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

Fix a bug related to wrong user input (duplicated events).

imputation_and_cleaning
Primoz 2022-11-15 09:53:31 +00:00
parent bd41f42a5d
commit 621f11b2d9
2 changed files with 17 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
NaN.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 22 KiB

12
src/features/phone_esm/straw/process_user_event_related_segments.py
View File

@ -135,7 +135,7 @@ def extract_ers(esm_df):
extracted_ers = extracted_ers[(~extracted_ers.se_time.str.startswith("0 - ")) & (~extracted_ers.se_duration.str.startswith("0 - "))] extracted_ers = extracted_ers[(~extracted_ers.se_time.str.startswith("0 - ")) & (~extracted_ers.se_duration.str.startswith("0 - "))]
# Transform data into its final form, ready for the extraction # Transform data into its final form, ready for the extraction
extracted_ers.reset_index(inplace=True) extracted_ers.reset_index(drop=True, inplace=True)
time_before_event = 5 * 60 # in seconds (5 minutes) time_before_event = 5 * 60 # in seconds (5 minutes)
extracted_ers['event_timestamp'] = pd.to_datetime(extracted_ers['se_time']).apply(lambda x: x.timestamp() * 1000).astype('int64') extracted_ers['event_timestamp'] = pd.to_datetime(extracted_ers['se_time']).apply(lambda x: x.timestamp() * 1000).astype('int64')
@ -154,13 +154,15 @@ 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) + time_before_event 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) + time_before_event
# Exclude events that are longer than 2.5 hours
extracted_ers = extracted_ers[extracted_ers["se_duration"] <= 2.5 * 60 * 60].reset_index(drop=True)
extracted_ers["label"] = f"straw_event_{segmenting_method}_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3)
extracted_ers['shift'] = format_timestamp(time_before_event) extracted_ers['shift'] = format_timestamp(time_before_event)
extracted_ers['length'] = extracted_ers['se_duration'].apply(lambda x: format_timestamp(x)) extracted_ers['length'] = extracted_ers['se_duration'].apply(lambda x: format_timestamp(x))
# Drop event_timestamp duplicates in case of user referencing the same event over multiple questionnaires
extracted_ers.drop_duplicates(subset=["event_timestamp"], keep='first', inplace=True)
extracted_ers.reset_index(drop=True, inplace=True)
extracted_ers["label"] = f"straw_event_{segmenting_method}_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3)
# Write the csv of extracted ERS labels with targets (stress event intensity) # Write the csv of extracted ERS labels with targets (stress event intensity)
extracted_ers[["label", "intensity"]].to_csv(snakemake.output[1], index=False) extracted_ers[["label", "intensity"]].to_csv(snakemake.output[1], index=False)