Testing different EDA findPeaks parameters.

sociality-task
Primoz 2022-06-30 15:15:37 +00:00
parent c851ab0763
commit 505c3a86b9
5 changed files with 23 additions and 14 deletions

3
.gitignore vendored
View File

@ -118,3 +118,6 @@ site/
# Docker container and other files # Docker container and other files
.devcontainer .devcontainer
# Calculating features module
calculatingfeatures/

View File

@ -3,7 +3,7 @@
######################################################################################################################## ########################################################################################################################
# See https://www.rapids.science/latest/setup/configuration/#participant-files # See https://www.rapids.science/latest/setup/configuration/#participant-files
PIDS: [p01] #p01, p02, p03] PIDS: [p02] #p01, p02, p03]
# See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files # See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
CREATE_PARTICIPANT_FILES: CREATE_PARTICIPANT_FILES:
@ -536,7 +536,7 @@ EMPATICA_ELECTRODERMAL_ACTIVITY:
'sigTonicDifference', 'freqFeats','maxPeakAmplitudeChangeBefore', 'maxPeakAmplitudeChangeAfter', 'avgPeakAmplitudeChangeBefore', 'sigTonicDifference', 'freqFeats','maxPeakAmplitudeChangeBefore', 'maxPeakAmplitudeChangeAfter', 'avgPeakAmplitudeChangeBefore',
'avgPeakAmplitudeChangeAfter', 'avgPeakChangeRatio', 'maxPeakIncreaseTime', 'maxPeakDecreaseTime', 'maxPeakDuration', 'maxPeakChangeRatio', 'avgPeakAmplitudeChangeAfter', 'avgPeakChangeRatio', 'maxPeakIncreaseTime', 'maxPeakDecreaseTime', 'maxPeakDuration', 'maxPeakChangeRatio',
'avgPeakIncreaseTime', 'avgPeakDecreaseTime', 'avgPeakDuration', 'signalOverallChange', 'changeDuration', 'changeRate', 'significantIncrease', 'avgPeakIncreaseTime', 'avgPeakDecreaseTime', 'avgPeakDuration', 'signalOverallChange', 'changeDuration', 'changeRate', 'significantIncrease',
'significantDecrease', maxPeakResponseSlopeBefore, maxPeakResponseSlopeAfter] 'significantDecrease']
WINDOWS: WINDOWS:
COMPUTE: True COMPUTE: True
WINDOW_LENGTH: 60 # specify window length in seconds WINDOW_LENGTH: 60 # specify window length in seconds

View File

@ -30,11 +30,13 @@ def extract_eda_features_from_intraday_data(eda_intraday_data, features, window_
if window_length is None: if window_length is None:
eda_intraday_features = \ eda_intraday_features = \
eda_intraday_data.groupby('local_segment').apply(\ eda_intraday_data.groupby('local_segment').apply(\
lambda x: extractGsrFeatures2D(convert_to2d(x['electrodermal_activity'], x.shape[0]), sampleRate=sample_rate, featureNames=features)) lambda x: extractGsrFeatures2D(convert_to2d(x['electrodermal_activity'], x.shape[0]), sampleRate=sample_rate, featureNames=features,
threshold=.01, offset=1, riseTime=5, decayTime=15))
else: else:
eda_intraday_features = \ eda_intraday_features = \
eda_intraday_data.groupby('local_segment').apply(\ eda_intraday_data.groupby('local_segment').apply(\
lambda x: extractGsrFeatures2D(convert_to2d(x['electrodermal_activity'], window_length*sample_rate), sampleRate=sample_rate, featureNames=features)) lambda x: extractGsrFeatures2D(convert_to2d(x['electrodermal_activity'], window_length*sample_rate), sampleRate=sample_rate, featureNames=features,
threshold=.01, offset=1, riseTime=5, decayTime=15))
eda_intraday_features.reset_index(inplace=True) eda_intraday_features.reset_index(inplace=True)

