def _num_feature_extraction(self, num_feats_b, b_df, b_agg_df, p_id):
for feature in num_feats_b:
print(feature)
b_agg_df = f.get_aggregate_features_num(b_df, b_agg_df, feature,
p_id)
# na_ind = b_agg_df[(b_agg_df[feature + '_std'].isna()==True) &
# ((b_agg_df[feature+'_mean'])==(b_agg_df[feature+'_median']))].index
#
# b_agg_df.loc[na_ind][feature+'_std'].fillna(0)
# b_agg_df.loc[na_ind][feature'_std'].isna().sum()
b_agg_df[feature + '_std'] = np.where(
(b_agg_df[feature + '_std'].isna() == True) &
((b_agg_df[feature + '_mean'])
== (b_agg_df[feature + '_median'])), 0,
b_agg_df[feature + '_std'])
b_agg_df.insert(0, p_id, b_agg_df.index)
b_agg_df.reset_index(drop=True, inplace=True)
return b_agg_df
# As the features are expected to be extracted and grouped at SK_ID_CURR level
# to synchronise at the Loan Application Client level.Hence we need to extract
# aggregated information at Client level out of the dataset
# This means that treatment to individual columns would not be generallised as
# we might loose information. Hence we will extract aggregated features first and then
# apply data correction (MISSING VALUES and OUTLIERS etc) at aggregate level based on the
# features qualitatively
b_agg_df = pd.DataFrame()
# Create a object for aggregation at SK_ID_CURR level
#b_agg = b_df.groupby('SK_ID_CURR')
#Aggregating bureau data at Customer Id level
for feature in num_feats_b:
b_agg_df = f.get_aggregate_features_num(b_df,b_agg_df, feature,'SK_ID_CURR')
# na_ind = b_agg_df[(b_agg_df[feature + '_std'].isna()==True) &
# ((b_agg_df[feature+'_mean'])==(b_agg_df[feature+'_median']))].index
#
# b_agg_df.loc[na_ind][feature+'_std'].fillna(0)
# b_agg_df.loc[na_ind][feature'_std'].isna().sum()
b_agg_df[feature+'_std'] = np.where((b_agg_df[feature+'_std'].isna()==True) &
((b_agg_df[feature+'_mean'])==(b_agg_df[feature+'_median'])),
0,
b_agg_df[feature+'_std'])
b_agg_df.insert(0,'SK_ID_CURR',b_agg_df.index)
b_agg_df.reset_index(drop=True)
for feature in cat_feats_b:
b_agg_cat = b_df.groupby('SK_ID_CURR')[feature].value_counts()
for i in b_df[feature].unique():
# As the features are expected to be extracted and grouped at SK_ID_CURR level
# to synchronise at the Loan Application Client level.Hence we need to extract
# aggregated information at Client level out of the dataset
# This means that treatment to individual columns would not be generallised as
# we might loose information. Hence we will extract aggregated features first and then
# apply data correction (MISSING VALUES and OUTLIERS etc) at aggregate level based on the
# features qualitatively
p_agg_df = pd.DataFrame()
# Create a object for aggregation at SK_ID_CURR level
#b_agg = b_df.groupby('SK_ID_CURR')
#Aggregating bureau data at Customer Id level
for feature in num_feats_p:
p_agg_df = f.get_aggregate_features_num(p_df, p_agg_df, feature,
'SK_ID_CURR')
p_agg_df[feature + '_std'] = np.where(
(p_agg_df[feature + '_std'].isna() == True) &
((p_agg_df[feature + '_mean']) == (p_agg_df[feature + '_median'])), 0,
p_agg_df[feature + '_std'])
p_agg_df.insert(0, 'SK_ID_CURR', p_agg_df.index)
p_agg_df.reset_index(drop=True)
for feature in cat_feats_p:
p_agg_cat = p_df.groupby('SK_ID_CURR')[feature].value_counts()
for i in p_df[feature].unique():
p_agg_df[feature + '_' + i + '_count'] = p_agg_cat.xs(key=i, level=1)
p_agg_df[feature + '_' + i + '_count'].fillna(value=0, inplace=True)
# Assuming the NA values where Bureau does not have the data which mean that
# in such scenarios the client does not have that entry which mean Zero