two_sigma_financial_modelling.py 文件源码

def feature_mapping_to_numerical_values(self, df):
        TwoSigmaFinModTools._is_one_hot_encoder = 0
        mask = ~df.isnull()
        # Assume that training set has all possible feature_var_names
        # Although it may occur in real life that a training set may hold a feature_var_name. But it is probably
        # avoided since such features cannot
        # be part of the trained learning algo.
        # Add missing feature_var_names of training set not occurring in test set. Add these with zeros in columns.
        if not any(tuple(df.columns == 'y')):
            # All one-hot encoded feature var names occurring in test data is assigned the public variable
            # df_test_all_feature_var_names.
            self.df_test_all_feature_var_names = df.columns

        _feature_names_num = np.zeros((TwoSigmaFinModTools._non_numerical_feature_names.shape[0],), dtype=object)
        ith = 0
        for feature_name in TwoSigmaFinModTools._non_numerical_feature_names:
            # Create a feature_nameNum list
            feature_name_num = ''.join([feature_name, 'Num'])
            _feature_names_num[ith] = feature_name_num
            ith += 1
            TwoSigmaFinModTools.encode_labels_in_numeric_format(df, feature_name)

            if TwoSigmaFinModTools._is_one_hot_encoder:
                is_with_label_binarizer = 0
                if is_with_label_binarizer:
                    mapper_df = DataFrameMapper([(feature_name, LabelBinarizer())], df_out=True)
                    feature_var_values = mapper_df.fit_transform(df.copy())
                    print(df[feature_name].isnull().sum().sum())
                    print(df[feature_name][mask[feature_name]].isnull().sum().sum())
                    for ite in feature_var_values.columns:
                        df[ite] = feature_var_values[ite]
                else:
                    TwoSigmaFinModTools.one_hot_encoder(df, feature_name)
        TwoSigmaFinModTools._feature_names_num = pd.Series(data=_feature_names_num, dtype=object)