Python LinearRegression.score方法代码示例

# 需要导入模块: from sklearn.linear_model.base import LinearRegression [as 别名]
# 或者: from sklearn.linear_model.base.LinearRegression import score [as 别名]
def test_linear_regression_sample_weights():
    # TODO: loop over sparse data as well

    rng = np.random.RandomState(0)

    # It would not work with under-determined systems
    for n_samples, n_features in ((6, 5), ):

        y = rng.randn(n_samples)
        X = rng.randn(n_samples, n_features)
        sample_weight = 1.0 + rng.rand(n_samples)

        for intercept in (True, False):

            # LinearRegression with explicit sample_weight
            reg = LinearRegression(fit_intercept=intercept)
            reg.fit(X, y, sample_weight=sample_weight)
            coefs1 = reg.coef_
            inter1 = reg.intercept_

            assert_equal(reg.coef_.shape, (X.shape[1], ))  # sanity checks
            assert_greater(reg.score(X, y), 0.5)

            # Closed form of the weighted least square
            # theta = (X^T W X)^(-1) * X^T W y
            W = np.diag(sample_weight)
            if intercept is False:
                X_aug = X
            else:
                dummy_column = np.ones(shape=(n_samples, 1))
                X_aug = np.concatenate((dummy_column, X), axis=1)

            coefs2 = linalg.solve(X_aug.T.dot(W).dot(X_aug),
                                  X_aug.T.dot(W).dot(y))

            if intercept is False:
                assert_array_almost_equal(coefs1, coefs2)
            else:
                assert_array_almost_equal(coefs1, coefs2[1:])
                assert_almost_equal(inter1, coefs2[0])

# 需要导入模块: from sklearn.linear_model.base import LinearRegression [as 别名]
# 或者: from sklearn.linear_model.base.LinearRegression import score [as 别名]
def test_linear_regression_sample_weights():
    rng = np.random.RandomState(0)

    for n_samples, n_features in ((6, 5), (5, 10)):
        y = rng.randn(n_samples)
        X = rng.randn(n_samples, n_features)
        sample_weight = 1.0 + rng.rand(n_samples)

        clf = LinearRegression()
        clf.fit(X, y, sample_weight)
        coefs1 = clf.coef_

        assert_equal(clf.coef_.shape, (X.shape[1], ))
        assert_greater(clf.score(X, y), 0.9)
        assert_array_almost_equal(clf.predict(X), y)

        # Sample weight can be implemented via a simple rescaling
        # for the square loss.
        scaled_y = y * np.sqrt(sample_weight)
        scaled_X = X * np.sqrt(sample_weight)[:, np.newaxis]
        clf.fit(X, y)
        coefs2 = clf.coef_

        assert_array_almost_equal(coefs1, coefs2)

# 需要导入模块: from sklearn.linear_model.base import LinearRegression [as 别名]
# 或者: from sklearn.linear_model.base.LinearRegression import score [as 别名]
    plt.scatter( feature, target, color=test_color ) 
for feature, target in zip(feature_train, target_train):
    plt.scatter( feature, target, color=train_color ) 

### labels for the legend
plt.scatter(feature_test[0], target_test[0], color=test_color, label="test")
plt.scatter(feature_test[0], target_test[0], color=train_color, label="train")


from sklearn.linear_model.base import LinearRegression

reg = LinearRegression()
reg.fit(feature_train, target_train)
print("Slope %s" % reg.coef_)
print("Intercept %s" % reg.intercept_)

print("Score = ", reg.score(feature_test, target_test))
### draw the regression line, once it's coded
try:
    plt.plot( feature_test, reg.predict(feature_test) )
except NameError:
    pass
reg.fit(feature_test, target_test)
plt.plot(feature_train, reg.predict(feature_train), color="b")
plt.xlabel(features_list[1])
plt.ylabel(features_list[0])
plt.legend()
plt.show()
print("Slope2 %s" % reg.coef_)
print("Intercept2 %s" % reg.intercept_)

# 需要导入模块: from sklearn.linear_model.base import LinearRegression [as 别名]
# 或者: from sklearn.linear_model.base.LinearRegression import score [as 别名]
### and n_columns is the number of features
ages       = numpy.reshape( numpy.array(ages), (len(ages), 1))
net_worths = numpy.reshape( numpy.array(net_worths), (len(net_worths), 1))
from sklearn.cross_validation import train_test_split
ages_train, ages_test, net_worths_train, net_worths_test = train_test_split(ages, net_worths, test_size=0.1, random_state=42)

### fill in a regression here!  Name the regression object reg so that
### the plotting code below works, and you can see what your regression looks like
from sklearn.linear_model.base import LinearRegression

reg = LinearRegression()
reg.fit(ages_train, net_worths_train)
print("Slope %s" % reg.coef_)
print("Intercept %s" % reg.intercept_)

print("Score = ", reg.score(ages_test, net_worths_test))






try:
    plt.plot(ages, reg.predict(ages), color="blue")
except NameError:
    pass
plt.scatter(ages, net_worths)
plt.show()


### identify and remove the most outlier-y points