def test_staged_predict():
    # Test whether staged decision function eventually gives
    # the same prediction.
    X, y = datasets.make_friedman1(n_samples=1200,
                                   random_state=1, noise=1.0)
    X_train, y_train = X[:200], y[:200]
    X_test = X[200:]
    clf = GradientBoostingRegressor()
    # test raise ValueError if not fitted
    assert_raises(ValueError, lambda X: np.fromiter(
        clf.staged_predict(X), dtype=np.float64), X_test)

    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)

    # test if prediction for last stage equals ``predict``
    for y in clf.staged_predict(X_test):
        assert_equal(y.shape, y_pred.shape)

    assert_array_almost_equal(y_pred, y) 

def test_rfe_min_step():
    n_features = 10
    X, y = make_friedman1(n_samples=50, n_features=n_features, random_state=0)
    n_samples, n_features = X.shape
    estimator = SVR(kernel="linear")

    # Test when floor(step * n_features) <= 0
    selector = RFE(estimator, step=0.01)
    sel = selector.fit(X, y)
    assert_equal(sel.support_.sum(), n_features // 2)

    # Test when step is between (0,1) and floor(step * n_features) > 0
    selector = RFE(estimator, step=0.20)
    sel = selector.fit(X, y)
    assert_equal(sel.support_.sum(), n_features // 2)

    # Test when step is an integer
    selector = RFE(estimator, step=5)
    sel = selector.fit(X, y)
    assert_equal(sel.support_.sum(), n_features // 2) 

def __init__(self, numFeatures, numSamples, randomSeed):
        """
        :param numFeatures: total number of features to be used (at least 5)
        :param numSamples: number of samples in dataset
        :param randomSeed: random seed value used for reproducible results
        """

        self.numFeatures = numFeatures
        self.numSamples = numSamples
        self.randomSeed = randomSeed

        # generate test data:
        self.X, self.y = datasets.make_friedman1(n_samples=self.numSamples, n_features=self.numFeatures,
                                                 noise=self.NOISE, random_state=self.randomSeed)

        # divide the data to a training set and a validation set:
        self.X_train, self.X_validation, self.y_train, self.y_validation = \
            model_selection.train_test_split(self.X, self.y, test_size=self.VALIDATION_SIZE, random_state=self.randomSeed)

        self.regressor = GradientBoostingRegressor(random_state=self.randomSeed) 

def test_stacked_regressor(self):
        bclf = LinearRegression()
        clfs = [RandomForestRegressor(n_estimators=50, random_state=1),
                GradientBoostingRegressor(n_estimators=25, random_state=1),
                Ridge(random_state=1)]

        # Friedman1
        X, y = datasets.make_friedman1(n_samples=1200,
                                       random_state=1,
                                       noise=1.0)
        X_train, y_train = X[:200], y[:200]
        X_test, y_test = X[200:], y[200:]

        sr = StackedRegressor(bclf,
                              clfs,
                              n_folds=3,
                              verbose=0,
                              oob_score_flag=True)
        sr.fit(X_train, y_train)
        mse = mean_squared_error(y_test, sr.predict(X_test))
        assert_less(mse, 6.0) 

def test_fwls_regressor(self):
        feature_func = lambda x: np.ones(x.shape)
        bclf = LinearRegression()
        clfs = [RandomForestRegressor(n_estimators=50, random_state=1),
                GradientBoostingRegressor(n_estimators=25, random_state=1),
                Ridge(random_state=1)]

        # Friedman1
        X, y = datasets.make_friedman1(n_samples=1200,
                                       random_state=1,
                                       noise=1.0)
        X_train, y_train = X[:200], y[:200]
        X_test, y_test = X[200:], y[200:]

        sr = FWLSRegressor(bclf,
                              clfs,
                              feature_func,
                              n_folds=3,
                              verbose=0,
                              oob_score_flag=True)
        sr.fit(X_train, y_train)
        mse = mean_squared_error(y_test, sr.predict(X_test))
        assert_less(mse, 6.0) 

