1.36
4.33
7.50
12
232
1
1
2008/2009
32
2009-05-02 00:00:00
493094
10001
9999
1
...
None
None
None
None
None
None
None
1.57
3.60
5.50
13
235
1
1
2008/2009
33
2009-05-09 00:00:00
493097
9985
8342
2
...
None
None
None
None
None
None
None
1.44
4.33
7.00
14
241
1
1
2008/2009
33
2009-05-09 00:00:00
493103
8635
9999
3
...
None
None
None
None
None
None
None
1.14
7.50
19.00
15
243
1
1
2008/2009
33
2009-05-09 00:00:00
493105
9984
10001
2
...
None
None
None
None
None
None
None
2.62
3.30
2.62
16
244
1
1
2008/2009
34
2009-05-16 00:00:00
493106
9987
8635
0
...
None
None
None
None
None
None
None
8.00
4.00
1.40
17
245
1
1
2008/2009
34
2009-05-16 00:00:00
493107
9991
9985
0
...
None
None
None
None
None
None
None
4.33
3.80
1.67
18
309
1
1
2009/2010
1
2009-08-02 00:00:00
665321
9984
9991
1
...
None
None
None
None
None
None
None
2.88
3.30
2.25
19
310
1
1
2009/2010
1
2009-08-01 00:00:00
665322
9994
10000
1
...
None
None
None
None
None
None
None
2.30
3.30
2.88
20
311
1
1
2009/2010
1
2009-08-01 00:00:00
665323
8571
8635
0
...
None
None
None
None
None
None
None
5.75
3.60
1.57
21
314
1
1
2009/2010
10
2009-10-04 00:00:00
665411
8342
8635
4
...
None
None
None
None
None
None
None
2.50
3.25
2.60
22
318
1
1
2009/2010
10
2009-10-03 00:00:00
665417
8203
9994
2
...
None
None
None
None
None
None
None
1.91
3.30
4.20
23
320
1
1
2009/2010
10
2009-10-03 00:00:00
665421
9993
10001
3
...
None
None
None
None
None
None
None
1.73
3.50
5.00
24
321
1
1
2009/2010
11
2009-10-18 00:00:00
665425
8342
9991
1
...
None
None
None
None
None
None
None
1.70
3.40
4.75
25
323
1
1
2009/2010
11
2009-10-18 00:00:00
665427
9987
8203
1
...
None
None
None
None
None
None
None
1.85
3.30
4.00
26
324
1
1
2009/2010
11
2009-10-17 00:00:00
665429
10000
9993
4
...
None
None
None
None
None
None
None
1.91
3.30
3.80
27
325
1
1
2009/2010
11
2009-10-17 00:00:00
665430
9994
9984
1
...
None
None
None
None
None
None
None
2.10
3.20
3.30
28
327
1
1
2009/2010
11
2009-10-17 00:00:00
665435
10001
9985
2
...
None
None
None
None
None
None
None
5.50
3.50
1.60
29
328
1
1
2009/2010
12
2009-10-24 00:00:00
665438
9985
10000
1
...
None
None
None
None
None
None
None
1.50
4.00
7.00
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
...
19570
24492
21484
21484
2015/2016
6
2015-09-27 00:00:00
2030140
9783
8558
3
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>47</comment><stats...
2.10
3.30
3.75
19571
24493
21484
21484
2015/2016
6
2015-09-27 00:00:00
2030141
9869
8603
1
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>61</comment><stats...
2.30
3.20
3.30
19572
24494
21484
21484
2015/2016
7
2015-10-03 00:00:00
2030142
8302
8634
2
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>44</comment><stats...
4.00
3.60
1.91
19573
24496
21484
21484
2015/2016
7
2015-10-02 00:00:00
2030144
9910
8305
0
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>56</comment><stats...
1.44
4.50
7.50
19574
24497
21484
21484
2015/2016
7
2015-10-04 00:00:00
2030145
8581
10205
1
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>43</comment><stats...
4.33
3.40
1.91
19575
24498
21484
21484
2015/2016
7
2015-10-04 00:00:00
2030146
9906
8633
1
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>44</comment><stats...
