Get, join and start processing required ERS stress event data.

imputation_and_cleaning
Primoz 2022-11-09 15:11:51 +00:00
parent f3c6a66da9
commit 9199b53ded
1 changed files with 47 additions and 9 deletions

View File

@ -22,6 +22,7 @@ def format_timestamp(x):
return tstring return tstring
def extract_ers_from_file(esm_df, device_id): def extract_ers_from_file(esm_df, device_id):
pd.set_option("display.max_rows", 20) pd.set_option("display.max_rows", 20)
@ -31,7 +32,7 @@ def extract_ers_from_file(esm_df, device_id):
config = yaml.load(stream, Loader=yaml.FullLoader) config = yaml.load(stream, Loader=yaml.FullLoader)
pd.DataFrame().to_csv(snakemake.output[1]) # Create an empty stress event file either way pd.DataFrame().to_csv(snakemake.output[1]) # Create an empty stress event file either way TODO
esm_preprocessed = clean_up_esm(preprocess_esm(esm_df)) esm_preprocessed = clean_up_esm(preprocess_esm(esm_df))
@ -45,7 +46,7 @@ def extract_ers_from_file(esm_df, device_id):
targets_method = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["TARGETS_METHOD"] targets_method = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["TARGETS_METHOD"]
if targets_method in ["30_before", "90_before"]: # takes 30-minute peroid before the questionnaire + the duration of the questionnaire if targets_method in ["30_before", "90_before"]: # takes 30-minute peroid before the questionnaire + the duration of the questionnaire
# 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() # is rounded up in seconds extracted_ers = esm_df.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index() # questionnaire length
extracted_ers["label"] = f"straw_event_{targets_method}_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3) extracted_ers["label"] = f"straw_event_{targets_method}_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3)
extracted_ers[['event_timestamp', 'device_id']] = esm_df.groupby(["device_id", "esm_session"])['timestamp'].min().reset_index()[['timestamp', 'device_id']] 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 = extracted_ers[extracted_ers["timestamp"] <= 15 * 60].reset_index(drop=True) # ensure that the longest duration of the questionnaire anwsering is 15 min
@ -72,19 +73,56 @@ def extract_ers_from_file(esm_df, device_id):
extracted_ers["shift"] = extracted_ers["diffs"].apply(lambda x: format_timestamp(x)) extracted_ers["shift"] = extracted_ers["diffs"].apply(lambda x: format_timestamp(x))
elif targets_method == "stress_event": elif targets_method == "stress_event":
pd.DataFrame().to_csv(snakemake.output[1])
# TODO: generiranje ERS datoteke za stress_events # TODO: generiranje ERS datoteke za stress_events
# 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 end timestamp
session_end_timestamp = esm_df.groupby(['device_id', 'esm_session'])['timestamp'].max().to_frame().rename(columns={'timestamp': 'session_end_timestamp'}) # questionnaire end timestamp
se_time = esm_df[esm_df.questionnaire_id == 90.].set_index(['device_id', 'esm_session'])['esm_user_answer'].to_frame().rename(columns={'esm_user_answer': 'se_time'})
se_duration = esm_df[esm_df.questionnaire_id == 91.].set_index(['device_id', 'esm_session'])['esm_user_answer'].to_frame().rename(columns={'esm_user_answer': 'se_duration'})
se_intensity = esm_df[esm_df.questionnaire_id == 87.].set_index(['device_id', 'esm_session'])['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'se_intensity'})
extracted_ers = extracted_ers.join(session_end_timestamp, on=['device_id', 'esm_session'], how='inner') \
.join(se_time, on=['device_id', 'esm_session'], how='inner') \
.join(se_duration, on=['device_id', 'esm_session'], how='inner') \
.join(se_intensity, on=['device_id', 'esm_session'], how='inner')
# Filter sessions that are not useful
extracted_ers = extracted_ers[(extracted_ers.se_time != "0 - Ne spomnim se")]
# Transform data into its final form, ready for the extraction
extracted_ers.reset_index(inplace=True)
extracted_ers["label"] = f"straw_event_{targets_method}_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3)
# Convert to unix timestamp
time_before_event = 90 * 60 # in seconds (10 minutes)
extracted_ers['event_timestamp'] = pd.to_datetime(extracted_ers['se_time']).apply(lambda x: x.timestamp() * 1000).astype('int64')
extracted_ers['shift'] = time_before_event
extracted_ers['shift_direction'] = -1
print(extracted_ers[['session_end_timestamp', 'event_timestamp']])
extracted_ers['se_duration'] = \
np.where(extracted_ers['se_duration'] == "1 - Še vedno traja",
extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'],
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)
sys.exit()
# VV Testiranje različnih povpraševanj za VV # VV Testiranje različnih povpraševanj za VV
# print(esm_df[esm_df.questionnaire_id == 87]) filter_esm = esm_df[(esm_df.esm_type == 7) & ((esm_df.questionnaire_id == 90.) | (esm_df.questionnaire_id == 91.))][['questionnaire_id', 'esm_user_answer', 'esm_session']]
# filter_esm = esm_df[(esm_df.esm_type == 7) & ((esm_df.questionnaire_id == 90.) | (esm_df.questionnaire_id == 91.))][['questionnaire_id', 'esm_user_answer', 'esm_session']] print(filter_esm[filter_esm.esm_user_answer == "1 - Še vedno traja"].shape)
# print(filter_esm[filter_esm.esm_user_answer == "1 - Še vedno traja"].shape) print(filter_esm.shape)
# print(filter_esm.shape)
# TODO: generiranje stress_events_targets datoteke (dodaj tudi stolpec s pid) + dodati moraš merge metodo, ki bo združila te datoteke # TODO: generiranje stress_events_targets datoteke (dodaj tudi stolpec s pid) + dodati moraš merge metodo, ki bo združila te datoteke
# TODO: na koncu se mora v čistilni skripti ustrezno odstraniti vse targete in prilepiti nove targete zraven ustreznih segmentov (zna se zgoditi, da bodo overlap) # TODO: na koncu se mora v čistilni skripti ustrezno odstraniti vse targete in prilepiti nove targete zraven ustreznih segmentov (zna se zgoditi, da bodo overlap)
pd.DataFrame().to_csv(snakemake.output[1])
sys.exit()
else: else:
raise Exception("Please select correct target method for the event-related segments.") raise Exception("Please select correct target method for the event-related segments.")
extracted_ers = pd.DataFrame(columns=["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"]) extracted_ers = pd.DataFrame(columns=["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"])