Python decomposition.SparsePCA类代码示例

def test_initialization():
    rng = np.random.RandomState(0)
    U_init = rng.randn(5, 3)
    V_init = rng.randn(3, 4)
    model = SparsePCA(n_components=3, U_init=U_init, V_init=V_init, max_iter=0, random_state=rng)
    model.fit(rng.randn(5, 4))
    assert_array_equal(model.components_, V_init)

def test_fit_transform_tall():
    rng = np.random.RandomState(0)
    Y, _, _ = generate_toy_data(3, 65, (8, 8), random_state=rng)  # tall array
    spca_lars = SparsePCA(n_components=3, method="lars", random_state=rng)
    U1 = spca_lars.fit_transform(Y)
    spca_lasso = SparsePCA(n_components=3, method="cd", random_state=rng)
    U2 = spca_lasso.fit(Y).transform(Y)
    assert_array_almost_equal(U1, U2)

 def sparse_pca(self):
     """
     Runs PCA on view and returns projected view, the principle components,
     and explained variance.
     """
     model = SparsePCA(n_components=param['components'], alpha=param['sparse_pca_alpha'])
     model.fit(self.view)
     return model.transform(self.view), model.components_

def test_transform_nan():
    # Test that SparsePCA won't return NaN when there is 0 feature in all
    # samples.
    rng = np.random.RandomState(0)
    Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)  # wide array
    Y[:, 0] = 0
    estimator = SparsePCA(n_components=8)
    assert_false(np.any(np.isnan(estimator.fit_transform(Y))))

def sccodedirect():
    "得到不带眼镜的RPCA结果"
    nglassmodel = np.load('nglassline.npy').astype('f')
    from sklearn.decomposition import SparsePCA
    learning = SparsePCA(500,verbose=True)
    learning.fit(nglassmodel)
    import cPickle
    cPickle.dump(learning,file('sparsepcadirect','wb'),-1)

def test_scaling_fit_transform():
    alpha = 1
    rng = np.random.RandomState(0)
    Y, _, _ = generate_toy_data(3, 1000, (8, 8), random_state=rng)
    spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
                          random_state=rng, normalize_components=True)
    results_train = spca_lars.fit_transform(Y)
    results_test = spca_lars.transform(Y[:10])
    assert_allclose(results_train[0], results_test[0])

def test_correct_shapes():
    rng = np.random.RandomState(0)
    X = rng.randn(12, 10)
    spca = SparsePCA(n_components=8, random_state=rng)
    U = spca.fit_transform(X)
    assert_equal(spca.components_.shape, (8, 10))
    assert_equal(U.shape, (12, 8))
    # test overcomplete decomposition
    spca = SparsePCA(n_components=13, random_state=rng)
    U = spca.fit_transform(X)
    assert_equal(spca.components_.shape, (13, 10))
    assert_equal(U.shape, (12, 13))

def test_initialization(norm_comp):
    rng = np.random.RandomState(0)
    U_init = rng.randn(5, 3)
    V_init = rng.randn(3, 4)
    model = SparsePCA(n_components=3, U_init=U_init, V_init=V_init, max_iter=0,
                      random_state=rng, normalize_components=norm_comp)
    model.fit(rng.randn(5, 4))
    if norm_comp:
        assert_allclose(model.components_,
                        V_init / np.linalg.norm(V_init, axis=1)[:, None])
    else:
        assert_allclose(model.components_, V_init)

def do_sparse_pca(sparse_matrix):
    # from skikit learn http://scikit-learn.org/stable/modules/generated/sklearn.decomposition.SparsePCA.html#sklearn.decomposition.SparsePCA

    dense_matrix = sparse_matrix.tobsr().toarray()
    # instantiate the spca with some parameters
    spca = SparsePCA(n_components=6, alpha=0.01, ridge_alpha=0.01, max_iter=1000, tol=1e-08, method='lars', n_jobs=1, U_init=None, V_init=None, verbose=False, random_state=None)

    # train the spca with our matrix
    spca.fit(dense_matrix)

    # return the components
    return spca.components_

def test_pca_vs_spca():
    rng = np.random.RandomState(0)
    Y, _, _ = generate_toy_data(3, 1000, (8, 8), random_state=rng)
    Z, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)
    spca = SparsePCA(alpha=0, ridge_alpha=0, n_components=2,
                     normalize_components=True)
    pca = PCA(n_components=2)
    pca.fit(Y)
    spca.fit(Y)
    results_test_pca = pca.transform(Z)
    results_test_spca = spca.transform(Z)
    assert_allclose(np.abs(spca.components_.dot(pca.components_.T)),
                    np.eye(2), atol=1e-5)
    results_test_pca *= np.sign(results_test_pca[0, :])
    results_test_spca *= np.sign(results_test_spca[0, :])
    assert_allclose(results_test_pca, results_test_spca)