3.20
3.30
2.30
19576
24499
21484
21484
2015/2016
7
2015-10-03 00:00:00
2030147
9864
8560
3
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>51</comment><stats...
2.38
3.10
3.30
19577
24500
21484
21484
2015/2016
7
2015-10-04 00:00:00
2030148
8315
10267
3
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>57</comment><stats...
2.30
3.30
3.20
19578
24501
21484
21484
2015/2016
7
2015-10-03 00:00:00
2030149
7878
9783
1
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>50</comment><stats...
2.60
3.20
2.80
19579
24502
21484
21484
2015/2016
7
2015-10-03 00:00:00
2030150
8558
9869
1
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><event_incident_typefk>123</even...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>42</comment><stats...
2.00
3.30
4.00
19580
24503
21484
21484
2015/2016
7
2015-10-04 00:00:00
2030151
8370
8603
0
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>60</comment><stats...
2.20
3.50
3.20
19581
24504
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030152
8634
8370
5
...
<shoton><value><event_incident_typefk>139</eve...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>55</comment><stats...
1.14
9.00
15.00
19582
24505
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030153
8372
8302
1
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><event_incident_typefk>123</even...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>42</comment><stats...
3.60
3.40
2.10
19583
24507
21484
21484
2015/2016
8
2015-10-18 00:00:00
2030155
10205
9910
1
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>46</comment><stats...
2.00
3.50
3.75
19584
24508
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030156
8633
8581
3
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>57</comment><stats...
1.08
12.00
23.00
19585
24509
21484
21484
2015/2016
8
2015-10-18 00:00:00
2030157
8560
9906
0
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>45</comment><stats...
4.00
3.20
2.05
19586
24510
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030158
10267
9864
3
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>62</comment><stats...
1.62
3.75
6.00
19587
24511
21484
21484
2015/2016
8
2015-10-18 00:00:00
2030159
9783
8315
2
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>48</comment><stats...
2.70
3.10
2.80
19588
24512
21484
21484
2015/2016
8
2015-10-19 00:00:00
2030160
9869
7878
3
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>61</comment><stats...
2.00
3.20
4.20
19589
24513
21484
21484
2015/2016
8
2015-10-17 00:00:00
2030161
8603
8558
1
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>47</comment><stats...
2.00
3.30
4.00
19590
24514
21484
21484
2015/2016
9
2015-10-25 00:00:00
2030162
8634
8372
3
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>66</comment><stats...
1.11
10.00
19.00
19591
24515
21484
21484
2015/2016
9
2015-10-24 00:00:00
2030163
8302
8305
5
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>56</comment><stats...
1.44
4.33
8.00
19592
24516
21484
21484
2015/2016
9
2015-10-25 00:00:00
2030164
8306
10205
0
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>59</comment><stats...
3.50
3.25
2.20
19593
24517
21484
21484
2015/2016
9
2015-10-24 00:00:00
2030165
9910
8633
1
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>46</comment><stats...
3.80
3.80
1.91
19594
24518
21484
21484
2015/2016
9
2015-10-25 00:00:00
2030166
8581
8560
0
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>51</comment><stats...
2.63
3.20
2.80
19595
24519
21484
21484
2015/2016
9
2015-10-25 00:00:00
2030167
9906
10267
2
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>49</comment><stats...
1.57
3.80
6.50
19596
24520
21484
21484
2015/2016
9
2015-10-24 00:00:00
2030168
9864
9783
2
...
<shoton><value><event_incident_typefk>876</eve...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>53</comment><stats...
2.25
3.25
3.40
19597
24521
21484
21484
2015/2016
9
2015-10-26 00:00:00
2030169
8315
9869
3
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>49</comment><stats...
1.53
4.00
7.00
19598
24522
21484
21484
2015/2016
9
2015-10-24 00:00:00
2030170
7878
8603
1
...
<shoton><value><stats><shoton>1</shoton></stat...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>50</comment><stats...
2.30
3.25
3.25
19599
24523
21484
21484
2015/2016
9
2015-10-23 00:00:00
2030171
8370
8558
3
...
