def UnequalMLPsEnsembleTest():
#dataset = DatasetFactory.friedman1(n_samples=200200)
#dataset = DatasetFactory.friedman2(n_samples=200200)
dataset = DatasetFactory.friedman3(n_samples=200200)
Xtrain, X, ytrain, y = model_selection.train_test_split(dataset.data,
dataset.target,
random_state=0,
train_size=200)
ensemble = EnsembleRegressor(type='auto_large')
ensemble.fit(Xtrain,
ytrain,
samples_per_regressor=200,
regressor_overlap=200)
Ztrain = ensemble.predict(Xtrain)
Z = ensemble.predict(X)
sio.savemat(
'ManualEnsembleDatasets\DifferentRegressors_Friedman3.mat', {
'names': ensemble.regressor_labels,
'Z': Z,
'y': y,
'Ztrain': Ztrain,
'ytrain': ytrain,
'samples_per_regressor': 200,
'regressor_samples_overlap': 200,
'Ey': np.mean(y),
'Ey2': np.mean(y**2),
'Description': 'Different Regressors (Friedman #3)'
})
def RidgeRegressionEnsembleTest():
#dataset = DatasetFactory.friedman1(n_samples=200200)
#dataset = DatasetFactory.friedman2(n_samples=200200)
dataset = DatasetFactory.friedman3(n_samples=200200)
Xtrain, X, ytrain, y = model_selection.train_test_split(dataset.data,
dataset.target,
random_state=0,
train_size=200)
ensemble = EnsembleRegressor(type='ridge')
ensemble.fit(Xtrain,
ytrain,
samples_per_regressor=200,
regressor_overlap=200)
ridgecv = linear_model.RidgeCV(alphas=np.arange(.1, 1, .2),
fit_intercept=True,
normalize=True)
ridgecv.fit(Xtrain, ytrain)
y_ridgecv = ridgecv.predict(X)
Z = ensemble.predict(X)
sio.savemat(
'RidgeRegression_Friedman3_200k.mat',
{
'names': ensemble.regressor_labels,
'Z': Z,
'y': y,
# 'Ztrain': Z_train, 'ytrain': ytrain,
'y_RidgeCV': y_ridgecv,
'samples_per_regressor': 200,
'regressor_samples_overlap': 200,
'Ey': np.mean(y),
'Ey2': np.mean(y**2),
'Description': 'Ridge Regression (Friedman #3)'
})
def UnequalMLPsEnsembleTest():
#dataset = DatasetFactory.friedman1(n_samples=200200)
#dataset = DatasetFactory.friedman2(n_samples=200200)
dataset = DatasetFactory.friedman3(n_samples=200200)
Xtrain, X, ytrain, y = cross_validation.train_test_split(
dataset.data, dataset.target, random_state=0, train_size=200)
ensemble = EnsembleRegressor(type='auto_large')
ensemble.fit(Xtrain,ytrain,samples_per_regressor=200,regressor_overlap=200)
Ztrain = ensemble.predict(Xtrain)
Z = ensemble.predict(X)
sio.savemat('ManualEnsembleDatasets\DifferentRegressors_Friedman3.mat', {
'names': ensemble.regressor_labels,
'Z': Z, 'y': y,
'Ztrain': Ztrain, 'ytrain': ytrain,
'samples_per_regressor': 200,
'regressor_samples_overlap': 200,
'Ey': np.mean(y),
'Ey2': np.mean(y ** 2),
'Description': 'Different Regressors (Friedman #3)'
})
def main():
# Create the RandomForest regressor, and replace its predict function with
# a predict that saves the individual regressor outputs to a member variable all_y_hat
regr = RandomForestRegressor(n_estimators=50)
regr.predict = types.MethodType(forest_regressor_predict, regr)
# Load Dataset
#ds = DatasetFactory.friedman1(n_samples=20200)
#ds = DatasetFactory.friedman2(n_samples=20200)
ds = DatasetFactory.friedman3(n_samples=20200)
Xtrain, X, ytrain, y = cross_validation.train_test_split(ds.data,
ds.target,
train_size=200,
random_state=0)
# Fit the model
regr.fit(Xtrain, ytrain)
yhat = regr.predict(X)
Z = np.array(regr.all_y_hat)
# Save results
sio.savemat(
'RandomForestTest_Friedman3.mat',
{
'names': str(regr.estimators_),
'Z': Z,
'y': y,
'y_RandomForest': yhat,
# 'Ztrain': Z_train, # NOTE: Combing DecisionTrees is unsupervised by nature
#'ytrain': ytrain,
'samples_per_regressor': 200,
'regressor_samples_overlap': 200,
'Ey': np.mean(y),
'Ey2': np.mean(y**2),
'Description': 'Random Forest Ensemble Test (Friedman #3)'
})
def RidgeRegressionEnsembleTest():
#dataset = DatasetFactory.friedman1(n_samples=200200)
#dataset = DatasetFactory.friedman2(n_samples=200200)
dataset = DatasetFactory.friedman3(n_samples=200200)
Xtrain, X, ytrain, y = cross_validation.train_test_split(
dataset.data, dataset.target, random_state=0, train_size=200)
ensemble = EnsembleRegressor(type='ridge')
ensemble.fit(Xtrain,ytrain,samples_per_regressor=200,regressor_overlap=200)
ridgecv = linear_model.RidgeCV(alphas=np.arange(.1,1,.2), fit_intercept=True, normalize=True)
ridgecv.fit(Xtrain,ytrain)
y_ridgecv = ridgecv.predict(X)
Z = ensemble.predict(X)
sio.savemat('RidgeRegression_Friedman3_200k.mat', {
'names': ensemble.regressor_labels,
'Z': Z, 'y': y,
# 'Ztrain': Z_train, 'ytrain': ytrain,
'y_RidgeCV': y_ridgecv,
'samples_per_regressor': 200,
'regressor_samples_overlap': 200,
'Ey': np.mean(y),
'Ey2': np.mean(y ** 2),
'Description': 'Ridge Regression (Friedman #3)'
})
def submit_one(data, target, filename):
return make_large_ensemble(DatasetFactory.Dataset(data, target), filename)