diff --git a/src/features/all_cleaning_individual/straw/main.py b/src/features/all_cleaning_individual/straw/main.py index 0edd06c6..387637f7 100644 --- a/src/features/all_cleaning_individual/straw/main.py +++ b/src/features/all_cleaning_individual/straw/main.py @@ -100,7 +100,7 @@ def straw_cleaning(sensor_data_files, provider): col.startswith('phone_screen_rapids_') or col.startswith('phone_wifi_visible')] - features[impute_zero] = features[impute_zero].fillna(0) + features[impute_zero+list(esm_cols.columns)] = features[impute_zero+list(esm_cols.columns)].fillna(0) ## (5) STANDARDIZATION if provider["STANDARDIZATION"]: diff --git a/src/features/all_cleaning_overall/straw/main.py b/src/features/all_cleaning_overall/straw/main.py index 3250f6d7..f9a86c20 100644 --- a/src/features/all_cleaning_overall/straw/main.py +++ b/src/features/all_cleaning_overall/straw/main.py @@ -14,6 +14,9 @@ def straw_cleaning(sensor_data_files, provider, target): features = pd.read_csv(sensor_data_files["sensor_data"][0]) + # print(features) + # sys.exit() + esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns with open('config.yaml', 'r') as stream: @@ -26,8 +29,12 @@ def straw_cleaning(sensor_data_files, provider, target): # (1) FILTER_OUT THE ROWS THAT DO NOT HAVE THE TARGET COLUMN AVAILABLE if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']: features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True) + + if features.empty: + return pd.DataFrame(columns=excluded_columns) graph_bf_af(features, "2target_rows_after") + print("HERE1", target, features["pid"]) # (2) QUALITY CHECK (DATA YIELD COLUMN) drops the rows where E4 or phone data is low quality phone_data_yield_unit = provider["PHONE_DATA_YIELD_FEATURE"].split("_")[3].lower() @@ -39,27 +46,30 @@ def straw_cleaning(sensor_data_files, provider, target): raise KeyError(f"RAPIDS provider needs to clean the selected event features based on {phone_data_yield_column} and empatica_data_yield columns. For phone data yield, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded{data_yield_unit}' in [FEATURES].") hist = features[["empatica_data_yield", phone_data_yield_column]].hist() - plt.legend() plt.savefig(f'phone_E4_histogram.png', bbox_inches='tight') # Drop rows where phone data yield is less then given threshold if provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]: - print("\nThreshold:", provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]) - print("Phone features data yield stats:", features[phone_data_yield_column].describe(), "\n") + # print("\nThreshold:", provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]) + # print("Phone features data yield stats:", features[phone_data_yield_column].describe(), "\n") # print(features[phone_data_yield_column].sort_values()) hist = features[phone_data_yield_column].hist(bins=5) plt.close() features = features[features[phone_data_yield_column] >= provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True) - + # Drop rows where empatica data yield is less then given threshold if provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]: - print("\nThreshold:", provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]) - print("E4 features data yield stats:", features["empatica_data_yield"].describe(), "\n") + # print("\nThreshold:", provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]) + # print("E4 features data yield stats:", features["empatica_data_yield"].describe(), "\n") # print(features["empatica_data_yield"].sort_values()) features = features[features["empatica_data_yield"] >= provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True) + graph_bf_af(features, "3data_yield_drop_rows") + if features.empty: + return pd.DataFrame(columns=excluded_columns) + # (3) CONTEXTUAL IMPUTATION # Impute selected phone features with a high number @@ -83,7 +93,7 @@ def straw_cleaning(sensor_data_files, provider, target): impute_w_sn3 = [col for col in features.columns if "loglocationvariance" in