python聚类指标计算

本文整理了python中CH指数及轮廓系数的代码。

具体调用方式为

from sklearn import metrics.calinski_harabasz_score

from sklearn import metrics.silhouette_score

score = metrics.calinski_harabasz_score(X_pca,kmeans.labels_)

 CH指数

def calinski_harabasz_score(X, labels):
    """Compute the Calinski and Harabasz score.

    It is also known as the Variance Ratio Criterion.

    The score is defined as ratio between the within-cluster dispersion and
    the between-cluster dispersion.

    Read more in the :ref:`User Guide <calinski_harabasz_index>`.

    Parameters
    ----------
    X : array-like of shape (n_samples, n_features)
        A list of ``n_features``-dimensional data points. Each row corresponds
        to a single data point.

    labels : array-like of shape (n_samples,)
        Predicted labels for each sample.

    Returns
    -------
    score : float
        The resulting Calinski-Harabasz score.

    References
    ----------
    .. [1] `T. Calinski and J. Harabasz, 1974. "A dendrite method for cluster
       analysis". Communications in Statistics
       <https://www.tandfonline.com/doi/abs/10.1080/03610927408827101>`_
    """
    X, labels = check_X_y(X, labels)
    le = LabelEncoder()
    labels = le.fit_transform(labels)

    n_samples, _ = X.shape
    n_labels = len(le.classes_)

    check_number_of_labels(n_labels, n_samples)

    extra_disp, intra_disp = 0., 0.
    mean = np.mean(X, axis=0)
    for k in range(n_labels):
        cluster_k = X[labels == k]
        mean_k = np.mean(cluster_k, axis=0)
        extra_disp += len(cluster_k) * np.sum((mean_k - mean) ** 2)
        intra_disp += np.sum((cluster_k - mean_k) ** 2)

    return (1. if intra_disp == 0. else
            extra_disp * (n_samples - n_labels) /
            (intra_disp * (n_labels - 1.)))

轮廓系数 （SC）

def silhouette_score(X, labels, *, metric='euclidean', sample_size=None,
                     random_state=None, **kwds):
    """Compute the mean Silhouette Coefficient of all samples.

    The Silhouette Coefficient is calculated using the mean intra-cluster
    distance (``a``) and the mean nearest-cluster distance (``b``) for each
    sample.  The Silhouette Coefficient for a sample is ``(b - a) / max(a,
    b)``.  To clarify, ``b`` is the distance between a sample and the nearest
    cluster that the sample is not a part of.
    Note that Silhouette Coefficient is only defined if number of labels
    is ``2 <= n_labels <= n_samples - 1``.

    This function returns the mean Silhouette Coefficient over all samples.
    To obtain the values for each sample, use :func:`silhouette_samples`.

    The best value is 1 and the worst value is -1. Values near 0 indicate
    overlapping clusters. Negative values generally indicate that a sample has
    been assigned to the wrong cluster, as a different cluster is more similar.

    Read more in the :ref:`User Guide <silhouette_coefficient>`.

    Parameters
    ----------
    X : array-like of shape (n_samples_a, n_samples_a) if metric == \
            "precomputed" or (n_samples_a, n_features) otherwise
        An array of pairwise distances between samples, or a feature array.

    labels : array-like of shape (n_samples,)
        Predicted labels for each sample.

    metric : str or callable, default='euclidean'
        The metric to use when calculating distance between instances in a
        feature array. If metric is a string, it must be one of the options
        allowed by :func:`metrics.pairwise.pairwise_distances
        <sklearn.metrics.pairwise.pairwise_distances>`. If ``X`` is
        the distance array itself, use ``metric="precomputed"``.

    sample_size : int, default=None
        The size of the sample to use when computing the Silhouette Coefficient
        on a random subset of the data.
        If ``sample_size is None``, no sampling is used.

    random_state : int, RandomState instance or None, default=None
        Determines random number generation for selecting a subset of samples.
        Used when ``sample_size is not None``.
        Pass an int for reproducible results across multiple function calls.
        See :term:`Glossary <random_state>`.

    **kwds : optional keyword parameters
        Any further parameters are passed directly to the distance function.
        If using a scipy.spatial.distance metric, the parameters are still
        metric dependent. See the scipy docs for usage examples.

    Returns
    -------
    silhouette : float
        Mean Silhouette Coefficient for all samples.

    References
    ----------

    .. [1] `Peter J. Rousseeuw (1987). "Silhouettes: a Graphical Aid to the
       Interpretation and Validation of Cluster Analysis". Computational
       and Applied Mathematics 20: 53-65.
       <https://www.sciencedirect.com/science/article/pii/0377042787901257>`_

    .. [2] `Wikipedia entry on the Silhouette Coefficient
           <https://en.wikipedia.org/wiki/Silhouette_(clustering)>`_

    """
    if sample_size is not None:
        X, labels = check_X_y(X, labels, accept_sparse=['csc', 'csr'])
        random_state = check_random_state(random_state)
        indices = random_state.permutation(X.shape[0])[:sample_size]
        if metric == "precomputed":
            X, labels = X[indices].T[indices].T, labels[indices]
        else:
            X, labels = X[indices], labels[indices]
    return np.mean(silhouette_samples(X, labels, metric=metric, **kwds))