Match Outcome Prediction Projetct

#importando as bibliotecas

import sqlite3
import pandas as pd
import numpy as np
import seaborn as sns
#import iterpools
import matplotlib.pyplot as plt
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn import linear_model
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report, accuracy_score
from sklearn.calibration import CalibratedClassifierCV
from sklearn import model_selection
from sklearn.model_selection import train_test_split
from sklearn.metrics import make_scorer
from time import time
from sklearn.decomposition import PCA, FastICA
from sklearn.pipeline import Pipeline
import warnings
warnings.simplefilter("ignore")


#carregar as funções
def get_match_label(match):
    
    #definir as variaveis
    home_goals = match['home_team_goal']
    away_goals = match['away_team_goal']
    
    label = pd.DataFrame()
    label.loc[0,'match_api_id'] = match ['match_api_id']
    
    #identificar quem ganhou
    if home_goals > away_goals:
        label.loc[0,'label'] = "Win"
        
    if home_goals == away_goals:
        label.loc[0,'label'] = "Draw"
    
    if home_goals < away_goals:
        label.loc[0,'label'] = "Defeat"
    
#retorna a partida
return label.loc[0]

def get_fifa_stats(match, player_stats):
    #agregar estatisticas para a partida
    
    #definir as variaveis
    match_id = match.match_api_id
    date = match['date']
    players = ['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']
    player_stats_new = pd.DataFrame()
    names = []
    
    #loop através dos jogadores
    for player in players:
    
        #ID do jogador
        player_id = match[player]
    
        #Estatistica do jogador
        stats = player_stats[player_stats.player_api_id == player_id]
    
        #Identificar as estatísticas atuais
        current_stats = stats[stats.date < date].sort_values(by = 'date', ascending = False)[:1]
        
    if np.isnan(player_id) == True:
        overral_rating = pd.Series(0)
        
    else:
        current_stats.reset_index(inplace = True, drop = True)
        overall_rating = pd.Series(current_stats.loc[0, "overral_rating"])
        
        #renomear as estatisticas
        name = "{}_overall_rating".format (player)
        names.append (name)
        
        #agregando as estatisticas
        player_stats_new = pd.concat([player_stats_new, overral_rating], axis = 1)
        
    player_stats_new.columns = names
    player_stats_new['match_api_id'] = match_id
    
    player_stats_new.reset_index(inplace=True, drop = True)
    
    #retorna a estatistica dos jogadores
    return player_stats_new.ix[0]

def get_fifa_data(matches, player_stats, path = None, data_exists = False):
    #coletando os dados das partidas
    
    #checar se os dados da fifa realmente existe
    if data_exists == True:
        
        fifa_data = pd.read_pickle(path)
        
    else:
        
        print("Coletando os dados da fifa de cada partida...")
        start = time()
        
        #aplicar 
        fifa_data = matches.apply(lambda x :get_fifa_stats(x, player_stats), axis = 1)
        
        end = time()
        print("dados da Fifa coletada in {:.1f} minutes".format((end - start)/60))
    
#retorna a data fifa
return fifa_data

def get_overall_fifa_rankings (fifa, get_overall = False):
    #notas da fifa através dos dados
    
    temp_data = fifa
    
    #verificar se apenas as estatisticas dos jogadores são desejadas
    
    if get_overall == True:
        
        #obtendo as estatísticas gerais
        data = temp_data.loc[:,(fifa.columns.str.contains('overall_rating'))]
        data.loc[:,'match_api_id'] = temp_data.loc[:,'match_api_id']
    
    else:
        
        #obtendo todas estatisticas exceto a estatisticas da data
        cols = fifa.loc [:,(fifa.columns.str.contains('date_stat'))]
        temp_data = fifa.drop(cols.columns, axis = 1)
        data = temp_data
    
#retorna os dados
return data

def get_last_matches_against_eachother(matches, date, home_team, away_team, x = 10):
    #retorna os ultimos "x" confronto de uma só equipe
    
    #filtrar partida por partida
    team_matches = matches[(matches['home_team_api_id'] == team)  |  (matches['away_team_api_id'] == team)]
    
    #filtrar "x" partidas do time
    last_matches = team_matches[team_matches.date < date].sort_values(by= 'date', ascending = False).iloc[0:x,:]
    
#retorna as ultimas partidas
return last_matches

def get_last_matches_against_eachother(matches, date, home_team, away_team, x = 10):
    #retorna as ultimas "x" partidas de outros dois times
    
    #filtrar a partida por partida
    team_matches = matches[(matches['home_team_api_id'] == team ) | (matches['awat_team_api_id'] == team)]
    
    #filtrar x ultimas partidas dos times
    last_matches = team_matches[team_matches.date < date].sort_values(by = 'date', ascending = False).iloc[:,x,:]
    
#retorna os dados
return last_matches