2022-06-10 14:34:48 +02:00
|
|
|
import pandas as pd
|
|
|
|
import seaborn as sns
|
|
|
|
import matplotlib.pyplot as plt
|
2022-06-14 17:09:14 +02:00
|
|
|
from itertools import compress
|
2022-06-10 14:34:48 +02:00
|
|
|
|
|
|
|
# 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"
|
2022-06-14 17:09:14 +02:00
|
|
|
path = "/rapids/data/interim/p01/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_cr_windows.csv"
|
2022-06-10 14:34:48 +02:00
|
|
|
# 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_temperature_features/empatica_temperature_python_cr_windows.csv"
|
|
|
|
|
|
|
|
df = pd.read_csv(path)
|
2022-06-14 17:09:14 +02:00
|
|
|
df_num_peaks_zero = df[df["empatica_electrodermal_activity_cr_numPeaks"] == 0]
|
|
|
|
columns_num_peaks_zero = df_num_peaks_zero.columns[df_num_peaks_zero.isna().any()].tolist()
|
|
|
|
|
|
|
|
df_num_peaks_non_zero_t = df[df["empatica_electrodermal_activity_cr_numPeaks"] != 0]
|
|
|
|
df_num_peaks_non_zero = df_num_peaks_non_zero_t[columns_num_peaks_zero]
|
2022-06-10 14:34:48 +02:00
|
|
|
|
|
|
|
|
|
|
|
# row_has_NaN = is_NaN. any(axis=1)
|
|
|
|
# rows_with_NaN = df[row_has_NaN]
|
|
|
|
# print(rows_with_NaN.size)
|
2022-06-14 17:09:14 +02:00
|
|
|
pd.set_option('display.max_columns', None)
|
|
|
|
# # pd.set_option('display.max_rows', None)
|
|
|
|
# print(df_num_peaks_non_zero)
|
|
|
|
df_q = pd.DataFrame()
|
|
|
|
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))
|
|
|
|
|
|
|
|
sns.heatmap(df_q)
|
|
|
|
plt.savefig('eda_windows_p01_window_non_zero.png', bbox_inches='tight')
|
|
|
|
plt.close()
|
|
|
|
|
|
|
|
# Filter columns that do not contain 0
|
|
|
|
non_zero_cols = list(compress(columns_num_peaks_zero, df_num_peaks_non_zero.all().tolist()))
|
|
|
|
zero_cols = list(set(columns_num_peaks_zero) - set(non_zero_cols))
|
|
|
|
|
|
|
|
print(non_zero_cols, "\n")
|
|
|
|
print(zero_cols)
|
|
|
|
|
|
|
|
# maxPeakAmplitudeChangeBefore
|
|
|
|
|
|
|
|
mpacb = df_num_peaks_non_zero_t\
|
|
|
|
[(df_num_peaks_non_zero_t['empatica_electrodermal_activity_cr_avgPeakAmplitudeChangeBefore'] != 0) \
|
|
|
|
& (df_num_peaks_non_zero_t['empatica_electrodermal_activity_cr_numPeaks'] != 0)]
|
|
|
|
print(mpacb['empatica_electrodermal_activity_cr_numPeaks'])
|
|
|
|
sns.heatmap(mpacb['empatica_electrodermal_activity_cr_numPeaks'])
|
|
|
|
plt.savefig('maxPeakAmplitudeChangeBefore.png', bbox_inches='tight')
|
2022-06-10 14:34:48 +02:00
|
|
|
|