Python datasets.make_friedman2函数代码示例

def test_make_friedman2():
    X, y = make_friedman2(n_samples=5, noise=0.0, random_state=0)

    assert_equal(X.shape, (5, 4), "X shape mismatch")
    assert_equal(y.shape, (5,), "y shape mismatch")

    assert_array_almost_equal(y, (X[:, 0] ** 2 + (X[:, 1] * X[:, 2] - 1 / (X[:, 1] * X[:, 3])) ** 2) ** 0.5)

def test_regression_synthetic():
    """Test on synthetic regression datasets used in Leo Breiman,
    `Bagging Predictors?. Machine Learning 24(2): 123-140 (1996). """
    random_state = check_random_state(1)
    regression_params = {'n_estimators': 100, 'max_depth': 4,
                         'min_samples_split': 1, 'learning_rate': 0.1,
                         'loss': 'ls'}

    # Friedman1
    X, y = datasets.make_friedman1(n_samples=1200,
                                   random_state=random_state, noise=1.0)
    X_train, y_train = X[:200], y[:200]
    X_test, y_test = X[200:], y[200:]
    clf = GradientBoostingRegressor()
    clf.fit(X_train, y_train)
    mse = mean_squared_error(y_test, clf.predict(X_test))
    assert mse < 5.0, "Failed on Friedman1 with mse = %.4f" % mse

    # Friedman2
    X, y = datasets.make_friedman2(n_samples=1200, random_state=random_state)
    X_train, y_train = X[:200], y[:200]
    X_test, y_test = X[200:], y[200:]
    clf = GradientBoostingRegressor(**regression_params)
    clf.fit(X_train, y_train)
    mse = mean_squared_error(y_test, clf.predict(X_test))
    assert mse < 1700.0, "Failed on Friedman2 with mse = %.4f" % mse

    # Friedman3
    X, y = datasets.make_friedman3(n_samples=1200, random_state=random_state)
    X_train, y_train = X[:200], y[:200]
    X_test, y_test = X[200:], y[200:]
    clf = GradientBoostingRegressor(**regression_params)
    clf.fit(X_train, y_train)
    mse = mean_squared_error(y_test, clf.predict(X_test))
    assert mse < 0.015, "Failed on Friedman3 with mse = %.4f" % mse

    def genFriedman(self, i=1, N=240, D=10):
        if i not in range(1,4):
            raise Exception('not a correct dataset')

        if i == 1:
            X, Y = datasets.make_friedman1(N, D )

        if i == 2:
            X, Y = datasets.make_friedman2(N, D)

        if i == 3:
            X, Y = datasets.make_friedman3(N, D)
        return X, Y

def test_regression_synthetic():
    # Test on synthetic regression datasets used in Leo Breiman,
    # `Bagging Predictors?. Machine Learning 24(2): 123-140 (1996).
    random_state = check_random_state(1)
    regression_params = {'n_estimators': 100, 'max_depth': 4,
                         'min_samples_split': 2, 'learning_rate': 0.1,
                         'loss': 'ls'}

    # Friedman1
    X, y = datasets.make_friedman1(n_samples=1200,
                                   random_state=random_state,
                                   noise=1.0)
    X_train, y_train = X[:200], y[:200]
    X_test, y_test = X[200:], y[200:]

    for presort in True, False:
        clf = GradientBoostingRegressor(presort=presort)
        clf.fit(X_train, y_train)
        mse = mean_squared_error(y_test, clf.predict(X_test))
        assert_less(mse, 5.0)

    # Friedman2
    X, y = datasets.make_friedman2(n_samples=1200, random_state=random_state)
    X_train, y_train = X[:200], y[:200]
    X_test, y_test = X[200:], y[200:]

    for presort in True, False:
        regression_params['presort'] = presort
        clf = GradientBoostingRegressor(**regression_params)
        clf.fit(X_train, y_train)
        mse = mean_squared_error(y_test, clf.predict(X_test))
        assert_less(mse, 1700.0)

