Compare commits

...

4 Commits

Author SHA1 Message Date
junos ce04394679 Merge commit 'c05b047c2d9452151553961928c846c01d7395bc' 2022-06-25 20:06:24 +02:00
junos c05b047c2d Correct outstanding baseline feature mistake. 2022-04-13 17:05:16 +02:00
junos 53ec52a954 Disable (SOME) feature cleaning for ESM data. 2022-04-13 16:01:31 +02:00
junos 144f0d0dcf Account for missing baseline data. 2022-04-13 14:56:28 +02:00
2 changed files with 9 additions and 6 deletions

View File

@ -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 "demand" in requested_features:
if "limesurvey_demand" in requested_features:
baseline_features.loc[0, "limesurvey_demand"] = limesurvey_demand[
"score"
].sum()
@ -136,9 +136,12 @@ if not participant_info.empty:
].sum()
if "limesurvey_demand_control_ratio" in requested_features:
limesurvey_demand_control_ratio = (
limesurvey_demand["score"].sum() / limesurvey_control["score"].sum()
)
if limesurvey_control["score"].sum():
limesurvey_demand_control_ratio = (
limesurvey_demand["score"].sum() / limesurvey_control["score"].sum()
)
else:
limesurvey_demand_control_ratio = 0
if (
JCQ_NORMS[participant_info.loc[0, "gender"]][0]
<= limesurvey_demand_control_ratio

View File

@ -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_if(~ sum(is.na(.)) / length(.) <= cols_nan_threshold )
clean_features <- clean_features %>% select(where(~ sum(is.na(.)) / length(.) <= cols_nan_threshold ), starts_with("phone_esm"))
# 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",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|phone_esm",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
# Drop highly correlated features
if(as.logical(drop_highly_correlated_features$COMPUTE)){