E4 data yield corrections. Changes in overal cs - standardization.

config.yaml

@@ -680,7 +680,7 @@ ALL_CLEANING_INDIVIDUAL:
 ALL_CLEANING_OVERALL:
   PROVIDERS:
     RAPIDS:
-      COMPUTE: True
+      COMPUTE: False
       IMPUTE_SELECTED_EVENT_FEATURES:
         COMPUTE: False
         MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33

src/features/all_cleaning_overall/straw/main.py

@@ -1,10 +1,9 @@
 import pandas as pd
 import numpy as np
-import math, sys, random
+import math, sys, random, warnings, yaml
-import yaml
 
 from sklearn.impute import KNNImputer
-from sklearn.preprocessing import StandardScaler
+from sklearn.preprocessing import StandardScaler, minmax_scale 
 import matplotlib.pyplot as plt
 import seaborn as sns
 
@@ -31,7 +30,7 @@ def straw_cleaning(sensor_data_files, provider):
 
     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
+    # (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()
     phone_data_yield_column = "phone_data_yield_rapids_ratiovalidyielded" + phone_data_yield_unit
 
@@ -43,42 +42,26 @@ def straw_cleaning(sensor_data_files, provider):
     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())
+        # 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(features["empatica_data_yield"].sort_values())
+        # 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")
 
-    # (2.2) DO THE ROWS CONSIST OF ENOUGH NON-NAN VALUES?
+    # (3) CONTEXTUAL IMPUTATION
-    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:
-            features[esm] = esm_cols[esm]
-
-    # (4) CONTEXTUAL IMPUTATION
 
     # Impute selected phone features with a high number
     impute_w_hn = [col for col in features.columns if \
@@ -91,7 +74,7 @@ def straw_cleaning(sensor_data_files, provider):
         "timelastmessages" in col]
     features[impute_w_hn] = impute(features[impute_w_hn], method="high_number")
 
-    graph_bf_af(features, "6high_number_imp")
+    graph_bf_af(features, "4high_number_imp")
 
     # Impute special case (mostcommonactivity) and (homelabel)
     impute_w_sn = [col for col in features.columns if "mostcommonactivity" in col]
@@ -112,7 +95,7 @@ def straw_cleaning(sensor_data_files, provider):
         col.startswith('phone_wifi_visible')]
     features[impute_zero] = impute(features[impute_zero], method="zero")
 
-    graph_bf_af(features, "7zero_imp")
+    graph_bf_af(features, "5zero_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]
@@ -128,29 +111,52 @@ 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]
     
+    # (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
 
-    # (5) STANDARDIZATION 
+    features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]]
-    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, "8standardization")
+    graph_bf_af(features, "6too_much_nans_cols")
 
-    # (6) IMPUTATION: IMPUTE DATA WITH KNN METHOD
+    # (5) REMOVE COLS WHERE VARIANCE IS 0
-    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, "9knn_after")
-
-    # (7) REMOVE COLS WHERE VARIANCE IS 0
-    esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')]
 
     if provider["COLS_VAR_THRESHOLD"]:
         features.drop(features.std()[features.std() == 0].index.values, axis=1, inplace=True)
 
-    graph_bf_af(features, "10variance_drop")
+    graph_bf_af(features, "7variance_drop")
+
+    # Preserve esm cols if deleted (has to come after drop cols operations)
+    for esm in esm_cols:
+        if esm not in features:
+            features[esm] = esm_cols[esm]
+    
+    # (6) 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, "8too_much_nans_rows")
+
+    # (7) STANDARDIZATION 
+    # I expect to see RuntimeWarnings in this block
+    if provider["STANDARDIZATION"]:
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", category=RuntimeWarning)
+            features.loc[:, ~features.columns.isin(excluded_columns + ["pid"])] = \
+                features.loc[:, ~features.columns.isin(excluded_columns)].groupby('pid').transform(lambda x: minmax_scale(x.astype(float)))
+
+    graph_bf_af(features, "9standardization")
+
+    # (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")
+
+
+    # (9) DROP HIGHLY CORRELATED FEATURES
+    esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')]
 
-    # (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
         
@@ -163,6 +169,11 @@ def straw_cleaning(sensor_data_files, provider):
         upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(np.bool))
         to_drop = [column for column in upper.columns if any(upper[column] > drop_corr_features["CORR_THRESHOLD"])]
 
