Python sklearn.decomposition.KernelPCA() Examples

def test_objectmapper(self):
        df = pdml.ModelFrame([])
        self.assertIs(df.decomposition.PCA, decomposition.PCA)
        self.assertIs(df.decomposition.IncrementalPCA,
                      decomposition.IncrementalPCA)
        self.assertIs(df.decomposition.KernelPCA, decomposition.KernelPCA)
        self.assertIs(df.decomposition.FactorAnalysis,
                      decomposition.FactorAnalysis)
        self.assertIs(df.decomposition.FastICA, decomposition.FastICA)
        self.assertIs(df.decomposition.TruncatedSVD, decomposition.TruncatedSVD)
        self.assertIs(df.decomposition.NMF, decomposition.NMF)
        self.assertIs(df.decomposition.SparsePCA, decomposition.SparsePCA)
        self.assertIs(df.decomposition.MiniBatchSparsePCA,
                      decomposition.MiniBatchSparsePCA)
        self.assertIs(df.decomposition.SparseCoder, decomposition.SparseCoder)
        self.assertIs(df.decomposition.DictionaryLearning,
                      decomposition.DictionaryLearning)
        self.assertIs(df.decomposition.MiniBatchDictionaryLearning,
                      decomposition.MiniBatchDictionaryLearning)

        self.assertIs(df.decomposition.LatentDirichletAllocation,
                      decomposition.LatentDirichletAllocation) 

def to_uts(mts, transformer):
    """PCA Dimension Reduction. Convert MTS to UTS

    Args:
        mts (ndarray): MTS
        transformer (class): PCA, KernelPCA, TSNE

    Returns:
        ndarray: UTS

    """
    model = PCA(n_components=1)
    if transformer == KernelPCA:
        model = KernelPCA(n_components=1, kernel="rbf")
    elif transformer == TSNE:
        model = TSNE(n_components=1, perplexity=40, n_iter=300)

    uts = model.fit_transform(mts)
    uts = uts.reshape(-1)
    return uts 

def to_uts(mts, transformer):
    """PCA Dimension Reduction. Convert MTS to UTS

    Args:
        mts (ndarray): MTS
        transformer (class): PCA, KernelPCA, TSNE

    Returns:
        ndarray: UTS

    """
    model = PCA(n_components=1)
    if transformer == KernelPCA:
        model = KernelPCA(n_components=1, kernel="rbf")
    elif transformer == TSNE:
        model = TSNE(n_components=1, perplexity=40, n_iter=300)

    uts = model.fit_transform(mts)
    uts = uts.reshape(-1)
    return uts 

def test_kernel_pca_precomputed():
    rng = np.random.RandomState(0)
    X_fit = rng.random_sample((5, 4))
    X_pred = rng.random_sample((2, 4))

    for eigen_solver in ("dense", "arpack"):
        X_kpca = KernelPCA(4, eigen_solver=eigen_solver).\
            fit(X_fit).transform(X_pred)
        X_kpca2 = KernelPCA(
            4, eigen_solver=eigen_solver, kernel='precomputed').fit(
                np.dot(X_fit, X_fit.T)).transform(np.dot(X_pred, X_fit.T))

        X_kpca_train = KernelPCA(
            4, eigen_solver=eigen_solver,
            kernel='precomputed').fit_transform(np.dot(X_fit, X_fit.T))
        X_kpca_train2 = KernelPCA(
            4, eigen_solver=eigen_solver, kernel='precomputed').fit(
                np.dot(X_fit, X_fit.T)).transform(np.dot(X_fit, X_fit.T))

        assert_array_almost_equal(np.abs(X_kpca),
                                  np.abs(X_kpca2))

        assert_array_almost_equal(np.abs(X_kpca_train),
                                  np.abs(X_kpca_train2)) 

def test_Decompositions_KernelPCA(self):
        iris = datasets.load_iris()
        df = pdml.ModelFrame(iris)

        mod1 = df.decomposition.KernelPCA()
        mod2 = decomposition.KernelPCA()

        df.fit(mod1)
        mod2.fit(iris.data, iris.target)

        result = df.transform(mod1)
        expected = mod2.transform(iris.data)

