Python sklearn.cluster方法代码示例

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def process_options(args):    
    options = argparser().parse_args(args)

    if options.max_rank is not None and options.max_rank < 1:
        raise ValueError('max-rank must be >= 1')
    if options.eps <= 0.0:
        raise ValueError('eps must be > 0')

    wv = wvlib.load(options.vectors[0], max_rank=options.max_rank)

    if options.normalize:
        logging.info('normalize vectors to unit length')
        wv.normalize()

    words, vectors = wv.words(), wv.vectors()

    if options.whiten:
        logging.info('normalize features to unit variance')
        vectors = scipy.cluster.vq.whiten(vectors)

    return words, vectors, options 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def run_kmeans(features, n_cluster):
    """
    Run kmeans on a set of features to find <n_cluster> cluster.

    Args:
        features:  np.ndarrary [n_samples x embed_dim], embedding training/testing samples for which kmeans should be performed.
        n_cluster: int, number of cluster.
    Returns:
        cluster_assignments: np.ndarray [n_samples x 1], per sample provide the respective cluster label it belongs to.
    """
    n_samples, dim = features.shape
    kmeans = faiss.Kmeans(dim, n_cluster)
    kmeans.n_iter, kmeans.min_points_per_centroid, kmeans.max_points_per_centroid = 20,5,1000000000
    kmeans.train(features)
    _, cluster_assignments = kmeans.index.search(features,1)
    return cluster_assignments 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def error(cluster, target_cluster, k):
    """ Compute error between cluster and target cluster
    :param cluster: proposed cluster
    :param target_cluster: target cluster
    :return: error
    """
    n = np.shape(target_cluster)[0]
    M = np.zeros((k, k))
    for i in range(k):
        for j in range(k):
            M[i][j] = np.sum(np.logical_and(cluster == i, target_cluster == j))
    m = Munkres()
    indexes = m.compute(-M)
    corresp = []
    for i in range(k):
        corresp.append(indexes[i][1])
    pred_corresp = [corresp[int(predicted)] for predicted in cluster]
    acc = np.sum(pred_corresp == target_cluster) / float(len(target_cluster))
    return acc 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def cluster(train_latents, train_labels, test_latents, test_labels):
    num_classes = np.shape(train_labels)[-1]
    labels_hot = np.argmax(test_labels, axis=-1)
    train_latents = np.reshape(train_latents,
                               newshape=[train_latents.shape[0], -1])
    test_latents = np.reshape(test_latents,
                              newshape=[test_latents.shape[0], -1])
    kmeans = KMeans(init='random', n_clusters=num_classes,
                    random_state=0, max_iter=1000, n_init=FLAGS.n_init,
                    n_jobs=FLAGS.n_jobs)
    kmeans.fit(train_latents)
    print(kmeans.cluster_centers_)
    print('Train/Test k-means objective = %.4f / %.4f' %
          (-kmeans.score(train_latents), -kmeans.score(test_latents)))
    print('Train/Test accuracy %.4f / %.3f' %
          (error(np.argmax(train_labels, axis=-1), kmeans.predict(train_latents), k=num_classes),
           error(np.argmax(test_labels, axis=-1), kmeans.predict(test_latents), k=num_classes)))
    return error(labels_hot, kmeans.predict(test_latents), k=num_classes) 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def __call__(self, features: np.array, term_index: list, use_tfidf: bool = True, **options):
        """
        Just call activated class instance to cluster data.
        :param features: np.array - term frequency matrix
        :param term_index:  list - list of term frequency matrix indexes
        :param use_tfidf: bool - whether to use TF IDF Transformer
        :param options: **dict - unpacked cluster algorithm options
        :return: ClusterEngine instance with attributes listed in __init__
        """
        self.features = features
        self.term_index = term_index
        self.num_records = features.shape[0]
        self.use_tfidf = use_tfidf
        self.user_options = options
        self.n_clusters = options.get('n_clusters')
        self.cluster_model = self.get_model()
        return self.cluster() 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def cluster(evecs, Cnorm, k, in_bound_idxs=None):
    X = evecs[:, :k] / (Cnorm[:, k - 1:k] + 1e-5)
    KM = sklearn.cluster.KMeans(n_clusters=k, n_init=50, max_iter=500)
    seg_ids = KM.fit_predict(X)

    ###############################################################
    # Locate segment boundaries from the label sequence
    if in_bound_idxs is None:
        bound_beats = 1 + np.flatnonzero(seg_ids[:-1] != seg_ids[1:])

        # Count beats 0 as a boundary
        bound_idxs = librosa.util.fix_frames(bound_beats, x_min=0)
    else:
        bound_idxs = in_bound_idxs