View File

@ -2,10 +2,11 @@ import pandas as pd
import seaborn as sns import seaborn as sns
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
participant = "p02"
# path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv" # all features all participants # path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv" # all features all participants
# path = "/rapids/data/interim/p03/empatica_accelerometer_features/empatica_accelerometer_python_cr_windows.csv" # path = "/rapids/data/interim/p03/empatica_accelerometer_features/empatica_accelerometer_python_cr_windows.csv"
path = "/rapids/data/interim/p01/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_cr_windows.csv" path = f"/rapids/data/interim/{participant}/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_cr_windows.csv"
# path = "/rapids/data/interim/p02/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_cr_windows.csv" # path = "/rapids/data/interim/p02/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_cr_windows.csv"
# path = "/rapids/data/interim/p02/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_cr_windows.csv" # path = "/rapids/data/interim/p02/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_cr_windows.csv"
# path = "/rapids/data/interim/p02/empatica_temperature_features/empatica_temperature_python_cr_windows.csv" # path = "/rapids/data/interim/p02/empatica_temperature_features/empatica_temperature_python_cr_windows.csv"
@ -15,9 +16,13 @@ print(df)
is_NaN = df.isnull() is_NaN = df.isnull()
row_has_NaN = is_NaN.any(axis=1) row_has_NaN = is_NaN.any(axis=1)
rows_with_NaN = df[row_has_NaN] rows_with_NaN = df[row_has_NaN]
print(rows_with_NaN.size)
print("All rows:", len(df.index))
print("\nCount NaN vals:", rows_with_NaN.size)
print("\nDf mean:")
print(df.mean())
sns.heatmap(df.isna(), cbar=False) sns.heatmap(df.isna(), cbar=False)
plt.savefig('eda_windows_p02_window_60_thresh_default.png', bbox_inches='tight') plt.savefig(f'eda_{participant}_windows_NaN.png', bbox_inches='tight')

View File

@ -3,9 +3,11 @@ import seaborn as sns
import matplotlib.pyplot as plt import matplotlib.pyplot as plt
from itertools import compress from itertools import compress
participant = "p02"
# path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv" # all features all participants # path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv" # all features all participants
# path = "/rapids/data/interim/p03/empatica_accelerometer_features/empatica_accelerometer_python_cr_windows.csv" # path = "/rapids/data/interim/p03/empatica_accelerometer_features/empatica_accelerometer_python_cr_windows.csv"
path = "/rapids/data/interim/p01/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_cr_windows.csv" path = f"/rapids/data/interim/{participant}/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_cr_windows.csv"
# path = "/rapids/data/interim/p02/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_cr_windows.csv" # path = "/rapids/data/interim/p02/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_cr_windows.csv"
# path = "/rapids/data/interim/p02/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_cr_windows.csv" # path = "/rapids/data/interim/p02/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_cr_windows.csv"
# path = "/rapids/data/interim/p02/empatica_temperature_features/empatica_temperature_python_cr_windows.csv" # path = "/rapids/data/interim/p02/empatica_temperature_features/empatica_temperature_python_cr_windows.csv"
@ -17,9 +19,6 @@ columns_num_peaks_zero = df_num_peaks_zero.columns[df_num_peaks_zero.isna().any(
df_num_peaks_non_zero = df[df["empatica_electrodermal_activity_cr_numPeaks"] != 0] df_num_peaks_non_zero = df[df["empatica_electrodermal_activity_cr_numPeaks"] != 0]
df_num_peaks_non_zero = df_num_peaks_non_zero[columns_num_peaks_zero] df_num_peaks_non_zero = df_num_peaks_non_zero[columns_num_peaks_zero]
print(df_num_peaks_non_zero[df_num_peaks_non_zero["empatica_electrodermal_activity_cr_maxPeakAmplitudeChangeBefore"] != 0])
pd.set_option('display.max_columns', None) pd.set_option('display.max_columns', None)
df_q = pd.DataFrame() df_q = pd.DataFrame()
@ -27,7 +26,7 @@ for col in df_num_peaks_non_zero:
df_q[col] = pd.to_numeric(pd.cut(df_num_peaks_non_zero[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) df_q[col] = pd.to_numeric(pd.cut(df_num_peaks_non_zero[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False))
sns.heatmap(df_q) sns.heatmap(df_q)
plt.savefig('eda_windows_p01_window_values_non_zero_peak_distribution_0thresh.png', bbox_inches='tight') plt.savefig(f'eda_{participant}_window_non_zero_peak_other_vals.png', bbox_inches='tight')
plt.close() plt.close()
# Filter columns that do not contain 0 # Filter columns that do not contain 0