<shoton><value><stats><blocked>1</blocked></st...
<shotoff><value><stats><shotoff>1</shotoff></s...
<foulcommit><value><stats><foulscommitted>1</f...
<card><value><comment>y</comment><stats><ycard...
<cross><value><stats><crosses>1</crosses></sta...
<corner><value><stats><corners>1</corners></st...
<possession><value><comment>59</comment><stats...
2.20
3.40
3.20
19600 rows × 88 columns
In [6]:
#Raw features
matches2.columns.values
Out[6]:
array(['id', 'country_id', 'league_id', 'season', 'stage', 'date',
'match_api_id', 'home_team_api_id', 'away_team_api_id',
'home_team_goal', 'away_team_goal', 'home_player_X1',
'home_player_X2', 'home_player_X3', 'home_player_X4',
'home_player_X5', 'home_player_X6', 'home_player_X7',
'home_player_X8', 'home_player_X9', 'home_player_X10',
'home_player_X11', 'away_player_X1', 'away_player_X2',
'away_player_X3', 'away_player_X4', 'away_player_X5',
'away_player_X6', 'away_player_X7', 'away_player_X8',
'away_player_X9', 'away_player_X10', 'away_player_X11',
'home_player_Y1', 'home_player_Y2', 'home_player_Y3',
'home_player_Y4', 'home_player_Y5', 'home_player_Y6',
'home_player_Y7', 'home_player_Y8', 'home_player_Y9',
'home_player_Y10', 'home_player_Y11', 'away_player_Y1',
'away_player_Y2', 'away_player_Y3', 'away_player_Y4',
'away_player_Y5', 'away_player_Y6', 'away_player_Y7',
'away_player_Y8', 'away_player_Y9', 'away_player_Y10',
'away_player_Y11', 'home_player_1', 'home_player_2',
'home_player_3', 'home_player_4', 'home_player_5', 'home_player_6',
'home_player_7', 'home_player_8', 'home_player_9', 'home_player_10',
'home_player_11', 'away_player_1', 'away_player_2', 'away_player_3',
'away_player_4', 'away_player_5', 'away_player_6', 'away_player_7',
'away_player_8', 'away_player_9', 'away_player_10',
'away_player_11', 'goal', 'shoton', 'shotoff', 'foulcommit', 'card',
'cross', 'corner', 'possession', 'B365H', 'B365D', 'B365A'], dtype=object)
Os dados presente nos campos goal, shoton, shotoff, foulcommit, card, cross, corner e possession estão no formato XML. Além disso, estes dados estao presentes em poucos jogos.
In [19]:
# 'shoton', 'shotoff','foulcommit', 'card','cross', 'corner', 'possession'
matches3 = matches2[matches2['goal'].notnull()]
matches3['possession'][1192]
Out[19]:
u'<possession><value><comment>56</comment><event_incident_typefk>352</event_incident_typefk><elapsed>25</elapsed><subtype>possession</subtype><sortorder>1</sortorder><awaypos>44</awaypos><homepos>56</homepos><n>68</n><type>special</type><id>379029</id></value><value><comment>54</comment><elapsed_plus>1</elapsed_plus><event_incident_typefk>352</event_incident_typefk><elapsed>45</elapsed><subtype>possession</subtype><sortorder>4</sortorder><awaypos>46</awaypos><homepos>54</homepos><n>117</n><type>special</type><id>379251</id></value><value><comment>54</comment><event_incident_typefk>352</event_incident_typefk><elapsed>70</elapsed><subtype>possession</subtype><sortorder>0</sortorder><awaypos>46</awaypos><homepos>54</homepos><n>190</n><type>special</type><id>379443</id></value><value><comment>55</comment><elapsed_plus>5</elapsed_plus><event_incident_typefk>352</event_incident_typefk><elapsed>90</elapsed><subtype>possession</subtype><sortorder>1</sortorder><awaypos>45</awaypos><homepos>55</homepos><n>252</n><type>special</type><id>379575</id></value></possession>'
In [ ]:
Content source: felipeapfer/artigoML
Similar notebooks: