Python metrics.pairwise_distances方法代码示例

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def test_lof_precomputed(random_state=42):
    """Tests LOF with a distance matrix."""
    # Note: smaller samples may result in spurious test success
    rng = np.random.RandomState(random_state)
    X = rng.random_sample((10, 4))
    Y = rng.random_sample((3, 4))
    DXX = metrics.pairwise_distances(X, metric='euclidean')
    DYX = metrics.pairwise_distances(Y, X, metric='euclidean')
    # As a feature matrix (n_samples by n_features)
    lof_X = neighbors.LocalOutlierFactor(n_neighbors=3, novelty=True)
    lof_X.fit(X)
    pred_X_X = lof_X._predict()
    pred_X_Y = lof_X.predict(Y)

    # As a dense distance matrix (n_samples by n_samples)
    lof_D = neighbors.LocalOutlierFactor(n_neighbors=3, algorithm='brute',
                                         metric='precomputed', novelty=True)
    lof_D.fit(DXX)
    pred_D_X = lof_D._predict()
    pred_D_Y = lof_D.predict(DYX)

    assert_array_almost_equal(pred_X_X, pred_D_X)
    assert_array_almost_equal(pred_X_Y, pred_D_Y) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def test_simple_example():
    """Test on a simple example.

    Puts four points in the input space where the opposite labels points are
    next to each other. After transform the samples from the same class
    should be next to each other.

    """
    X = np.array([[0, 0], [0, 1], [2, 0], [2, 1]])
    y = np.array([1, 0, 1, 0])
    nca = NeighborhoodComponentsAnalysis(n_components=2, init='identity',
                                         random_state=42)
    nca.fit(X, y)
    X_t = nca.transform(X)
    assert_array_equal(pairwise_distances(X_t).argsort()[:, 1],
                       np.array([2, 3, 0, 1])) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def compute_heterogeneity(data, k, centroids, cluster_assignment):

    heterogeneity = 0.0
    for i in range(k):

        # Select all data points that belong to cluster i. Fill in the blank (RHS only)
        member_data_points = data[cluster_assignment == i, :]

        if member_data_points.shape[0] > 0:  # check if i-th cluster is non-empty
            # Compute distances from centroid to data points (RHS only)
            distances = pairwise_distances(
                member_data_points, [centroids[i]], metric="euclidean"
            )
            squared_distances = distances ** 2
            heterogeneity += np.sum(squared_distances)

    return heterogeneity 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def get_similarities(query_feats, para_features, top=10, combine_feat_scores="mul"):
    """
    Get similarities based on multiple independent queries that are then combined using combine_feat_scores
    :param query_feats: Multiple vectorized text queries
    :param para_features: Multiple vectorized text paragraphs that will be scored against the queries
    :param top: Top N facts to keep
    :param combine_feat_scores: The way for combining the multiple scores
    :return: Ranked fact ids with scores List[tuple(id, weight)]
    """
    scores_per_feat = [pairwise_distances(q_feat, para_features, "cosine").ravel() for q_feat in query_feats]  # this is distance - low is better!!!
    comb_func = comb_funcs[combine_feat_scores]

    smoothing_val = 0.000001
    max_val = pow((1 + smoothing_val), 2)
    dists = scores_per_feat[0] + smoothing_val
    if len(scores_per_feat) > 1:
        for i in range(1, len(scores_per_feat)):
            dists = comb_func(scores_per_feat[i] + smoothing_val, dists)
    sorted_ix = np.argsort(dists).tolist()  # this is asc (lowers first), in case of ties, uses the earlier paragraph

    return [[i, (max_val - dists[i]) / max_val] for i in sorted_ix][:top] 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def combine_similarities(scores_per_feat, top=10, combine_feat_scores="mul"):
    """
    Get similarities based on multiple independent queries that are then combined using combine_feat_scores
    :param query_feats: Multiple vectorized text queries
    :param para_features: Multiple vectorized text paragraphs that will be scored against the queries
    :param top: Top N facts to keep
    :param combine_feat_scores: The way for combining the multiple scores
    :return: Ranked fact ids with scores List[tuple(id, weight)]
    """
    # scores_per_feat = [pairwise_distances(q_feat, para_features, "cosine").ravel() for q_feat in query_feats]  # this is distance - low is better!!!
    comb_func = comb_funcs[combine_feat_scores]

