使用IsolationForest 与Meanshift算法进行异常检测

def mean_shift(X, bandwidth=None, seeds=None, bin_seeding=False,
               min_bin_freq=1, cluster_all=True, max_iter=300,
               n_jobs=None):
    """Perform mean shift clustering of data using a flat kernel.
    Read more in the :ref:`User Guide <mean_shift>`.
    Parameters
    ----------
    X : array-like, shape=[n_samples, n_features]
        Input data.
    bandwidth : float, optional
        Kernel bandwidth.
        If bandwidth is not given, it is determined using a heuristic based on
        the median of all pairwise distances. This will take quadratic time in
        the number of samples. The sklearn.cluster.estimate_bandwidth function
        can be used to do this more efficiently.
    seeds : array-like, shape=[n_seeds, n_features] or None
        Point used as initial kernel locations. If None and bin_seeding=False,
        each data point is used as a seed. If None and bin_seeding=True,
        see bin_seeding.
    bin_seeding : boolean, default=False
        If true, initial kernel locations are not locations of all
        points, but rather the location of the discretized version of
        points, where points are binned onto a grid whose coarseness
        corresponds to the bandwidth. Setting this option to True will speed
        up the algorithm because fewer seeds will be initialized.
        Ignored if seeds argument is not None.
    min_bin_freq : int, default=1
       To speed up the algorithm, accept only those bins with at least
       min_bin_freq points as seeds.
    cluster_all : boolean, default True
        If true, then all points are clustered, even those orphans that are
        not within any kernel. Orphans are assigned to the nearest kernel.
        If false, then orphans are given cluster label -1.
    max_iter : int, default 300
        Maximum number of iterations, per seed point before the clustering
        operation terminates (for that seed point), if has not converged yet.
    n_jobs : int or None, optional (default=None)
        The number of jobs to use for the computation. This works by computing
        each of the n_init runs in parallel.
        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
        ``-1`` means using all processors. See :term:`Glossary <n_jobs>`
        for more details.
        .. versionadded:: 0.17
           Parallel Execution using *n_jobs*.
    Returns
    -------
    cluster_centers : array, shape=[n_clusters, n_features]
        Coordinates of cluster centers.
    labels : array, shape=[n_samples]
        Cluster labels for each point.
    Notes
    -----
    For an example, see :ref:`examples/cluster/plot_mean_shift.py
    <sphx_glr_auto_examples_cluster_plot_mean_shift.py>`.
    """

    if bandwidth is None:
        bandwidth = estimate_bandwidth(X, n_jobs=n_jobs)
    elif bandwidth <= 0:
        raise ValueError("bandwidth needs to be greater than zero or None,\
            got %f" % bandwidth)
    if seeds is None:
        if bin_seeding:
            seeds = get_bin_seeds(X, bandwidth, min_bin_freq)
        else:
            seeds = X
    n_samples, n_features = X.shape
    center_intensity_dict = {}

    # We use n_jobs=1 because this will be used in nested calls under
    # parallel calls to _mean_shift_single_seed so there is no need for
    # for further parallelism.
    nbrs = NearestNeighbors(radius=bandwidth, n_jobs=1).fit(X)

    # execute iterations on all seeds in parallel
    all_res = Parallel(n_jobs=n_jobs)(
        delayed(_mean_shift_single_seed)
        (seed, X, nbrs, max_iter) for seed in seeds)
    # copy results in a dictionary
    for i in range(len(seeds)):
        if all_res[i] is not None:
            center_intensity_dict[all_res[i][0]] = all_res[i][1]

    if not center_intensity_dict:
        # nothing near seeds
        raise ValueError("No point was within bandwidth=%f of any seed."
                         " Try a different seeding strategy \
                         or increase the bandwidth."
                         % bandwidth)

    # POST PROCESSING: remove near duplicate points
    # If the distance between two kernels is less than the bandwidth,
    # then we have to remove one because it is a duplicate. Remove the
    # one with fewer points.

    sorted_by_intensity = sorted(center_intensity_dict.items(),
                                 key=lambda tup: (tup[1], tup[0]),
                                 reverse=True)
    sorted_centers = np.array([tup[0] for tup in sorted_by_intensity])
    unique = np.ones(len(sorted_centers), dtype=np.bool)
    nbrs = NearestNeighbors(radius=bandwidth,
                            n_jobs=n_jobs).fit(sorted_centers)
    for i, center in enumerate(sorted_centers):
        if unique[i]:
            neighbor_idxs = nbrs.radius_neighbors([center],
                                                  return_distance=False)[0]
            unique[neighbor_idxs] = 0
            unique[i] = 1  # leave the current point as unique
    cluster_centers = sorted_centers[unique]

    # ASSIGN LABELS: a point belongs to the cluster that it is closest to
    nbrs = NearestNeighbors(n_neighbors=1, n_jobs=n_jobs).fit(cluster_centers)
    labels = np.zeros(n_samples, dtype=np.int)
    distances, idxs = nbrs.kneighbors(X)
    if cluster_all:
        labels = idxs.flatten()
    else:
        labels.fill(-1)
        bool_selector = distances.flatten() <= bandwidth
        labels[bool_selector] = idxs.flatten()[bool_selector]
    return cluster_centers, labels