From bd53dc1684b2b6fadf5653e2a9cc00c953410149 Mon Sep 17 00:00:00 2001 From: Primoz Date: Mon, 26 Sep 2022 15:54:00 +0000 Subject: [PATCH] Empatica data yield usage in the cleaning script. --- config.yaml | 10 ++-- .../all_cleaning_individual/straw/main.py | 60 +++++++------------ src/features/empatica_data_yield.py | 14 +++-- 3 files changed, 36 insertions(+), 48 deletions(-) diff --git a/config.yaml b/config.yaml index 3e6d43bd..83148bf3 100644 --- a/config.yaml +++ b/config.yaml @@ -671,8 +671,9 @@ ALL_CLEANING_INDIVIDUAL: COLS_NAN_THRESHOLD: 1 # set to 1 remove only columns that contains all 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 + PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES + PHONE_DATA_YIELD_RATIO_THRESHOLD: 0.4 # set to 0 to disable + EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0.25 # set to 0 to disable DROP_HIGHLY_CORRELATED_FEATURES: COMPUTE: True MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5 @@ -706,8 +707,9 @@ ALL_CLEANING_OVERALL: COLS_NAN_THRESHOLD: 1 # set to 1 remove only columns that contains all 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 + PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES + PHONE_DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable + EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable DROP_HIGHLY_CORRELATED_FEATURES: COMPUTE: True MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5 diff --git a/src/features/all_cleaning_individual/straw/main.py b/src/features/all_cleaning_individual/straw/main.py index e72b5637..f70f14d7 100644 --- a/src/features/all_cleaning_individual/straw/main.py +++ b/src/features/all_cleaning_individual/straw/main.py @@ -8,6 +8,8 @@ from sklearn.preprocessing import StandardScaler import matplotlib.pyplot as plt import seaborn as sns +from src.features import empatica_data_yield as edy + def straw_cleaning(sensor_data_files, provider): features = pd.read_csv(sensor_data_files["sensor_data"][0]) @@ -19,68 +21,52 @@ def straw_cleaning(sensor_data_files, provider): 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 features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True) - # TODO: imputate the rows where the participants have at least 2 rows (2 time segments) - error prevention (has to be tested) - # TODO: because of different imputation logic (e.g., the phone_data_yield parameter for phone features) the imputation has to - # be planned accordingly. Should the phone features first be imputated with 0 and only then general kNN imputation is executed - # i.e., on the rows that are missing when E4 and phone features availability is not synchronized. CHECK phone_data_yield feat. - # A lot of imputation types/levels (1) imputation related to feature's content (2) imputation related to phone / empatica - # structual specifics (3) general imputation which is needed when types of features desynchronization is present (row is not full) - # because of the lack of the availability. Secondly, there's a high importance that features data frame is checked if and NaN - # values still exist. - # (2) 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) features = features.loc[:, features.isna().sum() < provider["COLS_NAN_THRESHOLD"] * features.shape[0]] # (3.1) QUALITY CHECK (DATA YIELD COLUMN) which determines if the row stays or not (if either E4 or phone is low quality the row is useless - TODO: determine threshold) - # Here, the imputation is still not executed - only quality check - - # ??? Drop rows with the value of phone_data_yield_column less than data_yield_ratio_threshold ??? 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 - empatica_data_yield_column = "????????????" + features = edy.calculate_empatica_data_yield(features) - if not phone_data_yield_column in features.columns and not empatica_data_yield_column in features.columns: + 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} column, please set config[PHONE_DATA_YIELD][PROVIDERS][RAPIDS][COMPUTE] to True and include 'ratiovalidyielded{data_yield_unit}' in [FEATURES].") if provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]: features = features[features[phone_data_yield_column] >= provider["PHONE_DATA_YIELD_RATIO_THRESHOLD"]] - - # Potrebno premisliti točno kako bi izgledal data_yield za E4: bo se ustvaril dodaten stolpec; bodo različne spremenljivke, podobno kot hour in minute pri phone? + if provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]: - features = features[features['???????????????'] >= provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]] + features = features[features["empatica_data_yield"] >= provider["EMPATICA_DATA_YIELD_RATIO_THRESHOLD"]] # ---> imputation ?? - impute_phone_features = provider["IMPUTE_PHONE_SELECTED_EVENT_FEATURES"] + # impute_phone_features = provider["IMPUTE_PHONE_SELECTED_EVENT_FEATURES"] - if True: #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_')] + # if True: #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].") - 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()) + # 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_')] - print(features[features['phone_data_yield_rapids_ratiovalidyieldedminutes'] > impute_phone_features['MIN_DATA_YIELDED_MINUTES_TO_IMPUTE']][phone_cols]) + # 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()) + + # print(features[features['phone_data_yield_rapids_ratiovalidyieldedminutes'] > impute_phone_features['MIN_DATA_YIELDED_MINUTES_TO_IMPUTE']][phone_cols]) # (3.2) (optional) DOES ROW CONSIST OF ENOUGH NON-NAN VALUES? Possible some of these examples could still pass previous condition but not this one? - # () 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) @@ -118,11 +104,9 @@ def straw_cleaning(sensor_data_files, provider): features.drop(to_drop, axis=1, inplace=True) ## (8) STANDARDIZATION - if provider["STANDARDIZATION"]: features.loc[:, ~features.columns.isin(excluded_columns)] = StandardScaler().fit_transform(features.loc[:, ~features.columns.isin(excluded_columns)]) - # (9) VERIFY IF THERE ARE ANY NANS LEFT IN THE DATAFRAME if features.isna().any().any(): raise ValueError diff --git a/src/features/empatica_data_yield.py b/src/features/empatica_data_yield.py index 517113ef..9991fefd 100644 --- a/src/features/empatica_data_yield.py +++ b/src/features/empatica_data_yield.py @@ -10,17 +10,19 @@ def calculate_empatica_data_yield(features): datetime_end = datetime.strptime(df.loc[0, 'local_segment_end_datetime'], '%y-%m-%d %H:%M:%S') tseg_duration = (datetime_end - datetime_start).total_seconds() - acc_data_yield = (features['empatica_accelerometer_cr_SO_windowsCount'] * 15) / tseg_duration - temp_data_yield = (features['empatica_temperature_cr_SO_windowsCount'] * 300) / tseg_duration - acc_data_yield = (features['empatica_electrodermal_activity_cr_SO_windowsCount'] * 60) / tseg_duration - ibi_data_yield = (features['empatica_inter_beat_interval_cr_SO_windowsCount'] * 300) / tseg_duration + features["acc_data_yield"] = (features['empatica_accelerometer_cr_SO_windowsCount'] * 15) / tseg_duration + features["temp_data_yield"] = (features['empatica_temperature_cr_SO_windowsCount'] * 300) / tseg_duration + features["eda_data_yield"] = (features['empatica_electrodermal_activity_cr_SO_windowsCount'] * 60) / tseg_duration + features["ibi_data_yield"] = (features['empatica_inter_beat_interval_cr_SO_windowsCount'] * 300) / tseg_duration + + features["empatica_data_yield"] = features[['acc_data_yield', 'temp_data_yield', 'eda_data_yield', 'ibi_data_yield']].mean(axis=1) # TODO: morda smisleno obdelovati različne senzorje ločeno -> lahko da ibi ne bo dobre kvalitete, ostali pa bodo okej. Zakaj bi samo zaradi IBI zavrgli celotno vrstico ... # lahko se tudi naredi overall kvaliteta empatice npr. povprečje vseh data_yield rezultatov? Oz. povprečje z utežmi glede na število stolpcev, ki jih senzor vsebuje # ... čeprav št. stolpcev ni najboljše, saj je pomembnost nekaterih (npr. EDA) značilk zelo vprašljiva. - # TODO: bolja nastavitev delovnih ur sedaj je od 4 do 4... to povzroči veliko manjkajočih podatkov in posledično nizek (telefonski in E4) data_yield ... + # TODO: boljša nastavitev delovnih ur sedaj je od 4 do 4... to povzroči veliko manjkajočih podatkov in posledično nizek (telefonski in E4) data_yield ... - data_yield_features = [col for col in features.columns if "SO_windowsCount" in col and "a"] + return features