    smoothing_val = 0.000001
    max_val = pow((1 + smoothing_val), 2)
    dists = scores_per_feat[0] + smoothing_val
    if len(scores_per_feat) > 1:
        for i in range(1, len(scores_per_feat)):
            dists = comb_func(scores_per_feat[i] + smoothing_val, dists)
    sorted_ix = np.argsort(dists).tolist()  # this is asc (lowers first) ,in case of ties, uses the earlier paragraph

    max_val = max(np.max(dists), 1)
    return [[i, (max_val - dists[i]) / max_val] for i in sorted_ix][:top] 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def spatial_check(metric):
    dist_matrix = pairwise_distances(spatial_data, metric=metric)
    # scipy is bad sometimes
    if metric == "braycurtis":
        dist_matrix[np.where(~np.isfinite(dist_matrix))] = 0.0
    if metric in ("cosine", "correlation"):
        dist_matrix[np.where(~np.isfinite(dist_matrix))] = 1.0
        # And because distance between all zero vectors should be zero
        dist_matrix[10, 11] = 0.0
        dist_matrix[11, 10] = 0.0
    dist_function = dist.named_distances[metric]
    test_matrix = np.array(
        [
            [
                dist_function(spatial_data[i], spatial_data[j])
                for j in range(spatial_data.shape[0])
            ]
            for i in range(spatial_data.shape[0])
        ]
    )
    assert_array_almost_equal(
        test_matrix,
        dist_matrix,
        err_msg="Distances don't match " "for metric {}".format(metric),
    ) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def binary_check(metric):
    dist_matrix = pairwise_distances(binary_data, metric=metric)
    if metric in ("jaccard", "dice", "sokalsneath", "yule"):
        dist_matrix[np.where(~np.isfinite(dist_matrix))] = 0.0
    if metric in ("kulsinski", "russellrao"):
        dist_matrix[np.where(~np.isfinite(dist_matrix))] = 0.0
        # And because distance between all zero vectors should be zero
        dist_matrix[10, 11] = 0.0
        dist_matrix[11, 10] = 0.0
    dist_function = dist.named_distances[metric]
    test_matrix = np.array(
        [
            [
                dist_function(binary_data[i], binary_data[j])
                for j in range(binary_data.shape[0])
            ]
            for i in range(binary_data.shape[0])
        ]
    )
    assert_array_almost_equal(
        test_matrix,
        dist_matrix,
        err_msg="Distances don't match " "for metric {}".format(metric),
    ) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def test_seuclidean():
    v = np.abs(np.random.randn(spatial_data.shape[1]))
    dist_matrix = pairwise_distances(spatial_data, metric="seuclidean", V=v)
    test_matrix = np.array(
        [
            [
                dist.standardised_euclidean(spatial_data[i], spatial_data[j], v)
                for j in range(spatial_data.shape[0])
            ]
            for i in range(spatial_data.shape[0])
        ]
    )
    assert_array_almost_equal(
        test_matrix,
        dist_matrix,
        err_msg="Distances don't match " "for metric seuclidean",
    ) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def test_mahalanobis():
    v = np.cov(np.transpose(spatial_data))
    dist_matrix = pairwise_distances(spatial_data, metric="mahalanobis", VI=v)
    test_matrix = np.array(
        [
            [
                dist.mahalanobis(spatial_data[i], spatial_data[j], v)
                for j in range(spatial_data.shape[0])
            ]
            for i in range(spatial_data.shape[0])
        ]
    )
    assert_array_almost_equal(
        test_matrix,
        dist_matrix,
        err_msg="Distances don't match " "for metric mahalanobis",
    ) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def sparse_spatial_check(metric, sparse_spatial_data):
    # Check that metric is supported for this test, otherwise, fail!
    assert (
        metric in spdist.sparse_named_distances
    ), f"{metric} not supported for sparse data"
    dist_matrix = pairwise_distances(sparse_spatial_data.todense(), metric=metric)