        self.assertIsInstance(result, pdml.ModelFrame)
        tm.assert_series_equal(df.target, result.target)
        self.assert_numpy_array_almost_equal(result.data.values[:, :40],
                                             expected[:, :40]) 

def test_kernel_pca_sparse():
    rng = np.random.RandomState(0)
    X_fit = sp.csr_matrix(rng.random_sample((5, 4)))
    X_pred = sp.csr_matrix(rng.random_sample((2, 4)))

    for eigen_solver in ("auto", "arpack"):
        for kernel in ("linear", "rbf", "poly"):
            # transform fit data
            kpca = KernelPCA(4, kernel=kernel, eigen_solver=eigen_solver,
                             fit_inverse_transform=False)
            X_fit_transformed = kpca.fit_transform(X_fit)
            X_fit_transformed2 = kpca.fit(X_fit).transform(X_fit)
            assert_array_almost_equal(np.abs(X_fit_transformed),
                                      np.abs(X_fit_transformed2))

            # transform new data
            X_pred_transformed = kpca.transform(X_pred)
            assert_equal(X_pred_transformed.shape[1],
                         X_fit_transformed.shape[1])

            # inverse transform
            # X_pred2 = kpca.inverse_transform(X_pred_transformed)
            # assert_equal(X_pred2.shape, X_pred.shape) 

def test_kernel_pca_sparse():
    rng = np.random.RandomState(0)
    X_fit = sp.csr_matrix(rng.random_sample((5, 4)))
    X_pred = sp.csr_matrix(rng.random_sample((2, 4)))

    for eigen_solver in ("auto", "arpack"):
        for kernel in ("linear", "rbf", "poly"):
            # transform fit data
            kpca = KernelPCA(4, kernel=kernel, eigen_solver=eigen_solver,
                             fit_inverse_transform=False)
            X_fit_transformed = kpca.fit_transform(X_fit)
            X_fit_transformed2 = kpca.fit(X_fit).transform(X_fit)
            assert_array_almost_equal(np.abs(X_fit_transformed),
                                      np.abs(X_fit_transformed2))

            # transform new data
            X_pred_transformed = kpca.transform(X_pred)
            assert_equal(X_pred_transformed.shape[1],
                         X_fit_transformed.shape[1])

            # inverse transform
            # X_pred2 = kpca.inverse_transform(X_pred_transformed)
            # assert_equal(X_pred2.shape, X_pred.shape) 

def test_leave_zero_eig():
    """This test checks that fit().transform() returns the same result as
    fit_transform() in case of non-removed zero eigenvalue.
    Non-regression test for issue #12141 (PR #12143)"""
    X_fit = np.array([[1, 1], [0, 0]])

    # Assert that even with all np warnings on, there is no div by zero warning
    with pytest.warns(None) as record:
        with np.errstate(all='warn'):
            k = KernelPCA(n_components=2, remove_zero_eig=False,
                          eigen_solver="dense")
            # Fit, then transform
            A = k.fit(X_fit).transform(X_fit)
            # Do both at once
            B = k.fit_transform(X_fit)
            # Compare
            assert_array_almost_equal(np.abs(A), np.abs(B))

    for w in record:
        # There might be warnings about the kernel being badly conditioned,
        # but there should not be warnings about division by zero.
        # (Numpy division by zero warning can have many message variants, but
        # at least we know that it is a RuntimeWarning so lets check only this)
        assert not issubclass(w.category, RuntimeWarning) 

def test_kernel_pca_precomputed():
    rng = np.random.RandomState(0)
    X_fit = rng.random_sample((5, 4))
    X_pred = rng.random_sample((2, 4))

    for eigen_solver in ("dense", "arpack"):
        X_kpca = KernelPCA(4, eigen_solver=eigen_solver).\
            fit(X_fit).transform(X_pred)
        X_kpca2 = KernelPCA(
            4, eigen_solver=eigen_solver, kernel='precomputed').fit(
                np.dot(X_fit, X_fit.T)).transform(np.dot(X_pred, X_fit.T))

        X_kpca_train = KernelPCA(
            4, eigen_solver=eigen_solver,
            kernel='precomputed').fit_transform(np.dot(X_fit, X_fit.T))
        X_kpca_train2 = KernelPCA(
            4, eigen_solver=eigen_solver, kernel='precomputed').fit(
                np.dot(X_fit, X_fit.T)).transform(np.dot(X_fit, X_fit.T))

        assert_array_almost_equal(np.abs(X_kpca),
                                  np.abs(X_kpca2))

        assert_array_almost_equal(np.abs(X_kpca_train),
                                  np.abs(X_kpca_train2)) 

def test_gridsearch_pipeline_precomputed():
    # Test if we can do a grid-search to find parameters to separate
    # circles with a perceptron model using a precomputed kernel.
    X, y = make_circles(n_samples=400, factor=.3, noise=.05,
                        random_state=0)
    kpca = KernelPCA(kernel="precomputed", n_components=2)
    pipeline = Pipeline([("kernel_pca", kpca),
                         ("Perceptron", Perceptron(max_iter=5))])
    param_grid = dict(Perceptron__max_iter=np.arange(1, 5))
    grid_search = GridSearchCV(pipeline, cv=3, param_grid=param_grid)
    X_kernel = rbf_kernel(X, gamma=2.)
    grid_search.fit(X_kernel, y)
    assert_equal(grid_search.best_score_, 1)


# 0.23. warning about tol not having its correct default value. 

def test_nested_circles():
    # Test the linear separability of the first 2D KPCA transform
    X, y = make_circles(n_samples=400, factor=.3, noise=.05,
                        random_state=0)

    # 2D nested circles are not linearly separable
    train_score = Perceptron(max_iter=5).fit(X, y).score(X, y)
    assert_less(train_score, 0.8)

    # Project the circles data into the first 2 components of a RBF Kernel
    # PCA model.
    # Note that the gamma value is data dependent. If this test breaks
    # and the gamma value has to be updated, the Kernel PCA example will
    # have to be updated too.
    kpca = KernelPCA(kernel="rbf", n_components=2,
                     fit_inverse_transform=True, gamma=2.)
    X_kpca = kpca.fit_transform(X)

    # The data is perfectly linearly separable in that space
    train_score = Perceptron(max_iter=5).fit(X_kpca, y).score(X_kpca, y)
    assert_equal(train_score, 1.0) 

def dim_reduction_method(self):
        """
        select dimensionality reduction method
        """
        if self.dim_reduction=='pca':
            return PCA()
        elif self.dim_reduction=='factor-analysis':
            return FactorAnalysis()
        elif self.dim_reduction=='fast-ica':
            return FastICA()
        elif self.dim_reduction=='kernel-pca':
            return KernelPCA()
        elif self.dim_reduction=='sparse-pca':
            return SparsePCA()
        elif self.dim_reduction=='truncated-svd':
            return TruncatedSVD()
        elif self.dim_reduction!=None:
            raise ValueError('%s is not a supported dimensionality reduction method. Valid inputs are: \
                             "pca","factor-analysis","fast-ica,"kernel-pca","sparse-pca","truncated-svd".' 
                             %(self.dim_reduction)) 

def __init__(self, options):
        self.handle_options(options)

        out_params = convert_params(
            options.get('params', {}),
            ints=['k', 'degree', 'alpha', 'max_iteration'],
            floats=['gamma', 'tolerance'],
            aliases={'k': 'n_components', 'tolerance': 'tol',
                     'max_iteration': 'max_iter'},
        )

        out_params['kernel'] = 'rbf'

        if 'n_components' not in out_params:
            out_params['n_components'] = min(2, len(options['feature_variables']))
        elif out_params['n_components'] == 0:
            raise RuntimeError('k needs to be greater than zero.')

        self.estimator = _KPCA(**out_params)

    # sklearn's KernelPCA.transform tries to form a complete kernel
    # matrix of its input and the original data the model was fit
    # on. Unfortunately, this might consume a colossal amount of
    # memory for large inputs. We chunk the input to cut down on this. 

def test_kernel_pca_consistent_transform():
    # X_fit_ needs to retain the old, unmodified copy of X
    state = np.random.RandomState(0)
    X = state.rand(10, 10)
    kpca = KernelPCA(random_state=state).fit(X)
    transformed1 = kpca.transform(X)

    X_copy = X.copy()
    X[:, 0] = 666
    transformed2 = kpca.transform(X_copy)
    assert_array_almost_equal(transformed1, transformed2) 

def test_kernel_pca():
    rng = np.random.RandomState(0)
    X_fit = rng.random_sample((5, 4))
    X_pred = rng.random_sample((2, 4))

    def histogram(x, y, **kwargs):
        # Histogram kernel implemented as a callable.
        assert_equal(kwargs, {})    # no kernel_params that we didn't ask for
        return np.minimum(x, y).sum()

    for eigen_solver in ("auto", "dense", "arpack"):
        for kernel in ("linear", "rbf", "poly", histogram):
            # histogram kernel produces singular matrix inside linalg.solve
            # XXX use a least-squares approximation?
            inv = not callable(kernel)

            # transform fit data
            kpca = KernelPCA(4, kernel=kernel, eigen_solver=eigen_solver,
                             fit_inverse_transform=inv)
            X_fit_transformed = kpca.fit_transform(X_fit)
            X_fit_transformed2 = kpca.fit(X_fit).transform(X_fit)
            assert_array_almost_equal(np.abs(X_fit_transformed),
                                      np.abs(X_fit_transformed2))

            # non-regression test: previously, gamma would be 0 by default,
            # forcing all eigenvalues to 0 under the poly kernel
            assert_not_equal(X_fit_transformed.size, 0)

            # transform new data
            X_pred_transformed = kpca.transform(X_pred)
            assert_equal(X_pred_transformed.shape[1],
                         X_fit_transformed.shape[1])

            # inverse transform
            if inv:
                X_pred2 = kpca.inverse_transform(X_pred_transformed)
                assert_equal(X_pred2.shape, X_pred.shape) 

def test_kernel_pca_invalid_parameters():
    assert_raises(ValueError, KernelPCA, 10, fit_inverse_transform=True,
                  kernel='precomputed') 

def trainKernelPCA(data):
    """
    使用带有核函数的主成分分析对数据进行降维
    """
    model = KernelPCA(n_components=2, kernel="rbf", gamma=25)
    model.fit(data)
    return model 

def test_kernel_pca_linear_kernel():
    rng = np.random.RandomState(0)
    X_fit = rng.random_sample((5, 4))
    X_pred = rng.random_sample((2, 4))

    # for a linear kernel, kernel PCA should find the same projection as PCA
    # modulo the sign (direction)
    # fit only the first four components: fifth is near zero eigenvalue, so
    # can be trimmed due to roundoff error
    assert_array_almost_equal(
        np.abs(KernelPCA(4).fit(X_fit).transform(X_pred)),
        np.abs(PCA(4).fit(X_fit).transform(X_pred))) 

def test_remove_zero_eig():
    X = np.array([[1 - 1e-30, 1], [1, 1], [1, 1 - 1e-20]])

    # n_components=None (default) => remove_zero_eig is True
    kpca = KernelPCA()
    Xt = kpca.fit_transform(X)
    assert_equal(Xt.shape, (3, 0))

    kpca = KernelPCA(n_components=2)
    Xt = kpca.fit_transform(X)
    assert_equal(Xt.shape, (3, 2))

    kpca = KernelPCA(n_components=2, remove_zero_eig=True)
    Xt = kpca.fit_transform(X)
    assert_equal(Xt.shape, (3, 0)) 

def test_kernel_pca_invalid_kernel():
    rng = np.random.RandomState(0)
    X_fit = rng.random_sample((2, 4))
    kpca = KernelPCA(kernel="tototiti")
    assert_raises(ValueError, kpca.fit, X_fit) 

def test_gridsearch_pipeline():
    # Test if we can do a grid-search to find parameters to separate
    # circles with a perceptron model.
    X, y = make_circles(n_samples=400, factor=.3, noise=.05,
                        random_state=0)
    kpca = KernelPCA(kernel="rbf", n_components=2)
    pipeline = Pipeline([("kernel_pca", kpca),
                         ("Perceptron", Perceptron(max_iter=5))])
    param_grid = dict(kernel_pca__gamma=2. ** np.arange(-2, 2))
    grid_search = GridSearchCV(pipeline, cv=3, param_grid=param_grid)
    grid_search.fit(X, y)
    assert_equal(grid_search.best_score_, 1) 

def test_gridsearch_pipeline_precomputed():
    # Test if we can do a grid-search to find parameters to separate
    # circles with a perceptron model using a precomputed kernel.
    X, y = make_circles(n_samples=400, factor=.3, noise=.05,
                        random_state=0)
    kpca = KernelPCA(kernel="precomputed", n_components=2)
    pipeline = Pipeline([("kernel_pca", kpca),
                         ("Perceptron", Perceptron(max_iter=5))])
    param_grid = dict(Perceptron__max_iter=np.arange(1, 5))
    grid_search = GridSearchCV(pipeline, cv=3, param_grid=param_grid)
    X_kernel = rbf_kernel(X, gamma=2.)
    grid_search.fit(X_kernel, y)
    assert_equal(grid_search.best_score_, 1) 

def test_fit_transform_KernelPCA(self):
        iris = datasets.load_iris()
        df = pdml.ModelFrame(iris)

        mod1 = df.decomposition.KernelPCA()
        mod2 = decomposition.KernelPCA()

        result = df.fit_transform(mod1)
        expected = mod2.fit_transform(iris.data, iris.target)

        self.assertIsInstance(result, pdml.ModelFrame)
        tm.assert_series_equal(df.target, result.target)
        self.assert_numpy_array_almost_equal(result.data.values[:, :40],
                                             expected[:, :40]) 

def reduce_KernelPCA(x, **kwd_params):
    '''
        Reduce the dimensions using Principal Component
        Analysis with different kernels
    '''
    # create the PCA object
    pca = dc.KernelPCA(**kwd_params)

    # learn the principal components from all the features
    return pca.fit(x)

# the file name of the dataset 

def test_kernel_pca_invalid_kernel():
    rng = np.random.RandomState(0)
    X_fit = rng.random_sample((2, 4))
    kpca = KernelPCA(kernel="tototiti")
    assert_raises(ValueError, kpca.fit, X_fit) 

def test_remove_zero_eig():
    X = np.array([[1 - 1e-30, 1], [1, 1], [1, 1 - 1e-20]])

    # n_components=None (default) => remove_zero_eig is True
    kpca = KernelPCA()
    Xt = kpca.fit_transform(X)
    assert_equal(Xt.shape, (3, 0))

    kpca = KernelPCA(n_components=2)
    Xt = kpca.fit_transform(X)
    assert_equal(Xt.shape, (3, 2))

    kpca = KernelPCA(n_components=2, remove_zero_eig=True)
    Xt = kpca.fit_transform(X)
    assert_equal(Xt.shape, (3, 0)) 

def test_kernel_pca_n_components():
    rng = np.random.RandomState(0)
    X_fit = rng.random_sample((5, 4))
    X_pred = rng.random_sample((2, 4))

    for eigen_solver in ("dense", "arpack"):
        for c in [1, 2, 4]:
            kpca = KernelPCA(n_components=c, eigen_solver=eigen_solver)
            shape = kpca.fit(X_fit).transform(X_pred).shape

            assert_equal(shape, (2, c)) 

def test_kernel_pca_deterministic_output():
    rng = np.random.RandomState(0)
    X = rng.rand(10, 10)
    eigen_solver = ('arpack', 'dense')

    for solver in eigen_solver:
        transformed_X = np.zeros((20, 2))
        for i in range(20):
            kpca = KernelPCA(n_components=2, eigen_solver=solver,
                             random_state=rng)
            transformed_X[i, :] = kpca.fit_transform(X)[0]
        assert_allclose(
            transformed_X, np.tile(transformed_X[0, :], 20).reshape(20, 2)) 

def test_kernel_pca_consistent_transform():
    # X_fit_ needs to retain the old, unmodified copy of X
    state = np.random.RandomState(0)
    X = state.rand(10, 10)
    kpca = KernelPCA(random_state=state).fit(X)
    transformed1 = kpca.transform(X)

    X_copy = X.copy()
    X[:, 0] = 666
    transformed2 = kpca.transform(X_copy)
    assert_array_almost_equal(transformed1, transformed2) 

def test_kernel_pca_invalid_parameters():
    assert_raises(ValueError, KernelPCA, 10, fit_inverse_transform=True,
                  kernel='precomputed')