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

Improve strings formatting in straw_events file.

notes
Primoz 2022-10-25 08:53:44 +00:00
parent 0d81ad5756
commit bfd637eb9c
1 changed files with 16 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
src/features/phone_esm/straw/process_user_event_related_segments.py
View File

@ -8,6 +8,19 @@ from esm_preprocess import preprocess_esm, clean_up_esm
input_data_files = dict(snakemake.input) input_data_files = dict(snakemake.input)
def format_timestamp(x):
tstring=""
space = False
if x//3600 > 0:
tstring += f"{x//3600}H"
space = True
if x % 3600 // 60 > 0:
tstring += f" {x % 3600 // 60}M" if "H" in tstring else f"{x % 3600 // 60}M"
if x % 60 > 0:
tstring += f" {x % 60}S" if "M" in tstring or "H" in tstring else f"{x % 60}S"
return tstring
def extract_ers_from_file(esm_df, device_id): # TODO: kako se bodo pridobili device_id? Bo torej potreben tudi p0??.yaml? def extract_ers_from_file(esm_df, device_id): # TODO: kako se bodo pridobili device_id? Bo torej potreben tudi p0??.yaml?
pd.set_option("display.max_rows", None) pd.set_option("display.max_rows", None)
@ -26,11 +39,11 @@ def extract_ers_from_file(esm_df, device_id): # TODO: kako se bodo pridobili dev
extracted_ers = esm_df.groupby("esm_session")['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index() # in rounded up seconds extracted_ers = esm_df.groupby("esm_session")['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index() # in rounded up seconds
time_before_questionnaire = 30 * 60 # in seconds (30 minutes) time_before_questionnaire = 30 * 60 # in seconds (30 minutes)
extracted_ers["label"] = "straw_event_" + snakemake.params["pid"] + "_" + extracted_ers["esm_session"].astype(str) extracted_ers["label"] = "straw_event_" + snakemake.params["pid"] + "_" + extracted_ers["esm_session"].astype(str).str.zfill(3)
extracted_ers["event_timestamp"] = esm_df.groupby("esm_session")['timestamp'].min().reset_index()['timestamp'] 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: f"{x//3600}H {x % 3600 // 60}M {x % 60}S" if x//3600 > 0 else f"{x % 3600 // 60}M {x % 60}S") 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: f"{x//3600}H {x % 3600 // 60}M {x % 60}S" if x//3600 > 0 else f"{x % 3600 // 60}M {x % 60}S") 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 extracted_ers["device_id"] = device_id