88 lines
4.6 KiB
Python
88 lines
4.6 KiB
Python
import pandas as pd
|
|
import numpy as np
|
|
import math, sys
|
|
|
|
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].")
|
|
|
|
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)
|
|
|
|
# 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?
|
|
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)
|
|
|
|
# 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)
|
|
|
|
return features
|
|
|
|
def impute(df, method='zero'):
|
|
|
|
def k_nearest(df): # TODO: if needed, implement k-nearest imputation / interpolation
|
|
pass
|
|
|
|
return { # rest of the columns should be imputed with the selected method
|
|
'zero': df.fillna(0),
|
|
'mean': df.fillna(df.mean()),
|
|
'median': df.fillna(df.median()),
|
|
'k-nearest': k_nearest(df)
|
|
}[method]
|
|
|