UEFA_CL_Scraper/Applied.py at main · feamado/UEFA_CL_Scraper · GitHub

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
import csv
from bs4 import  BeautifulSoup
import requests
import Webscraping as ws
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd


#https://fbref.com/en/comps/8/2020-2021/2020-2021-Champions-League-Stats
#https://fbref.com/en/comps/8/2019-2020/2019-2020-Champions-League-Stats

def result_assignment(filename):
    df = pd.read_csv(filename)
    scores = df['Goals']
    print(scores)
    results = []
    for i in range(0,len(scores)-4,4):
        if scores[i]>scores[i+2]:
            results.append('W')
        if  scores[i]<scores[i+2]:
            results.append('L')
        if scores[i]==scores[i+2]:
            results.append('D')
        if scores[i+1]>scores[i+3]:
            results.append('W')
        if  scores[i+1]<scores[i+3]:
            results.append('L')
        if scores[i+1]==scores[i+3]:
            results.append('D')
        if scores[i]<scores[i+2]:
            results.append('W')
        if  scores[i]>scores[i+2]:
            results.append('L')
        if scores[i]==scores[i+2]:
            results.append('D')
        if scores[i+1]<scores[i+3]:
            results.append('W')
        if  scores[i+1]>scores[i+3]:
            results.append('L')
        if scores[i+1]==scores[i+3]:
            results.append('D')

    df['Results'] = results
    last_col = 'Results'
    df.columns = list(df.columns[:-1]) + [last_col]
    df.to_csv(filename,index=False)


#only usable with  files that have had results assigned
import pandas as pd

def compare_lead_stats_win_times(filename1, compare_stat):
    df1 = pd.read_csv(filename1)
    print(f"called for {compare_stat}")
    cnt = 0

    for i in range(0, len(df1) - 4, 2):
        stats_team1_game1 = df1.iloc[i][compare_stat]
        stats_team1_game2 = df1.iloc[i + 1][compare_stat]
        stats_team2_game1 = df1.iloc[i + 2][compare_stat]
        stats_team2_game2 = df1.iloc[i + 3][compare_stat]
        result_team1_game1 = df1.iloc[i]['Results']
        result_team1_game2 = df1.iloc[i + 1]['Results']
        result_team2_game1 = df1.iloc[i + 2]['Results']
        result_team2_game2 = df1.iloc[i + 3]['Results']

        # Compare stats of two games for both teams and increment counter
        if ((result_team1_game1 == 'W' or result_team1_game1 == 'D') and stats_team1_game1 >= stats_team2_game1):
            cnt += 1
        elif ((result_team2_game1 == 'W' or result_team2_game1 == 'D') and stats_team2_game1 >= stats_team1_game1):
            cnt += 1
        if ((result_team1_game2 == 'W' or result_team1_game2 == 'D') and stats_team1_game2 >=  stats_team2_game2):
            cnt += 1
        elif ((result_team2_game2 == 'W' or result_team2_game2 == 'D') and stats_team2_game2 >= stats_team1_game2):
            cnt += 1

    return cnt

def compare_all_lead_stats_win_times(filename1):
    df1 = pd.read_csv(filename1)
    headers = list(df1.columns[1:-1])
    list_cnts =[]
    for header in headers:
        list_cnts.append(compare_lead_stats_win_times(filename1,header))

    return list_cnts
def compare_all_lead_stats_win_time_rates_tournament(filename1,filename2,filename3):
    length =4+16+32
    df1 = pd.read_csv(filename1)
    headers = list(df1.columns[1:-1])
    list_cnts1 =[]
    list_cnts2=[]
    list_cnts3 = []
    for header in headers:
        list_cnts1.append(compare_lead_stats_win_times(filename1,header))
        list_cnts2.append(compare_lead_stats_win_times(filename2,header))
        list_cnts3.append(compare_lead_stats_win_times(filename3,header))
    a=np.array(list_cnts1)
    b=np.array(list_cnts2)
    c=np.array(list_cnts3)
    final = (a+b+c)/length

    return final

def compare_all_leaf_stats_win_percentages(filename):
    df1 = pd.read_csv(filename)
    length = len(df1['Goals'])
    list_times  = compare_all_lead_stats_win_times(filename)
    out = [(x/length)*100 for x in  list_times]
    return out
def win_rate_analysis_tournament(filename1,filename2,filename3):
    df1 = pd.read_csv(filename1)
    headers  = list(df1.columns[1:-1])
    analysis = compare_all_lead_stats_win_time_rates_tournament(filename1,filename2,filename3)
    i=2
    for header  in headers[2:]:
        print(f"{analysis[i]*100}%  of teams led in {header} and won their matches")
        i+=1
'''print(compare_all_leaf_stats_win_percentages('QF1.csv'))
print(compare_all_lead_stats_win_time_rates_tournament('Ro161.csv','SF1.csv','QF1.csv'))
print(compare_all_lead_stats_win_times('QF1.csv'))
win_rate_analysis_tournament('Ro161.csv','SF1.csv','QF1.csv')
#advanced stats to focus on XG,npXG,Shots on Target,Successful Takes,Goal Creating Actions
#GCA,npXG,xAG,ScsfulTakes,PrgP'''