    # Friedman3
    X, y = datasets.make_friedman3(n_samples=1200, random_state=random_state)
    X_train, y_train = X[:200], y[:200]
    X_test, y_test = X[200:], y[200:]

    for presort in True, False:
        regression_params['presort'] = presort
        clf = GradientBoostingRegressor(**regression_params)
        clf.fit(X_train, y_train)
        mse = mean_squared_error(y_test, clf.predict(X_test))
        assert_less(mse, 0.015)

def test_all_regressors():
    x, y  = make_friedman2(10000)
    x_train, y_train, x_test, y_test = test_helpers.split_dataset(x,y)
    #print y_test[:100]
    ols = LinearRegression()
    ols.fit(x_train, y_train)
    ols_pred = ols.predict(x_test)
    #print ols_pred[:100]
    ols_mse = mean_square_error(y_test, ols_pred)
    
    for fn in regressors:
        
        print fn
        model = fn(x_train,y_train)
        print model 
        pred = model.predict(x_test)
        #print pred[:100]
        mse = mean_square_error(y_test, pred)
        
        print "OLS MSE:", ols_mse, " Current MSE:", mse
        print "Ratio:",  mse / ols_mse 
        assert ols_mse > 1.1*mse

'''Friedman #2 data example'''

import rvm
from mpl_toolkits.mplot3d import Axes3D
import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import mean_squared_error
from sklearn.datasets import make_friedman2
from sklearn.datasets import make_friedman3

print('Friedman data set')

np.random.seed(2)
n_exp = 1
rel_vec = 0
RMSE = 0
for i in range(n_exp):
    train_x, train_y = make_friedman2(240, noise=0)
    cl = rvm.RVMRegression(kernel="rbf",  gamma=0.00001)
    cl.fit(np.matrix(train_x), np.matrix(train_y.reshape(240, 1)))
    rel_vec += len(cl.rel_ind)

    valid_x, valid_y = make_friedman2(240)
    pred_y = cl.predict(valid_x)

    RMSE += mean_squared_error(valid_y, pred_y) ** 0.5

print("Vectors: ", rel_vec / n_exp)
print("Root mean square = ", RMSE / n_exp)

def with_best_first(cls, max_leaf_nodes):
    return partial(cls, max_leaf_nodes=max_leaf_nodes)


def uniform_dataset(args):
    X = np.random.random(size=(args.num_examples, args.num_features))
    y = np.random.choice([-1, 1], size=args.num_examples)
    return (X, y)

DATASETS = {
    "uniform": uniform_dataset,
    "hastie": lambda args: datasets.make_hastie_10_2(
        n_samples=args.num_examples),
    "friedman1": lambda args: datasets.make_friedman1(
        n_samples=args.num_examples, n_features=args.num_features),
    "friedman2": lambda args: datasets.make_friedman2(
        n_samples=args.num_examples, noise=args.noise),
    "friedman3": lambda args: datasets.make_friedman3(
        n_samples=args.num_examples, noise=args.noise),
    "make_regression": lambda args: datasets.make_regression(
        n_samples=args.num_examples,
        n_features=args.num_features,
        n_informative=args.num_informative)
}

ENSEMBLE_REGRESSORS = [
    ("GB-D1", with_depth(ensemble.GradientBoostingRegressor, 1)),
    ("GB-D3", with_depth(ensemble.GradientBoostingRegressor, 3)),
    ("GB-B10", with_best_first(ensemble.GradientBoostingRegressor, 10)),
    ("RF-D1", with_depth(ensemble.RandomForestRegressor, 1)),
    ("RF-D3", with_depth(ensemble.RandomForestRegressor, 3)),
    ("RF-D5", with_depth(ensemble.RandomForestRegressor, 5)),

 def friedman2(n_samples=20000):
     """ Generated data """
     (data, target) = datasets.make_friedman2(n_samples=n_samples)
     return DatasetFactory.Dataset(data=data, target=target)