    if metric in ("braycurtis", "dice", "sokalsneath", "yule"):
        dist_matrix[np.where(~np.isfinite(dist_matrix))] = 0.0

    if metric in ("cosine", "correlation", "kulsinski", "russellrao"):
        dist_matrix[np.where(~np.isfinite(dist_matrix))] = 1.0
        # And because distance between all zero vectors should be zero
        dist_matrix[10, 11] = 0.0
        dist_matrix[11, 10] = 0.0

    run_test_sparse_metric(metric, sparse_spatial_data, dist_matrix) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def sparse_binary_check(metric, sparse_binary_data):
    # Check that metric is supported for this test, otherwise, fail!
    assert (
        metric in spdist.sparse_named_distances
    ), f"{metric} not supported for sparse data"
    dist_matrix = pairwise_distances(sparse_binary_data.todense(), metric=metric)
    if metric in ("jaccard", "dice", "sokalsneath", "yule"):
        dist_matrix[np.where(~np.isfinite(dist_matrix))] = 0.0

    if metric in ("kulsinski", "russellrao"):
        dist_matrix[np.where(~np.isfinite(dist_matrix))] = 1.0
        # And because distance between all zero vectors should be zero
        dist_matrix[10, 11] = 0.0
        dist_matrix[11, 10] = 0.0

    run_test_sparse_metric(metric, sparse_binary_data, dist_matrix)


# --------------------
# Spatial Metric Tests
# -------------------- 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def test_weighted_minkowski(spatial_data):
    v = np.abs(np.random.randn(spatial_data.shape[1]))
    dist_matrix = pairwise_distances(spatial_data, metric="wminkowski", w=v, p=3)
    test_matrix = np.array(
        [
            [
                dist.weighted_minkowski(spatial_data[i], spatial_data[j], v, p=3)
                for j in range(spatial_data.shape[0])
            ]
            for i in range(spatial_data.shape[0])
        ]
    )
    assert_array_almost_equal(
        test_matrix,
        dist_matrix,
        err_msg="Distances don't match " "for metric weighted_minkowski",
    ) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def test_mahalanobis(spatial_data):
    v = np.cov(np.transpose(spatial_data))
    dist_matrix = pairwise_distances(spatial_data, metric="mahalanobis", VI=v)
    test_matrix = np.array(
        [
            [
                dist.mahalanobis(spatial_data[i], spatial_data[j], v)
                for j in range(spatial_data.shape[0])
            ]
            for i in range(spatial_data.shape[0])
        ]
    )
    assert_array_almost_equal(
        test_matrix,
        dist_matrix,
        err_msg="Distances don't match " "for metric mahalanobis",
    ) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def gaussian(x, workers=None):
    """Default medial gaussian kernel similarity calculation"""
    l1 = pairwise_distances(X=x, metric="l1", n_jobs=workers)
    n = l1.shape[0]
    med = np.median(
        np.lib.stride_tricks.as_strided(
            l1, (n - 1, n + 1), (l1.itemsize * (n + 1), l1.itemsize)
        )[:, 1:]
    )
    # prevents division by zero when used on label vectors
    med = med if med else 1
    gamma = 1.0 / (2 * (med ** 2))
    return rbf_kernel(x, gamma=gamma)


# p-value computation 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import pairwise_distances [as 别名]
def _compute_isc(data, metric='median'):
    ''' Helper function to compute intersubject correlation from observations by subjects array.
        
        Args:
            data: (pd.DataFrame, np.array) observations by subjects where isc is computed across subjects
            metric: (str) type of association metric ['spearman','pearson','kendall']
        
        Returns:
            isc: (float) intersubject correlation coefficient
            
    '''

    from nltools.data import Adjacency

    similarity = Adjacency(1 - pairwise_distances(data.T, metric='correlation'), matrix_type='similarity')
    if metric =='mean':
        isc = np.tanh(similarity.r_to_z().mean())
    elif metric =='median':
        isc = similarity.median()
    return isc