improved model, fixed typos

data_filters.py

@@ -2,12 +2,12 @@ import pandas as pd
 from fuzzy import *
 
 
-def zapisz_do_csv(nazwa_pliku, dataframe):
+def save_to_csv(filename, dataframe):
-    dataframe.to_csv(nazwa_pliku, mode='a', index=False, header=not pd.DataFrame().append(dataframe).empty)
+    dataframe.to_csv(filename, mode='a', index=False, header=not pd.DataFrame().append(dataframe).empty)
 
-def podziel_na_partie(dataframe, rozmiar_partii):
+def split_to_parts(dataframe, part_size):
-    for i in range(0, len(dataframe), rozmiar_partii):
+    for i in range(0, len(dataframe), part_size):
-        yield dataframe.iloc[i:i + rozmiar_partii]
+        yield dataframe.iloc[i:i + part_size]
 
 def przetwarzaj_co_50_rekordow(plik_wejsciowy, plik_wyjsciowy):
     dataframe_wejsciowe = pd.read_csv(plik_wejsciowy)
@@ -40,16 +40,16 @@ def generateFuzzyLogicData(dataframe):
 
 
 def last5Matches(season, teamA, data, df):
-    # Wybierz rekordy dla danej pary drużyn i sezonu
+    
     subset = df[((df['season'] == season) & ((df['home_team'] == teamA) | (df['away_team'] == teamA)))]
 
-    # Filtruj dane, aby zawierały te przed daną datą
+    
     before_given_date = subset[pd.to_datetime(subset['date']) < pd.to_datetime(data)]
 
-    # Posortuj wg daty w odwrotnej kolejności
+   
     before_given_date = before_given_date.sort_values(by='date', ascending=False)
 
-    # Wybierz 5 ostatnich przed daną datą
+    
     last_before_date = before_given_date.head(5)
 
     return last_before_date, "_5m"

main.py

@@ -8,8 +8,7 @@ from sklearn.model_selection import train_test_split
 from sklearn.metrics import accuracy_score
 from sklearn.preprocessing import LabelEncoder
 from sklearn.metrics import classification_report
-
+from sklearn.ensemble import GradientBoostingClassifier
-
 
 
 # Ostatnie 5 spotkań
@@ -24,13 +23,12 @@ from sklearn.metrics import classification_report
 if __name__ == "__main__":
 
 
-    df = pd.read_csv('df_full_premierleague.csv')
+    df = pd.read_csv('df_parts.csv')
 
     
-
+    '''
 
         
-    '''
     df = pd.read_csv('df_full_premierleague.csv')
     result = last5Matches('10/11', 'Stoke City', '2010-10-02', df)[0]
     #print(result.to_markdown())
@@ -42,7 +40,6 @@ if __name__ == "__main__":
     print(calculatePoints(result,'Blackburn Rovers'))
     print(calculateGoalDifference(result, 'Blackburn Rovers'))
 
-    '''
 
    # df = generateTrainingData(df)
   #  df = add_column(df, categorize_passes, "c_away_passes", "away_passes")
@@ -158,8 +155,8 @@ if __name__ == "__main__":
     df.to_csv('df.csv', index=False)
 #TU sie zapisuje zbior
     
-    rozmiar_partii = 50
+    part_size = 50
-    for part in podziel_na_partie(df, rozmiar_partii):
+    for part in split_to_parts(df, part_size):
 
 
         part = add_column(part,
@@ -206,8 +203,8 @@ if __name__ == "__main__":
                         "c_away_passing_5btw")
         
 
-        zapisz_do_csv("df_parts", part)
+        save_to_csv("df_parts", part)
-
+'''
     df = generateFuzzyLogicData(df)
 
     label_encoder = LabelEncoder()
@@ -219,9 +216,12 @@ if __name__ == "__main__":
     df[['home_team', 'away_team']] = temp.unstack()
     X = df.drop(['result_full', 'date', 'c_home_result', 'c_away_result'], axis=1)
     y = df['c_home_result']
+    #y = label_encoder.fit_transform(df['c_home_result'])
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
-    model = RandomForestClassifier(n_estimators=100, random_state=42)
+    model = RandomForestClassifier(n_estimators=500, random_state=42)
+    #model = GradientBoostingClassifier(learning_rate=0.1, n_estimators=100, random_state = 42)
+
     model.fit(X_train, y_train)
 
     y_pred = model.predict(X_test)
@@ -232,6 +232,8 @@ if __name__ == "__main__":
     accuracy = accuracy_score(y_test, y_pred)
     print(f'Dokładność modelu: {accuracy}')
     print(classification_report(y_test, y_pred))
+
+    #print(model.feature_importances_)
     
 
     #print(categorize_fuzzy_passes(450,50))