Python sklearn.manifold 模块，LocallyLinearEmbedding() 实例源码

def do_embedding(self, event=None):
        converted = self.parent.converted
        if converted is None:
            #self.conversion.convert_frames()
            self.parent.converted = np.load(self.parent.output_folder+'/converted.npy') #FIXME For debugging
            converted = self.parent.converted

        method_ind = self.method.currentIndex()
        print('Doing %s' % self.method.currentText())
        if method_ind == 0:
            self.embedder = manifold.SpectralEmbedding(n_components=4, n_jobs=-1)
        elif method_ind == 1:
            self.embedder = manifold.Isomap(n_components=4, n_jobs=-1)
        elif method_ind == 2:
            self.embedder = manifold.LocallyLinearEmbedding(n_components=4, n_jobs=-1, n_neighbors=20, method='modified')
        elif method_ind == 3:
            self.embedder = manifold.LocallyLinearEmbedding(n_components=4, n_jobs=-1, n_neighbors=20, method='hessian', eigen_solver='dense')
        elif method_ind == 4:
            self.embedder = manifold.MDS(n_components=4, n_jobs=-1)
        elif method_ind == 5:
            self.embedder = manifold.TSNE(n_components=3, init='pca')
        self.embedder.fit(converted)
        self.embed = self.embedder.embedding_
        self.embed_plot = self.embed

        self.gen_hist()
        self.plot_embedding()
        if not self.embedded:
            self.add_classes_frame()
        self.embedded = True

def test_LocallyLinearEmbedding(*data):
    '''
    test the LLE method
    :param data: train_data, train_value
    :return: None
    '''
    X,y=data
    for n in [4,3,2,1]:
        lle=manifold.LocallyLinearEmbedding(n_components=n)
        lle.fit(X)
        print('reconstruction_error(n_components=%d) : %s'%
            (n, lle.reconstruction_error_))

def plot_LocallyLinearEmbedding_k(*data):
    '''
    test the performance with different n_neighbors and reduce to 2-D
    :param data: train_data, train_value
    :return: None
    '''
    X,y=data
    Ks=[1,5,25,y.size-1]

    fig=plt.figure()
    for i, k in enumerate(Ks):
        lle=manifold.LocallyLinearEmbedding(n_components=2,n_neighbors=k)
        X_r=lle.fit_transform(X)

        ax=fig.add_subplot(2,2,i+1)
        colors=((1,0,0),(0,1,0),(0,0,1),(0.5,0.5,0),(0,0.5,0.5),(0.5,0,0.5),
            (0.4,0.6,0),(0.6,0.4,0),(0,0.6,0.4),(0.5,0.3,0.2),)
        for label ,color in zip( np.unique(y),colors):
            position=y==label
            ax.scatter(X_r[position,0],X_r[position,1],label="target= {0}"
            .format(label),color=color)

        ax.set_xlabel("X[0]")
        ax.set_ylabel("X[1]")
        ax.legend(loc="best")
        ax.set_title("k={0}".format(k))
    plt.suptitle("LocallyLinearEmbedding")
    plt.show()

def plot_LocallyLinearEmbedding_k_d1(*data):
    '''
    test the performance with different n_neighbors and reduce to 1-D
    :param data: train_data, train_value
    :return: None
    '''
    X,y=data
    Ks=[1,5,25,y.size-1]

    fig=plt.figure()
    for i, k in enumerate(Ks):
        lle=manifold.LocallyLinearEmbedding(n_components=1,n_neighbors=k)
        X_r=lle.fit_transform(X)

        ax=fig.add_subplot(2,2,i+1)
        colors=((1,0,0),(0,1,0),(0,0,1),(0.5,0.5,0),(0,0.5,0.5),(0.5,0,0.5),
            (0.4,0.6,0),(0.6,0.4,0),(0,0.6,0.4),(0.5,0.3,0.2),)
        for label ,color in zip( np.unique(y),colors):
            position=y==label
            ax.scatter(X_r[position],np.zeros_like(X_r[position]),
            label="target= {0}".format(label),color=color)

        ax.set_xlabel("X")
        ax.set_ylabel("Y")
        ax.legend(loc="best")
        ax.set_title("k={0}".format(k))
    plt.suptitle("LocallyLinearEmbedding")
    plt.show()

def test_lle_simple_grid():
    # note: ARPACK is numerically unstable, so this test will fail for
    #       some random seeds.  We choose 2 because the tests pass.
    rng = np.random.RandomState(2)

    # grid of equidistant points in 2D, n_components = n_dim
    X = np.array(list(product(range(5), repeat=2)))
    X = X + 1e-10 * rng.uniform(size=X.shape)
    n_components = 2
    clf = manifold.LocallyLinearEmbedding(n_neighbors=5,
                                          n_components=n_components,
                                          random_state=rng)
    tol = 0.1

    N = barycenter_kneighbors_graph(X, clf.n_neighbors).toarray()
    reconstruction_error = linalg.norm(np.dot(N, X) - X, 'fro')
    assert_less(reconstruction_error, tol)

    for solver in eigen_solvers:
        clf.set_params(eigen_solver=solver)
        clf.fit(X)
        assert_true(clf.embedding_.shape[1] == n_components)
        reconstruction_error = linalg.norm(
            np.dot(N, clf.embedding_) - clf.embedding_, 'fro') ** 2

        assert_less(reconstruction_error, tol)
        assert_almost_equal(clf.reconstruction_error_,
                            reconstruction_error, decimal=1)

