two_sigma_financial_modelling.py 文件源码

def clean_data(self, df, is_with_MICE=0):
        df = df.copy()
        if df.isnull().sum().sum() > 0:
            if is_with_MICE:
                # Imputation using MICE
                numerical_features_names = self.extract_numerical_features(df)
                df.loc[:, tuple(numerical_features_names)] = self.estimate_by_mice(df[numerical_features_names])
            else:
                if any(tuple(df.columns == 'y')):
                    df = df.dropna()
                else:
                    df = df.dropna(1)
                    TwoSigmaFinModTools._feature_names_num = pd.Series(data=np.intersect1d(
                        TwoSigmaFinModTools._feature_names_num.values, df.columns), dtype=object)
        TwoSigmaFinModTools._numerical_feature_names = TwoSigmaFinModTools.extract_numerical_features(df)
        return df