diff --git a/Snakefile b/Snakefile index 7c5749d7..44e9b5bf 100644 --- a/Snakefile +++ b/Snakefile @@ -33,12 +33,6 @@ for provider in config["PHONE_DATA_YIELD"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_data_yield.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_DATA_YIELD"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_data_yield.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_MESSAGES"]["PROVIDERS"].keys(): if config["PHONE_MESSAGES"]["PROVIDERS"][provider]["COMPUTE"]: @@ -48,12 +42,6 @@ for provider in config["PHONE_MESSAGES"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_messages.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_MESSAGES"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_messages.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_CALLS"]["PROVIDERS"].keys(): if config["PHONE_CALLS"]["PROVIDERS"][provider]["COMPUTE"]: @@ -68,12 +56,6 @@ for provider in config["PHONE_CALLS"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_calls.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_CALLS"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_calls.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_BLUETOOTH"]["PROVIDERS"].keys(): if config["PHONE_BLUETOOTH"]["PROVIDERS"][provider]["COMPUTE"]: @@ -83,12 +65,6 @@ for provider in config["PHONE_BLUETOOTH"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_bluetooth.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_BLUETOOTH"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_bluetooth.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"].keys(): if config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"][provider]["COMPUTE"]: @@ -101,12 +77,6 @@ for provider in config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_activity_recognition.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_activity_recognition.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_BATTERY"]["PROVIDERS"].keys(): if config["PHONE_BATTERY"]["PROVIDERS"][provider]["COMPUTE"]: @@ -118,12 +88,6 @@ for provider in config["PHONE_BATTERY"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_battery.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_BATTERY"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_battery.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_SCREEN"]["PROVIDERS"].keys(): if config["PHONE_SCREEN"]["PROVIDERS"][provider]["COMPUTE"]: @@ -140,12 +104,6 @@ for provider in config["PHONE_SCREEN"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_screen.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_SCREEN"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_screen.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_LIGHT"]["PROVIDERS"].keys(): if config["PHONE_LIGHT"]["PROVIDERS"][provider]["COMPUTE"]: @@ -155,12 +113,6 @@ for provider in config["PHONE_LIGHT"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_light.csv", pid=config["PIDS"],)) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_LIGHT"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_light.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_ACCELEROMETER"]["PROVIDERS"].keys(): if config["PHONE_ACCELEROMETER"]["PROVIDERS"][provider]["COMPUTE"]: @@ -184,12 +136,6 @@ for provider in config["PHONE_APPLICATIONS_FOREGROUND"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_applications_foreground.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_APPLICATIONS_FOREGROUND"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_applications_foreground.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_WIFI_VISIBLE"]["PROVIDERS"].keys(): if config["PHONE_WIFI_VISIBLE"]["PROVIDERS"][provider]["COMPUTE"]: @@ -199,12 +145,6 @@ for provider in config["PHONE_WIFI_VISIBLE"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_wifi_visible.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_WIFI_VISIBLE"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_wifi_visible.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["PHONE_WIFI_CONNECTED"]["PROVIDERS"].keys(): if config["PHONE_WIFI_CONNECTED"]["PROVIDERS"][provider]["COMPUTE"]: @@ -233,12 +173,6 @@ for provider in config["PHONE_ESM"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_esm.csv", pid=config["PIDS"])) # files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv",pid=config["PIDS"])) # files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_ESM"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_esm.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") # We can delete these if's as soon as we add feature PROVIDERS to any of these sensors if isinstance(config["PHONE_APPLICATIONS_CRASHES"]["PROVIDERS"], dict): @@ -304,12 +238,6 @@ for provider in config["PHONE_LOCATIONS"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/phone_locations.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["LIST"] and config["STANDARDIZATION"]["PROVIDERS"]["OTHER"]["COMPUTE"] \ - and config["PHONE_LOCATIONS"]["PROVIDERS"][provider]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_phone_locations.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["FITBIT_CALORIES_INTRADAY"]["PROVIDERS"].keys(): if config["FITBIT_CALORIES_INTRADAY"]["PROVIDERS"][provider]["COMPUTE"]: @@ -400,13 +328,6 @@ for provider in config["EMPATICA_ACCELEROMETER"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/empatica_accelerometer.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"] \ - and config["EMPATICA_ACCELEROMETER"]["PROVIDERS"][provider]["WINDOWS"]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/interim/{pid}/empatica_accelerometer_features/z_empatica_accelerometer_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower())) - files_to_compute.extend(expand("data/processed/features/{pid}/z_empatica_accelerometer.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["EMPATICA_HEARTRATE"]["PROVIDERS"].keys(): if config["EMPATICA_HEARTRATE"]["PROVIDERS"][provider]["COMPUTE"]: @@ -426,13 +347,6 @@ for provider in config["EMPATICA_TEMPERATURE"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/empatica_temperature.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"] \ - and config["EMPATICA_TEMPERATURE"]["PROVIDERS"][provider]["WINDOWS"]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/interim/{pid}/empatica_temperature_features/z_empatica_temperature_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower())) - files_to_compute.extend(expand("data/processed/features/{pid}/z_empatica_temperature.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["EMPATICA_ELECTRODERMAL_ACTIVITY"]["PROVIDERS"].keys(): if config["EMPATICA_ELECTRODERMAL_ACTIVITY"]["PROVIDERS"][provider]["COMPUTE"]: @@ -442,13 +356,6 @@ for provider in config["EMPATICA_ELECTRODERMAL_ACTIVITY"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/empatica_electrodermal_activity.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"] \ - and config["EMPATICA_ELECTRODERMAL_ACTIVITY"]["PROVIDERS"][provider]["WINDOWS"]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/interim/{pid}/empatica_electrodermal_activity_features/z_empatica_electrodermal_activity_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower())) - files_to_compute.extend(expand("data/processed/features/{pid}/z_empatica_electrodermal_activity.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"].keys(): if config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"][provider]["COMPUTE"]: @@ -458,13 +365,6 @@ for provider in config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/empatica_blood_volume_pulse.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"] \ - and config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"][provider]["WINDOWS"]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/interim/{pid}/empatica_blood_volume_pulse_features/z_empatica_blood_volume_pulse_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower())) - files_to_compute.extend(expand("data/processed/features/{pid}/z_empatica_blood_volume_pulse.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") for provider in config["EMPATICA_INTER_BEAT_INTERVAL"]["PROVIDERS"].keys(): if config["EMPATICA_INTER_BEAT_INTERVAL"]["PROVIDERS"][provider]["COMPUTE"]: @@ -474,13 +374,6 @@ for provider in config["EMPATICA_INTER_BEAT_INTERVAL"]["PROVIDERS"].keys(): files_to_compute.extend(expand("data/processed/features/{pid}/empatica_inter_beat_interval.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])) files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv") - if provider in config["STANDARDIZATION"]["PROVIDERS"] and config["STANDARDIZATION"]["PROVIDERS"][provider]["COMPUTE"] \ - and config["EMPATICA_INTER_BEAT_INTERVAL"]["PROVIDERS"][provider]["WINDOWS"]["STANDARDIZE_FEATURES"]: - files_to_compute.extend(expand("data/interim/{pid}/empatica_inter_beat_interval_features/z_empatica_inter_beat_interval_{language}_{provider_key}_windows.csv", pid=config["PIDS"], language=get_script_language(config["STANDARDIZATION"]["PROVIDERS"][provider]["SRC_SCRIPT"]), provider_key=provider.lower())) - files_to_compute.extend(expand("data/processed/features/{pid}/z_empatica_inter_beat_interval.csv", pid=config["PIDS"])) - if config["STANDARDIZATION"]["MERGE_ALL"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"])) - files_to_compute.append("data/processed/features/all_participants/z_all_sensor_features.csv") if isinstance(config["EMPATICA_TAGS"]["PROVIDERS"], dict): for provider in config["EMPATICA_TAGS"]["PROVIDERS"].keys(): @@ -517,24 +410,16 @@ for provider in config["ALL_CLEANING_INDIVIDUAL"]["PROVIDERS"].keys(): if config["ALL_CLEANING_INDIVIDUAL"]["PROVIDERS"][provider]["COMPUTE"]: if provider == "STRAW": files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features_cleaned_" + provider.lower() + "_py.csv", pid=config["PIDS"])) - if config["ALL_CLEANING_INDIVIDUAL"]["CLEAN_STANDARDIZED"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features_cleaned_" + provider.lower() + "_py.csv", pid=config["PIDS"])) else: files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features_cleaned_" + provider.lower() + "_R.csv", pid=config["PIDS"])) - if config["ALL_CLEANING_INDIVIDUAL"]["CLEAN_STANDARDIZED"]: - files_to_compute.extend(expand("data/processed/features/{pid}/z_all_sensor_features_cleaned_" + provider.lower() + "_R.csv", pid=config["PIDS"])) for provider in config["ALL_CLEANING_OVERALL"]["PROVIDERS"].keys(): if config["ALL_CLEANING_OVERALL"]["PROVIDERS"][provider]["COMPUTE"]: if provider == "STRAW": - files_to_compute.extend(expand("data/processed/features/all_participants/all_sensor_features_cleaned_" + provider.lower() +"_py.csv")) - if config["ALL_CLEANING_OVERALL"]["CLEAN_STANDARDIZED"]: - files_to_compute.extend(expand("data/processed/features/all_participants/z_all_sensor_features_cleaned_" + provider.lower() +"_py.csv")) + for target in config["PARAMS_FOR_ANALYSIS"]["TARGET"]["ALL_LABELS"]: + files_to_compute.extend(expand("data/processed/features/all_participants/all_sensor_features_cleaned_" + provider.lower() +"_py_(" + target + ").csv")) else: - files_to_compute.extend(expand("data/processed/features/all_participants/all_sensor_features_cleaned_" + provider.lower() +"_R.csv")) - if config["ALL_CLEANING_OVERALL"]["CLEAN_STANDARDIZED"]: - files_to_compute.extend(expand("data/processed/features/all_participants/z_all_sensor_features_cleaned_" + provider.lower() +"_R.csv")) - + files_to_compute.extend(expand("data/processed/features/all_participants/all_sensor_features_cleaned_" + provider.lower() +"_R.csv")) # Baseline features if config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["COMPUTE"]: @@ -545,12 +430,9 @@ if config["PARAMS_FOR_ANALYSIS"]["BASELINE"]["COMPUTE"]: # Targets (labels) if config["PARAMS_FOR_ANALYSIS"]["TARGET"]["COMPUTE"]: - # files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/input.csv", pid=config["PIDS"])) - # files_to_compute.extend(expand("data/processed/models/population_model/input.csv")) - files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/z_input.csv", pid=config["PIDS"])) - files_to_compute.extend(expand("data/processed/models/population_model/z_input.csv")) - -#files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/output_{cv_method}/baselines.csv", pid=config["PIDS"], cv_method=config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"])) + files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/input.csv", pid=config["PIDS"])) + for target in config["PARAMS_FOR_ANALYSIS"]["TARGET"]["ALL_LABELS"]: + files_to_compute.extend(expand("data/processed/models/population_model/input_" + target + ".csv")) rule all: input: diff --git a/automl_test.py b/automl_test.py new file mode 100644 index 00000000..3e2e3b84 --- /dev/null +++ b/automl_test.py @@ -0,0 +1,57 @@ +from pprint import pprint +import sklearn.metrics +import autosklearn.regression + +import datetime +import importlib +import os +import sys + +import numpy as np +import matplotlib.pyplot as plt +import pandas as pd +import seaborn as sns +import yaml + +from sklearn import linear_model, svm, kernel_ridge, gaussian_process +from sklearn.model_selection import LeaveOneGroupOut, cross_val_score, train_test_split +from sklearn.metrics import mean_squared_error, r2_score +from sklearn.impute import SimpleImputer + +model_input = pd.read_csv("data/processed/models/population_model/input_PANAS_negative_affect_mean.csv") # Standardizirani podatki + +model_input.dropna(axis=1, how="all", inplace=True) +model_input.dropna(axis=0, how="any", subset=["target"], inplace=True) + +categorical_feature_colnames = ["gender", "startlanguage"] +categorical_feature_colnames += [col for col in model_input.columns if "mostcommonactivity" in col or "homelabel" in col] +categorical_features = model_input[categorical_feature_colnames].copy() +mode_categorical_features = categorical_features.mode().iloc[0] +categorical_features = categorical_features.fillna(mode_categorical_features) +categorical_features = categorical_features.apply(lambda col: col.astype("category")) +if not categorical_features.empty: + categorical_features = pd.get_dummies(categorical_features) +numerical_features = model_input.drop(categorical_feature_colnames, axis=1) +model_in = pd.concat([numerical_features, categorical_features], axis=1) + +index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"] +model_in.set_index(index_columns, inplace=True) + +X_train, X_test, y_train, y_test = train_test_split(model_in.drop(["target", "pid"], axis=1), model_in["target"], test_size=0.30) + +automl = autosklearn.regression.AutoSklearnRegressor( + time_left_for_this_task=7200, + per_run_time_limit=120 +) +automl.fit(X_train, y_train, dataset_name='straw') + +print(automl.leaderboard()) +pprint(automl.show_models(), indent=4) + +train_predictions = automl.predict(X_train) +print("Train R2 score:", sklearn.metrics.r2_score(y_train, train_predictions)) +test_predictions = automl.predict(X_test) +print("Test R2 score:", sklearn.metrics.r2_score(y_test, test_predictions)) + +import sys +sys.exit() diff --git a/config.yaml b/config.yaml index 770305e4..50b7dd41 100644 --- a/config.yaml +++ b/config.yaml @@ -21,9 +21,12 @@ CREATE_PARTICIPANT_FILES: # See https://www.rapids.science/latest/setup/configuration/#time-segments TIME_SEGMENTS: &time_segments - TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT - FILE: "data/external/timesegments_daily.csv" + TYPE: EVENT # FREQUENCY, PERIODIC, EVENT + FILE: "data/external/straw_events.csv" INCLUDE_PAST_PERIODIC_SEGMENTS: TRUE # Only relevant if TYPE=PERIODIC, see docs + TAILORED_EVENTS: # Only relevant if TYPE=EVENT + COMPUTE: True + SEGMENTING_METHOD: "30_before" # 30_before, 90_before, stress_event # See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study TIMEZONE: @@ -70,7 +73,6 @@ PHONE_ACCELEROMETER: COMPUTE: False FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"] SRC_SCRIPT: src/features/phone_accelerometer/rapids/main.py - PANDA: COMPUTE: False VALID_SENSED_MINUTES: False @@ -93,7 +95,6 @@ PHONE_ACTIVITY_RECOGNITION: STATIONARY: ["still", "tilting"] MOBILE: ["on_foot", "walking", "running", "on_bicycle"] VEHICLE: ["in_vehicle"] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_activity_recognition/rapids/main.py # See https://www.rapids.science/latest/features/phone-applications-crashes/ @@ -134,7 +135,6 @@ PHONE_APPLICATIONS_FOREGROUND: APP_EPISODES: ["countepisode", "minduration", "maxduration", "meanduration", "sumduration"] IGNORE_EPISODES_SHORTER_THAN: 0 # in minutes, set to 0 to disable IGNORE_EPISODES_LONGER_THAN: 300 # in minutes, set to 0 to disable - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_applications_foreground/rapids/main.py # See https://www.rapids.science/latest/features/phone-applications-notifications/ @@ -155,7 +155,6 @@ PHONE_BATTERY: RAPIDS: COMPUTE: True FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_battery/rapids/main.py # See https://www.rapids.science/latest/features/phone-bluetooth/ @@ -163,9 +162,8 @@ PHONE_BLUETOOTH: CONTAINER: bluetooth PROVIDERS: RAPIDS: - COMPUTE: True + COMPUTE: False FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_bluetooth/rapids/main.R DORYAB: @@ -183,7 +181,6 @@ PHONE_BLUETOOTH: DEVICES: ["countscans", "uniquedevices", "meanscans", "stdscans"] SCANS_MOST_FREQUENT_DEVICE: ["withinsegments", "acrosssegments", "acrossdataset"] SCANS_LEAST_FREQUENT_DEVICE: ["withinsegments", "acrosssegments", "acrossdataset"] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_bluetooth/doryab/main.py # See https://www.rapids.science/latest/features/phone-calls/ @@ -198,7 +195,6 @@ PHONE_CALLS: missed: [count, distinctcontacts, timefirstcall, timelastcall, countmostfrequentcontact] incoming: [count, distinctcontacts, meanduration, sumduration, minduration, maxduration, stdduration, modeduration, entropyduration, timefirstcall, timelastcall, countmostfrequentcontact] outgoing: [count, distinctcontacts, meanduration, sumduration, minduration, maxduration, stdduration, modeduration, entropyduration, timefirstcall, timelastcall, countmostfrequentcontact] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_calls/rapids/main.R # See https://www.rapids.science/latest/features/phone-conversation/ @@ -238,7 +234,6 @@ PHONE_DATA_YIELD: COMPUTE: True FEATURES: [ratiovalidyieldedminutes, ratiovalidyieldedhours] MINUTE_RATIO_THRESHOLD_FOR_VALID_YIELDED_HOURS: 0.5 # 0 to 1, minimum percentage of valid minutes in an hour to be considered valid. - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_data_yield/rapids/main.R PHONE_ESM: @@ -246,9 +241,9 @@ PHONE_ESM: PROVIDERS: STRAW: COMPUTE: True - SCALES: ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support"] + SCALES: ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support", + "appraisal_stressfulness_period", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge"] FEATURES: [mean] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_esm/straw/main.py # See https://www.rapids.science/latest/features/phone-keyboard/ @@ -267,7 +262,6 @@ PHONE_LIGHT: RAPIDS: COMPUTE: True FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_light/rapids/main.py # See https://www.rapids.science/latest/features/phone-locations/ @@ -292,7 +286,6 @@ PHONE_LOCATIONS: MINIMUM_DAYS_TO_DETECT_HOME_CHANGES: 3 CLUSTERING_ALGORITHM: DBSCAN # DBSCAN, OPTICS RADIUS_FOR_HOME: 100 - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_locations/doryab/main.py BARNETT: @@ -300,7 +293,6 @@ PHONE_LOCATIONS: FEATURES: ["hometime","disttravelled","rog","maxdiam","maxhomedist","siglocsvisited","avgflightlen","stdflightlen","avgflightdur","stdflightdur","probpause","siglocentropy","circdnrtn","wkenddayrtn"] IF_MULTIPLE_TIMEZONES: USE_MOST_COMMON MINUTES_DATA_USED: False # Use this for quality control purposes, how many minutes of data (location coordinates gruped by minute) were used to compute features - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_locations/barnett/main.R # See https://www.rapids.science/latest/features/phone-log/ @@ -320,7 +312,6 @@ PHONE_MESSAGES: FEATURES: received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact] sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_messages/rapids/main.R # See https://www.rapids.science/latest/features/phone-screen/ @@ -334,7 +325,6 @@ PHONE_SCREEN: IGNORE_EPISODES_LONGER_THAN: 360 # in minutes, set to 0 to disable FEATURES: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"] # "episodepersensedminutes" needs to be added later EPISODE_TYPES: ["unlock"] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_screen/rapids/main.py # See https://www.rapids.science/latest/features/phone-wifi-connected/ @@ -353,7 +343,6 @@ PHONE_WIFI_VISIBLE: RAPIDS: COMPUTE: True FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/phone_wifi_visible/rapids/main.R @@ -455,7 +444,6 @@ FITBIT_SLEEP_INTRADAY: UNIFIED: [awake, asleep] SLEEP_TYPES: [main, nap, all] SRC_SCRIPT: src/features/fitbit_sleep_intraday/rapids/main.py - PRICE: COMPUTE: False FEATURES: [avgduration, avgratioduration, avgstarttimeofepisodemain, avgendtimeofepisodemain, avgmidpointofepisodemain, stdstarttimeofepisodemain, stdendtimeofepisodemain, stdmidpointofepisodemain, socialjetlag, rmssdmeanstarttimeofepisodemain, rmssdmeanendtimeofepisodemain, rmssdmeanmidpointofepisodemain, rmssdmedianstarttimeofepisodemain, rmssdmedianendtimeofepisodemain, rmssdmedianmidpointofepisodemain] @@ -528,7 +516,6 @@ EMPATICA_ACCELEROMETER: COMPUTE: True WINDOW_LENGTH: 15 # specify window length in seconds SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows'] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/empatica_accelerometer/cr/main.py @@ -557,7 +544,6 @@ EMPATICA_TEMPERATURE: COMPUTE: True WINDOW_LENGTH: 300 # specify window length in seconds SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows'] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/empatica_temperature/cr/main.py # See https://www.rapids.science/latest/features/empatica-electrodermal-activity/ @@ -579,7 +565,6 @@ EMPATICA_ELECTRODERMAL_ACTIVITY: COMPUTE: True WINDOW_LENGTH: 60 # specify window length in seconds SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', count_windows, eda_num_peaks_non_zero] - STANDARDIZE_FEATURES: True IMPUTE_NANS: True SRC_SCRIPT: src/features/empatica_electrodermal_activity/cr/main.py @@ -599,7 +584,6 @@ EMPATICA_BLOOD_VOLUME_PULSE: COMPUTE: True WINDOW_LENGTH: 300 # specify window length in seconds SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows', 'hrv_num_windows_non_nan'] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/empatica_blood_volume_pulse/cr/main.py # See https://www.rapids.science/latest/features/empatica-inter-beat-interval/ @@ -619,7 +603,6 @@ EMPATICA_INTER_BEAT_INTERVAL: COMPUTE: True WINDOW_LENGTH: 300 # specify window length in seconds SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows', 'hrv_num_windows_non_nan'] - STANDARDIZE_FEATURES: True SRC_SCRIPT: src/features/empatica_inter_beat_interval/cr/main.py # See https://www.rapids.science/latest/features/empatica-tags/ @@ -667,10 +650,9 @@ HEATMAP_FEATURE_CORRELATION_MATRIX: ######################################################################################################################## ALL_CLEANING_INDIVIDUAL: - CLEAN_STANDARDIZED: True PROVIDERS: RAPIDS: - COMPUTE: True + COMPUTE: False IMPUTE_SELECTED_EVENT_FEATURES: COMPUTE: False MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33 @@ -684,28 +666,25 @@ ALL_CLEANING_INDIVIDUAL: MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5 CORR_THRESHOLD: 0.95 SRC_SCRIPT: src/features/all_cleaning_individual/rapids/main.R - STRAW: # currently the same as RAPIDS provider with a change in selecting the imputation type + STRAW: COMPUTE: True - IMPUTE_PHONE_SELECTED_EVENT_FEATURES: - COMPUTE: False - TYPE: median # options: zero, mean, median or k-nearest - MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33 - COLS_NAN_THRESHOLD: 1 # set to 1 to disable + PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_MINUTES # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES + PHONE_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable + EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable + ROWS_NAN_THRESHOLD: 0.33 # set to 1 to disable + COLS_NAN_THRESHOLD: 0.9 # set to 1 to remove only columns that contains all (100% of) NaN 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 - DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable DROP_HIGHLY_CORRELATED_FEATURES: COMPUTE: True MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5 CORR_THRESHOLD: 0.95 + STANDARDIZATION: True SRC_SCRIPT: src/features/all_cleaning_individual/straw/main.py ALL_CLEANING_OVERALL: - CLEAN_STANDARDIZED: True PROVIDERS: RAPIDS: - COMPUTE: True + COMPUTE: False IMPUTE_SELECTED_EVENT_FEATURES: COMPUTE: False MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33 @@ -719,40 +698,22 @@ ALL_CLEANING_OVERALL: MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5 CORR_THRESHOLD: 0.95 SRC_SCRIPT: src/features/all_cleaning_overall/rapids/main.R - STRAW: # currently the same as RAPIDS provider with a change in selecting the imputation type + STRAW: COMPUTE: True - IMPUTE_PHONE_SELECTED_EVENT_FEATURES: - COMPUTE: False - TYPE: median # options: zero, mean, median or k-nearest - MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33 - COLS_NAN_THRESHOLD: 1 # set to 1 to disable + PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_MINUTES # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES + PHONE_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable + EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable + ROWS_NAN_THRESHOLD: 0.33 # set to 1 to disable + COLS_NAN_THRESHOLD: 0.8 # set to 1 to remove only columns that contains all (100% of) NaN 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 - DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable DROP_HIGHLY_CORRELATED_FEATURES: COMPUTE: True MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5 CORR_THRESHOLD: 0.95 + STANDARDIZATION: False SRC_SCRIPT: src/features/all_cleaning_overall/straw/main.py -######################################################################################################################## -# Z-score standardization # -######################################################################################################################## - -STANDARDIZATION: # Standardization for both providers is executed if only one of two providers is marked COMPUTE: TRUE - MERGE_ALL: True # Creates the joint standardized file for each participant and all participants. Similar to merge_sensor_features_for_all_participants rule - PROVIDERS: - CR: - COMPUTE: True - SRC_SCRIPT: src/features/standardization/main.py - OTHER: - COMPUTE: True - LIST: [RAPIDS, DORYAB, BARNETT, STRAW] - SRC_SCRIPT: src/features/standardization/main.py - - ######################################################################################################################## # Baseline # ######################################################################################################################## @@ -771,4 +732,8 @@ PARAMS_FOR_ANALYSIS: TARGET: COMPUTE: True - LABEL: PANAS_negative_affect_mean + LABEL: appraisal_stressfulness_event_mean + ALL_LABELS: [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, 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, + # JCQ_coworker_support_mean, appraisal_stressfulness_period_mean, appraisal_stressfulness_event_mean, appraisal_threat_mean, appraisal_challenge_mean diff --git a/data/external/participant_files/p01.yaml b/data/external/participant_files/p01.yaml index fe394a76..add25858 100644 --- a/data/external/participant_files/p01.yaml +++ b/data/external/participant_files/p01.yaml @@ -1,11 +1,11 @@ PHONE: - DEVICE_IDS: [a748ee1a-1d0b-4ae9-9074-279a2b6ba524] # the participant's AWARE device id - PLATFORMS: [android] # or ios - LABEL: MyTestP01 # any string - START_DATE: 2020-01-01 # this can also be empty - END_DATE: 2021-01-01 # this can also be empty + DEVICE_IDS: [4b62a655-cbf0-4ac0-a448-06726f45b56a] + PLATFORMS: [android] + LABEL: uploader_53573 + START_DATE: 2021-05-21 09:21:24 + END_DATE: 2021-07-12 17:32:07 EMPATICA: - DEVICE_IDS: [empatica1] - LABEL: test01 - START_DATE: - END_DATE: + DEVICE_IDS: [uploader_53573] + LABEL: uploader_53573 + START_DATE: 2021-05-21 09:21:24 + END_DATE: 2021-07-12 17:32:07 diff --git a/data/external/timesegments_daily.csv b/data/external/timesegments_daily.csv index 605a4a53..183245b9 100644 --- a/data/external/timesegments_daily.csv +++ b/data/external/timesegments_daily.csv @@ -1,2 +1,3 @@ label,start_time,length,repeats_on,repeats_value daily,04:00:00,23H 59M 59S,every_day,0 +working_day,04:00:00,18H 00M 00S,every_day,0 diff --git a/environment.yml b/environment.yml index cba49edc..536149bc 100644 --- a/environment.yml +++ b/environment.yml @@ -86,8 +86,6 @@ dependencies: - readline=8.0 - requests=2.25.0 - retrying=1.3.3 - - scikit-learn=0.23.2 - - scipy=1.5.2 - setuptools=51.0.0 - six=1.15.0 - smmap=3.0.4 @@ -107,34 +105,61 @@ dependencies: - zlib=1.2.11 - pip: - amply==0.1.4 + - auto-sklearn==0.14.7 - bidict==0.22.0 - biosppy==0.8.0 + - build==0.8.0 - cached-property==1.5.2 + - cloudpickle==2.2.0 - configargparse==0.15.1 + - configspace==0.4.21 - cr-features==0.2.1 - cycler==0.11.0 + - cython==0.29.32 + - dask==2022.2.0 - decorator==4.4.2 + - distributed==2022.2.0 + - distro==1.7.0 + - emcee==3.1.2 - fonttools==4.33.2 + - fsspec==2022.8.2 - h5py==3.6.0 + - heapdict==1.0.1 - hmmlearn==0.2.7 - ipython-genutils==0.2.0 - jupyter-core==4.6.3 - kiwisolver==1.4.2 + - liac-arff==2.5.0 + - locket==1.0.0 - matplotlib==3.5.1 + - msgpack==1.0.4 - nbformat==5.0.7 - opencv-python==4.5.5.64 - packaging==21.3 + - partd==1.3.0 - peakutils==1.3.3 + - pep517==0.13.0 - pillow==9.1.0 - pulp==2.4 + - pynisher==0.6.4 - pyparsing==2.4.7 + - pyrfr==0.8.3 - pyrsistent==0.15.5 - pywavelets==1.3.0 - ratelimiter==1.2.0.post0 + - scikit-learn==0.24.2 + - scipy==1.7.3 - seaborn==0.11.2 - shortuuid==1.0.8 + - smac==1.2 - snakemake==5.30.2 + - sortedcontainers==2.4.0 + - tblib==1.7.0 + - tomli==2.0.1 + - toolz==0.12.0 - toposort==1.5 + - tornado==6.2 - traitlets==4.3.3 - typing-extensions==4.2.0 + - zict==2.2.0 prefix: /opt/conda/envs/rapids diff --git a/rules/common.smk b/rules/common.smk index a470012f..80b18485 100644 --- a/rules/common.smk +++ b/rules/common.smk @@ -40,15 +40,6 @@ def find_features_files(wildcards): feature_files.extend(expand("data/interim/{{pid}}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", sensor_key=wildcards.sensor_key.lower(), language=get_script_language(provider["SRC_SCRIPT"]), provider_key=provider_key.lower())) return(feature_files) -def find_empaticas_standardized_features_files(wildcards): - feature_files = [] - if "empatica" in wildcards.sensor_key: - for provider_key, provider in config[(wildcards.sensor_key).upper()]["PROVIDERS"].items(): - if provider["COMPUTE"] and provider.get("WINDOWS", False) and provider["WINDOWS"]["COMPUTE"]: - if "empatica" in wildcards.sensor_key: - feature_files.extend(expand("data/interim/{{pid}}/{sensor_key}_features/z_{sensor_key}_{language}_{provider_key}.csv", sensor_key=wildcards.sensor_key.lower(), language=get_script_language(provider["SRC_SCRIPT"]), provider_key=provider_key.lower())) - return(feature_files) - def find_joint_non_empatica_sensor_files(wildcards): joined_files = [] for config_key in config.keys(): @@ -82,18 +73,6 @@ def input_merge_sensor_features_for_individual_participants(wildcards): break return feature_files -def input_merge_standardized_sensor_features_for_individual_participants(wildcards): - feature_files = [] - for config_key in config.keys(): - if config_key.startswith(("PHONE", "FITBIT", "EMPATICA")) and "PROVIDERS" in config[config_key] and isinstance(config[config_key]["PROVIDERS"], dict): - for provider_key, provider in config[config_key]["PROVIDERS"].items(): - if "COMPUTE" in provider.keys() and provider["COMPUTE"] and ("STANDARDIZE_FEATURES" in provider.keys() and provider["STANDARDIZE_FEATURES"] or - "WINDOWS" in provider.keys() and "STANDARDIZE_FEATURES" in provider["WINDOWS"].keys() and provider["WINDOWS"]["STANDARDIZE_FEATURES"]): - feature_files.append("data/processed/features/{pid}/z_" + config_key.lower() + ".csv") - break - - return feature_files - def get_phone_sensor_names(): phone_sensor_names = [] for config_key in config.keys(): diff --git a/rules/features.smk b/rules/features.smk index 5331d827..2638a8f3 100644 --- a/rules/features.smk +++ b/rules/features.smk @@ -796,20 +796,6 @@ rule empatica_accelerometer_python_features: script: "../src/features/entry.py" -rule empatica_accelerometer_python_features_standardization: - input: - windows_features_data = "data/interim/{pid}/empatica_accelerometer_features/empatica_accelerometer_python_{provider_key}_windows.csv" - params: - provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"], - provider_key = "{provider_key}", - sensor_key = "empatica_accelerometer", - provider_main = config["EMPATICA_ACCELEROMETER"]["PROVIDERS"]["CR"] - output: - "data/interim/{pid}/empatica_accelerometer_features/z_empatica_accelerometer_python_{provider_key}.csv", - "data/interim/{pid}/empatica_accelerometer_features/z_empatica_accelerometer_python_{provider_key}_windows.csv" - script: - "../src/features/standardization/main.py" - rule empatica_accelerometer_r_features: input: sensor_data = "data/raw/{pid}/empatica_accelerometer_with_datetime.csv", @@ -864,20 +850,6 @@ rule empatica_temperature_python_features: script: "../src/features/entry.py" -rule empatica_temperature_python_features_standardization: - input: - windows_features_data = "data/interim/{pid}/empatica_temperature_features/empatica_temperature_python_{provider_key}_windows.csv" - params: - provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"], - provider_key = "{provider_key}", - sensor_key = "empatica_temperature", - provider_main = config["EMPATICA_TEMPERATURE"]["PROVIDERS"]["CR"] - output: - "data/interim/{pid}/empatica_temperature_features/z_empatica_temperature_python_{provider_key}.csv", - "data/interim/{pid}/empatica_temperature_features/z_empatica_temperature_python_{provider_key}_windows.csv" - script: - "../src/features/standardization/main.py" - rule empatica_temperature_r_features: input: sensor_data = "data/raw/{pid}/empatica_temperature_with_datetime.csv", @@ -905,20 +877,6 @@ rule empatica_electrodermal_activity_python_features: script: "../src/features/entry.py" -rule empatica_electrodermal_activity_python_features_standardization: - input: - windows_features_data = "data/interim/{pid}/empatica_electrodermal_activity_features/empatica_electrodermal_activity_python_{provider_key}_windows.csv" - params: - provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"], - provider_key = "{provider_key}", - sensor_key = "empatica_electrodermal_activity", - provider_main = config["EMPATICA_ELECTRODERMAL_ACTIVITY"]["PROVIDERS"]["CR"] - output: - "data/interim/{pid}/empatica_electrodermal_activity_features/z_empatica_electrodermal_activity_python_{provider_key}.csv", - "data/interim/{pid}/empatica_electrodermal_activity_features/z_empatica_electrodermal_activity_python_{provider_key}_windows.csv" - script: - "../src/features/standardization/main.py" - rule empatica_electrodermal_activity_r_features: input: sensor_data = "data/raw/{pid}/empatica_electrodermal_activity_with_datetime.csv", @@ -946,20 +904,6 @@ rule empatica_blood_volume_pulse_python_features: script: "../src/features/entry.py" -rule empatica_blood_volume_pulse_python_cr_features_standardization: - input: - windows_features_data = "data/interim/{pid}/empatica_blood_volume_pulse_features/empatica_blood_volume_pulse_python_{provider_key}_windows.csv" - params: - provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"], - provider_key = "{provider_key}", - sensor_key = "empatica_blood_volume_pulse", - provider_main = config["EMPATICA_BLOOD_VOLUME_PULSE"]["PROVIDERS"]["CR"] - output: - "data/interim/{pid}/empatica_blood_volume_pulse_features/z_empatica_blood_volume_pulse_python_{provider_key}.csv", - "data/interim/{pid}/empatica_blood_volume_pulse_features/z_empatica_blood_volume_pulse_python_{provider_key}_windows.csv" - script: - "../src/features/standardization/main.py" - rule empatica_blood_volume_pulse_r_features: input: sensor_data = "data/raw/{pid}/empatica_blood_volume_pulse_with_datetime.csv", @@ -987,20 +931,6 @@ rule empatica_inter_beat_interval_python_features: script: "../src/features/entry.py" -rule empatica_inter_beat_interval_python_features_standardization: - input: - windows_features_data = "data/interim/{pid}/empatica_inter_beat_interval_features/empatica_inter_beat_interval_python_{provider_key}_windows.csv" - params: - provider = config["STANDARDIZATION"]["PROVIDERS"]["CR"], - provider_key = "{provider_key}", - sensor_key = "empatica_inter_beat_interval", - provider_main = config["EMPATICA_INTER_BEAT_INTERVAL"]["PROVIDERS"]["CR"] - output: - "data/interim/{pid}/empatica_inter_beat_interval_features/z_empatica_inter_beat_interval_python_{provider_key}.csv", - "data/interim/{pid}/empatica_inter_beat_interval_features/z_empatica_inter_beat_interval_python_{provider_key}_windows.csv" - script: - "../src/features/standardization/main.py" - rule empatica_inter_beat_interval_r_features: input: sensor_data = "data/raw/{pid}/empatica_inter_beat_interval_with_datetime.csv", @@ -1048,38 +978,6 @@ rule merge_sensor_features_for_individual_participants: script: "../src/features/utils/merge_sensor_features_for_individual_participants.R" -rule join_standardized_features_from_empatica: - input: - sensor_features = find_empaticas_standardized_features_files - wildcard_constraints: - sensor_key = '(empatica).*' - output: - "data/processed/features/{pid}/z_{sensor_key}.csv" - script: - "../src/features/utils/join_features_from_providers.R" - -rule standardize_features_from_providers_no_empatica: - input: - sensor_features = find_joint_non_empatica_sensor_files - wildcard_constraints: - sensor_key = '(phone|fitbit).*' - params: - provider = config["STANDARDIZATION"]["PROVIDERS"]["OTHER"], - provider_key = "OTHER", - sensor_key = "{sensor_key}" - output: - "data/processed/features/{pid}/z_{sensor_key}.csv" - script: - "../src/features/standardization/main.py" - -rule merge_standardized_sensor_features_for_individual_participants: - input: - feature_files = input_merge_standardized_sensor_features_for_individual_participants - output: - "data/processed/features/{pid}/z_all_sensor_features.csv" - script: - "../src/features/utils/merge_sensor_features_for_individual_participants.R" - rule merge_sensor_features_for_all_participants: input: feature_files = expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]) @@ -1088,14 +986,6 @@ rule merge_sensor_features_for_all_participants: script: "../src/features/utils/merge_sensor_features_for_all_participants.R" -rule merge_standardized_sensor_features_for_all_participants: - input: - feature_files = expand("data/processed/features/{pid}/z_all_sensor_features.csv", pid=config["PIDS"]) - output: - "data/processed/features/all_participants/z_all_sensor_features.csv" - script: - "../src/features/utils/merge_standardized_sensor_features_for_all_participants.R" - rule clean_sensor_features_for_individual_participants: input: sensor_data = rules.merge_sensor_features_for_individual_participants.output @@ -1107,7 +997,7 @@ rule clean_sensor_features_for_individual_participants: script_extension = "{script_extension}", sensor_key = "all_cleaning_individual" output: - "data/processed/features/{pid}/all_sensor_features_cleaned_{provider_key}_{script_extension}.csv" # bo predstavljalo probleme za naprej (kako iskati datoteke + standardizacija itd.) + "data/processed/features/{pid}/all_sensor_features_cleaned_{provider_key}_{script_extension}.csv" script: "../src/features/entry.{params.script_extension}" @@ -1118,37 +1008,9 @@ rule clean_sensor_features_for_all_participants: provider = lambda wildcards: config["ALL_CLEANING_OVERALL"]["PROVIDERS"][wildcards.provider_key.upper()], provider_key = "{provider_key}", script_extension = "{script_extension}", - sensor_key = "all_cleaning_overall" + sensor_key = "all_cleaning_overall", + target = "{target}" output: - "data/processed/features/all_participants/all_sensor_features_cleaned_{provider_key}_{script_extension}.csv" + "data/processed/features/all_participants/all_sensor_features_cleaned_{provider_key}_{script_extension}_({target}).csv" script: "../src/features/entry.{params.script_extension}" - -rule clean_standardized_sensor_features_for_individual_participants: - input: - sensor_data = rules.merge_standardized_sensor_features_for_individual_participants.output - wildcard_constraints: - pid = "("+"|".join(config["PIDS"])+")" - params: - provider = lambda wildcards: config["ALL_CLEANING_INDIVIDUAL"]["PROVIDERS"][wildcards.provider_key.upper()], - provider_key = "{provider_key}", - script_extension = "{script_extension}", - sensor_key = "all_cleaning_individual" - output: - "data/processed/features/{pid}/z_all_sensor_features_cleaned_{provider_key}_{script_extension}.csv" - script: - "../src/features/entry.{params.script_extension}" - -rule clean_standardized_sensor_features_for_all_participants: - input: - sensor_data = rules.merge_standardized_sensor_features_for_all_participants.output - params: - provider = lambda wildcards: config["ALL_CLEANING_OVERALL"]["PROVIDERS"][wildcards.provider_key.upper()], - provider_key = "{provider_key}", - script_extension = "{script_extension}", - sensor_key = "all_cleaning_overall" - output: - "data/processed/features/all_participants/z_all_sensor_features_cleaned_{provider_key}_{script_extension}.csv" - script: - "../src/features/entry.{params.script_extension}" - diff --git a/rules/models.smk b/rules/models.smk index 3aade69a..2875297b 100644 --- a/rules/models.smk +++ b/rules/models.smk @@ -30,43 +30,23 @@ rule baseline_features: rule select_target: input: - cleaned_sensor_features = "data/processed/features/{pid}/z_all_sensor_features_cleaned_straw_py.csv" + cleaned_sensor_features = "data/processed/features/{pid}/all_sensor_features_cleaned_straw_py.csv" params: target_variable = config["PARAMS_FOR_ANALYSIS"]["TARGET"]["LABEL"] output: - "data/processed/models/individual_model/{pid}/z_input.csv" + "data/processed/models/individual_model/{pid}/input.csv" script: "../src/models/select_targets.py" rule merge_features_and_targets_for_population_model: input: - cleaned_sensor_features = "data/processed/features/all_participants/z_all_sensor_features_cleaned_straw_py.csv", + cleaned_sensor_features = "data/processed/features/all_participants/all_sensor_features_cleaned_straw_py_({target}).csv", demographic_features = expand("data/processed/features/{pid}/baseline_features.csv", pid=config["PIDS"]), params: - target_variable=config["PARAMS_FOR_ANALYSIS"]["TARGET"]["LABEL"] + target_variable="{target}" output: - "data/processed/models/population_model/z_input.csv" + "data/processed/models/population_model/input_{target}.csv" script: "../src/models/merge_features_and_targets_for_population_model.py" -# rule select_target: -# input: -# cleaned_sensor_features = "data/processed/features/{pid}/all_sensor_features_cleaned_straw_py.csv" -# params: -# target_variable = config["PARAMS_FOR_ANALYSIS"]["TARGET"]["LABEL"] -# output: -# "data/processed/models/individual_model/{pid}/input.csv" -# script: -# "../src/models/select_targets.py" - -# rule merge_features_and_targets_for_population_model: -# input: -# cleaned_sensor_features = "data/processed/features/all_participants/all_sensor_features_cleaned_straw_py.csv", -# demographic_features = expand("data/processed/features/{pid}/baseline_features.csv", pid=config["PIDS"]), -# params: -# target_variable=config["PARAMS_FOR_ANALYSIS"]["TARGET"]["LABEL"] -# output: -# "data/processed/models/population_model/input.csv" -# script: -# "../src/models/merge_features_and_targets_for_population_model.py" diff --git a/rules/preprocessing.smk b/rules/preprocessing.smk index fb583459..bf641c68 100644 --- a/rules/preprocessing.smk +++ b/rules/preprocessing.smk @@ -249,3 +249,29 @@ rule empatica_readable_datetime: "data/raw/{pid}/empatica_{sensor}_with_datetime.csv" script: "../src/data/datetime/readable_datetime.R" + + +rule extract_event_information_from_esm: + input: + esm_raw_input = "data/raw/{pid}/phone_esm_raw.csv", + pid_file = "data/external/participant_files/{pid}.yaml" + params: + stage = "extract", + pid = "{pid}" + output: + "data/raw/ers/{pid}_ers.csv", + "data/raw/ers/{pid}_stress_event_targets.csv" + script: + "../src/features/phone_esm/straw/process_user_event_related_segments.py" + +rule merge_event_related_segments_files: + input: + ers_files = expand("data/raw/ers/{pid}_ers.csv", pid=config["PIDS"]), + se_files = expand("data/raw/ers/{pid}_stress_event_targets.csv", pid=config["PIDS"]) + params: + stage = "merge" + output: + "data/external/straw_events.csv", + "data/external/stress_event_targets.csv" + script: + "../src/features/phone_esm/straw/process_user_event_related_segments.py" \ No newline at end of file diff --git a/src/data/datetime/assign_to_time_segment.R b/src/data/datetime/assign_to_time_segment.R index 4375cb73..b7b9d8da 100644 --- a/src/data/datetime/assign_to_time_segment.R +++ b/src/data/datetime/assign_to_time_segment.R @@ -5,13 +5,16 @@ options(scipen=999) assign_rows_to_segments <- function(data, segments){ # This function is used by all segment types, we use data.tables because they are fast + data <- data.table::as.data.table(data) data[, assigned_segments := ""] for(i in seq_len(nrow(segments))) { segment <- segments[i,] + data[segment$segment_start_ts<= timestamp & segment$segment_end_ts >= timestamp, assigned_segments := stringi::stri_c(assigned_segments, segment$segment_id, sep = "|")] } + data[,assigned_segments:=substring(assigned_segments, 2)] data } diff --git a/src/features/all_cleaning_individual/straw/__init__.py b/src/features/all_cleaning_individual/straw/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/src/features/all_cleaning_individual/straw/main.py b/src/features/all_cleaning_individual/straw/main.py index 6ba3ba5e..5578aac7 100644 --- a/src/features/all_cleaning_individual/straw/main.py +++ b/src/features/all_cleaning_individual/straw/main.py @@ -1,88 +1,174 @@ import pandas as pd import numpy as np -import math, sys +import math, sys, random +import yaml + +from sklearn.impute import KNNImputer +from sklearn.preprocessing import StandardScaler +import matplotlib.pyplot as plt +import seaborn as sns + +sys.path.append('/rapids/') +from src.features import empatica_data_yield as edy + +pd.set_option('display.max_columns', 20) def straw_cleaning(sensor_data_files, provider): features = pd.read_csv(sensor_data_files["sensor_data"][0]) - - # TODO: reorder the cleaning steps so it makes sense for the analysis - # TODO: add conditions that differentiates cleaning steps for standardized and nonstandardized features, for this - # the snakemake rules will also have to come with additional parameter (in rules/features.smk) - - # Impute selected features event - impute_phone_features = provider["IMPUTE_PHONE_SELECTED_EVENT_FEATURES"] - if impute_phone_features["COMPUTE"]: - if not 'phone_data_yield_rapids_ratiovalidyieldedminutes' in features.columns: - raise KeyError("RAPIDS provider needs to impute the selected event features based on phone_data_yield_rapids_ratiovalidyieldedminutes column, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyieldedminutes' in [FEATURES].") - - # TODO: if the type of the imputation will vary for different groups of features make conditional imputations here - phone_cols = [col for col in features if \ - col.startswith('phone_applications_foreground_rapids_') or - col.startswith('phone_battery_rapids_') or - col.startswith('phone_calls_rapids_') or - col.startswith('phone_keyboard_rapids_') or - col.startswith('phone_messages_rapids_') or - col.startswith('phone_screen_rapids_') or - col.startswith('phone_wifi_')] - - mask = features['phone_data_yield_rapids_ratiovalidyieldedminutes'] > impute_phone_features['MIN_DATA_YIELDED_MINUTES_TO_IMPUTE'] - features.loc[mask, phone_cols] = impute(features[mask][phone_cols], method=impute_phone_features["TYPE"].lower()) - - # Drop rows with the value of data_yield_column less than data_yield_ratio_threshold - data_yield_unit = provider["DATA_YIELD_FEATURE"].split("_")[3].lower() - data_yield_column = "phone_data_yield_rapids_ratiovalidyielded" + data_yield_unit - - if not data_yield_column in features.columns: - raise KeyError(f"RAPIDS provider needs to impute the selected event features based on {data_yield_column} column, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded{data_yield_unit}' in [FEATURES].") - - if provider["DATA_YIELD_RATIO_THRESHOLD"]: - features = features[features[data_yield_column] >= provider["DATA_YIELD_RATIO_THRESHOLD"]] - - esm_cols = features.loc[:, features.columns.str.startswith('phone_esm')] # For later preservation of esm_cols - - # Remove cols if threshold of NaN values is passed - features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]] - # Remove cols where variance is 0 - if provider["COLS_VAR_THRESHOLD"]: - features.drop(features.std()[features.std() == 0].index.values, axis=1, inplace=True) + esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns + + with open('config.yaml', 'r') as stream: + config = yaml.load(stream, Loader=yaml.FullLoader) + + excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime'] + + # (1) FILTER_OUT THE ROWS THAT DO NOT HAVE THE TARGET COLUMN AVAILABLE + if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']: + target = config['PARAMS_FOR_ANALYSIS']['TARGET']['LABEL'] # get target label from config + 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 + phone_data_yield_unit = provider["PHONE_DATA_YIELD_FEATURE"].split("_")[3].lower() + phone_data_yield_column = "phone_data_yield_rapids_ratiovalidyielded" + phone_data_yield_unit + + features = edy.calculate_empatica_data_yield(features) + + if not phone_data_yield_column in features.columns and not "empatica_data_yield" in features.columns: + raise KeyError(f"RAPIDS provider needs to clean the selected event features based on {phone_data_yield_column} and empatica_data_yield columns. For phone data yield, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded{data_yield_unit}' in [FEATURES].") + + # Drop rows where phone data yield is less then given threshold + if provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]: + features = features[features[phone_data_yield_column] >= provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True) + # Drop rows where empatica data yield is less then given threshold + if provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]: + features = features[features["empatica_data_yield"] >= provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True) + + if features.empty: + return features + + # (2.2) DO THE ROWS CONSIST OF ENOUGH NON-NAN VALUES? + min_count = math.ceil((1 - provider["ROWS_NAN_THRESHOLD"]) * features.shape[1]) # minimal not nan values in row + features.dropna(axis=0, thresh=min_count, inplace=True) # Thresh => at least this many not-nans + + # (3) REMOVE COLS IF THEIR NAN THRESHOLD IS PASSED (should be <= if even all NaN columns must be preserved - this solution now drops columns with all NaN rows) + esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns + + features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]] + # Preserve esm cols if deleted (has to come after drop cols operations) for esm in esm_cols: if esm not in features: features[esm] = esm_cols[esm] - - # Drop highly correlated features - To-Do še en thershold var, ki je v config + kako se tretirajo NaNs? + + # (4) CONTEXTUAL IMPUTATION + + # Impute selected phone features with a high number + impute_w_hn = [col for col in features.columns if \ + "timeoffirstuse" in col or + "timeoflastuse" in col or + "timefirstcall" in col or + "timelastcall" in col or + "firstuseafter" in col or + "timefirstmessages" in col or + "timelastmessages" in col] + features[impute_w_hn] = features[impute_w_hn].fillna(1500) + + + # Impute special case (mostcommonactivity) and (homelabel) + impute_w_sn = [col for col in features.columns if "mostcommonactivity" in col] + features[impute_w_sn] = features[impute_w_sn].fillna(4) # Special case of imputation - nominal/ordinal value + + impute_w_sn2 = [col for col in features.columns if "homelabel" in col] + features[impute_w_sn2] = features[impute_w_sn2].fillna(1) # Special case of imputation - nominal/ordinal value + + impute_w_sn3 = [col for col in features.columns if "loglocationvariance" in col] + features[impute_w_sn2] = features[impute_w_sn2].fillna(-1000000) # Special case of imputation - nominal/ordinal value + + + # Impute selected phone features with 0 + impute_zero = [col for col in features if \ + col.startswith('phone_applications_foreground_rapids_') or + col.startswith('phone_battery_rapids_') or + col.startswith('phone_bluetooth_rapids_') or + col.startswith('phone_light_rapids_') or + col.startswith('phone_calls_rapids_') or + col.startswith('phone_messages_rapids_') or + col.startswith('phone_screen_rapids_') or + col.startswith('phone_wifi_visible')] + + features[impute_zero+list(esm_cols.columns)] = features[impute_zero+list(esm_cols.columns)].fillna(0) + + ## (5) STANDARDIZATION + if provider["STANDARDIZATION"]: + features.loc[:, ~features.columns.isin(excluded_columns)] = StandardScaler().fit_transform(features.loc[:, ~features.columns.isin(excluded_columns)]) + + # (6) IMPUTATION: IMPUTE DATA WITH KNN METHOD + impute_cols = [col for col in features.columns if col not in excluded_columns] + features.reset_index(drop=True, inplace=True) + features[impute_cols] = impute(features[impute_cols], method="knn") + + # (7) REMOVE COLS WHERE VARIANCE IS 0 + esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] + + if provider["COLS_VAR_THRESHOLD"]: + features.drop(features.std()[features.std() == 0].index.values, axis=1, inplace=True) + + fe5 = features.copy() + + # (8) DROP HIGHLY CORRELATED FEATURES drop_corr_features = provider["DROP_HIGHLY_CORRELATED_FEATURES"] - if drop_corr_features["COMPUTE"]: + if drop_corr_features["COMPUTE"] and features.shape[0]: # If small amount of segments (rows) is present, do not execute correlation check numerical_cols = features.select_dtypes(include=np.number).columns.tolist() # Remove columns where NaN count threshold is passed valid_features = features[numerical_cols].loc[:, features[numerical_cols].isna().sum() < drop_corr_features['MIN_OVERLAP_FOR_CORR_THRESHOLD'] * features[numerical_cols].shape[0]] - cor_matrix = valid_features.corr(method='spearman').abs() - upper_tri = cor_matrix.where(np.triu(np.ones(cor_matrix.shape), k=1).astype(np.bool)) - to_drop = [column for column in upper_tri.columns if any(upper_tri[column] > drop_corr_features["CORR_THRESHOLD"])] + corr_matrix = valid_features.corr().abs() + upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(np.bool)) + to_drop = [column for column in upper.columns if any(upper[column] > drop_corr_features["CORR_THRESHOLD"])] features.drop(to_drop, axis=1, inplace=True) - # Remove rows if threshold of NaN values is passed - min_count = math.ceil((1 - provider["ROWS_NAN_THRESHOLD"]) * features.shape[1]) # minimal not nan values in row - features.dropna(axis=0, thresh=min_count, inplace=True) + # Preserve esm cols if deleted (has to come after drop cols operations) + for esm in esm_cols: + if esm not in features: + features[esm] = esm_cols[esm] + + # (9) VERIFY IF THERE ARE ANY NANS LEFT IN THE DATAFRAME + if features.isna().any().any(): + raise ValueError("There are still some NaNs present in the dataframe. Please check for implementation errors.") return features def impute(df, method='zero'): - def k_nearest(df): # TODO: if needed, implement k-nearest imputation / interpolation - pass + def k_nearest(df): + pd.set_option('display.max_columns', None) + imputer = KNNImputer(n_neighbors=3) + return pd.DataFrame(imputer.fit_transform(df), columns=df.columns) - return { # rest of the columns should be imputed with the selected method + return { 'zero': df.fillna(0), + 'high_number': df.fillna(1500), 'mean': df.fillna(df.mean()), 'median': df.fillna(df.median()), - 'k-nearest': k_nearest(df) + 'knn': k_nearest(df) }[method] - + +def graph_bf_af(features, phase_name, plt_flag=False): + if plt_flag: + sns.set(rc={"figure.figsize":(16, 8)}) + sns.heatmap(features.isna(), cbar=False) #features.select_dtypes(include=np.number) + plt.savefig(f'features_overall_nans_{phase_name}.png', bbox_inches='tight') + + print(f"\n-------------{phase_name}-------------") + print("Rows number:", features.shape[0]) + print("Columns number:", len(features.columns)) + print("---------------------------------------------\n") diff --git a/src/features/all_cleaning_overall/straw/__init__.py b/src/features/all_cleaning_overall/straw/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/src/features/all_cleaning_overall/straw/main.py b/src/features/all_cleaning_overall/straw/main.py index 6ba3ba5e..1362358d 100644 --- a/src/features/all_cleaning_overall/straw/main.py +++ b/src/features/all_cleaning_overall/straw/main.py @@ -1,88 +1,261 @@ import pandas as pd import numpy as np -import math, sys +import math, sys, random, warnings, yaml + +from sklearn.impute import KNNImputer +from sklearn.preprocessing import StandardScaler, minmax_scale +import matplotlib.pyplot as plt +import seaborn as sns + +sys.path.append('/rapids/') +from src.features import empatica_data_yield as edy + +def straw_cleaning(sensor_data_files, provider, target): -def straw_cleaning(sensor_data_files, provider): - features = pd.read_csv(sensor_data_files["sensor_data"][0]) - # TODO: reorder the cleaning steps so it makes sense for the analysis - # TODO: add conditions that differentiates cleaning steps for standardized and nonstandardized features, for this - # the snakemake rules will also have to come with additional parameter (in rules/features.smk) + with open('config.yaml', 'r') as stream: + config = yaml.load(stream, Loader=yaml.FullLoader) - # Impute selected features event - impute_phone_features = provider["IMPUTE_PHONE_SELECTED_EVENT_FEATURES"] - if impute_phone_features["COMPUTE"]: - if not 'phone_data_yield_rapids_ratiovalidyieldedminutes' in features.columns: - raise KeyError("RAPIDS provider needs to impute the selected event features based on phone_data_yield_rapids_ratiovalidyieldedminutes column, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyieldedminutes' in [FEATURES].") - - # TODO: if the type of the imputation will vary for different groups of features make conditional imputations here - phone_cols = [col for col in features if \ - col.startswith('phone_applications_foreground_rapids_') or - col.startswith('phone_battery_rapids_') or - col.startswith('phone_calls_rapids_') or - col.startswith('phone_keyboard_rapids_') or - col.startswith('phone_messages_rapids_') or - col.startswith('phone_screen_rapids_') or - col.startswith('phone_wifi_')] + esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns - mask = features['phone_data_yield_rapids_ratiovalidyieldedminutes'] > impute_phone_features['MIN_DATA_YIELDED_MINUTES_TO_IMPUTE'] - features.loc[mask, phone_cols] = impute(features[mask][phone_cols], method=impute_phone_features["TYPE"].lower()) + excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime'] - # Drop rows with the value of data_yield_column less than data_yield_ratio_threshold - data_yield_unit = provider["DATA_YIELD_FEATURE"].split("_")[3].lower() - data_yield_column = "phone_data_yield_rapids_ratiovalidyielded" + data_yield_unit + graph_bf_af(features, "1target_rows_before") - if not data_yield_column in features.columns: - raise KeyError(f"RAPIDS provider needs to impute the selected event features based on {data_yield_column} column, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded{data_yield_unit}' in [FEATURES].") - - if provider["DATA_YIELD_RATIO_THRESHOLD"]: - features = features[features[data_yield_column] >= provider["DATA_YIELD_RATIO_THRESHOLD"]] - - esm_cols = features.loc[:, features.columns.str.startswith('phone_esm')] # For later preservation of esm_cols - - # Remove cols if threshold of NaN values is passed - features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]] + # (1.0) OVERRIDE STRESSFULNESS EVENT TARGETS IF ERS SEGMENTING_METHOD IS "STRESS_EVENT" + if config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["SEGMENTING_METHOD"] == "stress_event": - # Remove cols where variance is 0 + stress_events_targets = pd.read_csv("data/external/stress_event_targets.csv") + + if "appraisal_stressfulness_event_mean" in config['PARAMS_FOR_ANALYSIS']['TARGET']['ALL_LABELS']: + features.drop(columns=['phone_esm_straw_appraisal_stressfulness_event_mean'], inplace=True) + features = features.merge(stress_events_targets[["label", "appraisal_stressfulness_event"]] \ + .rename(columns={'label': 'local_segment_label'}), on=['local_segment_label'], how='inner') \ + .rename(columns={'appraisal_stressfulness_event': 'phone_esm_straw_appraisal_stressfulness_event_mean'}) + + if "appraisal_threat_mean" in config['PARAMS_FOR_ANALYSIS']['TARGET']['ALL_LABELS']: + features.drop(columns=['phone_esm_straw_appraisal_threat_mean'], inplace=True) + features = features.merge(stress_events_targets[["label", "appraisal_threat"]] \ + .rename(columns={'label': 'local_segment_label'}), on=['local_segment_label'], how='inner') \ + .rename(columns={'appraisal_threat': 'phone_esm_straw_appraisal_threat_mean'}) + + if "appraisal_challenge_mean" in config['PARAMS_FOR_ANALYSIS']['TARGET']['ALL_LABELS']: + features.drop(columns=['phone_esm_straw_appraisal_challenge_mean'], inplace=True) + features = features.merge(stress_events_targets[["label", "appraisal_challenge"]] \ + .rename(columns={'label': 'local_segment_label'}), on=['local_segment_label'], how='inner') \ + .rename(columns={'appraisal_challenge': 'phone_esm_straw_appraisal_challenge_mean'}) + + esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns + + # (1.1) FILTER_OUT THE ROWS THAT DO NOT HAVE THE TARGET COLUMN AVAILABLE + if config['PARAMS_FOR_ANALYSIS']['TARGET']['COMPUTE']: + features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True) + + if features.empty: + return pd.DataFrame(columns=excluded_columns) + + graph_bf_af(features, "2target_rows_after") + + # (2) QUALITY CHECK (DATA YIELD COLUMN) drops 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_column = "phone_data_yield_rapids_ratiovalidyielded" + phone_data_yield_unit + + features = edy.calculate_empatica_data_yield(features) + + if not phone_data_yield_column in features.columns and not "empatica_data_yield" in features.columns: + raise KeyError(f"RAPIDS provider needs to clean the selected event features based on {phone_data_yield_column} and empatica_data_yield columns. For phone data yield, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded{data_yield_unit}' in [FEATURES].") + + hist = features[["empatica_data_yield", phone_data_yield_column]].hist() + plt.savefig(f'phone_E4_histogram.png', bbox_inches='tight') + + # Drop rows where phone data yield is less then given threshold + if provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]: + hist = features[phone_data_yield_column].hist(bins=5) + plt.close() + features = features[features[phone_data_yield_column] >= provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True) + + # Drop rows where empatica data yield is less then given threshold + if provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]: + features = features[features["empatica_data_yield"] >= provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]].reset_index(drop=True) + + if features.empty: + return pd.DataFrame(columns=excluded_columns) + + graph_bf_af(features, "3data_yield_drop_rows") + + if features.empty: + return pd.DataFrame(columns=excluded_columns) + + # (3) CONTEXTUAL IMPUTATION + + # Impute selected phone features with a high number + impute_w_hn = [col for col in features.columns if \ + "timeoffirstuse" in col or + "timeoflastuse" in col or + "timefirstcall" in col or + "timelastcall" in col or + "firstuseafter" in col or + "timefirstmessages" in col or + "timelastmessages" in col] + features[impute_w_hn] = features[impute_w_hn].fillna(1500) + + # Impute special case (mostcommonactivity) and (homelabel) + impute_w_sn = [col for col in features.columns if "mostcommonactivity" in col] + features[impute_w_sn] = features[impute_w_sn].fillna(4) # Special case of imputation - nominal/ordinal value + + impute_w_sn2 = [col for col in features.columns if "homelabel" in col] + features[impute_w_sn2] = features[impute_w_sn2].fillna(1) # Special case of imputation - nominal/ordinal value + + impute_w_sn3 = [col for col in features.columns if "loglocationvariance" in col] + features[impute_w_sn3] = features[impute_w_sn3].fillna(-1000000) # Special case of imputation - loglocation + + # Impute location features + impute_locations = [col for col in features \ + if col.startswith('phone_locations_doryab_') and + 'radiusgyration' not in col + ] + + # Impute selected phone, location, and esm features with 0 + impute_zero = [col for col in features if \ + col.startswith('phone_applications_foreground_rapids_') or + col.startswith('phone_activity_recognition_') or + col.startswith('phone_battery_rapids_') or + col.startswith('phone_bluetooth_rapids_') or + col.startswith('phone_light_rapids_') or + col.startswith('phone_calls_rapids_') or + col.startswith('phone_messages_rapids_') or + col.startswith('phone_screen_rapids_') or + col.startswith('phone_bluetooth_doryab_') or + col.startswith('phone_wifi_visible') + ] + + features[impute_zero+impute_locations+list(esm_cols.columns)] = features[impute_zero+impute_locations+list(esm_cols.columns)].fillna(0) + + pd.set_option('display.max_rows', None) + + graph_bf_af(features, "4context_imp") + + # (4) REMOVE COLS IF THEIR NAN THRESHOLD IS PASSED (should be <= if even all NaN columns must be preserved - this solution now drops columns with all NaN rows) + esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] # Get target (esm) columns + + features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]] + + graph_bf_af(features, "5too_much_nans_cols") + # (5) REMOVE COLS WHERE VARIANCE IS 0 + if provider["COLS_VAR_THRESHOLD"]: features.drop(features.std()[features.std() == 0].index.values, axis=1, inplace=True) - + + graph_bf_af(features, "6variance_drop") + # Preserve esm cols if deleted (has to come after drop cols operations) for esm in esm_cols: if esm not in features: features[esm] = esm_cols[esm] - # Drop highly correlated features - To-Do še en thershold var, ki je v config + kako se tretirajo NaNs? + # (6) DO THE ROWS CONSIST OF ENOUGH NON-NAN VALUES? + min_count = math.ceil((1 - provider["ROWS_NAN_THRESHOLD"]) * features.shape[1]) # minimal not nan values in row + features.dropna(axis=0, thresh=min_count, inplace=True) # Thresh => at least this many not-nans + + graph_bf_af(features, "7too_much_nans_rows") + + if features.empty: + return pd.DataFrame(columns=excluded_columns) + + # (7) STANDARDIZATION + if provider["STANDARDIZATION"]: + nominal_cols = [col for col in features.columns if "mostcommonactivity" in col or "homelabel" in col] # Excluded nominal features + # Expected warning within this code block + with warnings.catch_warnings(): + warnings.simplefilter("ignore", category=RuntimeWarning) + features.loc[:, ~features.columns.isin(excluded_columns + ["pid"] + nominal_cols)] = \ + features.loc[:, ~features.columns.isin(excluded_columns + nominal_cols)].groupby('pid').transform(lambda x: StandardScaler().fit_transform(x.values[:,np.newaxis]).ravel()) + + graph_bf_af(features, "8standardization") + + # (8) IMPUTATION: IMPUTE DATA WITH KNN METHOD + features.reset_index(drop=True, inplace=True) + impute_cols = [col for col in features.columns if col not in excluded_columns and col != "pid"] + + features[impute_cols] = impute(features[impute_cols], method="knn") + + graph_bf_af(features, "9knn_after") + + + # (9) DROP HIGHLY CORRELATED FEATURES + esm_cols = features.loc[:, features.columns.str.startswith('phone_esm_straw')] + drop_corr_features = provider["DROP_HIGHLY_CORRELATED_FEATURES"] - if drop_corr_features["COMPUTE"]: + if drop_corr_features["COMPUTE"] and features.shape[0] > 5: # If small amount of segments (rows) is present, do not execute correlation check numerical_cols = features.select_dtypes(include=np.number).columns.tolist() # Remove columns where NaN count threshold is passed valid_features = features[numerical_cols].loc[:, features[numerical_cols].isna().sum() < drop_corr_features['MIN_OVERLAP_FOR_CORR_THRESHOLD'] * features[numerical_cols].shape[0]] - cor_matrix = valid_features.corr(method='spearman').abs() - upper_tri = cor_matrix.where(np.triu(np.ones(cor_matrix.shape), k=1).astype(np.bool)) - to_drop = [column for column in upper_tri.columns if any(upper_tri[column] > drop_corr_features["CORR_THRESHOLD"])] + corr_matrix = valid_features.corr().abs() + upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(np.bool)) + to_drop = [column for column in upper.columns if any(upper[column] > drop_corr_features["CORR_THRESHOLD"])] + + # sns.heatmap(corr_matrix, cmap="YlGnBu") + # plt.savefig(f'correlation_matrix.png', bbox_inches='tight') + # plt.close() + + # s = corr_matrix.unstack() + # so = s.sort_values(ascending=False) + + # pd.set_option('display.max_rows', None) + # sorted_upper = upper.unstack().sort_values(ascending=False) + # print(sorted_upper[sorted_upper > drop_corr_features["CORR_THRESHOLD"]]) features.drop(to_drop, axis=1, inplace=True) - # Remove rows if threshold of NaN values is passed - min_count = math.ceil((1 - provider["ROWS_NAN_THRESHOLD"]) * features.shape[1]) # minimal not nan values in row - features.dropna(axis=0, thresh=min_count, inplace=True) + # Preserve esm cols if deleted (has to come after drop cols operations) + for esm in esm_cols: + if esm not in features: + features[esm] = esm_cols[esm] + + graph_bf_af(features, "10correlation_drop") + + # Transform categorical columns to category dtype + + cat1 = [col for col in features.columns if "mostcommonactivity" in col] + if cat1: # Transform columns to category dtype (mostcommonactivity) + features[cat1] = features[cat1].astype(int).astype('category') + + cat2 = [col for col in features.columns if "homelabel" in col] + if cat2: # Transform columns to category dtype (homelabel) + features[cat2] = features[cat2].astype(int).astype('category') + + # (10) VERIFY IF THERE ARE ANY NANS LEFT IN THE DATAFRAME + if features.isna().any().any(): + raise ValueError("There are still some NaNs present in the dataframe. Please check for implementation errors.") return features def impute(df, method='zero'): - def k_nearest(df): # TODO: if needed, implement k-nearest imputation / interpolation - pass + def k_nearest(df): + imputer = KNNImputer(n_neighbors=3) + return pd.DataFrame(imputer.fit_transform(df), columns=df.columns) - return { # rest of the columns should be imputed with the selected method + return { 'zero': df.fillna(0), + 'high_number': df.fillna(1500), 'mean': df.fillna(df.mean()), 'median': df.fillna(df.median()), - 'k-nearest': k_nearest(df) + 'knn': k_nearest(df) }[method] - + +def graph_bf_af(features, phase_name, plt_flag=False): + if plt_flag: + sns.set(rc={"figure.figsize":(16, 8)}) + sns.heatmap(features.isna(), cbar=False) #features.select_dtypes(include=np.number) + plt.savefig(f'features_overall_nans_{phase_name}.png', bbox_inches='tight') + + print(f"\n-------------{phase_name}-------------") + print("Rows number:", features.shape[0]) + print("Columns number:", len(features.columns)) + print("NaN values:", features.isna().sum().sum()) + print("---------------------------------------------\n") diff --git a/src/features/cr_features_helper_methods.py b/src/features/cr_features_helper_methods.py index 9e96c497..7bf02254 100644 --- a/src/features/cr_features_helper_methods.py +++ b/src/features/cr_features_helper_methods.py @@ -21,7 +21,7 @@ def extract_second_order_features(intraday_features, so_features_names, prefix=" so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).median().add_suffix("_SO_median")], axis=1) if "sd" in so_features_names: - so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).std().add_suffix("_SO_sd")], axis=1) + so_features = pd.concat([so_features, intraday_features.drop(prefix+"level_1", axis=1).groupby(groupby_cols).std().fillna(0).add_suffix("_SO_sd")], axis=1) if "nlargest" in so_features_names: # largest 5 -- maybe there is a faster groupby solution? for column in intraday_features.loc[:, ~intraday_features.columns.isin(groupby_cols+[prefix+"level_1"])]: diff --git a/src/features/empatica_accelerometer/cr/main.py b/src/features/empatica_accelerometer/cr/main.py index 77d18bfe..372a0e03 100644 --- a/src/features/empatica_accelerometer/cr/main.py +++ b/src/features/empatica_accelerometer/cr/main.py @@ -43,7 +43,11 @@ def extract_acc_features_from_intraday_data(acc_intraday_data, features, window_ def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs): - acc_intraday_data = pd.read_csv(sensor_data_files["sensor_data"]) + + data_types = {'local_timezone': 'str', 'device_id': 'str', 'timestamp': 'int64', 'double_values_0': 'float64', + 'double_values_1': 'float64', 'double_values_2': 'float64', 'local_date_time': 'str', 'local_date': "str", + 'local_time': "str", 'local_hour': "str", 'local_minute': "str", 'assigned_segments': "str"} + acc_intraday_data = pd.read_csv(sensor_data_files["sensor_data"], dtype=data_types) requested_intraday_features = provider["FEATURES"] diff --git a/src/features/empatica_data_yield.py b/src/features/empatica_data_yield.py new file mode 100644 index 00000000..2df2bcd2 --- /dev/null +++ b/src/features/empatica_data_yield.py @@ -0,0 +1,32 @@ +import pandas as pd +import numpy as np +from datetime import datetime + +import sys, yaml + +def calculate_empatica_data_yield(features): # TODO + + # Get time segment duration in seconds from all segments in features dataframe + datetime_start = pd.to_datetime(features['local_segment_start_datetime'], format='%Y-%m-%d %H:%M:%S') + datetime_end = pd.to_datetime(features['local_segment_end_datetime'], format='%Y-%m-%d %H:%M:%S') + tseg_duration = (datetime_end - datetime_start).dt.total_seconds() + + with open('config.yaml', 'r') as stream: + config = yaml.load(stream, Loader=yaml.FullLoader) + + sensors = ["EMPATICA_ACCELEROMETER", "EMPATICA_TEMPERATURE", "EMPATICA_ELECTRODERMAL_ACTIVITY", "EMPATICA_INTER_BEAT_INTERVAL"] + for sensor in sensors: + features[f"{sensor.lower()}_data_yield"] = \ + (features[f"{sensor.lower()}_cr_SO_windowsCount"] * config[sensor]["PROVIDERS"]["CR"]["WINDOWS"]["WINDOW_LENGTH"]) / tseg_duration \ + if f'{sensor.lower()}_cr_SO_windowsCount' in features else 0 + + empatica_data_yield_cols = [sensor.lower() + "_data_yield" for sensor in sensors] + pd.set_option('display.max_rows', None) + + # Assigns 1 to values that are over 1 (in case of windows not being filled fully) + features[empatica_data_yield_cols] = features[empatica_data_yield_cols].apply(lambda x: [y if y <= 1 or np.isnan(y) else 1 for y in x]) + + features["empatica_data_yield"] = features[empatica_data_yield_cols].mean(axis=1).fillna(0) + features.drop(empatica_data_yield_cols, axis=1, inplace=True) # In case of if the advanced operations will later not be needed (e.g., weighted average) + + return features diff --git a/src/features/empatica_electrodermal_activity/cr/main.py b/src/features/empatica_electrodermal_activity/cr/main.py index 0b09f02b..4f8e8379 100644 --- a/src/features/empatica_electrodermal_activity/cr/main.py +++ b/src/features/empatica_electrodermal_activity/cr/main.py @@ -44,7 +44,11 @@ def extract_eda_features_from_intraday_data(eda_intraday_data, features, window_ def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs): - eda_intraday_data = pd.read_csv(sensor_data_files["sensor_data"]) + + data_types = {'local_timezone': 'str', 'device_id': 'str', 'timestamp': 'int64', 'electrodermal_activity': 'float64', 'local_date_time': 'str', + 'local_date': "str", 'local_time': "str", 'local_hour': "str", 'local_minute': "str", 'assigned_segments': "str"} + + eda_intraday_data = pd.read_csv(sensor_data_files["sensor_data"], dtype=data_types) requested_intraday_features = provider["FEATURES"] diff --git a/src/features/empatica_inter_beat_interval/cr/main.py b/src/features/empatica_inter_beat_interval/cr/main.py index 803bf3a8..7797e329 100644 --- a/src/features/empatica_inter_beat_interval/cr/main.py +++ b/src/features/empatica_inter_beat_interval/cr/main.py @@ -50,6 +50,11 @@ def extract_ibi_features_from_intraday_data(ibi_intraday_data, features, window_ def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs): + + data_types = {'local_timezone': 'str', 'device_id': 'str', 'timestamp': 'int64', 'inter_beat_interval': 'float64', 'timings': 'float64', 'local_date_time': 'str', + 'local_date': "str", 'local_time': "str", 'local_hour': "str", 'local_minute': "str", 'assigned_segments': "str"} + + temperature_intraday_data = pd.read_csv(sensor_data_files["sensor_data"], dtype=data_types) ibi_intraday_data = pd.read_csv(sensor_data_files["sensor_data"]) requested_intraday_features = provider["FEATURES"] diff --git a/src/features/empatica_temperature/cr/main.py b/src/features/empatica_temperature/cr/main.py index 36e720bd..4158e7ee 100644 --- a/src/features/empatica_temperature/cr/main.py +++ b/src/features/empatica_temperature/cr/main.py @@ -37,7 +37,10 @@ def extract_temp_features_from_intraday_data(temperature_intraday_data, features def cr_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs): - temperature_intraday_data = pd.read_csv(sensor_data_files["sensor_data"]) + data_types = {'local_timezone': 'str', 'device_id': 'str', 'timestamp': 'int64', 'temperature': 'float64', 'local_date_time': 'str', + 'local_date': "str", 'local_time': "str", 'local_hour': "str", 'local_minute': "str", 'assigned_segments': "str"} + + temperature_intraday_data = pd.read_csv(sensor_data_files["sensor_data"], dtype=data_types) requested_intraday_features = provider["FEATURES"] diff --git a/src/features/entry.py b/src/features/entry.py index 288ba168..2b995fc7 100644 --- a/src/features/entry.py +++ b/src/features/entry.py @@ -13,7 +13,10 @@ calc_windows = True if (provider.get("WINDOWS", False) and provider["WINDOWS"].g if sensor_key == "all_cleaning_individual" or sensor_key == "all_cleaning_overall": # Data cleaning - sensor_features = run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files) + if "overall" in sensor_key: + sensor_features = run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files, snakemake.params["target"]) + else: + sensor_features = run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files) else: # Extract sensor features del sensor_data_files["time_segments_labels"] diff --git a/src/features/phone_activity_recognition/rapids/main.py b/src/features/phone_activity_recognition/rapids/main.py index 063061fe..e5752388 100644 --- a/src/features/phone_activity_recognition/rapids/main.py +++ b/src/features/phone_activity_recognition/rapids/main.py @@ -37,6 +37,6 @@ def rapids_features(sensor_data_files, time_segment, provider, filter_data_by_se ar_features.index.names = ["local_segment"] ar_features = ar_features.reset_index() - ar_features.fillna(value={"count": 0, "countuniqueactivities": 0, "durationstationary": 0, "durationmobile": 0, "durationvehicle": 0}, inplace=True) + ar_features.fillna(value={"count": 0, "countuniqueactivities": 0, "durationstationary": 0, "durationmobile": 0, "durationvehicle": 0, "mostcommonactivity": 4}, inplace=True) return ar_features diff --git a/src/features/phone_applications_foreground/rapids/main.py b/src/features/phone_applications_foreground/rapids/main.py index f35fa066..d9204547 100644 --- a/src/features/phone_applications_foreground/rapids/main.py +++ b/src/features/phone_applications_foreground/rapids/main.py @@ -9,19 +9,19 @@ def compute_features(filtered_data, apps_type, requested_features, apps_features if "timeoffirstuse" in requested_features: time_first_event = filtered_data.sort_values(by="timestamp", ascending=True).drop_duplicates(subset="local_segment", keep="first").set_index("local_segment") if time_first_event.empty: - apps_features["timeoffirstuse" + apps_type] = np.nan + apps_features["timeoffirstuse" + apps_type] = 1500 # np.nan else: apps_features["timeoffirstuse" + apps_type] = time_first_event["local_hour"] * 60 + time_first_event["local_minute"] if "timeoflastuse" in requested_features: time_last_event = filtered_data.sort_values(by="timestamp", ascending=False).drop_duplicates(subset="local_segment", keep="first").set_index("local_segment") if time_last_event.empty: - apps_features["timeoflastuse" + apps_type] = np.nan + apps_features["timeoflastuse" + apps_type] = 1500 # np.nan else: apps_features["timeoflastuse" + apps_type] = time_last_event["local_hour"] * 60 + time_last_event["local_minute"] if "frequencyentropy" in requested_features: apps_with_count = filtered_data.groupby(["local_segment","application_name"]).count().sort_values(by="timestamp", ascending=False).reset_index() if (len(apps_with_count.index) < 2 ): - apps_features["frequencyentropy" + apps_type] = np.nan + apps_features["frequencyentropy" + apps_type] = 0 # np.nan else: apps_features["frequencyentropy" + apps_type] = apps_with_count.groupby("local_segment")["timestamp"].agg(entropy) if "countevent" in requested_features: @@ -43,6 +43,7 @@ def compute_features(filtered_data, apps_type, requested_features, apps_features apps_features["sumduration" + apps_type] = filtered_data.groupby(by = ["local_segment"])["duration"].sum() apps_features.index.names = ["local_segment"] + return apps_features def process_app_features(data, requested_features, time_segment, provider, filter_data_by_segment): diff --git a/src/features/phone_bluetooth/doryab/main.py b/src/features/phone_bluetooth/doryab/main.py index 6efec19a..bbc7a47c 100644 --- a/src/features/phone_bluetooth/doryab/main.py +++ b/src/features/phone_bluetooth/doryab/main.py @@ -14,8 +14,8 @@ def deviceFeatures(devices, ownership, common_devices, features_to_compute, feat features = features.join(device_value_counts.groupby("local_segment")["bt_address"].nunique().to_frame("uniquedevices" + ownership), how="outer") if "meanscans" in features_to_compute: features = features.join(device_value_counts.groupby("local_segment")["scans"].mean().to_frame("meanscans" + ownership), how="outer") - if "stdscans" in features_to_compute: - features = features.join(device_value_counts.groupby("local_segment")["scans"].std().to_frame("stdscans" + ownership), how="outer") + if "stdscans" in features_to_compute: + features = features.join(device_value_counts.groupby("local_segment")["scans"].std().to_frame("stdscans" + ownership).fillna(0), how="outer") # Most frequent device within segments, across segments, and across dataset if "countscansmostfrequentdevicewithinsegments" in features_to_compute: features = features.join(device_value_counts.groupby("local_segment")["scans"].max().to_frame("countscansmostfrequentdevicewithinsegments" + ownership), how="outer") diff --git a/src/features/phone_calls/rapids/main.R b/src/features/phone_calls/rapids/main.R index d793f706..d6c8ab88 100644 --- a/src/features/phone_calls/rapids/main.R +++ b/src/features/phone_calls/rapids/main.R @@ -88,6 +88,16 @@ rapids_features <- function(sensor_data_files, time_segment, provider){ features <- call_features_of_type(calls_of_type, features_type, call_type, time_segment, requested_features) call_features <- merge(call_features, features, all=TRUE) } - call_features <- call_features %>% mutate_at(vars(contains("countmostfrequentcontact") | contains("distinctcontacts") | contains("count") | contains("sumduration") | contains("minduration") | contains("maxduration") | contains("meanduration") | contains("modeduration")), list( ~ replace_na(., 0))) + + # Fill seleted columns with a high number + time_cols <- select(call_features, contains("timefirstcall") | contains("timelastcall")) %>% + colnames(.) + + call_features <- call_features %>% + mutate_at(., time_cols, ~replace(., is.na(.), 1500)) + + # Fill NA values with 0 + call_features <- call_features %>% mutate_all(~replace(., is.na(.), 0)) + return(call_features) } \ No newline at end of file diff --git a/src/features/phone_esm/straw/esm.py b/src/features/phone_esm/straw/esm.py new file mode 100644 index 00000000..6b6d9d7c --- /dev/null +++ b/src/features/phone_esm/straw/esm.py @@ -0,0 +1,274 @@ +from collections.abc import Collection + +import numpy as np +import pandas as pd +from pytz import timezone +import datetime, json + +# from config.models import ESM, Participant +# from features import helper + +ESM_STATUS_ANSWERED = 2 + +GROUP_SESSIONS_BY = ["device_id", "esm_session"] # 'participant_id + +SESSION_STATUS_UNANSWERED = "ema_unanswered" +SESSION_STATUS_DAY_FINISHED = "day_finished" +SESSION_STATUS_COMPLETE = "ema_completed" + +ANSWER_DAY_FINISHED = "DayFinished3421" +ANSWER_DAY_OFF = "DayOff3421" +ANSWER_SET_EVENING = "DayFinishedSetEvening" + +MAX_MORNING_LENGTH = 3 +# When the participants was not yet at work at the time of the first (morning) EMA, +# only three items were answered. +# Two sleep related items and one indicating NOT starting work yet. +# Daytime EMAs are all longer, in fact they always consist of at least 6 items. + + +TZ_LJ = timezone("Europe/Ljubljana") +COLUMN_TIMESTAMP = "timestamp" +COLUMN_TIMESTAMP_ESM = "double_esm_user_answer_timestamp" + + +def get_date_from_timestamp(df_aware) -> pd.DataFrame: + """ + Transform a UNIX timestamp into a datetime (with Ljubljana timezone). + Additionally, extract only the date part, where anything until 4 AM is considered the same day. + + Parameters + ---------- + df_aware: pd.DataFrame + Any AWARE-type data as defined in models.py. + + Returns + ------- + df_aware: pd.DataFrame + The same dataframe with datetime_lj and date_lj columns added. + + """ + if COLUMN_TIMESTAMP_ESM in df_aware: + column_timestamp = COLUMN_TIMESTAMP_ESM + else: + column_timestamp = COLUMN_TIMESTAMP + + df_aware["datetime_lj"] = df_aware[column_timestamp].apply( + lambda x: datetime.datetime.fromtimestamp(x / 1000.0, tz=TZ_LJ) + ) + df_aware = df_aware.assign( + date_lj=lambda x: (x.datetime_lj - datetime.timedelta(hours=4)).dt.date + ) + # Since daytime EMAs could *theoretically* last beyond midnight, but never after 4 AM, + # the datetime is first translated to 4 h earlier. + + return df_aware + + +def preprocess_esm(df_esm: pd.DataFrame) -> pd.DataFrame: + """ + Convert timestamps into human-readable datetimes and dates + and expand the JSON column into several Pandas DF columns. + + Parameters + ---------- + df_esm: pd.DataFrame + A dataframe of esm data. + + Returns + ------- + df_esm_preprocessed: pd.DataFrame + A dataframe with added columns: datetime in Ljubljana timezone and all fields from ESM_JSON column. + """ + df_esm = get_date_from_timestamp(df_esm) + + df_esm_json = df_esm["esm_json"].apply(json.loads) + df_esm_json = pd.json_normalize(df_esm_json).drop( + columns=["esm_trigger"] + ) # The esm_trigger column is already present in the main df. + return df_esm.join(df_esm_json) + + +def classify_sessions_by_completion(df_esm_preprocessed: pd.DataFrame) -> pd.DataFrame: + """ + For each distinct EMA session, determine how the participant responded to it. + Possible outcomes are: SESSION_STATUS_UNANSWERED, SESSION_STATUS_DAY_FINISHED, and SESSION_STATUS_COMPLETE + + This is done in three steps. + + First, the esm_status is considered. + If any of the ESMs in a session has a status *other than* "answered", then this session is taken as unfinished. + + Second, the sessions which do not represent full questionnaires are identified. + These are sessions where participants only marked they are finished with the day or have not yet started working. + + Third, the sessions with only one item are marked with their trigger. + We never offered questionnaires with single items, so we can be sure these are unfinished. + + Finally, all sessions that remain are marked as completed. + By going through different possibilities in expl_esm_adherence.ipynb, this turned out to be a reasonable option. + + Parameters + ---------- + df_esm_preprocessed: pd.DataFrame + A preprocessed dataframe of esm data, which must include the session ID (esm_session). + + Returns + ------- + df_session_counts: pd.Dataframe + A dataframe of all sessions (grouped by GROUP_SESSIONS_BY) with their statuses and the number of items. + """ + sessions_grouped = df_esm_preprocessed.groupby(GROUP_SESSIONS_BY) + + # 0. First, assign all session statuses as NaN. + df_session_counts = pd.DataFrame(sessions_grouped.count()["timestamp"]).rename( + columns={"timestamp": "esm_session_count"} + ) + df_session_counts["session_response"] = np.nan + + # 1. Identify all ESMs with status other than answered. + esm_not_answered = sessions_grouped.apply( + lambda x: (x.esm_status != ESM_STATUS_ANSWERED).any() + ) + df_session_counts.loc[ + esm_not_answered, "session_response" + ] = SESSION_STATUS_UNANSWERED + + # 2. Identify non-sessions, i.e. answers about the end of the day. + non_session = sessions_grouped.apply( + lambda x: ( + (x.esm_user_answer == ANSWER_DAY_FINISHED) # I finished working for today. + | (x.esm_user_answer == ANSWER_DAY_OFF) # I am not going to work today. + | ( + x.esm_user_answer == ANSWER_SET_EVENING + ) # When would you like to answer the evening EMA? + ).any() + ) + df_session_counts.loc[non_session, "session_response"] = SESSION_STATUS_DAY_FINISHED + + # 3. Identify sessions appearing only once, as those were not true EMAs for sure. + singleton_sessions = (df_session_counts.esm_session_count == 1) & ( + df_session_counts.session_response.isna() + ) + df_session_1 = df_session_counts[singleton_sessions] + df_esm_unique_session = df_session_1.join( + df_esm_preprocessed.set_index(GROUP_SESSIONS_BY), how="left" + ) + df_esm_unique_session = df_esm_unique_session.assign( + session_response=lambda x: x.esm_trigger + )["session_response"] + df_session_counts.loc[ + df_esm_unique_session.index, "session_response" + ] = df_esm_unique_session + + # 4. Mark the remaining sessions as completed. + df_session_counts.loc[ + df_session_counts.session_response.isna(), "session_response" + ] = SESSION_STATUS_COMPLETE + + return df_session_counts + + +def classify_sessions_by_time(df_esm_preprocessed: pd.DataFrame) -> pd.DataFrame: + """ + For each EMA session, determine the time of the first user answer and its time type (morning, workday, or evening.) + + Parameters + ---------- + df_esm_preprocessed: pd.DataFrame + A preprocessed dataframe of esm data, which must include the session ID (esm_session). + + Returns + ------- + df_session_time: pd.DataFrame + A dataframe of all sessions (grouped by GROUP_SESSIONS_BY) with their time type and timestamp of first answer. + """ + df_session_time = ( + df_esm_preprocessed.sort_values(["datetime_lj"]) # "participant_id" + .groupby(GROUP_SESSIONS_BY) + .first()[["time", "datetime_lj"]] + ) + return df_session_time + + +def classify_sessions_by_completion_time( + df_esm_preprocessed: pd.DataFrame, +) -> pd.DataFrame: + """ + The point of this function is to not only classify sessions by using the previously defined functions. + It also serves to "correct" the time type of some EMA sessions. + + A morning questionnaire could seamlessly transition into a daytime questionnaire, + if the participant was already at work. + In this case, the "time" label changed mid-session. + Because of the way classify_sessions_by_time works, this questionnaire was classified as "morning". + But for all intents and purposes, it can be treated as a "daytime" EMA. + + The way this scenario is differentiated from a true "morning" questionnaire, + where the participants NOT yet at work, is by considering their length. + + Parameters + ---------- + df_esm_preprocessed: pd.DataFrame + A preprocessed dataframe of esm data, which must include the session ID (esm_session). + + Returns + ------- + df_session_counts_time: pd.DataFrame + A dataframe of all sessions (grouped by GROUP_SESSIONS_BY) with statuses, the number of items, + their time type (with some morning EMAs reclassified) and timestamp of first answer. + + """ + df_session_counts = classify_sessions_by_completion(df_esm_preprocessed) + df_session_time = classify_sessions_by_time(df_esm_preprocessed) + + df_session_counts_time = df_session_time.join(df_session_counts) + + morning_transition_to_daytime = (df_session_counts_time.time == "morning") & ( + df_session_counts_time.esm_session_count > MAX_MORNING_LENGTH + ) + + df_session_counts_time.loc[morning_transition_to_daytime, "time"] = "daytime" + + return df_session_counts_time + + +# def clean_up_esm(df_esm_preprocessed: pd.DataFrame) -> pd.DataFrame: +# """ +# This function eliminates invalid ESM responses. +# It removes unanswered ESMs and those that indicate end of work and similar. +# It also extracts a numeric answer from strings such as "4 - I strongly agree". + +# Parameters +# ---------- +# df_esm_preprocessed: pd.DataFrame +# A preprocessed dataframe of esm data. + +# Returns +# ------- +# df_esm_clean: pd.DataFrame +# A subset of the original dataframe. + +# """ +# df_esm_clean = df_esm_preprocessed[ +# df_esm_preprocessed["esm_status"] == ESM_STATUS_ANSWERED +# ] +# df_esm_clean = df_esm_clean[ +# ~df_esm_clean["esm_user_answer"].isin( +# [ANSWER_DAY_FINISHED, ANSWER_DAY_OFF, ANSWER_SET_EVENING] +# ) +# ] +# df_esm_clean["esm_user_answer_numeric"] = np.nan +# esm_type_numeric = [ +# ESM.ESM_TYPE.get("radio"), +# ESM.ESM_TYPE.get("scale"), +# ESM.ESM_TYPE.get("number"), +# ] +# df_esm_clean.loc[ +# df_esm_clean["esm_type"].isin(esm_type_numeric) +# ] = df_esm_clean.loc[df_esm_clean["esm_type"].isin(esm_type_numeric)].assign( +# esm_user_answer_numeric=lambda x: x.esm_user_answer.str.slice(stop=1).astype( +# int +# ) +# ) +# return df_esm_clean diff --git a/src/features/phone_esm/straw/main.py b/src/features/phone_esm/straw/main.py index 306bb681..8a55b8eb 100644 --- a/src/features/phone_esm/straw/main.py +++ b/src/features/phone_esm/straw/main.py @@ -42,7 +42,8 @@ def straw_features(sensor_data_files, time_segment, provider, filter_data_by_seg requested_features = provider["FEATURES"] # name of the features this function can compute requested_scales = provider["SCALES"] - base_features_names = ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support"] + base_features_names = ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support", + "appraisal_stressfulness_period", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge"] #TODO Check valid questionnaire and feature names. # the subset of requested features this function can compute features_to_compute = list(set(requested_features) & set(base_features_names)) @@ -52,7 +53,6 @@ def straw_features(sensor_data_files, time_segment, provider, filter_data_by_seg if not esm_data.empty: esm_features = pd.DataFrame() - for scale in requested_scales: questionnaire_id = QUESTIONNAIRE_IDS[scale] mask = esm_data["questionnaire_id"] == questionnaire_id @@ -60,4 +60,7 @@ def straw_features(sensor_data_files, time_segment, provider, filter_data_by_seg #TODO Create the column esm_user_score in esm_clean. Currently, this is only done when reversing. esm_features = esm_features.reset_index() + if 'index' in esm_features: # In calse of empty esm_features df + esm_features.rename(columns={'index': 'local_segment'}, inplace=True) + return esm_features diff --git a/src/features/phone_esm/straw/process_user_event_related_segments.py b/src/features/phone_esm/straw/process_user_event_related_segments.py new file mode 100644 index 00000000..353e714c --- /dev/null +++ b/src/features/phone_esm/straw/process_user_event_related_segments.py @@ -0,0 +1,220 @@ +import pandas as pd +import numpy as np +import datetime + +import math, sys, yaml + +from esm_preprocess import clean_up_esm +from esm import classify_sessions_by_completion_time, preprocess_esm + +input_data_files = dict(snakemake.input) + +def format_timestamp(x): + """This method formates inputed timestamp into format "HH MM SS". Including spaces. If there is no