2022-07-20 15:51:22 +02:00
import pandas as pd
import numpy as np
2022-09-29 16:33:21 +02:00
import math , sys , random
import typing
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 )
2022-07-20 15:51:22 +02:00
def straw_cleaning ( sensor_data_files , provider ) :
features = pd . read_csv ( sensor_data_files [ " sensor_data " ] [ 0 ] )
2022-09-29 16:33:21 +02:00
esm_cols = features . loc [ : , features . columns . str . startswith ( ' phone_esm_straw ' ) ] # Get target (esm) columns
2022-07-20 15:51:22 +02:00
2022-09-29 16:33:21 +02:00
with open ( ' config.yaml ' , ' r ' ) as stream :
config = yaml . load ( stream , Loader = yaml . FullLoader )
2022-07-22 17:31:30 +02:00
2022-09-29 16:33:21 +02:00
excluded_columns = [ ' local_segment ' , ' local_segment_label ' , ' local_segment_start_datetime ' , ' local_segment_end_datetime ' ]
2022-07-20 15:51:22 +02:00
2022-09-29 16:33:21 +02:00
# (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 )
2022-07-20 15:51:22 +02:00
2022-09-29 16:33:21 +02:00
# (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 )
2022-08-18 16:21:05 +02:00
2022-09-29 16:33:21 +02:00
# 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 )
2022-07-20 15:51:22 +02:00
2022-09-29 16:33:21 +02:00
# (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 ] ]
2022-08-18 16:21:05 +02:00
# 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 ]
2022-09-29 16:33:21 +02:00
# (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 ] = impute ( features [ impute_w_hn ] , method = " high_number " )
# Impute special case (mostcommonactivity)
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
# 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_locations ] = impute ( features [ impute_locations ] , method = " zero " )
# Impute phone locations with median - should this rather be imputed at kNN step??
# impute_locations = [col for col in features.columns if "phone_locations_" in col]
# # features[impute_locations] = features[impute_locations].mask(np.random.random(features[impute_locations].shape) < .1)
# # features.at[0,'pid'] = "p01"
# # features.at[1,'pid'] = "p01"
# # features.at[2,'pid'] = "p02"
# # features.at[3,'pid'] = "p02"
# # graph_bf_af(features[impute_locations], "phoneloc_before")
# features[impute_locations] = features[impute_locations + ["pid"]].groupby("pid").transform(lambda x: x.fillna(x.median()))[impute_locations]
## (5) STANDARDIZATION
if provider [ " STANDARDIZATION " ] :
features . loc [ : , ~ features . columns . isin ( excluded_columns + [ " pid " ] ) ] = \
features . loc [ : , ~ features . columns . isin ( excluded_columns ) ] . groupby ( ' pid ' ) . transform ( lambda x : 0 if ( x . std ( ) == 0 ) else ( x - x . mean ( ) ) / x . std ( ) )
graph_bf_af ( features [ impute_locations ] , " knn_before " )
# (6) IMPUTATION: IMPUTE DATA WITH KNN METHOD
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 [ impute_locations ] , " knn_after " )
# (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 )
# (8) DROP HIGHLY CORRELATED FEATURES
2022-07-20 15:51:22 +02:00
drop_corr_features = provider [ " DROP_HIGHLY_CORRELATED_FEATURES " ]
2022-09-29 16:33:21 +02:00
if drop_corr_features [ " COMPUTE " ] and features . shape [ 0 ] > 5 : # If small amount of segments (rows) is present, do not execute correlation check
2022-07-22 17:31:30 +02:00
2022-07-20 15:51:22 +02:00
numerical_cols = features . select_dtypes ( include = np . number ) . columns . tolist ( )
2022-07-22 17:31:30 +02:00
# 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 ] ]
2022-07-20 15:51:22 +02:00
2022-09-29 16:33:21 +02:00
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 " ] ) ]
2022-07-20 15:51:22 +02:00
features . drop ( to_drop , axis = 1 , inplace = True )
2022-09-29 16:33:21 +02:00
# 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
sys . exit ( )
2022-07-20 15:51:22 +02:00
return features
def impute ( df , method = ' zero ' ) :
2022-07-22 17:31:30 +02:00
2022-09-29 16:33:21 +02:00
def k_nearest ( df ) :
imputer = KNNImputer ( n_neighbors = 3 )
return pd . DataFrame ( imputer . fit_transform ( df ) , columns = df . columns )
2022-07-22 17:31:30 +02:00
2022-09-29 16:33:21 +02:00
return {
2022-07-20 15:51:22 +02:00
' zero ' : df . fillna ( 0 ) ,
2022-09-29 16:33:21 +02:00
' high_number ' : df . fillna ( 1000000 ) ,
2022-07-20 15:51:22 +02:00
' mean ' : df . fillna ( df . mean ( ) ) ,
' median ' : df . fillna ( df . median ( ) ) ,
2022-09-29 16:33:21 +02:00
' knn ' : k_nearest ( df )
2022-07-20 15:51:22 +02:00
} [ method ]
2022-09-29 16:33:21 +02:00
def graph_bf_af ( features , phase_name ) :
sns . set ( rc = { " figure.figsize " : ( 16 , 8 ) } )
print ( features )
sns . heatmap ( features . isna ( ) , cbar = False ) #features.select_dtypes(include=np.number)
plt . savefig ( f ' features_overall_nans_ { phase_name } .png ' , bbox_inches = ' tight ' )
class SklearnWrapper :
def __init__ ( self , transform : typing . Callable ) :
self . transform = transform
def __call__ ( self , df ) :
transformed = self . transform . fit_transform ( df . values )
return pd . DataFrame ( transformed , columns = df . columns , index = df . index )
2022-07-20 15:51:22 +02:00