print("start")
dataset=wholeDataset.values
print(dataset.shape)
X = dataset[0:1460,2:276]
Y = trainDataset['SalePrice']
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3)
xgbclassifier = xgb.XGBRegressor(colsample_bytree=0.7,
gamma=0,
min_child_weight=1.5,
n_estimators=1000,
reg_alpha=0.75,
reg_lambda=0.45,
subsample=0.6,
seed=42,
max_features=220)
xgbclassifier.fit(X_train, Y_train)
rfclassifier = RandomForestRegressor(n_estimators = 1000, max_features=220)
rfclassifier.fit(X_train, Y_train)
stack_gen = StackingCVRegressor(regressors=(xgbclassifier,rfclassifier),
meta_regressor=xgbclassifier,
use_features_in_secondary=True)
stack_gen.fit(X_train,Y_train)
print("Score rf",rfclassifier.score(X_test, Y_test))
print("Score xgb",xgbclassifier.score(X_test, Y_test))
print("Score stack",stack_gen.score(X_test, Y_test))
from mlxtend.regressor import StackingCVRegressor y = dataset['PM'] x = dataset.drop(columns=['PM','CBWD']) x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42) lr = LinearRegression() dtr = DecisionTreeRegressor() svr_rbf = SVR(kernel='rbf', gamma='auto') knr = KNeighborsRegressor() ridge = Ridge() lasso = Lasso() regression_models = [lr, dtr, svr_rbf, knr, ridge, lasso] sclf = StackingCVRegressor(regression_models, meta_regressor=ridge) sclf.fit(x_train, y_train) pred = sclf.predict(x_test) print(sclf.score(x_train, y_train)) %matplotlib inline plt.scatter([i*10 for i in range(len(y_test))], y_test, c='red', lw=1) plt.plot([i*10 for i in range(len(y_test))], pred, c='black', lw=1) plt.show() `# In[ ]: