Python distance.canberra方法代碼示例

# 需要導入模塊: from scipy.spatial import distance [as 別名]
# 或者: from scipy.spatial.distance import canberra [as 別名]
def __calc_distances__(self, v1s, v2s, is_sparse=True):
        if is_sparse:
            dcosine     = np.array([cosine(x.toarray(), y.toarray())       for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            dcityblock  = np.array([cityblock(x.toarray(), y.toarray())    for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            dcanberra  = np.array([canberra(x.toarray(), y.toarray())     for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            deuclidean = np.array([euclidean(x.toarray(), y.toarray())    for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            dminkowski  = np.array([minkowski(x.toarray(), y.toarray(), 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            dbraycurtis = np.array([braycurtis(x.toarray(), y.toarray())   for (x, y) in zip(v1s, v2s)]).reshape((-1,1))

            dskew_q1 = [skew(x.toarray().ravel()) for x in v1s]
            dskew_q2 = [skew(x.toarray().ravel()) for x in v2s]
            dkur_q1  = [kurtosis(x.toarray().ravel()) for x in v1s]
            dkur_q2  = [kurtosis(x.toarray().ravel()) for x in v2s]

            dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
            dkur_diff  = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
        else:
            dcosine     = np.array([cosine(x, y)       for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            dcityblock  = np.array([cityblock(x, y)    for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            dcanberra  = np.array([canberra(x, y)     for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            deuclidean = np.array([euclidean(x, y)    for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            dminkowski  = np.array([minkowski(x, y, 3) for (x, y) in zip(v1s, v2s)]).reshape((-1,1))
            dbraycurtis = np.array([braycurtis(x, y)   for (x, y) in zip(v1s, v2s)]).reshape((-1,1))

            dskew_q1 = [skew(x) for x in v1s]
            dskew_q2 = [skew(x) for x in v2s]
            dkur_q1  = [kurtosis(x) for x in v1s]
            dkur_q2  = [kurtosis(x) for x in v2s]

            dskew_diff = np.abs(np.array(dskew_q1) - np.array(dskew_q2)).reshape((-1,1))
            dkur_diff  = np.abs(np.array(dkur_q1) - np.array(dkur_q2)).reshape((-1,1))
        return np.hstack((dcosine,dcityblock,dcanberra,deuclidean,dminkowski,dbraycurtis,dskew_diff,dkur_diff)) 

# 需要導入模塊: from scipy.spatial import distance [as 別名]
# 或者: from scipy.spatial.distance import canberra [as 別名]
def get_distance_function(requested_metric):
    """
    This function returns a specified distance function.

    Paramters
    ---------

    requested_metric: str
        Distance function. Can be any function in: https://docs.scipy.org/doc/scipy/reference/spatial.distance.html.

    Returns
    -------

    requested_metric : distance function

    """
    distance_options = {
        'braycurtis': distance.braycurtis,
        'canberra': distance.canberra,
        'chebyshev': distance.chebyshev,
        'cityblock': distance.cityblock,
        'correlation': distance.correlation,
        'cosine': distance.cosine,
        'euclidean': distance.euclidean,
        'sqeuclidean': distance.sqeuclidean,
        'dice': distance.dice,
        'hamming': distance.hamming,
        'jaccard': distance.jaccard,
        'kulsinski': distance.kulsinski,
        'matching': distance.matching,
        'rogerstanimoto': distance.rogerstanimoto,
        'russellrao': distance.russellrao,
        'sokalmichener': distance.sokalmichener,
        'sokalsneath': distance.sokalsneath,
        'yule': distance.yule,
    }
    if requested_metric in distance_options:
        return distance_options[requested_metric]
    else:
        raise ValueError('Distance function cannot be found.') 

# 需要導入模塊: from scipy.spatial import distance [as 別名]
# 或者: from scipy.spatial.distance import canberra [as 別名]
def similarity_function(x, y):
    """ Similarity function for comparing user features.

    This actually really should be implemented in taar.similarity_recommender
    and then imported here for consistency.
    """

    def safe_get(field, row, default_value):
        # Safely get a value from the Row. If the value is None, get the
        # default value.
        return row[field] if row[field] is not None else default_value

    # Extract the values for the categorical and continuous features for both
    # the x and y samples. Use an empty string as the default value for missing
    # categorical fields and 0 for the continuous ones.
    x_categorical_features = [safe_get(k, x, "") for k in CATEGORICAL_FEATURES]
    y_categorical_features = [safe_get(k, y, "") for k in CATEGORICAL_FEATURES]
    x_continuous_features = [
        float(safe_get(k, x, 0)) for k in CONTINUOUS_FEATURES
    ]
    y_continuous_features = [
        float(safe_get(k, y, 0)) for k in CONTINUOUS_FEATURES
    ]

    # Here a larger distance indicates a poorer match between categorical variables.
    j_d = distance.hamming(x_categorical_features, y_categorical_features)
    j_c = distance.canberra(x_continuous_features, y_continuous_features)

    # Take the product of similarities to attain a univariate similarity score.
    # Add a minimal constant to prevent zero values from categorical features.
    # Note: since both the distance function return a Numpy type, we need to
    # call the |item| function to get the underlying Python type. If we don't
    # do that this job will fail when performing KDE due to SPARK-20803 on
    # Spark 2.2.0.
    return abs((j_c + 0.001) * j_d).item() 

# 需要導入模塊: from scipy.spatial import distance [as 別名]
# 或者: from scipy.spatial.distance import canberra [as 別名]
def similarity_function(x, y):
    """ Similarity function for comparing user features.

    This actually really should be implemented in taar.similarity_recommender
    and then imported here for consistency.
    """

    def safe_get(field, row, default_value):
        # Safely get a value from the Row. If the value is None, get the
        # default value.
        return row[field] if row[field] is not None else default_value

    # Extract the values for the categorical and continuous features for both
    # the x and y samples. Use an empty string as the default value for missing
    # categorical fields and 0 for the continuous ones.
    x_categorical_features = [safe_get(k, x, "") for k in CATEGORICAL_FEATURES]
    x_continuous_features = [safe_get(k, x, 0) for k in CONTINUOUS_FEATURES]
    y_categorical_features = [safe_get(k, y, "") for k in CATEGORICAL_FEATURES]
    y_continuous_features = [safe_get(k, y, 0) for k in CONTINUOUS_FEATURES]

    # Here a larger distance indicates a poorer match between categorical variables.
    j_d = distance.hamming(x_categorical_features, y_categorical_features)
    j_c = distance.canberra(x_continuous_features, y_continuous_features)

    # Take the product of similarities to attain a univariate similarity score.
    # Add a minimal constant to prevent zero values from categorical features.
    # Note: since both the distance function return a Numpy type, we need to
    # call the |item| function to get the underlying Python type. If we don't
    # do that this job will fail when performing KDE due to SPARK-20803 on
    # Spark 2.2.0.
    return abs((j_c + 0.001) * j_d).item() 

# 需要導入模塊: from scipy.spatial import distance [as 別名]
# 或者: from scipy.spatial.distance import canberra [as 別名]
def dist(self, G1, G2):
        """A scalable approach to network similarity.

        A network similarity measure based on node signature distributions.

        The results dictionary includes the underlying feature matrices in
        `'feature_matrices'` and the underlying signature vectors in
        `'signature_vectors'`.

        Parameters
        ----------

        G1, G2 (nx.Graph)
            two undirected networkx graphs to be compared.

        Returns
        -------

        dist (float)
            the distance between `G1` and `G2`.

        References
        ----------

        .. [1] Michele Berlingerio, Danai Koutra, Tina Eliassi-Rad,
               Christos Faloutsos: NetSimile: A Scalable Approach to
               Size-Independent Network Similarity. CoRR abs/1209.2684
               (2012)

        """

        # find the graph node feature matrices
        G1_node_features = feature_extraction(G1)
        G2_node_features = feature_extraction(G2)

        # get the graph signature vectors
        G1_signature = graph_signature(G1_node_features)
        G2_signature = graph_signature(G2_node_features)

        # the final distance is the absolute canberra distance
        dist = abs(canberra(G1_signature, G2_signature))

        self.results['feature_matrices'] = G1_node_features, G2_node_features
        self.results['signature_vectors'] = G1_signature, G2_signature
        self.results['dist'] = dist

        return dist