Testing and modifying the code with different E4 data.

config.yaml

@@ -3,7 +3,7 @@
 ########################################################################################################################
 
 # See https://www.rapids.science/latest/setup/configuration/#participant-files
-PIDS: [p01]
+PIDS: [p02, p01]
 
 # See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
 CREATE_PARTICIPANT_FILES:
@@ -477,11 +477,11 @@ EMPATICA_ACCELEROMETER:
   CONTAINER: ACC
   PROVIDERS:
     DBDP:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
       SRC_SCRIPT: src/features/empatica_accelerometer/dbdp/main.py
     CR:
-      COMPUTE: True
+      COMPUTE: False
       FEATURES: ["fqHighestPeakFreqs", "fqHighestPeaks", "fqEnergyFeat", "fqEntropyFeat", "fqHistogramBins","fqAbsMean", "fqSkewness", "fqKurtosis", "fqInterquart", # Freq features
                   "meanLow", "areaLow", "totalAbsoluteAreaBand", "totalMagnitudeBand", "entropyBand", "skewnessBand", "kurtosisBand", 
                   "postureDistanceLow", "absoluteMeanBand", "absoluteAreaBand", "quartilesBand", "interQuartileRangeBand", "varianceBand", 

src/features/cr_features_helper_methods.py

@@ -1,4 +1,7 @@
 import pandas as pd
+import math as m
+
+import sys
 
 def extract_second_order_features(intraday_features, so_features_names):
     if not intraday_features.empty:
@@ -21,10 +24,11 @@ def extract_second_order_features(intraday_features, so_features_names):
 
     return so_features
 
-def get_sample_rate(data):
+def get_sample_rate(data): # To-Do get the sample rate information from the file's metadata
     try:
         timestamps_diff = data['timestamp'].diff().dropna().mean()
+        print("Timestamp diff:", timestamps_diff)
     except:
         raise Exception("Error occured while trying to get the mean sample rate from the data.")
 
-    return int(1000/timestamps_diff)
+    return m.ceil(1000/timestamps_diff)

src/features/empatica_accelerometer/cr/main.py

@@ -3,7 +3,7 @@ from scipy.stats import entropy
 
 from cr_features.helper_functions import convert_to2d, accelerometer_features, frequency_features
 from cr_features.calculate_features_old import calculateFeatures
-from cr_features_helper_methods import get_sample_rate, extract_second_order_features
+from cr_features_helper_methods import extract_second_order_features
 
 import sys
 
@@ -11,7 +11,7 @@ def extract_acc_features_from_intraday_data(acc_intraday_data, features, window_
     acc_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
 
     if not acc_intraday_data.empty:   
-        sample_rate = get_sample_rate(acc_intraday_data)
+        sample_rate = 32
      
         acc_intraday_data = filter_data_by_segment(acc_intraday_data, time_segment)
 

src/features/empatica_blood_volume_pulse/cr/main.py

@@ -3,24 +3,16 @@ from scipy.stats import entropy
 
 from cr_features.helper_functions import convert_to2d, hrv_features, hrv_freq_features
 from cr_features.hrv import extract_hrv_features_2d_wrapper
-from cr_features_helper_methods import get_sample_rate, extract_second_order_features
+from cr_features_helper_methods import extract_second_order_features
 
 import sys
 
 
-def get_sample_rate(data):
-    try:
-        timestamps_diff = data['timestamp'].diff().dropna().mean()
-    except:
-        raise Exception("Error occured while trying to get the mean sample rate from the data.")
-
-    return int(1000/timestamps_diff)
-
 def extract_bvp_features_from_intraday_data(bvp_intraday_data, features, window_length, time_segment, filter_data_by_segment):
     bvp_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
 
     if not bvp_intraday_data.empty:
-        sample_rate = get_sample_rate(bvp_intraday_data)  
+        sample_rate = 64
      
         bvp_intraday_data = filter_data_by_segment(bvp_intraday_data, time_segment)
 

