Seperate target standardization from rest of the features.
parent
e40f0fd8dc
commit
3ce7f2c2a5
|
@ -710,7 +710,8 @@ ALL_CLEANING_OVERALL:
|
||||||
COMPUTE: True
|
COMPUTE: True
|
||||||
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
|
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
|
||||||
CORR_THRESHOLD: 0.95
|
CORR_THRESHOLD: 0.95
|
||||||
STANDARDIZATION: False
|
STANDARDIZATION: True
|
||||||
|
TARGET_STANDARDIZATION: False
|
||||||
SRC_SCRIPT: src/features/all_cleaning_overall/straw/main.py
|
SRC_SCRIPT: src/features/all_cleaning_overall/straw/main.py
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -169,8 +169,12 @@ def straw_cleaning(sensor_data_files, provider, target):
|
||||||
# Expected warning within this code block
|
# Expected warning within this code block
|
||||||
with warnings.catch_warnings():
|
with warnings.catch_warnings():
|
||||||
warnings.simplefilter("ignore", category=RuntimeWarning)
|
warnings.simplefilter("ignore", category=RuntimeWarning)
|
||||||
features.loc[:, ~features.columns.isin(excluded_columns + ["pid"] + nominal_cols)] = \
|
if provider["TARGET_STANDARDIZATION"]:
|
||||||
features.loc[:, ~features.columns.isin(excluded_columns + nominal_cols)].groupby('pid').transform(lambda x: StandardScaler().fit_transform(x.values[:,np.newaxis]).ravel())
|
features.loc[:, ~features.columns.isin(excluded_columns + ["pid"] + nominal_cols)] = \
|
||||||
|
features.loc[:, ~features.columns.isin(excluded_columns + nominal_cols)].groupby('pid').transform(lambda x: StandardScaler().fit_transform(x.values[:,np.newaxis]).ravel())
|
||||||
|
else:
|
||||||
|
features.loc[:, ~features.columns.isin(excluded_columns + ["pid"] + nominal_cols + ['phone_esm_straw_' + target])] = \
|
||||||
|
features.loc[:, ~features.columns.isin(excluded_columns + nominal_cols + ['phone_esm_straw_' + target])].groupby('pid').transform(lambda x: StandardScaler().fit_transform(x.values[:,np.newaxis]).ravel())
|
||||||
|
|
||||||
graph_bf_af(features, "8standardization")
|
graph_bf_af(features, "8standardization")
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue