-
Notifications
You must be signed in to change notification settings - Fork 0
/
worldcuppredictor.py
199 lines (150 loc) · 6.85 KB
/
worldcuppredictor.py
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
# -*- coding: utf-8 -*-
"""
Created on Tue May 12 17:41:56 2020
@author: viswa janith
"""
#import all libraries and dependencies
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.ticker as ticker
import matplotlib.ticker as plticker
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
#load data
world_cup = pd.read_csv('datasets/World Cup 2019 Dataset.csv')
results = pd.read_csv('datasets/results.csv')
df = results[(results['Team_1'] == 'India') | (results['Team_2'] == 'India')]
india = df.iloc[:]
#just print india.head()
#creating a column for matches played in 2010
year = []
for row in india['date']:
year.append(int(row[7:]))
india ['match_year']= year
india_2010 = india[india.match_year >= 10]
#just print india_2010.count()
#narrowing to team patcipating in the world cup
worldcup_teams = ['England', ' South Africa', '', 'West Indies',
'Pakistan', 'New Zealand', 'Sri Lanka', 'Afghanistan',
'Australia', 'Bangladesh', 'India']
df_teams_1 = results[results['Team_1'].isin(worldcup_teams)]
df_teams_2 = results[results['Team_2'].isin(worldcup_teams)]
df_teams = pd.concat((df_teams_1, df_teams_2))
df_teams.drop_duplicates()
#just print df_teams.count()
#dropping columns that wll not affect match outcomes
df_teams_2010 = df_teams.drop(['date','Margin', 'Ground'], axis=1)
# just print df_teams_2010.head()
#Building the model
#the prediction label: The winning_team column will show "1" Team 1 has won and "2" if the away team has won.
df_teams_2010 = df_teams_2010.reset_index(drop=True)
df_teams_2010.loc[df_teams_2010.Winner == df_teams_2010.Team_1,'winning_team']=1
df_teams_2010.loc[df_teams_2010.Winner == df_teams_2010.Team_2, 'winning_team']=2
df_teams_2010 = df_teams_2010.drop(['winning_team'], axis=1)
#print df_teams_2010.head()
#convert team-1 and team-2 from categorical variables to continous inputs
# Get dummy variables
final = pd.get_dummies(df_teams_2010, prefix=['Team_1', 'Team_2'], columns=['Team_1', 'Team_2'])
# Separate X and y sets
X = final.drop(['Winner'], axis=1)
y = final["Winner"]
# Separate train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42)
rf = RandomForestClassifier(n_estimators=100, max_depth=20,random_state=0)
rf.fit(X_train, y_train)
score = rf.score(X_train, y_train)
score2 = rf.score(X_test, y_test)
print("Training set accuracy: ", '%.3f'%(score))
print("Test set accuracy: ", '%.3f'%(score2))
#adding ICC rankings
#the team which is positioned higher on the ICC Ranking will be considered "favourite" for the match
#and therefore, will be positioned under the "Team_1" column
# Loading new datasets
ranking = pd.read_csv('datasets/icc_rankings.csv')
fixtures = pd.read_csv('datasets/fixtures.csv')
# List for storing the group stage games
pred_set = []
# Create new columns with ranking position of each team
fixtures.insert(1, 'first_position', fixtures['Team_1'].map(ranking.set_index('Team')['Position']))
fixtures.insert(2, 'second_position', fixtures['Team_2'].map(ranking.set_index('Team')['Position']))
# We only need the group stage games, so we have to slice the dataset
fixtures = fixtures.iloc[:45, :]
##print fixtures.tail()
# Loop to add teams to new prediction dataset based on the ranking position of each team
for index, row in fixtures.iterrows():
if row['first_position'] < row['second_position']:
pred_set.append({'Team_1': row['Team_1'], 'Team_2': row['Team_2'], 'winning_team': None})
else:
pred_set.append({'Team_1': row['Team_2'], 'Team_2': row['Team_1'], 'winning_team': None})
pred_set = pd.DataFrame(pred_set)
backup_pred_set = pred_set
#print pred_set.head()
# Get dummy variables and drop winning_team column
pred_set = pd.get_dummies(pred_set, prefix=['Team_1', 'Team_2'], columns=['Team_1', 'Team_2'])
# Add missing columns compared to the model's training dataset
missing_cols = set(final.columns) - set(pred_set.columns)
for c in missing_cols:
pred_set[c] = 0
pred_set = pred_set[final.columns]
pred_set = pred_set.drop(['Winner'], axis=1)
#print pred_set.head()
#group matches
predictions = rf.predict(pred_set)
for i in range(fixtures.shape[0]):
print(backup_pred_set.iloc[i, 1] + " and " + backup_pred_set.iloc[i, 0])
if predictions[i] == 1:
print("Winner: " + backup_pred_set.iloc[i, 1])
else:
print("Winner: " + backup_pred_set.iloc[i, 0])
print("")
# List of tuples before
semi = [('New Zealand', 'India'),
('England', 'South Africa')]
def clean_and_predict(matches, ranking, final, logreg):
# Initialization of auxiliary list for data cleaning
positions = []
# Loop to retrieve each team's position according to ICC ranking
for match in matches:
positions.append(ranking.loc[ranking['Team'] == match[0],'Position'].iloc[0])
positions.append(ranking.loc[ranking['Team'] == match[1],'Position'].iloc[0])
# Creating the DataFrame for prediction
pred_set = []
# Initializing iterators for while loop
i = 0
j = 0
# 'i' will be the iterator for the 'positions' list, and 'j' for the list of matches (list of tuples)
while i < len(positions):
dict1 = {}
# If position of first team is better then this team will be the 'Team_1' team, and vice-versa
if positions[i] < positions[i + 1]:
dict1.update({'Team_1': matches[j][0], 'Team_2': matches[j][1]})
else:
dict1.update({'Team_1': matches[j][1], 'Team_2': matches[j][0]})
# Append updated dictionary to the list, that will later be converted into a DataFrame
pred_set.append(dict1)
i += 2
j += 1
# Convert list into DataFrame
pred_set = pd.DataFrame(pred_set)
backup_pred_set = pred_set
# Get dummy variables and drop winning_team column
pred_set = pd.get_dummies(pred_set, prefix=['Team_1', 'Team_2'], columns=['Team_1', 'Team_2'])
# Add missing columns compared to the model's training dataset
missing_cols2 = set(final.columns) - set(pred_set.columns)
for c in missing_cols2:
pred_set[c] = 0
pred_set = pred_set[final.columns]
pred_set = pred_set.drop(['Winner'], axis=1)
# Predict!
predictions = logreg.predict(pred_set)
for i in range(len(pred_set)):
print(backup_pred_set.iloc[i, 1] + " and " + backup_pred_set.iloc[i, 0])
if predictions[i] == 1:
print("Winner: " + backup_pred_set.iloc[i, 1])
else:
print("Winner: " + backup_pred_set.iloc[i, 0])
print("")
s=clean_and_predict(semi, ranking, final, rf)