src/features/empatica_electrodermal_activity/cr/main.py

@@ -3,14 +3,14 @@ from scipy.stats import entropy
 
 from cr_features.helper_functions import convert_to2d, gsr_features
 from cr_features.calculate_features import calculate_features
-from cr_features_helper_methods import get_sample_rate, extract_second_order_features
+from cr_features_helper_methods import extract_second_order_features
 
 
 def extract_eda_features_from_intraday_data(eda_intraday_data, features, window_length, time_segment, filter_data_by_segment):
     eda_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
 
     if not eda_intraday_data.empty:   
-        sample_rate = get_sample_rate(eda_intraday_data)   
+        sample_rate = 4  
      
         eda_intraday_data = filter_data_by_segment(eda_intraday_data, time_segment)
 

src/features/empatica_inter_beat_interval/cr/main.py

@@ -3,7 +3,7 @@ import numpy as np
 
 from cr_features.helper_functions import convert_ibi_to2d_time, hrv_features, hrv_freq_features
 from cr_features.hrv import extract_hrv_features_2d_wrapper
-from cr_features_helper_methods import get_sample_rate, extract_second_order_features
+from cr_features_helper_methods import extract_second_order_features
 
 import math
 import sys
@@ -16,7 +16,6 @@ def extract_ibi_features_from_intraday_data(ibi_intraday_data, features, window_
     ibi_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
 
     if not ibi_intraday_data.empty:   
-        sample_rate = get_sample_rate(ibi_intraday_data)   
 
         ibi_intraday_data = filter_data_by_segment(ibi_intraday_data, time_segment)
 

src/features/empatica_temperature/cr/main.py

@@ -3,23 +3,15 @@ from scipy.stats import entropy
 
 from cr_features.helper_functions import convert_to2d, generic_features
 from cr_features.calculate_features_old import calculateFeatures
-from cr_features_helper_methods import get_sample_rate, extract_second_order_features
+from cr_features_helper_methods import extract_second_order_features
 
 import sys
 
-def get_sample_rate(data):
-    try:
-        timestamps_diff = data['timestamp'].diff().dropna().mean()
-    except:
-        raise Exception("Error occured while trying to get the mean sample rate from the data.")
-
-    return int(1000/timestamps_diff)
-
 def extract_temp_features_from_intraday_data(temperature_intraday_data, features, window_length, time_segment, filter_data_by_segment):
     temperature_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
 
     if not temperature_intraday_data.empty:
-        sample_rate = get_sample_rate(temperature_intraday_data)   
+        sample_rate = 4
 
         temperature_intraday_data = filter_data_by_segment(temperature_intraday_data, time_segment)
 

src/features/utils/utils.py

@@ -118,9 +118,9 @@ def fetch_provider_features(provider, provider_key, sensor_key, sensor_data_file
                 features[0].columns = ["{}{}".format("" if col.startswith("local_segment") else (sensor_key + "_"+ provider_key + "_"), col) for col in features[0].columns]
                 features[1].columns = ["{}{}".format("" if col.startswith("local_segment") else (sensor_key + "_"+ provider_key + "_"), col) for col in features[1].columns]
                 if not features[0].empty:
-                    sensor_fo_features = pd.concat([sensor_features, features[0]], axis=0, sort=False)                
+                    sensor_fo_features = pd.concat([sensor_fo_features, features[0]], axis=0, sort=False)                
                 if not features[1].empty:
-                    sensor_so_features = pd.concat([sensor_features, features[1]], axis=0, sort=False)
+                    sensor_so_features = pd.concat([sensor_so_features, features[1]], axis=0, sort=False)
             else: 
                 if not "local_segment" in features.columns:
                     raise ValueError("The dataframe returned by the " + sensor_key + " provider '" + provider_key + "' is missing the 'local_segment' column added by the 'filter_data_by_segment()' function. Check the provider script is using such function and is not removing 'local_segment' by accident (" + provider["SRC_SCRIPT"] + ")\n  The 'local_segment' column is used to index a provider's features (each row corresponds to a different time segment instance (e.g. 2020-01-01, 2020-01-02, 2020-01-03, etc.)")