Fix a bug in the making of the individual model (when there is no target in the participants columns).

imputation_and_cleaning
Primoz 2022-11-16 09:50:18 +00:00
parent 286de93bfd
commit 99c2fab8f9
4 changed files with 14 additions and 7 deletions

View File

@ -732,7 +732,7 @@ PARAMS_FOR_ANALYSIS:
TARGET: TARGET:
COMPUTE: True COMPUTE: True
LABEL: PANAS_negative_affect_mean LABEL: appraisal_stressfulness_event_mean
ALL_LABELS: [appraisal_stressfulness_event_mean, appraisal_threat_mean, appraisal_challenge_mean] ALL_LABELS: [appraisal_stressfulness_event_mean, appraisal_threat_mean, appraisal_challenge_mean]
# PANAS_positive_affect_mean, PANAS_negative_affect_mean, JCQ_job_demand_mean, JCQ_job_control_mean, JCQ_supervisor_support_mean, # PANAS_positive_affect_mean, PANAS_negative_affect_mean, JCQ_job_demand_mean, JCQ_job_control_mean, JCQ_supervisor_support_mean,
# JCQ_coworker_support_mean, appraisal_stressfulness_period_mean, appraisal_stressfulness_event_mean # JCQ_coworker_support_mean, appraisal_stressfulness_period_mean, appraisal_stressfulness_event_mean

View File

@ -27,7 +27,10 @@ def straw_cleaning(sensor_data_files, provider):
# (1) FILTER_OUT THE ROWS THAT DO NOT HAVE THE TARGET COLUMN AVAILABLE # (1) FILTER_OUT THE ROWS THAT DO NOT HAVE THE TARGET COLUMN AVAILABLE
if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']: if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']:
target = config['PARAMS_FOR_ANALYSIS']['TARGET']['LABEL'] # get target label from config target = config['PARAMS_FOR_ANALYSIS']['TARGET']['LABEL'] # get target label from config
features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True) if 'phone_esm_straw_' + target in features:
features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True)
else:
return features
# (2.1) QUALITY CHECK (DATA YIELD COLUMN) deletes the rows where E4 or phone data is low quality # (2.1) QUALITY CHECK (DATA YIELD COLUMN) deletes the rows where E4 or phone data is low quality
phone_data_yield_unit = provider["PHONE_DATA_YIELD_FEATURE"].split("_")[3].lower() phone_data_yield_unit = provider["PHONE_DATA_YIELD_FEATURE"].split("_")[3].lower()

View File

@ -1,5 +1,6 @@
import pandas as pd import pandas as pd
import sys
import warnings
def retain_target_column(df_input: pd.DataFrame, target_variable_name: str): def retain_target_column(df_input: pd.DataFrame, target_variable_name: str):
column_names = df_input.columns column_names = df_input.columns
@ -8,9 +9,9 @@ def retain_target_column(df_input: pd.DataFrame, target_variable_name: str):
esm_names = column_names[esm_names_index] esm_names = column_names[esm_names_index]
target_variable_index = esm_names.str.contains(target_variable_name) target_variable_index = esm_names.str.contains(target_variable_name)
if all(~target_variable_index): if all(~target_variable_index):
raise ValueError("The requested target (", target_variable_name, warnings.warn(f"The requested target (, {target_variable_name} ,)cannot be found in the dataset. Please check the names of phone_esm_ columns in z_all_sensor_features_cleaned_straw_py.csv")
")cannot be found in the dataset.", return False
"Please check the names of phone_esm_ columns in z_all_sensor_features_cleaned_straw_py.csv")
sensor_features_plus_target = df_input.drop(esm_names, axis=1) sensor_features_plus_target = df_input.drop(esm_names, axis=1)
sensor_features_plus_target["target"] = df_input[esm_names[target_variable_index]] sensor_features_plus_target["target"] = df_input[esm_names[target_variable_index]]
# We will only keep one column related to phone_esm and that will be our target variable. # We will only keep one column related to phone_esm and that will be our target variable.

View File

@ -7,4 +7,7 @@ target_variable_name = snakemake.params["target_variable"]
model_input = retain_target_column(cleaned_sensor_features, target_variable_name) model_input = retain_target_column(cleaned_sensor_features, target_variable_name)
model_input.to_csv(snakemake.output[0], index=False) if not model_input:
pd.DataFrame().to_csv(snakemake.output[0])
else:
model_input.to_csv(snakemake.output[0], index=False)