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

Update ERS stress_event logic.

sociality-task
Primoz 2022-12-19 15:40:40 +00:00
parent 7f5a4e6744
commit 41a17d35f1
2 changed files with 16 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
config.yaml
View File

@ -27,8 +27,8 @@ TIME_SEGMENTS: &time_segments
TAILORED_EVENTS: # Only relevant if TYPE=EVENT TAILORED_EVENTS: # Only relevant if TYPE=EVENT
COMPUTE: True COMPUTE: True
SEGMENTING_METHOD: "stress_event" # 30_before, 90_before, stress_event SEGMENTING_METHOD: "stress_event" # 30_before, 90_before, stress_event
INTERVAL_OF_INTEREST: 5 # duration of event of interest [minutes] INTERVAL_OF_INTEREST: 10 # duration of event of interest [minutes]
INTERVAL_OF_INTEREST_PADDING: 7.5 # interval of interest padding (before and after IOI) [minutes] IOI_ERROR_TOLERANCE: 5 # interval of interest erorr tolerance (before and after IOI) [minutes]
# See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study # See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study
TIMEZONE: TIMEZONE:

23
src/features/phone_esm/straw/process_user_event_related_segments.py
View File

@ -124,7 +124,7 @@ def extract_ers(esm_df):
""" """
ioi = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["INTERVAL_OF_INTEREST"] * 60 # interval of interest in seconds ioi = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["INTERVAL_OF_INTEREST"] * 60 # interval of interest in seconds
ioi_padding = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["INTERVAL_OF_INTEREST_PADDING"] * 60 # interval of interest padding in seconds ioi_error_tolerance = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["IOI_ERROR_TOLERANCE"] * 60 # interval of interest error tolerance in seconds
# Get and join required data # Get and join required data
extracted_ers = esm_df.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index().rename(columns={'timestamp': 'session_length'}) # questionnaire length extracted_ers = esm_df.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index().rename(columns={'timestamp': 'session_length'}) # questionnaire length
@ -154,12 +154,13 @@ def extract_ers(esm_df):
# Filter-out the sessions that are not useful. Because of the ambiguity this excludes: # Filter-out the sessions that are not useful. Because of the ambiguity this excludes:
# (1) straw event times that are marked as "0 - I don't remember" # (1) straw event times that are marked as "0 - I don't remember"
# (2) straw event durations that are marked as "0 - I don't remember" extracted_ers = extracted_ers[~extracted_ers.se_time.astype(str).str.startswith("0 - ")]
extracted_ers = extracted_ers[(~extracted_ers.se_time.astype(str).str.startswith("0 - ")) & (~extracted_ers.se_duration.astype(str).str.startswith("0 - "))]
extracted_ers.reset_index(drop=True, inplace=True) extracted_ers.reset_index(drop=True, inplace=True)
extracted_ers.loc[extracted_ers.se_duration.astype(str).str.startswith("0 - "), 'se_duration'] = 0
# Add default duration in case if participant answered that no stressful event occured # Add default duration in case if participant answered that no stressful event occured
extracted_ers["se_duration"] = extracted_ers["se_duration"].fillna(int((ioi + 2*ioi_padding) * 1000)) extracted_ers["se_duration"] = extracted_ers["se_duration"].fillna(int((ioi + 2*ioi_error_tolerance) * 1000))
# Prepare data to fit the data structure in the CSV file ... # Prepare data to fit the data structure in the CSV file ...
# Add the event time as the end of the questionnaire if no stress event occured # Add the event time as the end of the questionnaire if no stress event occured
@ -183,20 +184,22 @@ def extract_ers(esm_df):
extracted_ers['se_duration'] = \ extracted_ers['se_duration'] = \
extracted_ers['se_duration'].apply(lambda x: math.ceil(x / 1000) if isinstance(x, int) else (pd.to_datetime(x).hour * 60 + pd.to_datetime(x).minute) * 60) extracted_ers['se_duration'].apply(lambda x: math.ceil(x / 1000) if isinstance(x, int) else (pd.to_datetime(x).hour * 60 + pd.to_datetime(x).minute) * 60)
# Check whether min se_duration is at least the same duration as the ioi. Filter-out the rest. # Check explicitley whether min duration is at least 0. This will eliminate rows that would be investigated after the end of the questionnaire.
extracted_ers = extracted_ers[extracted_ers["se_duration"] >= ioi].reset_index(drop=True) extracted_ers = extracted_ers[extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'] >= 0]
# Double check whether min se_duration is at least 0. Filter-out the rest. Negative values are considered invalid.
extracted_ers = extracted_ers[extracted_ers["se_duration"] >= 0].reset_index(drop=True)
""">>>>> end section <<<<<""" """>>>>> end section <<<<<"""
# Simply override all remaining durations to be of an equal amount # Simply override all durations to be of an equal amount
extracted_ers['se_duration'] = ioi + 2*ioi_padding extracted_ers['se_duration'] = ioi + 2*ioi_error_tolerance
# # If target is 0 then shift by the total stress event duration, otherwise shift it by ioi_tolerance
extracted_ers['shift'] = \ extracted_ers['shift'] = \
np.where( np.where(
extracted_ers['appraisal_stressfulness_event'] == 0, extracted_ers['appraisal_stressfulness_event'] == 0,
extracted_ers['se_duration'], extracted_ers['se_duration'],
ioi_padding ioi_error_tolerance
) )
extracted_ers['shift'] = extracted_ers['shift'].apply(lambda x: format_timestamp(int(x))) extracted_ers['shift'] = extracted_ers['shift'].apply(lambda x: format_timestamp(int(x)))