col] features[impute_w_sn2] = features[impute_w_sn2].fillna(-1000000) # Special case of imputation - loglocation - # Impute selected phone features with 0 + # Impute selected phone features with 0 + impute ESM features with 0 impute_zero = [col for col in features if \ col.startswith('phone_applications_foreground_rapids_') or col.startswith('phone_battery_rapids_') or @@ -94,23 +104,22 @@ def straw_cleaning(sensor_data_files, provider, target): col.startswith('phone_screen_rapids_') or col.startswith('phone_wifi_visible')] - features[impute_zero] = features[impute_zero].fillna(0) + features[impute_zero+list(esm_cols.columns)] = features[impute_zero+list(esm_cols.columns)].fillna(0) - graph_bf_af(features, "5zero_imp") + graph_bf_af(features, "4context_imp") # (4) REMOVE COLS IF THEIR NAN THRESHOLD IS PASSED (should be <= if even all NaN columns must be preserved - this solution now drops columns with all NaN rows) esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]] - graph_bf_af(features, "6too_much_nans_cols") - + graph_bf_af(features, "5too_much_nans_cols") # (5) REMOVE COLS WHERE VARIANCE IS 0 if provider["COLS_VAR_THRESHOLD"]: features.drop(features.std()[features.std() == 0].index.values, axis=1, inplace=True) - graph_bf_af(features, "7variance_drop") + graph_bf_af(features, "6variance_drop") # Preserve esm cols if deleted (has to come after drop cols operations) for esm in esm_cols: @@ -121,9 +130,13 @@ def straw_cleaning(sensor_data_files, provider, target): min_count = math.ceil((1 - provider["ROWS_NAN_THRESHOLD"]) * features.shape[1]) # minimal not nan values in row features.dropna(axis=0, thresh=min_count, inplace=True) # Thresh => at least this many not-nans - graph_bf_af(features, "8too_much_nans_rows") + graph_bf_af(features, "7too_much_nans_rows") - # (7) STANDARDIZATION + if features.empty: + return pd.DataFrame(columns=excluded_columns) + + + # (7) STANDARDIZATION TODO: exclude nominal features from standardization if provider["STANDARDIZATION"]: # Expected warning within this code block @@ -132,14 +145,15 @@ def straw_cleaning(sensor_data_files, provider, target): features.loc[:, ~features.columns.isin(excluded_columns + ["pid"])] = \ features.loc[:, ~features.columns.isin(excluded_columns)].groupby('pid').transform(lambda x: StandardScaler().fit_transform(x.values[:,np.newaxis]).ravel()) - graph_bf_af(features, "9standardization") + graph_bf_af(features, "8standardization") # (8) IMPUTATION: IMPUTE DATA WITH KNN METHOD features.reset_index(drop=True, inplace=True) impute_cols = [col for col in features.columns if col not in excluded_columns and col != "pid"] + features[impute_cols] = impute(features[impute_cols], method="knn") - graph_bf_af(features, "10knn_after") + graph_bf_af(features, "9knn_after") # (9) DROP HIGHLY CORRELATED FEATURES diff --git a/src/models/merge_features_and_targets_for_population_model.py b/src/models/merge_features_and_targets_for_population_model.py index f9e9acd2..0ede61f8 100644 --- a/src/models/merge_features_and_targets_for_population_model.py +++ b/src/models/merge_features_and_targets_for_population_model.py @@ -12,9 +12,13 @@ for baseline_features_path in snakemake.input["demographic_features"]: all_baseline_features = pd.concat([all_baseline_features, baseline_features], axis=0) # merge sensor features and baseline features -features = sensor_features.merge(all_baseline_features, on="pid", how="left") +if not sensor_features.empty: + features = sensor_features.merge(all_baseline_features, on="pid", how="left") -target_variable_name = snakemake.params["target_variable"] -model_input = retain_target_column(features, target_variable_name) + target_variable_name = snakemake.params["target_variable"] + model_input = retain_target_column(features, target_variable_name) -model_input.to_csv(snakemake.output[0], index=False) + model_input.to_csv(snakemake.output[0], index=False) + +else: + sensor_features.to_csv(snakemake.output[0], index=False)