From bbeabeee6ff7e3f8cc429470404c2c4b246b6a22 Mon Sep 17 00:00:00 2001 From: Primoz Date: Mon, 3 Oct 2022 12:53:31 +0000 Subject: [PATCH] Last changes before processing on the server. --- .../all_cleaning_individual/straw/main.py | 31 ++++----- .../all_cleaning_overall/straw/main.py | 63 ++++++++++++++----- 2 files changed, 65 insertions(+), 29 deletions(-) diff --git a/src/features/all_cleaning_individual/straw/main.py b/src/features/all_cleaning_individual/straw/main.py index 4004386d..27d7ff80 100644 --- a/src/features/all_cleaning_individual/straw/main.py +++ b/src/features/all_cleaning_individual/straw/main.py @@ -73,9 +73,12 @@ def straw_cleaning(sensor_data_files, provider): "timelastmessages" in col] features[impute_w_hn] = impute(features[impute_w_hn], method="high_number") - # Impute special case (mostcommonactivity) + # Impute special case (mostcommonactivity) and (homelabel) impute_w_sn = [col for col in features.columns if "mostcommonactivity" in col] - features[impute_w_sn] = features[impute_w_sn].fillna(4) # Special case of imputation + features[impute_w_sn] = features[impute_w_sn].fillna(4) # Special case of imputation - nominal/ordinal value + + impute_w_sn2 = [col for col in features.columns if "homelabel" in col] + features[impute_w_sn2] = features[impute_w_sn2].fillna(1) # Special case of imputation - nominal/ordinal value # Impute selected phone features with 0 impute_zero = [col for col in features if \ @@ -87,20 +90,16 @@ def straw_cleaning(sensor_data_files, provider): col.startswith('phone_messages_rapids_') or col.startswith('phone_screen_rapids_') or col.startswith('phone_wifi_visible')] - features[impute_locations] = impute(features[impute_locations], method="zero") + features[impute_zero] = impute(features[impute_zero], method="zero") ## (5) STANDARDIZATION if provider["STANDARDIZATION"]: features.loc[:, ~features.columns.isin(excluded_columns)] = StandardScaler().fit_transform(features.loc[:, ~features.columns.isin(excluded_columns)]) - - graph_bf_af(features[impute_locations], "knn_before") # (6) IMPUTATION: IMPUTE DATA WITH KNN METHOD impute_cols = [col for col in features.columns if col not in excluded_columns] features[impute_cols] = impute(features[impute_cols], method="knn") - graph_bf_af(features[impute_locations], "knn_after") - # (7) REMOVE COLS WHERE VARIANCE IS 0 esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] @@ -131,8 +130,6 @@ def straw_cleaning(sensor_data_files, provider): if features.isna().any().any(): raise ValueError - sys.exit() - return features def impute(df, method='zero'): @@ -149,9 +146,13 @@ def impute(df, method='zero'): 'knn': k_nearest(df) }[method] -def graph_bf_af(features, phase_name): - sns.set(rc={"figure.figsize":(16, 8)}) - print(features) - sns.heatmap(features.isna(), cbar=False) #features.select_dtypes(include=np.number) - plt.savefig(f'features_individual_nans_{phase_name}.png', bbox_inches='tight') - +def graph_bf_af(features, phase_name, plt_flag=False): + if plt_flag: + sns.set(rc={"figure.figsize":(16, 8)}) + sns.heatmap(features.isna(), cbar=False) #features.select_dtypes(include=np.number) + plt.savefig(f'features_overall_nans_{phase_name}.png', bbox_inches='tight') + + print(f"\n-------------{phase_name}-------------") + print("Rows number:", features.shape[0]) + print("Columns number:", len(features.columns)) + print("---------------------------------------------\n") diff --git a/src/features/all_cleaning_overall/straw/main.py b/src/features/all_cleaning_overall/straw/main.py index 99a6da72..57869da8 100644 --- a/src/features/all_cleaning_overall/straw/main.py +++ b/src/features/all_cleaning_overall/straw/main.py @@ -11,8 +11,6 @@ import seaborn as sns sys.path.append('/rapids/') from src.features import empatica_data_yield as edy -pd.set_option('display.max_columns', 20) - def straw_cleaning(sensor_data_files, provider): features = pd.read_csv(sensor_data_files["sensor_data"][0]) @@ -24,11 +22,15 @@ def straw_cleaning(sensor_data_files, provider): excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime'] + graph_bf_af(features, "1target_rows_before") + # (1) FILTER_OUT THE ROWS THAT DO NOT HAVE THE TARGET COLUMN AVAILABLE if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']: target = config['PARAMS_FOR_ANALYSIS']['TARGET']['LABEL'] # get target label from config features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True) + graph_bf_af(features, "2target_rows_after") + # (2.1) QUALITY CHECK (DATA YIELD COLUMN) deletes the rows where E4 or phone data is low quality phone_data_yield_unit = provider["PHONE_DATA_YIELD_FEATURE"].split("_")[3].lower() phone_data_yield_column = "phone_data_yield_rapids_ratiovalidyielded" + phone_data_yield_unit @@ -38,23 +40,41 @@ def straw_cleaning(sensor_data_files, provider): if not phone_data_yield_column in features.columns and not "empatica_data_yield" in features.columns: 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(features[phone_data_yield_column].sort_values()) + hist = features[phone_data_yield_column].hist(bins=5) 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(features["empatica_data_yield"].sort_values()) features = features[features["empatica_data_yield"] >= provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True) + + sys.exit() + graph_bf_af(features, "3data_yield_drop_rows") # (2.2) DO THE ROWS CONSIST OF ENOUGH NON-NAN VALUES? 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, "4too_much_nans_rows") + # (3) 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, "5too_much_nans_cols") + # Preserve esm cols if deleted (has to come after drop cols operations) for esm in esm_cols: if esm not in features: @@ -73,9 +93,14 @@ def straw_cleaning(sensor_data_files, provider): "timelastmessages" in col] features[impute_w_hn] = impute(features[impute_w_hn], method="high_number") - # Impute special case (mostcommonactivity) + graph_bf_af(features, "6high_number_imp") + + # Impute special case (mostcommonactivity) and (homelabel) impute_w_sn = [col for col in features.columns if "mostcommonactivity" in col] - features[impute_w_sn] = features[impute_w_sn].fillna(4) # Special case of imputation + features[impute_w_sn] = features[impute_w_sn].fillna(4) # Special case of imputation - nominal/ordinal value + + impute_w_sn2 = [col for col in features.columns if "homelabel" in col] + features[impute_w_sn2] = features[impute_w_sn2].fillna(1) # Special case of imputation - nominal/ordinal value # Impute selected phone features with 0 impute_zero = [col for col in features if \ @@ -87,7 +112,9 @@ def straw_cleaning(sensor_data_files, provider): col.startswith('phone_messages_rapids_') or col.startswith('phone_screen_rapids_') or col.startswith('phone_wifi_visible')] - features[impute_locations] = impute(features[impute_locations], method="zero") + features[impute_zero] = impute(features[impute_zero], method="zero") + + graph_bf_af(features, "7zero_imp") # Impute phone locations with median - should this rather be imputed at kNN step?? # impute_locations = [col for col in features.columns if "phone_locations_" in col] @@ -103,18 +130,19 @@ def straw_cleaning(sensor_data_files, provider): # features[impute_locations] = features[impute_locations + ["pid"]].groupby("pid").transform(lambda x: x.fillna(x.median()))[impute_locations] + # (5) STANDARDIZATION if provider["STANDARDIZATION"]: features.loc[:, ~features.columns.isin(excluded_columns + ["pid"])] = \ features.loc[:, ~features.columns.isin(excluded_columns)].groupby('pid').transform(lambda x: 0 if (x.std() == 0) else (x - x.mean()) / x.std()) - graph_bf_af(features[impute_locations], "knn_before") + graph_bf_af(features, "8standardization") # (6) IMPUTATION: IMPUTE DATA WITH KNN METHOD 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[impute_locations], "knn_after") + graph_bf_af(features, "9knn_after") # (7) REMOVE COLS WHERE VARIANCE IS 0 esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] @@ -122,6 +150,8 @@ def straw_cleaning(sensor_data_files, provider): if provider["COLS_VAR_THRESHOLD"]: features.drop(features.std()[features.std() == 0].index.values, axis=1, inplace=True) + graph_bf_af(features, "10variance_drop") + # (8) DROP HIGHLY CORRELATED FEATURES drop_corr_features = provider["DROP_HIGHLY_CORRELATED_FEATURES"] if drop_corr_features["COMPUTE"] and features.shape[0] > 5: # If small amount of segments (rows) is present, do not execute correlation check @@ -142,12 +172,12 @@ def straw_cleaning(sensor_data_files, provider): if esm not in features: features[esm] = esm_cols[esm] + graph_bf_af(features, "11correlation_drop") + # (9) VERIFY IF THERE ARE ANY NANS LEFT IN THE DATAFRAME if features.isna().any().any(): raise ValueError - sys.exit() - return features def impute(df, method='zero'): @@ -164,9 +194,14 @@ def impute(df, method='zero'): 'knn': k_nearest(df) }[method] -def graph_bf_af(features, phase_name): - sns.set(rc={"figure.figsize":(16, 8)}) - print(features) - sns.heatmap(features.isna(), cbar=False) #features.select_dtypes(include=np.number) - plt.savefig(f'features_overall_nans_{phase_name}.png', bbox_inches='tight') +def graph_bf_af(features, phase_name, plt_flag=False): + if plt_flag: + sns.set(rc={"figure.figsize":(16, 8)}) + sns.heatmap(features.isna(), cbar=False) #features.select_dtypes(include=np.number) + plt.savefig(f'features_overall_nans_{phase_name}.png', bbox_inches='tight') + + print(f"\n-------------{phase_name}-------------") + print("Rows number:", features.shape[0]) + print("Columns number:", len(features.columns)) + print("---------------------------------------------\n")