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

Fix the generating procedure of ERS file for participants with multiple devices.

imputation_and_cleaning
Primoz 2022-10-28 09:00:13 +00:00
parent cd137af15a
commit 30b38bfc02
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/features/phone_esm/straw/process_user_event_related_segments.py
View File

@ -33,6 +33,7 @@ def extract_ers_from_file(esm_df, device_id):
# esm_df = clean_up_esm(preprocess_esm(esm_df)) # esm_df = clean_up_esm(preprocess_esm(esm_df))
esm_preprocessed = clean_up_esm(preprocess_esm(esm_df)) esm_preprocessed = clean_up_esm(preprocess_esm(esm_df))
# Take only during work sessions # Take only during work sessions
# during_work = esm_df[esm_df["esm_trigger"].str.contains("during_work", na=False)] # during_work = esm_df[esm_df["esm_trigger"].str.contains("during_work", na=False)]
# esm_trigger_group = esm_df.groupby("esm_session").agg(pd.Series.mode)['esm_trigger'] # Get most frequent esm_trigger within particular session # esm_trigger_group = esm_df.groupby("esm_session").agg(pd.Series.mode)['esm_trigger'] # Get most frequent esm_trigger within particular session
@ -45,18 +46,16 @@ def extract_ers_from_file(esm_df, device_id):
esm_df = esm_preprocessed[esm_preprocessed["esm_session"].isin(esm_filtered_sessions)] esm_df = esm_preprocessed[esm_preprocessed["esm_session"].isin(esm_filtered_sessions)]
# Extract time-relevant information # Extract time-relevant information
extracted_ers = esm_df.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index() # in rounded up seconds
extracted_ers = extracted_ers[extracted_ers["timestamp"] <= 15 * 60].reset_index(drop=True) # ensure that the longest duration of the questionnaire anwsering is 15 min
time_before_questionnaire = 30 * 60 # in seconds (30 minutes) time_before_questionnaire = 30 * 60 # in seconds (30 minutes)
extracted_ers = esm_df.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index() # in rounded up in seconds
extracted_ers[['event_timestamp', 'device_id']] = esm_df.groupby(["device_id", "esm_session"])['timestamp'].min().reset_index()[['timestamp', 'device_id']]
extracted_ers = extracted_ers[extracted_ers["timestamp"] <= 15 * 60].reset_index(drop=True) # ensure that the longest duration of the questionnaire anwsering is 15 min
extracted_ers["label"] = "straw_event_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3) extracted_ers["label"] = "straw_event_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3)
extracted_ers["event_timestamp"] = esm_df.groupby("esm_session")['timestamp'].min().reset_index()['timestamp']
extracted_ers["length"] = (extracted_ers["timestamp"] + time_before_questionnaire).apply(lambda x: format_timestamp(x)) extracted_ers["length"] = (extracted_ers["timestamp"] + time_before_questionnaire).apply(lambda x: format_timestamp(x))
extracted_ers["shift"] = time_before_questionnaire extracted_ers["shift"] = time_before_questionnaire
extracted_ers["shift"] = extracted_ers["shift"].apply(lambda x: format_timestamp(x)) extracted_ers["shift"] = extracted_ers["shift"].apply(lambda x: format_timestamp(x))
extracted_ers["shift_direction"] = -1 extracted_ers["shift_direction"] = -1
extracted_ers["device_id"] = device_id
return extracted_ers[["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"]] return extracted_ers[["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"]]