Python samples_generator.make_regression函数代码示例

def test_f_regression_select():
    print "==> a lot of features"
    X, y = make_regression(n_samples=20000, n_features=200, n_informative=150,
                             shuffle=False, random_state=0)
    idx_sel = f_regression_select(X, y, verbose=2)
    print "==> few ones"
    X, y = make_regression(n_samples=200, n_features=20, n_informative=5, noise=0.5,
                             shuffle=False, random_state=0)
    idx_sel = f_regression_select(X, y, verbose=1)
    print "tests ok"

def test_csr_sparse_center_data():
    # Test output format of sparse_center_data, when input is csr
    X, y = make_regression()
    X[X < 2.5] = 0.0
    csr = sparse.csr_matrix(X)
    csr_, y, _, _, _ = sparse_center_data(csr, y, True)
    assert_equal(csr_.getformat(), 'csr')

def test_invalid_percentile():
    X, y = make_regression(n_samples=10, n_features=20, n_informative=2, shuffle=False, random_state=0)

    assert_raises(ValueError, SelectPercentile(percentile=-1).fit, X, y)
    assert_raises(ValueError, SelectPercentile(percentile=101).fit, X, y)
    assert_raises(ValueError, GenericUnivariateSelect(mode="percentile", param=-1).fit, X, y)
    assert_raises(ValueError, GenericUnivariateSelect(mode="percentile", param=101).fit, X, y)

    def single_fdr(alpha, n_informative, random_state):
        X, y = make_regression(
            n_samples=150,
            n_features=20,
            n_informative=n_informative,
            shuffle=False,
            random_state=random_state,
            noise=10,
        )

        with warnings.catch_warnings(record=True):
            # Warnings can be raised when no features are selected
            # (low alpha or very noisy data)
            univariate_filter = SelectFdr(f_regression, alpha=alpha)
            X_r = univariate_filter.fit(X, y).transform(X)
            X_r2 = GenericUnivariateSelect(f_regression, mode="fdr", param=alpha).fit(X, y).transform(X)

        assert_array_equal(X_r, X_r2)
        support = univariate_filter.get_support()
        num_false_positives = np.sum(support[n_informative:] == 1)
        num_true_positives = np.sum(support[:n_informative] == 1)

        if num_false_positives == 0:
            return 0.0
        false_discovery_rate = num_false_positives / (num_true_positives + num_false_positives)
        return false_discovery_rate

def test_select_percentile_regression():
    """
    Test whether the relative univariate feature selection
    gets the correct items in a simple regression problem
    with the percentile heuristic
    """
    X, y = make_regression(n_samples=200, n_features=20,
                           n_informative=5, shuffle=False, random_state=0)

    univariate_filter = SelectPercentile(f_regression, percentile=25)
    X_r = univariate_filter.fit(X, y).transform(X)
    assert_best_scores_kept(univariate_filter)
    X_r2 = GenericUnivariateSelect(
        f_regression, mode='percentile', param=25).fit(X, y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.zeros(20)
    gtruth[:5] = 1
    assert_array_equal(support, gtruth)
    X_2 = X.copy()
    X_2[:, np.logical_not(support)] = 0
    assert_array_equal(X_2, univariate_filter.inverse_transform(X_r))
    # Check inverse_transform respects dtype
    assert_array_equal(X_2.astype(bool),
                       univariate_filter.inverse_transform(X_r.astype(bool)))

def prepare_data(mydata = True):
    '''
    dim(X) -> (10,2)
    each_row(X) -> training point
    each_column(X) -> x_0, x_1

    dim(Y) -> (10,1)
    each_row(Y) -> result

    dim(theta) ->(2,1)
    theta[0][0] -> x_0
    theta[1][0] -> x_1
    Odd Even Linked List'''
    if mydata:
        num_trainingpoint = 3
        X =  np.array([range(num_trainingpoint)]).T
        theta = np.array([[1],[2]])
        x0 = np.ones(shape=(num_trainingpoint,1))
        m, n = np.shape(X)
        X = np.c_[ np.ones(m), X]
        Y =  X.dot(theta)
    else:
        X, Y = make_regression(n_samples=100, n_features=1, n_informative=1, 
                                random_state=0, noise=35) 
        m, n = np.shape(X)
        X = np.c_[ np.ones(m), X] # insert column

    theta = np.ones(shape=(2,1))

    return X, Y, theta

def generate_dataset(n_train, n_test, n_features, noise=0.1, verbose=False):
    """Generate a regression dataset with the given parameters."""
    if verbose:
        print("generating dataset...")
    X, y, coef = make_regression(n_samples=n_train + n_test,
                                 n_features=n_features, noise=noise, coef=True)
    X_train = X[:n_train]
    y_train = y[:n_train]
    X_test = X[n_train:]
    y_test = y[n_train:]
    idx = np.arange(n_train)
    np.random.seed(13)
    np.random.shuffle(idx)
    X_train = X_train[idx]
    y_train = y_train[idx]

    std = X_train.std(axis=0)
    mean = X_train.mean(axis=0)
    X_train = (X_train - mean) / std
    X_test = (X_test - mean) / std

    std = y_train.std(axis=0)
    mean = y_train.mean(axis=0)
    y_train = (y_train - mean) / std
    y_test = (y_test - mean) / std

    gc.collect()
    if verbose:
        print("ok")
    return X_train, y_train, X_test, y_test

def create_regression():
    x, y = make_regression(
        n_samples=100,
        n_features=1,
        n_informative=1,
        random_state=0,
        noise=35
    )

    # learning rate
    alpha = 1
    # convergence criteria
    ep = 1e-12
    # max iterations
    max_iter = 20

    theta0, theta1, cost_f = gradient_descent(alpha, x, y, ep, max_iter)

    slope, intercept, r_value, p_value, slope_std_error = stats.linregress(x[:, 0], y)
    print ('intercept = %s slope = %s') % (intercept, slope)

    for i in range(x.shape[0]):
        y_predict = theta0 + theta1 * x

    pylab.plot(x, y, 'o')
    pylab.plot(x, y_predict, '-')
    pylab.show()
    print "Done."

def test_mutual_info_regression():
    X, y = make_regression(n_samples=100, n_features=10, n_informative=2,
                           shuffle=False, random_state=0, noise=10)

    # Test in KBest mode.
    univariate_filter = SelectKBest(mutual_info_regression, k=2)
    X_r = univariate_filter.fit(X, y).transform(X)
    assert_best_scores_kept(univariate_filter)
    X_r2 = GenericUnivariateSelect(
        mutual_info_regression, mode='k_best', param=2).fit(X, y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.zeros(10)
    gtruth[:2] = 1
    assert_array_equal(support, gtruth)

    # Test in Percentile mode.
    univariate_filter = SelectPercentile(mutual_info_regression, percentile=20)
    X_r = univariate_filter.fit(X, y).transform(X)
    X_r2 = GenericUnivariateSelect(mutual_info_regression, mode='percentile',
                                   param=20).fit(X, y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.zeros(10)
    gtruth[:2] = 1
    assert_array_equal(support, gtruth)

def test_regression_squared_loss():
    X, y = make_regression(n_samples=100, n_features=10, n_informative=8, random_state=0)
    reg = SGDRegressor(loss="squared", penalty="l2", learning_rate="constant", eta0=1e-2, random_state=0)

    reg.fit(X, y)
    pred = reg.predict(X)
    assert_almost_equal(np.mean((pred - y) ** 2), 4.913, 3)

def test_regression_squared_loss_multiple_output():
    X, y = make_regression(n_samples=100, n_features=10, n_informative=8, random_state=0)
    reg = SGDRegressor(loss="squared", penalty="l2", learning_rate="constant", eta0=1e-2, random_state=0, max_iter=10)
    Y = np.zeros((len(y), 2))
    Y[:, 0] = y
    Y[:, 1] = y
    reg.fit(X, Y)
    pred = reg.predict(X)
    assert_almost_equal(np.mean((pred - Y) ** 2), 4.541, 3)

def main():
    
    # load the dataset to the two variables
    X, y = make_regression(n_samples=100, n_features=1, n_informative=1, random_state=0, noise=35) 
    m = np.shape(X)[0]
    X = np.c_[ np.ones(m), X]

    # get the slope
    theta = grad_desc_vector(X, y, 0.001, 1500)

    print theta   

def test_select_percentile_regression_full():
    # Test whether the relative univariate feature selection
    # selects all features when '100%' is asked.
    X, y = make_regression(n_samples=200, n_features=20, n_informative=5, shuffle=False, random_state=0)

    univariate_filter = SelectPercentile(f_regression, percentile=100)
    X_r = univariate_filter.fit(X, y).transform(X)
    assert_best_scores_kept(univariate_filter)
    X_r2 = GenericUnivariateSelect(f_regression, mode="percentile", param=100).fit(X, y).transform(X)
    assert_array_equal(X_r, X_r2)
    support = univariate_filter.get_support()
    gtruth = np.ones(20)
    assert_array_equal(support, gtruth)

def test_f_regression():
    """
    Test whether the F test yields meaningful results
    on a simple simulated regression problem
    """
    X, Y = make_regression(n_samples=200, n_features=20, n_informative=5, shuffle=False, random_state=0)

    F, pv = f_regression(X, Y)
    assert (F > 0).all()
    assert (pv > 0).all()
    assert (pv < 1).all()
    assert (pv[:5] < 0.05).all()
    assert (pv[5:] > 1.0e-4).all()

def test_regression_big():
    X, y = make_regression(n_samples=200000,
                           n_features=10,
                           n_informative=5,
                           noise=30.0,
                           random_state=0)
    X = pd.DataFrame(X)
    y = pd.Series(y)
    cls = MALSS(X, y, 'regression', n_jobs=3)
    cls.execute()
    # cls.make_report('test_regression_big')

    assert len(cls.algorithms) == 1
    assert cls.algorithms[0].best_score is not None