def XY1():
X, y, X_test, X_test_index = load_xy()
####### VARIABLES
dummy_cols = ['Weekday', 'DepartmentDescription']
keep_cols = ['ScanCount', 'Returns']
funcs = [np.sum, np.count_nonzero]
dfta = ft.DataFrameToArray()
add_returns = ft.NGAddReturns()
gdd = ft.GDummyAndKeepTransform(dummy_cols, keep_cols,
funcs) # Doesn't work!
transform_steps = [("imputer", ft.NGNAImputer())] + \
list(ft.wrapStep(("add_returns", add_returns))) + \
list(ft.wrapStep(('grouper', gdd))) + \
[("dfta", dfta)]
transform_pipe = Pipeline(steps=transform_steps)
kh.start_pipeline()
kh.record_metric("validation", "start", "NA", "transform_pipeline",
str(transform_pipe), "NA")
return {
"X": transform_pipe.fit_transform(X),
"y": y,
"X_test": transform_pipe.transform(X_test),
"X_test_index": X_test_index
}
def XY7():
X, y, X_test, X_test_index = load_xy()
#### DON'T CHANGE BEFORE
dummy_cols = ['DepartmentDescription']
keep_cols = ['Weekday']
mul_col = 'ScanCount'
dfta = ft.DataFrameToArray()
grouper = ft.GDummyKeepAndMultiplierTransform(dummy_cols, mul_col,
keep_cols)
transform_steps = [("imputer", ft.NGNAImputer())] + \
list(ft.wrapStep(('grouper', grouper)))
### DON'T CHANGE AFTER
transform_steps.append((("dfta", dfta)))
transform_pipe = Pipeline(steps=transform_steps)
kh.start_pipeline()
kh.record_metric("validation", "start", "NA", "transform_pipeline",
str(transform_pipe), "NA")
return {
"X": transform_pipe.fit_transform(X),
"y": y,
"X_test": transform_pipe.transform(X_test),
"X_test_index": X_test_index
}