+        sns.heatmap(corr_matrix, cmap="YlGnBu", annot=True)
+        plt.savefig(f'correlation_matrix.png', bbox_inches='tight')
+        plt.close()
+        # TODO: katere značilke se izbrišejo - ali korelirajo kakšni pari E4:PHONE?
+
         features.drop(to_drop, axis=1, inplace=True)
 
     # Preserve esm cols if deleted (has to come after drop cols operations)
@@ -172,10 +183,11 @@ def straw_cleaning(sensor_data_files, provider):
 
     graph_bf_af(features, "11correlation_drop")
 
-    # (9) VERIFY IF THERE ARE ANY NANS LEFT IN THE DATAFRAME
+    # (10) VERIFY IF THERE ARE ANY NANS LEFT IN THE DATAFRAME
     if features.isna().any().any():
-        raise ValueError
+        raise ValueError("There are still some NaNs present in the dataframe. Please check for implementation errors.")
 
+    sys.exit()
     return features
 
 def impute(df, method='zero'):
@@ -192,7 +204,7 @@ def impute(df, method='zero'):
         'knn': k_nearest(df) 
     }[method]
 
-def graph_bf_af(features, phase_name, plt_flag=False):
+def graph_bf_af(features, phase_name, plt_flag=True):
     if plt_flag:
         sns.set(rc={"figure.figsize":(16, 8)})
         sns.heatmap(features.isna(), cbar=False) #features.select_dtypes(include=np.number)
@@ -201,5 +213,5 @@ def graph_bf_af(features, phase_name, plt_flag=False):
     print(f"\n-------------{phase_name}-------------")
     print("Rows number:", features.shape[0])
     print("Columns number:", len(features.columns))
+    print("NaN values:", features.isna().sum().sum())
     print("---------------------------------------------\n")
-    

src/features/empatica_data_yield.py

@@ -10,12 +10,15 @@ def calculate_empatica_data_yield(features):
     datetime_end = datetime.strptime(features.loc[0, 'local_segment_end_datetime'], '%Y-%m-%d %H:%M:%S')
     tseg_duration = (datetime_end - datetime_start).total_seconds()
 
-    features["acc_data_yield"] = (features['empatica_accelerometer_cr_SO_windowsCount'] * 15) / tseg_duration
+    features["acc_data_yield"] = (features['empatica_accelerometer_cr_SO_windowsCount'] * 15) / tseg_duration \
-    features["temp_data_yield"] = (features['empatica_temperature_cr_SO_windowsCount'] * 300) / tseg_duration
+        if 'empatica_accelerometer_cr_SO_windowsCount' in features else 0
-    features["eda_data_yield"] = (features['empatica_electrodermal_activity_cr_SO_windowsCount'] * 60) / tseg_duration
+    features["temp_data_yield"] = (features['empatica_temperature_cr_SO_windowsCount'] * 300) / tseg_duration \
-    features["ibi_data_yield"] = (features['empatica_inter_beat_interval_cr_SO_windowsCount'] * 300) / tseg_duration
+        if 'empatica_temperature_cr_SO_windowsCount' in features else 0
+    features["eda_data_yield"] = (features['empatica_electrodermal_activity_cr_SO_windowsCount'] * 60) / tseg_duration \
+        if 'empatica_electrodermal_activity_cr_SO_windowsCount' in features else 0
+    features["ibi_data_yield"] = (features['empatica_inter_beat_interval_cr_SO_windowsCount'] * 300) / tseg_duration \
+        if 'empatica_inter_beat_interval_cr_SO_windowsCount' in features else 0
 
-    # TODO: boljša nastavitev delovnih ur sedaj je od 4:00 do 4:00... to povzroči veliko manjkajočih podatkov in posledično nizek (telefonski in E4) data_yield ... 
     empatica_data_yield_cols = ['acc_data_yield', 'temp_data_yield', 'eda_data_yield', 'ibi_data_yield']
     features["empatica_data_yield"] = features[empatica_data_yield_cols].mean(axis=1).fillna(0)
     features.drop(empatica_data_yield_cols, axis=1, inplace=True) # In case of if the advanced operations will later not be needed (e.g., weighted average)