    # Compute the segment label for each boundary
    bound_segs = list(seg_ids[bound_idxs])

    # Tack on the end-time
    bound_idxs = list(np.append(bound_idxs, len(Cnorm) - 1))

    return bound_idxs, bound_segs 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def do_segmentation(C, M, config, in_bound_idxs=None):
    embedding = embed_beats(C, M, config)
    Cnorm = np.cumsum(embedding ** 2, axis=1) ** 0.5

    if config["hier"]:
        est_idxs = []
        est_labels = []
        for k in range(1, config["num_layers"] + 1):
            est_idx, est_label = cluster(embedding, Cnorm, k)
            est_idxs.append(est_idx)
            est_labels.append(np.asarray(est_label, dtype=np.int))

    else:
        est_idxs, est_labels = cluster(embedding, Cnorm, config["scluster_k"], in_bound_idxs)
        est_labels = np.asarray(est_labels, dtype=np.int)

    return est_idxs, est_labels, Cnorm 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def save(self, name, resolution, gain, equalize=True, cluster='agglomerative', statistics='db', max_K=5):
        """
        Generates a topological representation using the Mapper algorithm with resolution and gain specified by the
        parameters 'resolution' and 'gain'. When equalize is set to True, patches are chosen such that they
        contain the same number of points. The parameter 'cluster' specifies the clustering method ('agglomerative' or
        'kmeans'). The parameter 'statistics' specifies the criterion for choosing the optimal number of clusters
        ('db' for Davies-Bouildin index, or 'gap' for the gap statistic). The parameter 'max_K' specifies the maximum
        number of clusters to be considered within each patch. The topological representation is stored in the files
        'name.gexf' and 'name.json'. It returns a dictionary with the patches.
        """
        G, all_clusters, patches = sakmapper.mapper_graph(self.df, lens_data=self.lens_data_mds,
                                                          resolution=resolution,
                                                          gain=gain, equalize=equalize, clust=cluster,
                                                          stat=statistics, max_K=max_K)
        dic = {}
        for n, rs in enumerate(all_clusters):
            dic[str(n)] = map(lambda x: int(x), rs)
        with open(name + '.json', 'wb') as handle3:
            json.dump(dic, handle3)
        networkx.write_gexf(G, name + '.gexf')
        return patches 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def cellular_subpopulations(self, threshold=0.05, min_cells=5, clus_thres=0.65):
        """
        Identifies potential transient cellular subpopulations. The parameter
        'threshold' sets an upper bound of the q-value of the genes that are considered in the analysis.
        The parameter 'min_cells' sets the minimum number of cells on which each of the genes considered in the
        analysis is expressed. Cellular subpopulations are determined by clustering the Jensen-Shannon distance
        matrix of the genes that pass all the constraints. The number of clusters is controlled in this case by
        the parameter 'clus_thres'. In both cases a list with the genes associated to each cluster is returned.
        It requires the presence of the file 'name.genes.tsv', produced by the method RotedGraph.save().
        """
        con = []
        dis = []
        nam = []
        f = open(self.name + '.genes.tsv', 'r')
        for n, line in enumerate(f):
            if n > 0:
                sp = line[:-1].split('\t')
                if float(sp[7]) < threshold and float(sp[1]) > min_cells:
                    nam.append(sp[0])
        f.close()
        mat2 = self.JSD_matrix(nam)
        return [map(lambda xx: nam[xx], m)
                for m in find_clusters(hierarchical_clustering(mat2, labels=nam,
                                                               cluster_distance=True, thres=clus_thres)).values()] 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def computeF1_macro(confusion_matrix,matching, num_clusters):
	"""
	computes the macro F1 score
	confusion matrix : requres permutation
	matching according to which matrix must be permuted
	"""
	##Permute the matrix columns
	permuted_confusion_matrix = np.zeros([num_clusters,num_clusters])
	for cluster in xrange(num_clusters):
		matched_cluster = matching[cluster]
 		permuted_confusion_matrix[:,cluster] = confusion_matrix[:,matched_cluster]
 	##Compute the F1 score for every cluster
 	F1_score = 0
 	for cluster in xrange(num_clusters):
 		TP = permuted_confusion_matrix[cluster,cluster]
 		FP = np.sum(permuted_confusion_matrix[:,cluster]) - TP
 		FN = np.sum(permuted_confusion_matrix[cluster,:]) - TP
 		precision = TP/(TP + FP)
 		recall = TP/(TP + FN)
 		f1 = stats.hmean([precision,recall])
 		F1_score += f1
 	F1_score /= num_clusters
 	return F1_score 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def test_monkey_patching(self):
        _tokens = daal4py.sklearn.sklearn_patch_names()
        self.assertTrue(isinstance(_tokens, list) and len(_tokens) > 0)
        for t in _tokens:
            daal4py.sklearn.unpatch_sklearn(t)
        for t in _tokens:
            daal4py.sklearn.patch_sklearn(t)

