Python t_sne.TSNE类代码示例

def test_reduction_to_one_component():
    # t-SNE should allow reduction to one component (issue #4154).
    random_state = check_random_state(0)
    tsne = TSNE(n_components=1)
    X = random_state.randn(5, 2)
    X_embedded = tsne.fit(X).embedding_
    assert(np.all(np.isfinite(X_embedded)))

def test_accessible_kl_divergence():
    # Ensures that the accessible kl_divergence matches the computed value
    random_state = check_random_state(0)
    X = random_state.randn(100, 2)
    tsne = TSNE(n_iter_without_progress=2, verbose=2,
                random_state=0, method='exact')

    old_stdout = sys.stdout
    sys.stdout = StringIO()
    try:
        tsne.fit_transform(X)
    finally:
        out = sys.stdout.getvalue()
        sys.stdout.close()
        sys.stdout = old_stdout

    # The output needs to contain the accessible kl_divergence as the error at
    # the last iteration
    for line in out.split('\n')[::-1]:
        if 'Iteration' in line:
            _, _, error = line.partition('error = ')
            if error:
                error, _, _ = error.partition(',')
                break
    assert_almost_equal(tsne.kl_divergence_, float(error), decimal=5)

def check_uniform_grid(method, seeds=[0, 1, 2], n_iter=1000):
    """Make sure that TSNE can approximately recover a uniform 2D grid

    Due to ties in distances between point in X_2d_grid, this test is platform
    dependent for ``method='barnes_hut'`` due to numerical imprecision.

    Also, t-SNE is not assured to converge to the right solution because bad
    initialization can lead to convergence to bad local minimum (the
    optimization problem is non-convex). To avoid breaking the test too often,
    we re-run t-SNE from the final point when the convergence is not good
    enough.
    """
    for seed in seeds:
        tsne = TSNE(n_components=2, init='random', random_state=seed,
                    perplexity=20, n_iter=n_iter, method=method)
        Y = tsne.fit_transform(X_2d_grid)

        try_name = "{}_{}".format(method, seed)
        try:
            assert_uniform_grid(Y, try_name)
        except AssertionError:
            # If the test fails a first time, re-run with init=Y to see if
            # this was caused by a bad initialization. Note that this will
            # also run an early_exaggeration step.
            try_name += ":rerun"
            tsne.init = Y
            Y = tsne.fit_transform(X_2d_grid)
            assert_uniform_grid(Y, try_name)

def test_preserve_trustworthiness_approximately_with_precomputed_distances():
    # Nearest neighbors should be preserved approximately.
    random_state = check_random_state(0)
    X = random_state.randn(100, 2)
    D = squareform(pdist(X), "sqeuclidean")
    tsne = TSNE(n_components=2, perplexity=2, learning_rate=100.0, metric="precomputed", random_state=0, verbose=0)
    X_embedded = tsne.fit_transform(D)
    assert_almost_equal(trustworthiness(D, X_embedded, n_neighbors=1, precomputed=True), 1.0, decimal=1)

def test_64bit():
    # Ensure 64bit arrays are handled correctly.
    random_state = check_random_state(0)
    methods = ["barnes_hut", "exact"]
    for method in methods:
        for dt in [np.float32, np.float64]:
            X = random_state.randn(100, 2).astype(dt)
            tsne = TSNE(n_components=2, perplexity=2, learning_rate=100.0, random_state=0, method=method)
            tsne.fit_transform(X)

def test_fit_csr_matrix():
    # X can be a sparse matrix.
    random_state = check_random_state(0)
    X = random_state.randn(100, 2)
    X[(np.random.randint(0, 100, 50), np.random.randint(0, 2, 50))] = 0.0
    X_csr = sp.csr_matrix(X)
    tsne = TSNE(n_components=2, perplexity=10, learning_rate=100.0, random_state=0, method="exact")
    X_embedded = tsne.fit_transform(X_csr)
    assert_almost_equal(trustworthiness(X_csr, X_embedded, n_neighbors=1), 1.0, decimal=1)

def test_preserve_trustworthiness_approximately():
    """Nearest neighbors should be preserved approximately."""
    random_state = check_random_state(0)
    X = random_state.randn(100, 2)
    for init in ('random', 'pca'):
        tsne = TSNE(n_components=2, perplexity=10, learning_rate=100.0,
                    init=init, random_state=0)
        X_embedded = tsne.fit_transform(X)
        assert_almost_equal(trustworthiness(X, X_embedded, n_neighbors=1), 1.0,
                            decimal=1)