def test_regressor(self):
        X, y = datasets.make_friedman1(n_samples=1200,
                                       random_state=1,
                                       noise=1.0)
        X_train, y_train = X[:200], y[:200]
        index = [i for i in range(200)]

        rf = RandomForestRegressor()
        jrf = JoblibedRegressor(rf, "rfr", cache_dir='')
        jrf.fit(X_train, y_train, index)
        prediction = jrf.predict(X_train, index)
        mse = mean_squared_error(y_train, prediction)
        assert_less(mse, 6.0)

        rf = RandomForestRegressor(n_estimators=20)
        jrf = JoblibedRegressor(rf, "rfr", cache_dir='')
        jrf.fit(X_train, y_train, index)
        prediction2 = jrf.predict(X_train, index)
        assert_allclose(prediction, prediction2) 

def test_staged_predict():
    # Test whether staged decision function eventually gives
    # the same prediction.
    X, y = datasets.make_friedman1(n_samples=1200,
                                   random_state=1, noise=1.0)
    X_train, y_train = X[:200], y[:200]
    X_test = X[200:]
    clf = GradientBoostingRegressor()
    # test raise ValueError if not fitted
    assert_raises(ValueError, lambda X: np.fromiter(
        clf.staged_predict(X), dtype=np.float64), X_test)

    clf.fit(X_train, y_train)
    y_pred = clf.predict(X_test)

    # test if prediction for last stage equals ``predict``
    for y in clf.staged_predict(X_test):
        assert_equal(y.shape, y_pred.shape)

    assert_array_equal(y_pred, y) 

def test_rfe_min_step():
    n_features = 10
    X, y = make_friedman1(n_samples=50, n_features=n_features, random_state=0)
    n_samples, n_features = X.shape
    estimator = SVR(kernel="linear")

    # Test when floor(step * n_features) <= 0
    selector = RFE(estimator, step=0.01)
    sel = selector.fit(X, y)
    assert_equal(sel.support_.sum(), n_features // 2)

    # Test when step is between (0,1) and floor(step * n_features) > 0
    selector = RFE(estimator, step=0.20)
    sel = selector.fit(X, y)
    assert_equal(sel.support_.sum(), n_features // 2)

    # Test when step is an integer
    selector = RFE(estimator, step=5)
    sel = selector.fit(X, y)
    assert_equal(sel.support_.sum(), n_features // 2) 

def run():
    """Run profiling."""
    lc = LayerGenerator().get_sequential('stack', False, False)

    cm = CMLog(verbose=False)
    cm.monitor()

    sleep(5)

    t1 = int(np.floor(perf_counter() - cm._t0) * 10)
    sleep(0.1)
    x, z = make_friedman1(int(5 * 1e6))

    sleep(5)

    t2 = int(np.floor(perf_counter() - cm._t0) * 10)
    sleep(0.1)
    lc.fit(x, z)
    t3 = int(np.floor(perf_counter() - cm._t0) * 10)

    sleep(5)

    while not hasattr(cm, 'cpu'):
        cm.collect()
        sleep(1)

    return cm, t1, t2, t3 

def test_make_friedman1():
    X, y = make_friedman1(n_samples=5, n_features=10, noise=0.0,
                          random_state=0)

    assert_equal(X.shape, (5, 10), "X shape mismatch")
    assert_equal(y.shape, (5,), "y shape mismatch")

    assert_array_almost_equal(y,
                              10 * np.sin(np.pi * X[:, 0] * X[:, 1])
                              + 20 * (X[:, 2] - 0.5) ** 2
                              + 10 * X[:, 3] + 5 * X[:, 4]) 

def test_make_friedman1():
    X, y = make_friedman1(n_samples=5, n_features=10, noise=0.0,
                          random_state=0)

    assert_equal(X.shape, (5, 10), "X shape mismatch")
    assert_equal(y.shape, (5,), "y shape mismatch")

    assert_array_almost_equal(y,
                              10 * np.sin(np.pi * X[:, 0] * X[:, 1])
                              + 20 * (X[:, 2] - 0.5) ** 2
                              + 10 * X[:, 3] + 5 * X[:, 4]) 

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_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)