hours or minutes present + that part is ignored, e.g., "MM SS" or just "SS". + + Args: + x (int): unix timestamp in seconds + + Returns: + str: formatted timestamp using "HH MM SS" sintax + """ + tstring="" + space = False + if x//3600 > 0: + tstring += f"{x//3600}H" + space = True + if x % 3600 // 60 > 0: + tstring += f" {x % 3600 // 60}M" if "H" in tstring else f"{x % 3600 // 60}M" + if x % 60 > 0: + tstring += f" {x % 60}S" if "M" in tstring or "H" in tstring else f"{x % 60}S" + + return tstring + + +def extract_ers(esm_df): + """This method has two major functionalities: + (1) It prepares STRAW event-related segments file with the use of esm file. The execution protocol is depended on + the segmenting method specified in the config.yaml file. + (2) It prepares and writes csv with targets and corresponding time segments labels. This is later used + in the overall cleaning script (straw). + + Details about each segmenting method are listed below by each corresponding condition. Refer to the RAPIDS documentation for the + ERS file format: https://www.rapids.science/1.9/setup/configuration/#time-segments -> event segments + + Args: + esm_df (DataFrame): read esm file that is dependend on the current participant. + + Returns: + extracted_ers (DataFrame): dataframe with all necessary information to write event-related segments file + in the correct format. + """ + pd.set_option("display.max_rows", 20) + pd.set_option("display.max_columns", None) + + with open('config.yaml', 'r') as stream: + config = yaml.load(stream, Loader=yaml.FullLoader) + + pd.DataFrame(columns=["label", "intensity"]).to_csv(snakemake.output[1]) # Create an empty stress_events_targets file + + esm_preprocessed = clean_up_esm(preprocess_esm(esm_df)) + + # Take only ema_completed sessions responses + classified = classify_sessions_by_completion_time(esm_preprocessed) + esm_filtered_sessions = classified[classified["session_response"] == 'ema_completed'].reset_index()[['device_id', 'esm_session']] + esm_df = esm_preprocessed.loc[(esm_preprocessed['device_id'].isin(esm_filtered_sessions['device_id'])) & (esm_preprocessed['esm_session'].isin(esm_filtered_sessions['esm_session']))] + + segmenting_method = config["TIME_SEGMENTS"]["TAILORED_EVENTS"]["SEGMENTING_METHOD"] + + if segmenting_method in ["30_before", "90_before"]: # takes 30-minute peroid before the questionnaire + the duration of the questionnaire + """ '30-minutes and 90-minutes before' have the same fundamental logic with couple of deviations that will be explained below. + Both take x-minute period before the questionnaire that is summed with the questionnaire duration. + All questionnaire durations over 15 minutes are excluded from the querying. + """ + # Extract time-relevant information + extracted_ers = esm_df.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index() # questionnaire length + extracted_ers["label"] = f"straw_event_{segmenting_method}_" + snakemake.params["pid"] + "_" + extracted_ers.index.astype(str).str.zfill(3) + extracted_ers[['event_timestamp', 'device_id']] = esm_df.groupby(["device_id", "esm_session"])['timestamp'].min().reset_index()[['timestamp', 'device_id']] + extracted_ers = extracted_ers[extracted_ers["timestamp"] <= 15 * 60].reset_index(drop=True) # ensure that the longest duration of the questionnaire anwsering is 15 min + extracted_ers["shift_direction"] = -1 + + if segmenting_method == "30_before": + """The method 30-minutes before simply takes 30 minutes before the questionnaire and sums it with the questionnaire duration. + The timestamps are formatted with the help of format_timestamp() method. + """ + time_before_questionnaire = 30 * 60 # in seconds (30 minutes) + + extracted_ers["length"] = (extracted_ers["timestamp"] + time_before_questionnaire).apply(lambda x: format_timestamp(x)) + extracted_ers["shift"] = time_before_questionnaire + extracted_ers["shift"] = extracted_ers["shift"].apply(lambda x: format_timestamp(x)) + + elif segmenting_method == "90_before": + """The method 90-minutes before has an important condition. If the time between the current and the previous questionnaire is + longer then 90 minutes it takes 90 minutes, otherwise it takes the original time difference between the questionnaires. + """ + time_before_questionnaire = 90 * 60 # in seconds (90 minutes) + + extracted_ers[['end_event_timestamp', 'device_id']] = esm_df.groupby(["device_id", "esm_session"])['timestamp'].max().reset_index()[['timestamp', 'device_id']] + + extracted_ers['diffs'] = extracted_ers['event_timestamp'].astype('int64') - extracted_ers['end_event_timestamp'].shift(1, fill_value=0).astype('int64') + extracted_ers.loc[extracted_ers['diffs'] > time_before_questionnaire * 1000, 'diffs'] = time_before_questionnaire * 1000 + + extracted_ers["diffs"] = (extracted_ers["diffs"] / 1000).apply(lambda x: math.ceil(x)) + + extracted_ers["length"] = (extracted_ers["timestamp"] + extracted_ers["diffs"]).apply(lambda x: format_timestamp(x)) + extracted_ers["shift"] = extracted_ers["diffs"].apply(lambda x: format_timestamp(x)) + + elif segmenting_method == "stress_event": + """This is a special case of the method as it consists of two important parts: + (1) Generating of the ERS file (same as the methods above) and + (2) Generating targets file alongside with the correct time segment labels. + + This extracts event-related segments, depended on the event time and duration specified by the participant in the next + questionnaire. Additionally, 5 minutes before the specified start time of this event is taken to take into a account the + possiblity of the participant not remembering the start time percisely => this parameter can be manipulated with the variable + "time_before_event" which is defined below. + + By default, this method also excludes all events that are longer then 2.5 hours so that the segments are easily comparable. + """ + # Get and join required data + extracted_ers = esm_df.groupby(["device_id", "esm_session"])['timestamp'].apply(lambda x: math.ceil((x.max() - x.min()) / 1000)).reset_index().rename(columns={'timestamp': 'session_length'}) # questionnaire end timestamp + extracted_ers = extracted_ers[extracted_ers["session_length"] <= 15 * 60].reset_index(drop=True) # ensure that the longest duration of the questionnaire anwsering is 15 min + session_end_timestamp = esm_df.groupby(['device_id', 'esm_session'])['timestamp'].max().to_frame().rename(columns={'timestamp': 'session_end_timestamp'}) # questionnaire end timestamp + se_time = esm_df[esm_df.questionnaire_id == 90.].set_index(['device_id', 'esm_session'])['esm_user_answer'].to_frame().rename(columns={'esm_user_answer': 'se_time'}) + se_duration = esm_df[esm_df.questionnaire_id == 91.].set_index(['device_id', 'esm_session'])['esm_user_answer'].to_frame().rename(columns={'esm_user_answer': 'se_duration'}) + + # Extracted 3 targets that will be transfered with the csv file to the cleaning script. + se_stressfulness_event_tg = esm_df[esm_df.questionnaire_id == 87.].set_index(['device_id', 'esm_session'])['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_stressfulness_event'}) + se_threat_tg = esm_df[esm_df.questionnaire_id == 88.].groupby(["device_id", "esm_session"]).mean()['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_threat'}) + se_challenge_tg = esm_df[esm_df.questionnaire_id == 89.].groupby(["device_id", "esm_session"]).mean()['esm_user_answer_numeric'].to_frame().rename(columns={'esm_user_answer_numeric': 'appraisal_challenge'}) + + # All relevant features are joined by inner join to remove standalone columns (e.g., stressfulness event target has larger count) + extracted_ers = extracted_ers.join(session_end_timestamp, on=['device_id', 'esm_session'], how='inner') \ + .join(se_time, on=['device_id', 'esm_session'], how='inner') \ + .join(se_duration, on=['device_id', 'esm_session'], how='inner') \ + .join(se_stressfulness_event_tg, on=['device_id', 'esm_session'], how='inner') \ + .join(se_threat_tg, on=['device_id', 'esm_session'], how='inner') \ + .join(se_challenge_tg, on=['device_id', 'esm_session'], how='inner') + + + # Filter sessions that are not useful. Because of the ambiguity this excludes: + # (1) straw event times that are marked as "0 - I don't remember" + # (2) straw event durations that are marked as "0 - I don't remember" + 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 + extracted_ers.reset_index(drop=True, inplace=True) + + 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['shift_direction'] = -1 + + # Checks whether the duration is marked with "1 - It's still ongoing" which means that the end of the current questionnaire + # is taken as end time of the segment. Else the user input duration is taken. + extracted_ers['se_duration'] = \ + np.where( + extracted_ers['se_duration'].str.startswith("1 - "), + extracted_ers['session_end_timestamp'] - extracted_ers['event_timestamp'], + extracted_ers['se_duration'] + ) + + # This converts the rows of timestamps in miliseconds and the row with datetime to timestamp in seconds. + 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['shift'] = format_timestamp(time_before_event) + 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 related to stressfulness event + extracted_ers[["label", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge"]].to_csv(snakemake.output[1], index=False) + + else: + raise Exception("Please select correct target method for the event-related segments.") + extracted_ers = pd.DataFrame(columns=["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"]) + + return extracted_ers[["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"]] + + +""" +Here the code is executed - this .py file is used both for extraction of the STRAW time_segments file for the individual +participant, and also for merging all participant's files into one combined file which is later used for the time segments +to all sensors assignment. + +There are two files involved (see rules extract_event_information_from_esm and merge_event_related_segments_files in preprocessing.smk) +(1) ERS file which contains all the information about the time segment timings and +(2) targets file which has corresponding target value for the segment label which is later used to merge with other features in the cleaning script. +For more information, see the comment in the method above. +""" +if snakemake.params["stage"] == "extract": + esm_df = pd.read_csv(input_data_files['esm_raw_input']) + + extracted_ers = extract_ers(esm_df) + + extracted_ers.to_csv(snakemake.output[0], index=False) + +elif snakemake.params["stage"] == "merge": + + input_data_files = dict(snakemake.input) + straw_events = pd.DataFrame(columns=["label", "event_timestamp", "length", "shift", "shift_direction", "device_id"]) + stress_events_targets = pd.DataFrame(columns=["label", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge"]) + + for input_file in input_data_files["ers_files"]: + ers_df = pd.read_csv(input_file) + straw_events = pd.concat([straw_events, ers_df], axis=0, ignore_index=True) + + straw_events.to_csv(snakemake.output[0], index=False) + + for input_file in input_data_files["se_files"]: + se_df = pd.read_csv(input_file) + stress_events_targets = pd.concat([stress_events_targets, se_df], axis=0, ignore_index=True) + + stress_events_targets.to_csv(snakemake.output[1], index=False) + + + diff --git a/src/features/phone_light/rapids/main.py b/src/features/phone_light/rapids/main.py index 32df47ef..f5644c7e 100644 --- a/src/features/phone_light/rapids/main.py +++ b/src/features/phone_light/rapids/main.py @@ -29,7 +29,7 @@ def rapids_features(sensor_data_files, time_segment, provider, filter_data_by_se if "medianlux" in features_to_compute: light_features["medianlux"] = light_data.groupby(["local_segment"])["double_light_lux"].median() if "stdlux" in features_to_compute: - light_features["stdlux"] = light_data.groupby(["local_segment"])["double_light_lux"].std() + light_features["stdlux"] = light_data.groupby(["local_segment"])["double_light_lux"].std().fillna(0) light_features = light_features.reset_index() diff --git a/src/features/phone_locations/doryab/main.py b/src/features/phone_locations/doryab/main.py index 19a7b8d5..e4dc0117 100644 --- a/src/features/phone_locations/doryab/main.py +++ b/src/features/phone_locations/doryab/main.py @@ -37,7 +37,8 @@ def variance_and_logvariance_features(location_data, location_features): location_data["longitude_for_wvar"] = (location_data["double_longitude"] - location_data["longitude_wavg"]) ** 2 * location_data["duration"] * 60 location_features["locationvariance"] = ((location_data_grouped["latitude_for_wvar"].sum() + location_data_grouped["longitude_for_wvar"].sum()) / (location_data_grouped["duration"].sum() * 60 - 1)).fillna(0) - location_features["loglocationvariance"] = np.log10(location_features["locationvariance"]).replace(-np.inf, np.nan) + + location_features["loglocationvariance"] = np.log10(location_features["locationvariance"]).replace(-np.inf, -1000000) return location_features diff --git a/src/features/phone_messages/rapids/main.R b/src/features/phone_messages/rapids/main.R index b92769fd..d5dddc73 100644 --- a/src/features/phone_messages/rapids/main.R +++ b/src/features/phone_messages/rapids/main.R @@ -65,6 +65,15 @@ rapids_features <- function(sensor_data_files, time_segment, provider){ features <- message_features_of_type(messages_of_type, message_type, time_segment, requested_features) messages_features <- merge(messages_features, features, all=TRUE) } - messages_features <- messages_features %>% mutate_at(vars(contains("countmostfrequentcontact") | contains("distinctcontacts") | contains("count")), list( ~ replace_na(., 0))) + # Fill seleted columns with a high number + time_cols <- select(messages_features, contains("timefirstmessages") | contains("timelastmessages")) %>% + colnames(.) + + messages_features <- messages_features %>% + mutate_at(., time_cols, ~replace(., is.na(.), 1500)) + + # Fill NA values with 0 + messages_features <- messages_features %>% mutate_all(~replace(., is.na(.), 0)) + return(messages_features) } \ No newline at end of file diff --git a/src/features/phone_screen/rapids/main.py b/src/features/phone_screen/rapids/main.py index 5740e430..26580640 100644 --- a/src/features/phone_screen/rapids/main.py +++ b/src/features/phone_screen/rapids/main.py @@ -15,7 +15,7 @@ def getEpisodeDurationFeatures(screen_data, time_segment, episode, features, ref if "avgduration" in features: duration_helper = pd.concat([duration_helper, screen_data_episode.groupby(["local_segment"])[["duration"]].mean().rename(columns = {"duration":"avgduration" + episode})], axis = 1) if "stdduration" in features: - duration_helper = pd.concat([duration_helper, screen_data_episode.groupby(["local_segment"])[["duration"]].std().rename(columns = {"duration":"stdduration" + episode})], axis = 1) + duration_helper = pd.concat([duration_helper, screen_data_episode.groupby(["local_segment"])[["duration"]].std().fillna(0).rename(columns = {"duration":"stdduration" + episode})], axis = 1) if "firstuseafter" + "{0:0=2d}".format(reference_hour_first_use) in features: screen_data_episode_after_hour = screen_data_episode.copy() screen_data_episode_after_hour["hour"] = pd.to_datetime(screen_data_episode["local_start_date_time"]).dt.hour diff --git a/src/features/phone_wifi_visible/rapids/main.R b/src/features/phone_wifi_visible/rapids/main.R index 8a973809..a8a433fa 100644 --- a/src/features/phone_wifi_visible/rapids/main.R +++ b/src/features/phone_wifi_visible/rapids/main.R @@ -9,21 +9,26 @@ compute_wifi_feature <- function(data, feature, time_segment){ "countscans" = data %>% summarise(!!feature := n()), "uniquedevices" = data %>% summarise(!!feature := n_distinct(bssid))) return(data) + } else if(feature == "countscansmostuniquedevice"){ # Get the most scanned device - mostuniquedevice <- data %>% + mostuniquedevice <- data %>% + filter(bssid != "") %>% group_by(bssid) %>% mutate(N=n()) %>% ungroup() %>% filter(N == max(N)) %>% head(1) %>% # if there are multiple device with the same amount of scans pick the first one only pull(bssid) + data <- data %>% filter_data_by_segment(time_segment) + return(data %>% filter(bssid == mostuniquedevice) %>% group_by(local_segment) %>% - summarise(!!feature := n()) %>% - replace(is.na(.), 0)) + summarise(!!feature := n()) + ) + } } @@ -43,6 +48,6 @@ rapids_features <- function(sensor_data_files, time_segment, provider){ feature <- compute_wifi_feature(wifi_data, feature_name, time_segment) features <- merge(features, feature, by="local_segment", all = TRUE) } - + features <- features %>% mutate_all(~replace(., is.na(.), 0)) return(features) } diff --git a/src/features/standardization/main.py b/src/features/standardization/main.py deleted file mode 100644 index d91fca6d..00000000 --- a/src/features/standardization/main.py +++ /dev/null @@ -1,50 +0,0 @@ -import pandas as pd -import numpy as np -from sklearn.preprocessing import StandardScaler - -import sys - -sensor_data_files = dict(snakemake.input) - -provider = snakemake.params["provider"] -provider_key = snakemake.params["provider_key"] -sensor_key = snakemake.params["sensor_key"] - -pd.set_option('display.max_columns', None) - -if provider_key == "cr": - sys.path.append('/rapids/src/features/') - from cr_features_helper_methods import extract_second_order_features - - provider_main = snakemake.params["provider_main"] - prefix = sensor_key + "_" + provider_key + "_" - - windows_features_data = pd.read_csv(sensor_data_files["windows_features_data"]) - excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime', prefix + "level_1"] - - if windows_features_data.empty: - windows_features_data.to_csv(snakemake.output[1], index=False) - windows_features_data.to_csv(snakemake.output[0], index=False) - else: - windows_features_data.loc[:, ~windows_features_data.columns.isin(excluded_columns)] = StandardScaler().fit_transform(windows_features_data.loc[:, ~windows_features_data.columns.isin(excluded_columns)]) - - windows_features_data.to_csv(snakemake.output[1], index=False) - - if provider_main["WINDOWS"]["COMPUTE"] and "SECOND_ORDER_FEATURES" in provider_main["WINDOWS"]: - so_features_names = provider_main["WINDOWS"]["SECOND_ORDER_FEATURES"] - windows_so_features_data = extract_second_order_features(windows_features_data, so_features_names, prefix) - windows_so_features_data.to_csv(snakemake.output[0], index=False) - else: - pd.DataFrame().to_csv(snakemake.output[0], index=False) - -else: - for sensor_features in sensor_data_files["sensor_features"]: - if "/" + sensor_key + ".csv" in sensor_features: - sensor_data = pd.read_csv(sensor_features) - excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime'] - - if not sensor_data.empty: - sensor_data.loc[:, ~sensor_data.columns.isin(excluded_columns)] = StandardScaler().fit_transform(sensor_data.loc[:, ~sensor_data.columns.isin(excluded_columns)]) - - sensor_data.to_csv(snakemake.output[0], index=False) - break \ No newline at end of file diff --git a/src/features/utils/utils.py b/src/features/utils/utils.py index 7303ac86..8a4d2130 100644 --- a/src/features/utils/utils.py +++ b/src/features/utils/utils.py @@ -160,12 +160,16 @@ def fetch_provider_features(provider, provider_key, sensor_key, sensor_data_file return sensor_features -def run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files): +def run_provider_cleaning_script(provider, provider_key, sensor_key, sensor_data_files, target=False): from importlib import import_module, util print("{} Processing {} {}".format(rapids_log_tag, sensor_key, provider_key)) cleaning_module = import_path(provider["SRC_SCRIPT"]) cleaning_function = getattr(cleaning_module, provider_key.lower() + "_cleaning") - sensor_features = cleaning_function(sensor_data_files, provider) + + if target: + sensor_features = cleaning_function(sensor_data_files, provider, target) + else: + sensor_features = cleaning_function(sensor_data_files, provider) return sensor_features \ No newline at end of file diff --git a/src/models/helper.py b/src/models/helper.py index 61f9f666..2e007810 100644 --- a/src/models/helper.py +++ b/src/models/helper.py @@ -1,5 +1,6 @@ import pandas as pd - +import sys +import warnings def retain_target_column(df_input: pd.DataFrame, target_variable_name: str): 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] target_variable_index = esm_names.str.contains(target_variable_name) 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 z_all_sensor_features_cleaned_straw_py.csv") + warnings.warn(f"The requested target (, {target_variable_name} ,)cannot be found in the dataset. Please check the names of phone_esm_ columns in cleaned python file") + return None + 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. diff --git a/src/models/merge_features_and_targets_for_population_model.py b/src/models/merge_features_and_targets_for_population_model.py index f9e9acd2..0ede61f8 100644 --- a/src/models/merge_features_and_targets_for_population_model.py +++ b/src/models/merge_features_and_targets_for_population_model.py @@ -12,9 +12,13 @@ for baseline_features_path in snakemake.input["demographic_features"]: all_baseline_features = pd.concat([all_baseline_features, baseline_features], axis=0) # merge sensor features and baseline features -features = sensor_features.merge(all_baseline_features, on="pid", how="left") +if not sensor_features.empty: + features = sensor_features.merge(all_baseline_features, on="pid", how="left") -target_variable_name = snakemake.params["target_variable"] -model_input = retain_target_column(features, target_variable_name) + target_variable_name = snakemake.params["target_variable"] + model_input = retain_target_column(features, target_variable_name) -model_input.to_csv(snakemake.output[0], index=False) + model_input.to_csv(snakemake.output[0], index=False) + +else: + sensor_features.to_csv(snakemake.output[0], index=False) diff --git a/src/models/select_targets.py b/src/models/select_targets.py index 4dc4a252..c6abe687 100644 --- a/src/models/select_targets.py +++ b/src/models/select_targets.py @@ -6,6 +6,8 @@ cleaned_sensor_features = pd.read_csv(snakemake.input["cleaned_sensor_features"] target_variable_name = snakemake.params["target_variable"] model_input = retain_target_column(cleaned_sensor_features, target_variable_name) -model_input.dropna(axis ="index", how="any", subset=["target"], inplace=True) -model_input.to_csv(snakemake.output[0], index=False) +if model_input is None: + pd.DataFrame().to_csv(snakemake.output[0]) +else: + model_input.to_csv(snakemake.output[0], index=False) diff --git a/tests/scripts/NaN.png b/tests/scripts/NaN.png new file mode 100644 index 00000000..e1178739 Binary files /dev/null and b/tests/scripts/NaN.png differ diff --git a/tests/scripts/missing_vals.py b/tests/scripts/missing_vals.py index acbae0bb..41cf4709 100644 --- a/tests/scripts/missing_vals.py +++ b/tests/scripts/missing_vals.py @@ -3,8 +3,8 @@ import seaborn as sns import matplotlib.pyplot as plt -participant = "p031" -all_sensors = ["eda", "bvp", "ibi", "temp", "acc"] +participant = "p01" +all_sensors = ["eda", "ibi", "temp", "acc"] for sensor in all_sensors: diff --git a/tests/scripts/phone_feats.py b/tests/scripts/phone_feats.py new file mode 100644 index 00000000..060fe3fd --- /dev/null +++ b/tests/scripts/phone_feats.py @@ -0,0 +1,285 @@ +import pandas as pd +import seaborn as sns +import matplotlib.pyplot as plt + + +path = "/rapids/data/processed/features/all_participants/all_sensor_features.csv" +df = pd.read_csv(path) + +# activity_recognition + +cols = [col for col in df.columns if "activity_recognition" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'activity_recognition_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_activity_recognition_values', bbox_inches='tight') +plt.close() + +# applications_foreground + +cols = [col for col in df.columns if "applications_foreground" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'applications_foreground_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_applications_foreground_values', bbox_inches='tight') +plt.close() + +# battery + +cols = [col for col in df.columns if "phone_battery" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'phone_battery_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_phone_battery_values', bbox_inches='tight') +plt.close() + +# bluetooth_doryab + +cols = [col for col in df.columns if "bluetooth_doryab" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'bluetooth_doryab_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_bluetooth_doryab_values', bbox_inches='tight') +plt.close() + +# bluetooth_rapids + +cols = [col for col in df.columns if "bluetooth_rapids" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'bluetooth_rapids_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_bluetooth_rapids_values', bbox_inches='tight') +plt.close() + +# calls + +cols = [col for col in df.columns if "phone_calls" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'phone_calls_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_phone_calls_values', bbox_inches='tight') +plt.close() + +# data_yield + +cols = [col for col in df.columns if "data_yield" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'data_yield_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_data_yield_values', bbox_inches='tight') +plt.close() + +# esm + +cols = [col for col in df.columns if "phone_esm" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'phone_esm_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_phone_esm_values', bbox_inches='tight') +plt.close() + +# light + +cols = [col for col in df.columns if "phone_light" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'phone_light_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_phone_light_values', bbox_inches='tight') +plt.close() + +# locations_doryab + +cols = [col for col in df.columns if "locations_doryab" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'locations_doryab_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_locations_doryab_values', bbox_inches='tight') +plt.close() + +# locations_barnett + +# Not working + +# messages + +cols = [col for col in df.columns if "phone_messages" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'phone_messages_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_phone_messages_values', bbox_inches='tight') +plt.close() + +# screen + +cols = [col for col in df.columns if "phone_screen" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'phone_screen_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_phone_screen_values', bbox_inches='tight') +plt.close() + +# wifi_visible + +cols = [col for col in df.columns if "wifi_visible" in col] +df_x = df[cols] + +print(len(cols)) +print(df_x) + +df_x = df_x.dropna(axis=0, how="all") +sns.heatmap(df_x.isna(), xticklabels=1) +plt.savefig(f'wifi_visible_values', bbox_inches='tight') + +df_q = pd.DataFrame() +for col in df_x: + df_q[col] = pd.to_numeric(pd.cut(df_x[col], bins=[-1,0,0.000000000001,1000], labels=[-1,0,1], right=False)) + +sns.heatmap(df_q, cbar=False, xticklabels=1) +plt.savefig(f'cut_wifi_visible_values', bbox_inches='tight') +plt.close() + +# All features + +print(len(df)) +print(df) + +# df = df.dropna(axis=0, how="all") +# df = df.dropna(axis=1, how="all") +sns.heatmap(df.isna()) +plt.savefig(f'all_features', bbox_inches='tight') + +print(df.columns[df.isna().all()].tolist()) +print("All NaNs:", df.isna().sum().sum()) +print("Df shape NaNs:", df.shape) \ No newline at end of file diff --git a/tests/scripts/standardization_methods_test.py b/tests/scripts/standardization_methods_test.py new file mode 100644 index 00000000..0747339d --- /dev/null +++ b/tests/scripts/standardization_methods_test.py @@ -0,0 +1,70 @@ +import pandas as pd +import numpy as np +import matplotlib.pyplot as plt +from sklearn.preprocessing import StandardScaler +import sys + +sys.path.append('/rapids/') +from src.features import cr_features_helper_methods as crhm + +pd.set_option("display.max_columns", None) +features_win = pd.read_csv("data/interim/p031/empatica_temperature_features/empatica_temperature_python_cr_windows.csv", usecols=[0, 1, 2, 3, 4, 5]) + +# First standardization method +excluded_columns = ['local_segment', 'local_segment_label', 'local_segment_start_datetime', 'local_segment_end_datetime', "empatica_temperature_cr_level_1"] +z1_windows = features_win.copy() +z1_windows.loc[:, ~z1_windows.columns.isin(excluded_columns)] = StandardScaler().fit_transform(z1_windows.loc[:, ~z1_windows.columns.isin(excluded_columns)]) +z1 = crhm.extract_second_order_features(z1_windows, ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows'], prefix="empatica_temperature_cr_") +z1 = z1.iloc[:,4:] +# print(z1) + +# Second standardization method +so_features_reg = crhm.extract_second_order_features(features_win, ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows'], prefix="empatica_temperature_cr_") +so_features_reg = so_features_reg.iloc[:,4:] +z2 = pd.DataFrame(StandardScaler().fit_transform(so_features_reg), columns=so_features_reg.columns) +# print(z2) + +# Standardization of the first standardization method values +z1_z = pd.DataFrame(StandardScaler().fit_transform(z1), columns=z1.columns) +# print(z1_z) + +# For SD +fig, axs = plt.subplots(3, figsize=(8, 10)) +axs[0].plot(z1['empatica_temperature_cr_squareSumOfComponent_X_SO_sd']) +axs[0].set_title("Z1 - standardizirana okna, nato ekstrahiranje značilk SO") + +axs[1].plot(z2['empatica_temperature_cr_squareSumOfComponent_X_SO_sd']) +axs[1].set_title("Z2 - ekstrahirane značilke SO 'normalnih' vrednosti, nato standardizacija") + +axs[2].plot(z1_z['empatica_temperature_cr_squareSumOfComponent_X_SO_sd']) +axs[2].set_title("Standardiziran Z1") + +fig.suptitle('Z-Score methods for temperature_squareSumOfComponent_SO_sd') +plt.savefig('z_score_comparison_temperature_squareSumOfComponent_X_SO_sd', bbox_inches='tight') + +showcase = pd.DataFrame() +showcase['Z1__SD'] = z1['empatica_temperature_cr_squareSumOfComponent_X_SO_sd'] +showcase['Z2__SD'] = z2['empatica_temperature_cr_squareSumOfComponent_X_SO_sd'] +showcase['Z1__SD_STANDARDIZED'] = z1_z['empatica_temperature_cr_squareSumOfComponent_X_SO_sd'] +print(showcase) + +# For +fig, axs = plt.subplots(3, figsize=(8, 10)) +axs[0].plot(z1['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest']) +axs[0].set_title("Z1 - standardizirana okna, nato ekstrahiranje značilk SO") + +axs[1].plot(z2['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest']) +axs[1].set_title("Z2") + +axs[2].plot(z1_z['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest']) +axs[2].set_title("Standardized Z1") + +fig.suptitle('Z-Score methods for temperature_squareSumOfComponent_SO_nlargest') +plt.savefig('z_score_comparison_temperature_squareSumOfComponent_X_SO_nlargest', bbox_inches='tight') + +showcase2 = pd.DataFrame() +showcase2['Z1__nlargest'] = z1['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest'] +showcase2['Z2__nlargest'] = z2['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest'] +showcase2['Z1__nlargest_STANDARDIZED'] = z1_z['empatica_temperature_cr_squareSumOfComponent_X_SO_nlargest'] +print(showcase2) + diff --git a/tests/scripts/test_acc.py b/tests/scripts/test_acc.py new file mode 100644 index 00000000..7bf3e074 --- /dev/null +++ b/tests/scripts/test_acc.py @@ -0,0 +1,38 @@ +import numpy as np +import pandas as pd +import matplotlib.pyplot as plt + +import sys + +df = pd.read_csv(f"/rapids/data/raw/p03/empatica_accelerometer_raw.csv") + + +df['date'] = pd.to_datetime(df['timestamp'],unit='ms') +df.set_index('date', inplace=True) +print(df) +df = df['double_values_0'].resample("31ms").mean() +print(df) + +st='2021-05-21 12:28:27' +en='2021-05-21 12:59:12' + +df = df.loc[(df.index > st) & (df.index < en)] +plt.plot(df) + +plt.savefig(f'NaN.png') +sys.exit() + + +plt.plot(df) + +esm = pd.read_csv(f"/rapids/data/raw/p03/phone_esm_raw.csv") + +esm['date'] = pd.to_datetime(esm['timestamp'],unit='ms') +esm = esm[esm['date']] +esm.set_index('date', inplace=True) +print(esm) + +esm = esm['esm_session'].resample("2900ms").mean() + +plt.plot(esm) +plt.savefig(f'NaN.png')