136 lines
6.6 KiB
Python
136 lines
6.6 KiB
Python
import pandas as pd
|
|
import numpy as np
|
|
import math, sys
|
|
import yaml
|
|
|
|
from sklearn.impute import KNNImputer
|
|
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])
|
|
|
|
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
|
|
features = features[features['phone_esm_straw_' + target].notna()].reset_index(drop=True)
|
|
|
|
# (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)
|
|
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} 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"]]
|
|
|
|
if 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"]
|
|
|
|
# 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].")
|
|
|
|
# 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())
|
|
|
|
# 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?
|
|
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)
|
|
|
|
# (4) IMPUTATION: IMPUTE DATA WITH KNN METHOD (TODO: for now only kNN)
|
|
# - no other input restriction for this method except that rows are full enough and have reasonably high quality as assessed by data yield
|
|
graph_bf_af(features, "before_knn")
|
|
|
|
impute_cols = [col for col in features.columns if col not in excluded_columns]
|
|
features[impute_cols] = impute(features[impute_cols], method="knn")
|
|
|
|
graph_bf_af(features, "after_knn")
|
|
|
|
# (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)
|
|
|
|
# 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]
|
|
|
|
# (6) DROP HIGHLY CORRELATED FEATURES
|
|
drop_corr_features = provider["DROP_HIGHLY_CORRELATED_FEATURES"]
|
|
if drop_corr_features["COMPUTE"]:
|
|
|
|
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"])]
|
|
|
|
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
|
|
|
|
sys.exit()
|
|
|
|
return features
|
|
|
|
def graph_bf_af(features, phase_name):
|
|
sns.set(rc={"figure.figsize":(16, 8)})
|
|
sns.heatmap(features.isna(), cbar=False)
|
|
plt.savefig(f'features_nans_{phase_name}.png', bbox_inches='tight')
|
|
|
|
def impute(df, method='zero'):
|
|
|
|
def k_nearest(df):
|
|
imputer = KNNImputer(n_neighbors=3)
|
|
return pd.DataFrame(imputer.fit_transform(df), columns=df.columns)
|
|
|
|
return {
|
|
'zero': df.fillna(0),
|
|
'mean': df.fillna(df.mean()),
|
|
'median': df.fillna(df.median()),
|
|
'knn': k_nearest(df)
|
|
}[method]
|
|
|