def test_optimization_minimizes_kl_divergence():
    """t-SNE should give a lower KL divergence with more iterations."""
    random_state = check_random_state(0)
    X, _ = make_blobs(n_features=3, random_state=random_state)
    kl_divergences = []
    for n_iter in [200, 250, 300]:
        tsne = TSNE(n_components=2, perplexity=10, learning_rate=100.0, n_iter=n_iter, random_state=0)
        tsne.fit_transform(X)
        kl_divergences.append(tsne.kl_divergence_)
    assert_less_equal(kl_divergences[1], kl_divergences[0])
    assert_less_equal(kl_divergences[2], kl_divergences[1])

def test_kl_divergence_not_nan(method):
    # Ensure kl_divergence_ is computed at last iteration
    # even though n_iter % n_iter_check != 0, i.e. 1003 % 50 != 0
    random_state = check_random_state(0)

    X = random_state.randn(50, 2)
    tsne = TSNE(n_components=2, perplexity=2, learning_rate=100.0,
                random_state=0, method=method, verbose=0, n_iter=1003)
    tsne.fit_transform(X)

    assert not np.isnan(tsne.kl_divergence_)

def TSNE_Gist(name, csvfilename):
    idsT = imagesHandler.get_all_img_ids()
    ids = []
    for id in idsT:
        ids.append(str(id[0]))
    print ids
    gistVals = util.loadCSV(csvfilename)
    X = np.array(gistVals)
    model = TSNE(n_components=2, random_state=0)
    tsne_vals = model.fit_transform(X)
    tsneHandler.storeTsneValsWIds(name, tsne_vals, ids)
    return tsne_vals, ids

def test_preserve_trustworthiness_approximately_with_precomputed_distances():
    # Nearest neighbors should be preserved approximately.
    random_state = check_random_state(0)
    for i in range(3):
        X = random_state.randn(100, 2)
        D = squareform(pdist(X), "sqeuclidean")
        tsne = TSNE(n_components=2, perplexity=2, learning_rate=100.0,
                    early_exaggeration=2.0, metric="precomputed",
                    random_state=i, verbose=0)
        X_embedded = tsne.fit_transform(D)
        t = trustworthiness(D, X_embedded, n_neighbors=1, metric="precomputed")
        assert t > .95

def test_64bit(method, dt):
    # Ensure 64bit arrays are handled correctly.
    random_state = check_random_state(0)

    X = random_state.randn(50, 2).astype(dt)
    tsne = TSNE(n_components=2, perplexity=2, learning_rate=100.0,
                random_state=0, method=method, verbose=0)
    X_embedded = tsne.fit_transform(X)
    effective_type = X_embedded.dtype

    # tsne cython code is only single precision, so the output will
    # always be single precision, irrespectively of the input dtype
    assert effective_type == np.float32

def test_preserve_trustworthiness_approximately():
    # Nearest neighbors should be preserved approximately.
    random_state = check_random_state(0)
    n_components = 2
    methods = ['exact', 'barnes_hut']
    X = random_state.randn(50, n_components).astype(np.float32)
    for init in ('random', 'pca'):
        for method in methods:
            tsne = TSNE(n_components=n_components, init=init, random_state=0,
                        method=method)
            X_embedded = tsne.fit_transform(X)
            t = trustworthiness(X, X_embedded, n_neighbors=1)
            assert_greater(t, 0.9)

def test_n_iter_used():
    # check that the ``n_iter`` parameter has an effect
    random_state = check_random_state(0)
    n_components = 2
    methods = ['exact', 'barnes_hut']
    X = random_state.randn(25, n_components).astype(np.float32)
    for method in methods:
        for n_iter in [251, 500]:
            tsne = TSNE(n_components=n_components, perplexity=1,
                        learning_rate=0.5, init="random", random_state=0,
                        method=method, early_exaggeration=1.0, n_iter=n_iter)
            tsne.fit_transform(X)

            assert tsne.n_iter_ == n_iter - 1

def TSNE_sift(name):
    conn = sqlite3.connect(dirm.sqlite_file)
    c = conn.cursor()
    dist = sift_cb_handler.get_distributions()
    X_Ids = []
    X_data = []
    for d in dist:
        x_id = d[0]
        x_data = d[1:]
        X_Ids.append(x_id)
        X_data.append(x_data)
    X_data = np.array(X_data)
    model = TSNE(n_components=2)
    tsne_x = model.fit_transform(X_data)
    tsneHandler.storeTsneValsWIds(name, tsne_x, X_Ids)
    return tsne_x, X_Ids