    # re-embed a noisy version of X using the transform method
    noise = rng.randn(*X.shape) / 100
    X_reembedded = clf.transform(X + noise)
    assert_less(linalg.norm(X_reembedded - clf.embedding_), tol)

def test_lle_manifold():
    rng = np.random.RandomState(0)
    # similar test on a slightly more complex manifold
    X = np.array(list(product(np.arange(18), repeat=2)))
    X = np.c_[X, X[:, 0] ** 2 / 18]
    X = X + 1e-10 * rng.uniform(size=X.shape)
    n_components = 2
    for method in ["standard", "hessian", "modified", "ltsa"]:
        clf = manifold.LocallyLinearEmbedding(n_neighbors=6,
                                              n_components=n_components,
                                              method=method, random_state=0)
        tol = 1.5 if method == "standard" else 3

        N = barycenter_kneighbors_graph(X, clf.n_neighbors).toarray()
        reconstruction_error = linalg.norm(np.dot(N, X) - X)
        assert_less(reconstruction_error, tol)

        for solver in eigen_solvers:
            clf.set_params(eigen_solver=solver)
            clf.fit(X)
            assert_true(clf.embedding_.shape[1] == n_components)
            reconstruction_error = linalg.norm(
                np.dot(N, clf.embedding_) - clf.embedding_, 'fro') ** 2
            details = ("solver: %s, method: %s" % (solver, method))
            assert_less(reconstruction_error, tol, msg=details)
            assert_less(np.abs(clf.reconstruction_error_ -
                               reconstruction_error),
                        tol * reconstruction_error, msg=details)


# Test the error raised when parameter passed to lle is invalid

def test_lle_init_parameters():
    X = np.random.rand(5, 3)

    clf = manifold.LocallyLinearEmbedding(eigen_solver="error")
    msg = "unrecognized eigen_solver 'error'"
    assert_raise_message(ValueError, msg, clf.fit, X)

    clf = manifold.LocallyLinearEmbedding(method="error")
    msg = "unrecognized method 'error'"
    assert_raise_message(ValueError, msg, clf.fit, X)

def test_pipeline():
    # check that LocallyLinearEmbedding works fine as a Pipeline
    # only checks that no error is raised.
    # TODO check that it actually does something useful
    from sklearn import pipeline, datasets
    X, y = datasets.make_blobs(random_state=0)
    clf = pipeline.Pipeline(
        [('filter', manifold.LocallyLinearEmbedding(random_state=0)),
         ('clf', neighbors.KNeighborsClassifier())])
    clf.fit(X, y)
    assert_less(.9, clf.score(X, y))


# Test the error raised when the weight matrix is singular

def visualize_encodings(encodings, file_name=None,
                        grid=None, skip_every=999, fast=False, fig=None, interactive=False):
  encodings = manual_pca(encodings)
  if encodings.shape[1] <= 3:
    return print_data_only(encodings, file_name, fig=fig, interactive=interactive)

  encodings = encodings[0:720]
  hessian_euc = dist.squareform(dist.pdist(encodings[0:720], 'euclidean'))
  hessian_cos = dist.squareform(dist.pdist(encodings[0:720], 'cosine'))
  grid = (3, 4) if grid is None else grid
  project_ops = []

  n = 2
  project_ops.append(("LLE ltsa       N:%d" % n, mn.LocallyLinearEmbedding(10, n, method='ltsa')))
  project_ops.append(("LLE modified   N:%d" % n, mn.LocallyLinearEmbedding(10, n, method='modified')))
  project_ops.append(('MDS euclidean  N:%d' % n, mn.MDS(n, max_iter=300, n_init=1, dissimilarity='precomputed')))
  project_ops.append(("TSNE 30/2000   N:%d" % n, TSNE(perplexity=30, n_components=n, init='pca', n_iter=2000)))
  n = 3
  project_ops.append(("LLE ltsa       N:%d" % n, mn.LocallyLinearEmbedding(10, n, method='ltsa')))
  project_ops.append(("LLE modified   N:%d" % n, mn.LocallyLinearEmbedding(10, n, method='modified')))
  project_ops.append(('MDS euclidean  N:%d' % n, mn.MDS(n, max_iter=300, n_init=1, dissimilarity='precomputed')))
  project_ops.append(('MDS cosine     N:%d' % n, mn.MDS(n, max_iter=300, n_init=1, dissimilarity='precomputed')))

  plot_places = []
  for i in range(12):
    u, v = int(i / (skip_every - 1)), i % (skip_every - 1)
    j = v + u * skip_every + 1
    plot_places.append(j)

  fig = get_figure(fig)
  fig.set_size_inches(fig.get_size_inches()[0] * grid[0] / 1.,
                      fig.get_size_inches()[1] * grid[1] / 2.0)

  for i, (name, manifold) in enumerate(project_ops):
    is3d = 'N:3' in name

    try:
      if is3d:
        subplot = plt.subplot(grid[0], grid[1], plot_places[i], projection='3d')
      else:
        subplot = plt.subplot(grid[0], grid[1], plot_places[i])

      data_source = encodings if not _needs_hessian(manifold) else \
        (hessian_cos if 'cosine' in name else hessian_euc)
      projections = manifold.fit_transform(data_source)
      scatter(subplot, projections, is3d, _build_radial_colors(len(data_source)))
      subplot.set_title(name)
    except:
      print(name, "Unexpected error: ", sys.exc_info()[0], sys.exc_info()[1] if len(sys.exc_info()) > 1 else '')

  visualize_data_same(encodings, grid=grid, places=plot_places[-4:])
  if not interactive:
    save_fig(file_name, fig)
  ut.print_time('visualization finished')