    def __init__(self, num_components=10,
                 catalog_name='unknown',
                 alpha = 0.1,
                 ridge_alpha = 0.01,
                 max_iter = 2000,
                 tol = 1e-9,
                 n_jobs = 1,
                 random_state = None):

        self._decomposition  = 'Sparse PCA'
        self._num_components = num_components
        self._catalog_name   = catalog_name
        self._alpha          = alpha
        self._ridge_alpha    = ridge_alpha
        self._n_jobs         = n_jobs
        self._max_iter       = max_iter
        self._tol            = tol
        self._random_state   = random_state

        self._SPCA = SparsePCA(n_components=self._num_components,
                              alpha        = self._alpha,
                              ridge_alpha  = self._ridge_alpha,
                              n_jobs       = self._n_jobs,
                              max_iter     = self._max_iter,
                              tol          = self._tol,
                              random_state = self._random_state)

def spca(data, num_components=None, alpha=1):
		# creates a matrix with sparse principal component analysis
		# build matrix with all data
		data = [d.flatten() for d in data if not any(isnan(d))]
		datamatrix = row_stack(data)
		
		# center data
		cdata = datamatrix - mean(datamatrix, axis=0)
		
		if num_components is None:
			num_components = cdata.shape[0]
		
		# do spca on matrix
		spca = SparsePCA(n_components=num_components, alpha=alpha)
		spca.fit(cdata)
		
		# normalize components
		components = spca.components_.T
		for r in xrange(0,components.shape[1]):
			compnorm = numpy.apply_along_axis(numpy.linalg.norm, 0, components[:,r])
			if not compnorm == 0:
				components[:,r] /= compnorm
		components = components.T
		
		# calc adjusted explained variance from "Sparse Principal Component Analysis" by Zou, Hastie, Tibshirani
		spca.components_ = components
		#nuz = spca.transform(cdata).T
		nuz = ridge_regression(spca.components_.T, cdata.T, 0.01, solver='dense_cholesky').T
		
		#nuz = dot(components, cdata.T)
		q,r = qr(nuz.T)
		cumulative_var = []
		for i in range(1,num_components+1):
			cumulative_var.append(trace(r[0:i,]*r[0:i,]))
		explained_var = [math.sqrt(cumulative_var[0])]
		for i in range(1,num_components):
			explained_var.append(math.sqrt(cumulative_var[i])-math.sqrt(cumulative_var[i-1]))
		
		order = numpy.argsort(explained_var)[::-1]
		components = numpy.take(components,order,axis=0)
		evars = numpy.take(explained_var,order).tolist()
		#evars = numpy.take(explained_var,order)
		#order2 = [0,1,2,4,5,7,12,19]
		#components = numpy.take(components,order2,axis=0)
		#evars = numpy.take(evars,order2).tolist()
		
		return components, evars

def test_fit_transform():
    alpha = 1
    rng = np.random.RandomState(0)
    Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)  # wide array
    spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
                          random_state=0)
    spca_lars.fit(Y)
    U1 = spca_lars.transform(Y)
    # Test multiple CPUs
    spca = SparsePCA(n_components=3, n_jobs=2, method='lars', alpha=alpha,
                     random_state=0).fit(Y)
    U2 = spca.transform(Y)
    assert_true(not np.all(spca_lars.components_ == 0))
    assert_array_almost_equal(U1, U2)
    # Test that CD gives similar results
    spca_lasso = SparsePCA(n_components=3, method='cd', random_state=0,
                           alpha=alpha)
    spca_lasso.fit(Y)
    assert_array_almost_equal(spca_lasso.components_, spca_lars.components_)

def test_fit_transform():
    alpha = 1
    rng = np.random.RandomState(0)
    Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)  # wide array
    spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
                          random_state=0)
    spca_lars.fit(Y)

    # Test that CD gives similar results
    spca_lasso = SparsePCA(n_components=3, method='cd', random_state=0,
                           alpha=alpha)
    spca_lasso.fit(Y)
    assert_array_almost_equal(spca_lasso.components_, spca_lars.components_)

def test_fit_transform_parallel(norm_comp):
    alpha = 1
    rng = np.random.RandomState(0)
    Y, _, _ = generate_toy_data(3, 10, (8, 8), random_state=rng)  # wide array
    spca_lars = SparsePCA(n_components=3, method='lars', alpha=alpha,
                          random_state=0, normalize_components=norm_comp)
    spca_lars.fit(Y)
    U1 = spca_lars.transform(Y)
    # Test multiple CPUs
    spca = SparsePCA(n_components=3, n_jobs=2, method='lars', alpha=alpha,
                     random_state=0, normalize_components=norm_comp).fit(Y)
    U2 = spca.transform(Y)
    assert_true(not np.all(spca_lars.components_ == 0))
    assert_array_almost_equal(U1, U2)