def get_pipe(self, ):
if self.inner_cv is None:
inner_cv = RepeatedKFold(n_splits=10, n_repeats=3, random_state=0)
else:
inner_cv = self.inner_cv
gridpoints = self.gridpoints
param_grid = {'C': np.logspace(-2, 4, gridpoints)}
steps = [
('polyfeat',
PolynomialFeatures(interaction_only=0,
degree=2)), # create interactions among them
('drop_constant', DropConst()),
('shrink_k2',
ShrinkBigKTransformer(
selector=LassoLarsCV(cv=inner_cv, max_iter=64))),
('scaler', StandardScaler()),
('reg',
GridSearchCV(LinearSVR(random_state=0, tol=1e-4, max_iter=1000),
param_grid=param_grid))
]
if self.bestT:
steps = [
steps[0],
('xtransform',
ColumnBestTransformer(float_k=len(self.float_idx))),
*steps[1:]
]
outerpipe = Pipeline(steps=steps)
if self.do_prep:
steps = [('prep', MissingValHandler(prep_dict=self.prep_dict)),
('post', outerpipe)]
outerpipe = Pipeline(steps=steps)
return outerpipe
def get_pipe(self, ):
if self.inner_cv is None:
inner_cv = RepeatedKFold(n_splits=self.cv_splits,
n_repeats=self.cv_repeats,
random_state=0)
else:
inner_cv = self.inner_cv
gridpoints = self.gridpoints
param_grid = {
'C': np.logspace(-2, 2, gridpoints),
'gamma': np.logspace(-2, 0.5, gridpoints)
}
steps = [('scaler', StandardScaler()),
('reg',
GridSearchCV(SVR(kernel='rbf',
cache_size=10000,
tol=1e-4,
max_iter=5000),
param_grid=param_grid))]
if self.bestT:
steps.insert(0,
('xtransform',
ColumnBestTransformer(float_k=len(self.float_idx))))
outerpipe = Pipeline(steps=steps)
if self.do_prep:
steps = [('prep', MissingValHandler(prep_dict=self.prep_dict)),
('post', outerpipe)]
outerpipe = Pipeline(steps=steps)
return outerpipe
def get_pipe(self, ):
if self.inner_cv is None:
inner_cv = RepeatedKFold(n_splits=self.cv_splits,
n_repeats=self.cv_repeats,
random_state=0)
else:
inner_cv = self.inner_cv
steps = [('scaler', StandardScaler()),
('select', ShrinkBigKTransformer(max_k=4)),
('reg', FlexibleEstimator(**self.flex_kwargs))]
if self.bestT:
steps.insert(0, 'xtransform',
ColumnBestTransformer(float_k=len(self.float_idx)))
pipe = Pipeline(steps=steps)
param_grid = {
'select__k_share': np.linspace(0.2, 1, self.gridpoints * 2)
}
if self.functional_form_search:
param_grid['reg__form'] = ['powXB', 'expXB'] # ,'linear']
outerpipe = GridSearchCV(pipe, param_grid=param_grid)
if self.do_prep:
steps = [('prep', MissingValHandler(prep_dict=self.prep_dict)),
('post', outerpipe)]
outerpipe = Pipeline(steps=steps)
return outerpipe
def get_pipe(self, ):
if self.inner_cv is None:
inner_cv = RepeatedKFold(n_splits=self.cv_splits,
n_repeats=self.cv_repeats,
random_state=0)
else:
inner_cv = self.inner_cv
gridpoints = self.gridpoints
n_alphas = gridpoints * 5
l1_ratio = 1 - np.logspace(-2, -.03, gridpoints * 2)
steps = [('scaler', StandardScaler()),
('reg',
ElasticNetCV(cv=inner_cv,
normalize=False,
l1_ratio=l1_ratio,
n_alphas=n_alphas))]
if self.bestT:
steps.insert(0,
('xtransform',
ColumnBestTransformer(float_k=len(self.float_idx))))
outerpipe = Pipeline(steps=steps)
if self.do_prep:
steps = [('prep', MissingValHandler(prep_dict=self.prep_dict)),
('post', outerpipe)]
outerpipe = Pipeline(steps=steps)
return outerpipe
def get_pipe(self):
if self.inner_cv is None:
inner_cv = RepeatedKFold(n_splits=self.cv_splits,
