junos
/
rapids
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Include feature calculations for different scales.

labels
junos 2022-04-05 19:05:34 +02:00
parent cbc8ae4e03
commit 2e545e81f0
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/features/phone_esm/straw/main.py
View File

@ -1,11 +1,15 @@
import pandas as pd import pandas as pd
from esm_preprocess import QUESTIONNAIRE_IDS
def straw_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs): def straw_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
esm_data = pd.read_csv(sensor_data_files["sensor_data"]) esm_data = pd.read_csv(sensor_data_files["sensor_data"])
requested_features = provider["FEATURES"] requested_features = provider["FEATURES"]
# name of the features this function can compute # name of the features this function can compute
requested_scales = provider["SCALES"]
base_features_names = ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support"] base_features_names = ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support"]
#TODO Check valid questionnaire and feature names.
# the subset of requested features this function can compute # the subset of requested features this function can compute
features_to_compute = list(set(requested_features) & set(base_features_names)) features_to_compute = list(set(requested_features) & set(base_features_names))
esm_features = pd.DataFrame(columns=["local_segment"] + features_to_compute) esm_features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
@ -15,8 +19,11 @@ def straw_features(sensor_data_files, time_segment, provider, filter_data_by_seg
if not esm_data.empty: if not esm_data.empty:
esm_features = pd.DataFrame() esm_features = pd.DataFrame()
esm_features["mean"] = esm_data.groupby(["local_segment"])["esm_user_score"].mean() for scale in requested_scales:
#TODO Create the column esm_user_score in esm_clean. Currently, this is only done when reversing. questionnaire_id = QUESTIONNAIRE_IDS[scale]
mask = esm_data["questionnaire_id"] == questionnaire_id
esm_features[scale + "_mean"] = esm_data.loc[mask].groupby(["local_segment"])["esm_user_score"].mean()
#TODO Create the column esm_user_score in esm_clean. Currently, this is only done when reversing.
esm_features = esm_features.reset_index() esm_features = esm_features.reset_index()
return esm_features return esm_features