src/data/baseline_features.py

@@ -95,7 +95,7 @@ if not participant_info.empty:
                 - limesurvey_demand.loc[rows_demand_reverse, "score_original"]
             )
             baseline_interim = pd.concat([baseline_interim, limesurvey_demand], axis=0, ignore_index=True)
-            if "limesurvey_demand" in requested_features:
+            if "demand" in requested_features:
                 baseline_features.loc[0, "limesurvey_demand"] = limesurvey_demand[
                     "score"
                 ].sum()
@@ -136,12 +136,9 @@ if not participant_info.empty:
                 ].sum()
 
         if "limesurvey_demand_control_ratio" in requested_features:
-            if limesurvey_control["score"].sum():
-                limesurvey_demand_control_ratio = (
-                        limesurvey_demand["score"].sum() / limesurvey_control["score"].sum()
-                )
-            else:
-                limesurvey_demand_control_ratio = 0
+            limesurvey_demand_control_ratio = (
+                limesurvey_demand["score"].sum() / limesurvey_control["score"].sum()
+            )
             if (
                 JCQ_NORMS[participant_info.loc[0, "gender"]][0]
                 <= limesurvey_demand_control_ratio

src/features/all_cleaning_individual/rapids/main.R

@@ -44,11 +44,11 @@ rapids_cleaning <- function(sensor_data_files, provider){
 
     # Drop columns with a percentage of NA values above cols_nan_threshold
     if(nrow(clean_features))
-        clean_features <- clean_features %>% select(where(~ sum(is.na(.)) / length(.) <= cols_nan_threshold ), starts_with("phone_esm"))
+        clean_features <- clean_features %>% select_if(~ sum(is.na(.)) / length(.) <= cols_nan_threshold )
 
     # Drop columns with zero variance
     if(drop_zero_variance_columns)
-    clean_features <- clean_features %>% select_if(grepl("pid|local_segment|local_segment_label|local_segment_start_datetime|local_segment_end_datetime|phone_esm",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
+    clean_features <- clean_features %>% select_if(grepl("pid|local_segment|local_segment_label|local_segment_start_datetime|local_segment_end_datetime",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
 
     # Drop highly correlated features
     if(as.logical(drop_highly_correlated_features$COMPUTE)){