Python multioutput.MultiOutputRegressor类代码示例

    def test_multioutput(self):

        # http://scikit-learn.org/stable/auto_examples/ensemble/plot_random_forest_regression_multioutput.html#sphx-glr-auto-examples-ensemble-plot-random-forest-regression-multioutput-py

        from sklearn.multioutput import MultiOutputRegressor
        from sklearn.ensemble import RandomForestRegressor

        # Create a random dataset
        rng = np.random.RandomState(1)
        X = np.sort(200 * rng.rand(600, 1) - 100, axis=0)
        y = np.array([np.pi * np.sin(X).ravel(), np.pi * np.cos(X).ravel()]).T
        y += (0.5 - rng.rand(*y.shape))

        df = pdml.ModelFrame(X, target=y)

        max_depth = 30

        rf1 = df.ensemble.RandomForestRegressor(max_depth=max_depth,
                                                random_state=self.random_state)
        reg1 = df.multioutput.MultiOutputRegressor(rf1)

        rf2 = RandomForestRegressor(max_depth=max_depth,
                                    random_state=self.random_state)
        reg2 = MultiOutputRegressor(rf2)

        df.fit(reg1)
        reg2.fit(X, y)

        result = df.predict(reg2)
        expected = pd.DataFrame(reg2.predict(X))
        tm.assert_frame_equal(result, expected)

def test_multi_target_sample_weights_api():
    X = [[1, 2, 3], [4, 5, 6]]
    y = [[3.141, 2.718], [2.718, 3.141]]
    w = [0.8, 0.6]

    rgr = MultiOutputRegressor(Lasso())
    assert_raises_regex(ValueError, "does not support sample weights", rgr.fit, X, y, w)

    # no exception should be raised if the base estimator supports weights
    rgr = MultiOutputRegressor(GradientBoostingRegressor(random_state=0))
    rgr.fit(X, y, w)

def test_acquisition_per_second_gradient(acq_func):
    rng = np.random.RandomState(0)
    X = rng.randn(20, 10)
    # Make the second component large, so that mean_grad and std_grad
    # do not become zero.
    y = np.vstack((X[:, 0], np.abs(X[:, 0])**3)).T

    for X_new in [rng.randn(10), rng.randn(10)]:
        gpr = cook_estimator("GP", Space(((-5.0, 5.0),)), random_state=0)
        mor = MultiOutputRegressor(gpr)
        mor.fit(X, y)
        check_gradient_correctness(X_new, mor, acq_func, 1.5)

def test_multi_target_sparse_regression():
    X, y = datasets.make_regression(n_targets=3)
    X_train, y_train = X[:50], y[:50]
    X_test = X[50:]

    for sparse in [sp.csr_matrix, sp.csc_matrix, sp.coo_matrix, sp.dok_matrix, sp.lil_matrix]:
        rgr = MultiOutputRegressor(Lasso(random_state=0))
        rgr_sparse = MultiOutputRegressor(Lasso(random_state=0))

        rgr.fit(X_train, y_train)
        rgr_sparse.fit(sparse(X_train), y_train)

        assert_almost_equal(rgr.predict(X_test), rgr_sparse.predict(sparse(X_test)))

def test_multi_target_sample_weight_partial_fit():
    # weighted regressor
    X = [[1, 2, 3], [4, 5, 6]]
    y = [[3.141, 2.718], [2.718, 3.141]]
    w = [2., 1.]
    rgr_w = MultiOutputRegressor(SGDRegressor(random_state=0))
    rgr_w.partial_fit(X, y, w)

    # weighted with different weights
    w = [2., 2.]
    rgr = MultiOutputRegressor(SGDRegressor(random_state=0))
    rgr.partial_fit(X, y, w)

    assert_not_equal(rgr.predict(X)[0][0], rgr_w.predict(X)[0][0])

def test_multi_target_sample_weights():
    # weighted regressor
    Xw = [[1, 2, 3], [4, 5, 6]]
    yw = [[3.141, 2.718], [2.718, 3.141]]
    w = [2., 1.]
    rgr_w = MultiOutputRegressor(GradientBoostingRegressor(random_state=0))
    rgr_w.fit(Xw, yw, w)

    # unweighted, but with repeated samples
    X = [[1, 2, 3], [1, 2, 3], [4, 5, 6]]
    y = [[3.141, 2.718], [3.141, 2.718], [2.718, 3.141]]
    rgr = MultiOutputRegressor(GradientBoostingRegressor(random_state=0))
    rgr.fit(X, y)

    X_test = [[1.5, 2.5, 3.5], [3.5, 4.5, 5.5]]
    assert_almost_equal(rgr.predict(X_test), rgr_w.predict(X_test))

        mplpyplot.show()
# nodebox section end


# Create a random dataset
rng = np.random.RandomState(1)
X = np.sort(200 * rng.rand(600, 1) - 100, axis=0)
y = np.array([np.pi * np.sin(X).ravel(), np.pi * np.cos(X).ravel()]).T
y += (0.5 - rng.rand(*y.shape))

X_train, X_test, y_train, y_test = train_test_split(X, y,
                                                    train_size=400,
                                                    random_state=4)

max_depth = 30
regr_multirf = MultiOutputRegressor(RandomForestRegressor(max_depth=max_depth,
                                                          random_state=0))
regr_multirf.fit(X_train, y_train)

regr_rf = RandomForestRegressor(max_depth=max_depth, random_state=2)
regr_rf.fit(X_train, y_train)

# Predict on new data
y_multirf = regr_multirf.predict(X_test)
y_rf = regr_rf.predict(X_test)

# Plot the results
plt.figure()
s = 50
a = 0.4
plt.scatter(y_test[:, 0], y_test[:, 1], edgecolor='k',
            c="navy", s=s, marker="s", alpha=a, label="Data")

feature = "Diabetes"
# get X and y data
train = pd.read_csv("train.csv", delimiter=",")
train = train.drop_duplicates() # ensure no duplicates
y_train = train[feature].to_frame()
names = y_train[feature].unique()
X_train = train.drop(feature, 1)
X_names = list(X_train)

# Get test data
test = pd.read_csv("test.csv", delimiter=",")
X_test = test

max_depth = 3
regr_multirf = MultiOutputRegressor(RandomForestRegressor(max_depth=max_depth))
regr_multirf.fit(X_train, y_train)

regr_rf = RandomForestRegressor(n_estimators=20, max_depth=max_depth)
regr_rf.fit(X_train, y_train)

# Predict on new data
y_multirf = regr_multirf.predict(X_test)
y_rf = regr_rf.predict(X_test)

# put predictions into csv
IDs = pd.DataFrame(X_test["ID"])
y_pred = pd.DataFrame(y_multirf)
pred_data = IDs.join(y_pred)
pred_data.columns = ['ID', 'Prediction']
pred_data.to_csv(path_or_buf="prediction_multirf.csv", index=False)