PlayerCollection.py 文件源码

def get_classification_data(self, division_dummies=True, samples=None, percentile=100):
        raw = PlayerCollection.filter_by_class(self.raw)
        df = PlayerCollection.raw_to_df(raw)
        players, divisions = PlayerCollection.aggregate_df(df)
        players, divisions = PlayerCollection.to_matrix(players, divisions)
        players, divisions = PlayerCollection.subsample(players, divisions, samples)
        X_train, X_test, y_train, y_test = train_test_split(
            players, divisions, random_state=42, stratify=divisions)

        selector = SelectPercentile(f_classif, percentile=percentile)
        selector.fit(X_train, y_train)
        X_train = selector.transform(X_train)
        X_test = selector.transform(X_test)

        if division_dummies:
            y_train = pd.get_dummies(y_train).as_matrix()
            y_test = pd.get_dummies(y_test).as_matrix()
        scaler = StandardScaler()
        X_train = scaler.fit_transform(X_train)
        X_test = scaler.transform(X_test)
        return X_train, X_test, y_train, y_test