        import sklearn
        for a in [(sklearn.decomposition, 'PCA'),
                  (sklearn.linear_model, 'Ridge'),
                  (sklearn.linear_model, 'LinearRegression'),
                  (sklearn.cluster, 'KMeans'),
                  (sklearn.svm, 'SVC'),]:
            class_module = getattr(a[0], a[1]).__module__
            self.assertTrue(class_module.startswith('daal4py')) 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def kmeans(X_train, y_train, X_val, y_val):
    n_clusters = 10
    kmeans = KMeans(n_clusters=n_clusters, random_state=0, verbose=0, n_jobs=int(0.8*n_cores)).fit(X_train)
    c_train = kmeans.predict(X_train)
    c_pred = kmeans.predict(X_val)
    centroids = kmeans.cluster_centers_
    for i in range(n_clusters):
        print('--------analyzing cluster %d--------' %i)
        train_mask = c_train==i
        std_train = np.std(y_train[train_mask])
        mean_train = np.mean(y_train[train_mask])
        print("# examples & price mean & std for training set within cluster %d is:(%d, %.2f, %.2f)" %(i, train_mask.sum(), np.float(mean_train), np.float(std_train)))
        pred_mask = c_pred==i
        std_pred = np.std(y_val[pred_mask])
        mean_pred = np.mean(y_val[pred_mask])
        print("# examples & price mean & std for validation set within cluster %d is:(%d, %.2f, %.2f)" %(i, pred_mask.sum(), np.float(mean_pred), np.float(std_pred)))
        if pred_mask.sum() == 0:
            print('Zero membered test set! Skipping the test and training validation.')
            continue
        LinearModel(X_train[train_mask], y_train[train_mask], X_val[pred_mask], y_val[pred_mask])
        print('--------Finished analyzing cluster %d--------' %i)
    
    
    return c_pred, centroids 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def predict(self, X):
        """Predict the closest cluster each sample in X belongs to.
        In the vector quantization literature, `cluster_centers_` is called
        the code book and each value returned by `predict` is the index of
        the closest code in the code book.

        Parameters
        ----------
        X : array-like, shape = [n_samples, n_features]
            New data to predict.

        Returns
        -------
        labels : array, shape [n_samples,]
            Index of the cluster each sample belongs to.
        """
        check_is_fitted(self, "cluster_centers_")
        X = self._check_array(X)
        labels = pairwise_distances_argmin_min(X, self.cluster_centers_)[0].astype(
            np.int32
        )
        return labels 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def process_options(args):    
    options = argparser().parse_args(args)

    if options.max_rank is not None and options.max_rank < 1:
        raise ValueError('max-rank must be >= 1')
    if options.k is not None and options.k < 2:
        raise ValueError('cluster number must be >= 2')

    if options.method == MINIBATCH_KMEANS and not with_sklearn:
        logging.warning('minibatch kmeans not available, using kmeans (slow)')
        options.method = KMEANS

    if options.jobs != 1 and (options.method != KMEANS or not with_sklearn):
        logging.warning('jobs > 1 only supported scikit-learn %s' % KMEANS)
        options.jobs = 1

    wv = wvlib.load(options.vectors[0], max_rank=options.max_rank)

    if options.k is None:
        options.k = int(math.ceil((len(wv.words())/2)**0.5))
        logging.info('set k=%d (%d words)' % (options.k, len(wv.words())))

    if options.normalize:
        logging.info('normalize vectors to unit length')
        wv.normalize()

    words, vectors = wv.words(), wv.vectors()

    if options.whiten:
        logging.info('normalize features to unit variance')
        vectors = scipy.cluster.vq.whiten(vectors)

    return words, vectors, options 

# 需要导入模块: import sklearn [as 别名]
# 或者: from sklearn import cluster [as 别名]
def minibatch_kmeans(vectors, k):
    if not with_sklearn:
        raise NotImplementedError
    # Sculley (http://www.eecs.tufts.edu/~dsculley/papers/fastkmeans.pdf)
    # uses batch size 1000. sklearn KMeans defaults to n_init 10
    kmeans = sklearn.cluster.MiniBatchKMeans(k, batch_size=1000, n_init=10)
    kmeans.fit(vectors)
    return kmeans.labels_