from sklearn.datasets import load_boston
data = load_boston()
X, y = data['data'], data['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=111)
# create dataset
dataset = Dataset(X_train,y_train,X_test)
# initialize RandomForest & LinearRegression
model_rf = Regressor(dataset=dataset, estimator=RandomForestRegressor, parameters={'n_estimators': 50},name='rf')
model_lr = Regressor(dataset=dataset, estimator=LinearRegression, parameters={'normalize': True},name='lr')
# Stack two models
# Returns new dataset with out-of-fold predictions
pipeline = ModelsPipeline(model_rf,model_lr)
stack_ds = pipeline.blend(proportion=0.2,seed=111)
# Train LinearRegression on stacked data (second stage)
stacker = Regressor(dataset=stack_ds, estimator=LinearRegression)
results = stacker.predict()
# Validate results using 10 fold cross-validation
results = stacker.validate(k=10,scorer=mean_absolute_error)
#Weighted
dataset = Dataset(preprocessor=boston_dataset)
model_rf = Regressor(dataset=dataset, estimator=RandomForestRegressor, parameters={'n_estimators': 151},name='rf')
model_lr = Regressor(dataset=dataset, estimator=LinearRegression, parameters={'normalize': True},name='lr')
model_knn = Regressor(dataset=dataset, estimator=KNeighborsRegressor, parameters={'n_neighbors': 15},name='knn')
dataset = Dataset(X_train, y_train, X_test)
# initialize RandomForest & LinearRegression
model_rf = Regressor(dataset=dataset,
estimator=RandomForestRegressor,
parameters={'n_estimators': 50},
name='rf')
model_lr = Regressor(dataset=dataset,
estimator=LinearRegression,
parameters={'normalize': True},
name='lr')
# Stack two models
# Returns new dataset with out-of-fold predictions
pipeline = ModelsPipeline(model_rf, model_lr)
stack_ds = pipeline.blend(proportion=0.2, seed=111)
# Train LinearRegression on stacked data (second stage)
stacker = Regressor(dataset=stack_ds, estimator=LinearRegression)
results = stacker.predict()
# Validate results using 10 fold cross-validation
results = stacker.validate(k=10, scorer=mean_absolute_error)
#Weighted
dataset = Dataset(preprocessor=boston_dataset)
model_rf = Regressor(dataset=dataset,
estimator=RandomForestRegressor,
parameters={'n_estimators': 151},
name='rf')
model_lr = Regressor(dataset=dataset,
#model_lascv = Regressor(dataset=dataset, estimator=lascv, parameters=params_lascv,name='lascv')
model_br = Regressor(dataset=dataset, estimator=br, parameters=params_br,name='br')
model_knn = Regressor(dataset=dataset, estimator=knn, parameters=params_knn,name='knn')
#blending = pipeline.blend(proportion=0.3,seed=111)
params_las = {'alpha':1.7}
params_rcv2 = {'cv':5,'normalize':True,'gcv_mode':'auto','scoring':'neg_mean_squared_error'}
params_lascv = {'max_iter':500,'cv':8}
pipeline = ModelsPipeline(model_rf1,model_knn)
stack_ds = pipeline.stack(k=5,seed=111)
stacker = Regressor(dataset=stack_ds,estimator=LassoCV, parameters=params_lascv)
y_pre = stacker.predict()
pipeline2 = ModelsPipeline(model_rf1,model_knn)
stack_ds2 = pipeline2.blend(seed=111)
blending = Regressor(dataset=stack_ds2,estimator=LassoCV, parameters=params_lascv)
y_pre2 = blending.predict()
blending_pre.append(y_pre2)
#print(y_pre)
#y_pre = pipeline.blend()
#print(y_pre)
###
#loss_stack = Evaluation([y_pre],[y_test])
stacking_pre.append(y_pre)
#weights = pipeline.find_weights(mean_absolute_error)
#print(weights)
#result = pipeline.weight(weights).execute()