n_repeats=self.cv_repeats,
random_state=0)
else:
inner_cv = self.inner_cv
if self.est_kwargs is None:
self.est_kwargs = {'max_depth': [3, 4], 'n_estimators': [64, 128]}
hyper_param_dict, gbr_params = self.extractParams(self.est_kwargs)
if not 'random_state' in gbr_params:
gbr_params['random_state'] = 0
steps = [('reg',
GridSearchCV(GradientBoostingRegressor(**gbr_params),
param_grid=hyper_param_dict,
cv=inner_cv))]
if self.bestT:
steps.insert(0, 'xtransform',
ColumnBestTransformer(float_k=len(self.float_idx)))
outerpipe = Pipeline(steps=steps)
if self.do_prep:
steps = [('prep', MissingValHandler(prep_dict=self.prep_dict)),
('post', outerpipe)]
outerpipe = Pipeline(steps=steps)
return outerpipe
def get_pipe(self, ):
if self.inner_cv is None:
inner_cv = RepeatedKFold(n_splits=self.cv_splits, n_repeats=self.cv_repeats, random_state=0)
else:
inner_cv = self.inner_cv
gridpoints = self.gridpoints
transformer_list = [None_T(), Log_T(), LogP1_T()] # ,logp1_T()] # log_T()]#
steps = [
('shrink_k1', ShrinkBigKTransformer(selector=LassoLarsCV(cv=inner_cv, max_iter=32))), # retain a subset of the best original variables
('polyfeat', PolynomialFeatures(interaction_only=0, degree=2)), # create interactions among them
('drop_constant', DropConst()),
('shrink_k2', ShrinkBigKTransformer(selector=LassoLarsCV(cv=inner_cv, max_iter=64))), # pick from all of those options
('reg', LinearRegression())]
if self.bestT:
steps.insert(0, ('xtransform', ColumnBestTransformer(float_k=len(self.float_idx))))
X_T_pipe = Pipeline(steps=steps)
Y_T_X_T_pipe = Pipeline(steps=[('ttr', TransformedTargetRegressor(regressor=X_T_pipe))])
Y_T__param_grid = {
'ttr__transformer': transformer_list,
'ttr__regressor__polyfeat__degree': [2],
}
outerpipe = GridSearchCV(Y_T_X_T_pipe, param_grid=Y_T__param_grid, cv=inner_cv)
if self.do_prep:
steps = [('prep', MissingValHandler(prep_dict=self.prep_dict)),
('post', outerpipe)]
outerpipe = Pipeline(steps=steps)
return outerpipe
def get_pipe(self):
if self.inner_cv is None:
inner_cv = RepeatedKFold(n_splits=self.cv_splits, n_repeats=self.cv_repeats, random_state=0)
else:
inner_cv = self.inner_cv
steps = [('reg', LassoLarsCV(cv=inner_cv, max_n_alphas=self.max_n_alphas))]
if self.bestT:
steps.insert(0, 'xtransform', ColumnBestTransformer(float_k=len(self.float_idx)))
outerpipe = Pipeline(steps=steps)
if self.do_prep:
steps = [('prep', MissingValHandler(prep_dict=self.prep_dict)), ('post', outerpipe)]
outerpipe = Pipeline(steps=steps)
return outerpipe
def get_pipe(self):
if self.inner_cv is None:
inner_cv = RepeatedKFold(n_splits=10, n_repeats=1, random_state=0)
else:
inner_cv = self.inner_cv
param_grid = {'max_depth': list(range(1, 3)),
'n_estimators': [75, 100]
}
steps = [('reg', GridSearchCV(GradientBoostingRegressor(random_state=0), param_grid=param_grid, cv=inner_cv, n_jobs=1))]
# steps = [('reg', GradientBoostingRegressor(random_state=0))]
if self.bestT:
steps.insert(0, 'xtransform', ColumnBestTransformer(float_k=len(self.float_idx)))
outerpipe = Pipeline(steps=steps)
if self.do_prep:
steps = [('prep', MissingValHandler(prep_dict=self.prep_dict)),
('post', outerpipe)]
outerpipe = Pipeline(steps=steps)
return outerpipe