import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn import preprocessing
import kaggle

kaggle.api.authenticate()

kaggle.api.dataset_download_files('martj42/international-football-results-from-1872-to-2017', path='.', unzip=True)

results = pd.read_csv('results.csv')

#brak wierszy z NaN
results.dropna()

#normalizacja itp
for collumn in ['home_team', 'away_team', 'tournament', 'city', 'country']:
    results[collumn] = results[collumn].str.lower()
    
# Podział zbioru 6:1:1
train, test = train_test_split(results, test_size= 1 - 0.6)

valid, test = train_test_split(test, test_size=0.5) 


print("All data: ", results.size)
print("Train size: ", train.size)
print("Test size: ", test.size)
print("Validate size: ", valid.size)
print(results.describe(include='all'))

# sprawdzenie czy cały dataset oraz podział na podzbiory jest równy
print(train.size+test.size+valid.size)