diff --git a/config.yaml b/config.yaml index b38f16ce..770305e4 100644 --- a/config.yaml +++ b/config.yaml @@ -3,7 +3,7 @@ ######################################################################################################################## # See https://www.rapids.science/latest/setup/configuration/#participant-files -PIDS: ['p01'] +PIDS: ['p031', 'p032', 'p033', 'p034', 'p035', 'p036', 'p037', 'p038', 'p039', 'p040', 'p042', 'p043', 'p044', 'p045', 'p046', 'p049', 'p050', 'p052', 'p053', 'p054', 'p055', 'p057', 'p058', 'p059', 'p060', 'p061', 'p062', 'p064', 'p067', 'p068', 'p069', 'p070', 'p071', 'p072', 'p073', 'p074', 'p075', 'p076', 'p077', 'p078', 'p079', 'p080', 'p081', 'p082', 'p083', 'p084', 'p085', 'p086', 'p088', 'p089', 'p090', 'p091', 'p092', 'p093', 'p106', 'p107'] # See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files CREATE_PARTICIPANT_FILES: @@ -674,7 +674,7 @@ ALL_CLEANING_INDIVIDUAL: IMPUTE_SELECTED_EVENT_FEATURES: COMPUTE: False MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33 - COLS_NAN_THRESHOLD: 0.3 # set to 1 to disable + COLS_NAN_THRESHOLD: 1 # set to 1 to disable COLS_VAR_THRESHOLD: True ROWS_NAN_THRESHOLD: 1 # set to 1 to disable DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES @@ -690,7 +690,7 @@ ALL_CLEANING_INDIVIDUAL: COMPUTE: False TYPE: median # options: zero, mean, median or k-nearest MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33 - COLS_NAN_THRESHOLD: 0.3 # set to 1 to disable + COLS_NAN_THRESHOLD: 1 # set to 1 to disable COLS_VAR_THRESHOLD: True ROWS_NAN_THRESHOLD: 1 # set to 1 to disable DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES @@ -709,7 +709,7 @@ ALL_CLEANING_OVERALL: IMPUTE_SELECTED_EVENT_FEATURES: COMPUTE: False MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33 - COLS_NAN_THRESHOLD: 0.3 # set to 1 to disable + COLS_NAN_THRESHOLD: 1 # set to 1 to disable COLS_VAR_THRESHOLD: True ROWS_NAN_THRESHOLD: 1 # set to 1 to disable DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES @@ -725,7 +725,7 @@ ALL_CLEANING_OVERALL: COMPUTE: False TYPE: median # options: zero, mean, median or k-nearest MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33 - COLS_NAN_THRESHOLD: 0.3 # set to 1 to disable + COLS_NAN_THRESHOLD: 1 # set to 1 to disable COLS_VAR_THRESHOLD: True ROWS_NAN_THRESHOLD: 1 # set to 1 to disable DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES @@ -759,7 +759,7 @@ STANDARDIZATION: # Standardization for both providers is executed if only one of PARAMS_FOR_ANALYSIS: BASELINE: - COMPUTE: False + COMPUTE: True FOLDER: data/external/baseline CONTAINER: [results-survey637813_final.csv, # Slovenia results-survey358134_final.csv, # Belgium 1 @@ -770,5 +770,5 @@ PARAMS_FOR_ANALYSIS: CATEGORICAL_FEATURES: [gender] TARGET: - COMPUTE: False + COMPUTE: True LABEL: PANAS_negative_affect_mean diff --git a/rules/models.smk b/rules/models.smk index 4ae8eb6d..b027ca2c 100644 --- a/rules/models.smk +++ b/rules/models.smk @@ -30,7 +30,7 @@ rule baseline_features: rule select_target: input: - cleaned_sensor_features = "data/processed/features/{pid}/all_sensor_features_cleaned_rapids.csv" + cleaned_sensor_features = "data/processed/features/{pid}/all_sensor_features_cleaned_rapids_R.csv" params: target_variable = config["PARAMS_FOR_ANALYSIS"]["TARGET"]["LABEL"] output: @@ -40,7 +40,7 @@ rule select_target: rule merge_features_and_targets_for_population_model: input: - cleaned_sensor_features = "data/processed/features/all_participants/all_sensor_features_cleaned_rapids.csv", + cleaned_sensor_features = "data/processed/features/all_participants/all_sensor_features_cleaned_rapids_R.csv", demographic_features = expand("data/processed/features/{pid}/baseline_features.csv", pid=config["PIDS"]), params: target_variable=config["PARAMS_FOR_ANALYSIS"]["TARGET"]["LABEL"] diff --git a/src/features/all_cleaning_overall/rapids/main.R b/src/features/all_cleaning_overall/rapids/main.R index b3b7284d..98dfb884 100644 --- a/src/features/all_cleaning_overall/rapids/main.R +++ b/src/features/all_cleaning_overall/rapids/main.R @@ -46,11 +46,11 @@ 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)){ diff --git a/src/models/helper.py b/src/models/helper.py index ffae7208..77f3260e 100644 --- a/src/models/helper.py +++ b/src/models/helper.py @@ -10,7 +10,7 @@ def retain_target_column(df_input: pd.DataFrame, target_variable_name: str): if all(~target_variable_index): raise ValueError("The requested target (", target_variable_name, ")cannot be found in the dataset.", - "Please check the names of phone_esm_ columns in all_sensor_features_cleaned_rapids.csv") + "Please check the names of phone_esm_ columns in all_sensor_features_cleaned_rapids_R.csv") sensor_features_plus_target = df_input.drop(esm_names, axis=1) 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.