def main():
"""Main function."""
training_set, test_set = load_data.split_train_and_test_set()
housing, label = load_data.split_dataframe_column(training_set,
'median_house_value')
CombinedAttributesAdder.compute_index(housing)
housing_training = sklearn_feature_union.prepare_data(housing)
# Train
lin_reg = LinearRegression()
lin_reg.fit(housing_training, label)
# Evaluate
housing, label = load_data.split_dataframe_column(test_set,
'median_house_value')
housing_test = sklearn_feature_union.prepare_data(housing)
predition = lin_reg.predict(housing_test)
lin_mse = mean_squared_error(label, predition)
lin_rmse = np.sqrt(lin_mse)
print('root_mean_squared_error = {}'.format(lin_rmse))
def main():
"""Main function."""
training_set, test_set = load_data.split_train_and_test_set()
housing, label = load_data.split_dataframe_column(training_set,
'median_house_value')
CombinedAttributesAdder.compute_index(housing)
housing_training = sklearn_feature_union.prepare_data(housing)
# Train
param_grid = [
{
'n_estimators': [3, 10, 30],
'max_features': [2, 4, 6, 8]
},
{
'bootstrap': [False],
'n_estimators': [3, 10],
'max_features': [2, 3, 4]
},
]
forest_reg = RandomForestRegressor()
grid_search = GridSearchCV(forest_reg,
param_grid,
cv=5,
scoring='neg_mean_squared_error')
grid_search.fit(housing_training, label)
# Evaluate
housing, label = load_data.split_dataframe_column(test_set,
'median_house_value')
housing_test = sklearn_feature_union.prepare_data(housing)
predition = grid_search.best_estimator_.predict(housing_test)
grid_mse = mean_squared_error(label, predition)
grid_rmse = np.sqrt(grid_mse)
print('Best params = {}'.format(grid_search.best_params_))
print('root_mean_squared_error = {}'.format(grid_rmse))
print('Prediction: {}'.format(predition[:5]))
print('Label: {}'.format(list(label.iloc[:5])))
def main():
"""Main function."""
training_set, _ = load_data.split_train_and_test_set()
housing_num, _ = load_data.split_dataframe_column(training_set,
'ocean_proximity')
CombinedAttributesAdder.compute_index(housing_num)
num_pipeline = Pipeline([
('imputer', Imputer(strategy="median")),
('attribs_adder', CombinedAttributesAdder()),
('std_scaler', StandardScaler()),
])
housing_num_tr = num_pipeline.fit_transform(housing_num)
print(housing_num_tr)
def main():
"""Main function."""
training_set, test_set = load_data.split_train_and_test_set()
housing, label = load_data.split_dataframe_column(training_set,
'median_house_value')
CombinedAttributesAdder.compute_index(housing)
housing_training = sklearn_feature_union.prepare_data(housing)
# Train
tree_reg = DecisionTreeRegressor()
scores = cross_val_score(tree_reg,
housing_training,
label,
scoring="neg_mean_squared_error",
cv=10)
tree_rmse_scores = np.sqrt(-scores)
def display_scores(scores):
print("Scores:", scores)
print("Mean:", scores.mean())
print("Standard deviation:", scores.std())
display_scores(tree_rmse_scores)