def test_boston(self):
from sklearn.tree import DecisionTreeRegressor as DecisionTreeRegressorSklearn
model = DecisionTreeRegressor(max_n_splits=3)
model_sklearn = DecisionTreeRegressorSklearn()
dataset = load_boston()
mse = []
mse_sklearn = []
for fold in range(5):
X_train, X_test, y_train, y_test = train_test_split(dataset.data,
dataset.target,
test_size=0.33)
model.fit(X_train, y_train)
y = model.predict(X_test)
mse.append(mean_squared_error(y, y_test))
model_sklearn.fit(X_train, y_train)
y = model_sklearn.predict(X_test)
mse_sklearn.append(mean_squared_error(y, y_test))
mean_mse = np.mean(mse)
mean_mse_sklearn = np.mean(mse_sklearn)
print(mean_mse, mean_mse_sklearn)
# Check that our model differs in MSE no worse than 20%
self.assertTrue(
np.abs(mean_mse - mean_mse_sklearn) / mean_mse_sklearn < 0.2)
def test_boston(self):
from sklearn.tree import DecisionTreeRegressor as DecisionTreeRegressorSklearn
model = DecisionTreeRegressor(tree_type='oblivious', max_n_splits=3)
model_sklearn = DecisionTreeRegressorSklearn()
dataset = load_boston()
mse = []
mse_sklearn = []
for fold in range(5):
X_train, X_test, y_train, y_test = train_test_split(
dataset.data, dataset.target, test_size=0.33)
model.fit(X_train, y_train)
y = model.predict(X_test)
mse.append(mean_squared_error(y, y_test))
model_sklearn.fit(X_train, y_train)
y = model_sklearn.predict(X_test)
mse_sklearn.append(mean_squared_error(y, y_test))
mean_mse = np.mean(mse)
mean_mse_sklearn = np.mean(mse_sklearn)
print(mean_mse, mean_mse_sklearn)
# Check that our model differs in MSE no worse than 50%
self.assertTrue(np.abs(mean_mse - mean_mse_sklearn) / mean_mse_sklearn < 0.5)
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn.datasets import load_boston
from sklearn.metrics import mean_squared_error
from pines.estimators import DecisionTreeRegressor
from pines.tree_builders import TreeType
if __name__ == '__main__':
model = DecisionTreeRegressor(max_n_splits=10, max_depth=4, tree_type=TreeType.OBLIVIOUS)
dataset = load_boston()
mse = []
for fold in range(4):
X_train, X_test, y_train, y_test = train_test_split(
dataset.data, dataset.target, test_size=0.33)
model.fit(X_train, y_train)
# print(model._tree)
y = model.predict(X_test)
mse.append(mean_squared_error(y, y_test))
mean_mse = np.mean(mse)
print(mean_mse)
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn.datasets import load_boston
from sklearn.metrics import mean_squared_error
from pines.estimators import DecisionTreeRegressor
from pines.tree_builders import TreeType
if __name__ == '__main__':
model = DecisionTreeRegressor(max_n_splits=10,
max_depth=4,
tree_type=TreeType.OBLIVIOUS)
dataset = load_boston()
mse = []
for fold in range(4):
X_train, X_test, y_train, y_test = train_test_split(dataset.data,
dataset.target,
test_size=0.33)
model.fit(X_train, y_train)
# print(model._tree)
y = model.predict(X_test)
mse.append(mean_squared_error(y, y_test))
mean_mse = np.mean(mse)
print(mean_mse)