Python cluster.MeanShift类代码示例

def meanShift(flat_image):
    # Estimate Bandwidth
    bandwidth = estimate_bandwidth(flat_image, quantile = 0.2, n_samples=500)
    ms = MeanShift(bandwidth, bin_seeding=True)
    ms.fit(flat_image)
    labels = ms.labels_
    return ms.labels_, ms.cluster_centers_

 def meanshift_for_hough_line(self):
     # init mean shift
     pixels_of_label = {}
     points_of_label = {}
     for hough_line in self.points_of_hough_line:
         pixels = self.pixels_of_hough_line[hough_line]
         pixels = np.array(pixels)
         bandwidth = estimate_bandwidth(pixels, quantile=QUANTILE, n_samples=500)
         if bandwidth == 0:
             bandwidth = 2
         ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
         ms.fit(pixels)
         labels = ms.labels_
         labels_unique = np.unique(labels)
         n_clusters_ = len(labels_unique)
         for k in range(n_clusters_):
             label = list(hough_line)
             label.append(k)
             pixels_of_label[tuple(label)] = map(tuple, pixels[labels==k])
     for label in pixels_of_label:
         pixels = pixels_of_label[label]
         points = map(self.img.get_bgr_value, pixels)
         points_of_label[label] = points
     self.pixels_of_hough_line = pixels_of_label
     self.points_of_hough_line = points_of_label

    def _fit_mean_shift(self, x):
        for c in xrange(len(self.crange)):
            quant = 0.015 * (c + 1)
            for r in xrange(self.repeats):
                bandwidth = estimate_bandwidth(
                    x, quantile=quant, random_state=r)
                idx = c * self.repeats + r
                model = MeanShift(
                    bandwidth=bandwidth, bin_seeding=True)
                model.fit(x)
                self._labels[idx] = model.labels_
                self._parameters[idx] = model.cluster_centers_

                # build equivalent gmm
                k = model.cluster_centers_.shape[0]
                model_gmm = GMM(n_components=k, covariance_type=self.cvtype,
                                init_params='c', n_iter=0)
                model_gmm.means_ = model.cluster_centers_
                model_gmm.weights_ = sp.array(
                    [(model.labels_ == i).sum() for i in xrange(k)])
                model_gmm.fit(x)

                # evaluate goodness of fit
                self._ll[idx] = model_gmm.score(x).sum()
                if self.gof_type == 'aic':
                    self._gof[idx] = model_gmm.aic(x)
                if self.gof_type == 'bic':
                    self._gof[idx] = model_gmm.bic(x)

                print quant, k, self._gof[idx]

    def cluster_pixels_ms(self):
        # reshape
        """
        cluster points descriptors by meahs shift
        :type self: ColorRemover
        """
        fg_pixels = self.img.fg_pixels.keys()
        descriptors = []
        for r, c in fg_pixels:
            descriptors.append(self.descriptor_map[r][c])
        descriptors = np.array(descriptors)
        descriptors = PCA(n_components=int(VECTOR_DIMENSION)/2).fit_transform(descriptors)
        # descriptors = self.descriptor_map.reshape(descriptors_rows, 1, VECTOR_DIMENSION)
        bandwidth = estimate_bandwidth(descriptors, quantile=0.05)
        ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
        ms.fit(descriptors)
        labels = ms.labels_

        for i in range(len(labels)):
            xy = fg_pixels[i]
            label = labels[i]
            self.labels_map.itemset(xy, label)
        # save the indices and BGR values of each cluster as a dictionary with keys of label
        for label in range(K):
            self.pixels_of_hough_line_in_sphere[label] = map(tuple, np.argwhere((self.labels_map == label)))
            self.cluster_bgr[label] = map(tuple, self.img.bgr[self.labels_map == label])

def applyMeanShift(data,quantileValue=0.2,clusterall=False):
	result=[]
	n_samples=len(data)
	print "Nombre de points du dataset: %d" %n_samples
	
	bandwidth = estimate_bandwidth(data, quantile=quantileValue)
	ms = MeanShift(bandwidth=bandwidth,cluster_all=clusterall)
	#Applique le MeanShift
	clustereddata=ms.fit(data)
	clusteredlabels= clustereddata.labels_
	barycenters=ms.cluster_centers_

	labels_unique = np.unique(clusteredlabels)
	nbOfClusters = len(labels_unique)

	print "number of estimated clusters : %d" % nbOfClusters

	for i in labels_unique:
		print "###Indices des points du cluster %d : ###" %i
		# print [indice[0] for indice in np.argwhere(clusteredlabels == i)]
		result.append([indice[0] for indice in np.argwhere(clusteredlabels == i)])
	#Add a zero coordinates vector to takeinto account the fact that -1 "cluster" does not have a barycenter
	if -1 in labels_unique:
		barycenters= np.append([[0 for k in range(len(barycenters[0]))]],barycenters,axis=0)

	return [result,barycenters]

def cluster_data(data,clustering_method,num_clusters):
    cluster_centers = labels_unique = labels = extra = None
    if clustering_method == 'KMeans':
        # http://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html#sklearn.cluster.KMeans
        k_means = KMeans(n_clusters=num_clusters,init='k-means++',n_init=10,max_iter=100,tol=0.0001,
                                precompute_distances=True, verbose=0, random_state=None, copy_x=True, n_jobs=1)
        k_means.fit(data)
        labels = k_means.labels_
        cluster_centers = k_means.cluster_centers_
    elif clustering_method == 'MeanShift':
        ms =  MeanShift( bin_seeding=True,cluster_all=False)
        ms.fit(data)
        labels = ms.labels_
        cluster_centers = ms.cluster_centers_
    elif clustering_method == 'AffinityPropagation':
        af = AffinityPropagation().fit(data)
        cluster_centers = [data[i] for i in  af.cluster_centers_indices_]
        labels = af.labels_
    elif clustering_method == "AgglomerativeClustering":
        n_neighbors=min(10,len(data)/2)
        connectivity = kneighbors_graph(data, n_neighbors=n_neighbors)
        ward = AgglomerativeClustering(n_clusters=num_clusters, connectivity=connectivity,
                               linkage='ward').fit(data)
        labels = ward.labels_
    elif clustering_method == "DBSCAN":
        db = DBSCAN().fit(data)
        core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
        core_samples_mask[db.core_sample_indices_] = True
        extra = core_samples_mask
        labels = db.labels_

    if labels is not None:
        labels_unique = np.unique(labels)
    return labels,cluster_centers,labels_unique,extra

def mean_shift_cluster_analysis(x,y,quantile=0.2,n_samples=1000):
    # ADAPTED FROM:
    # http://scikit-learn.org/stable/auto_examples/cluster/plot_mean_shift.html#example-cluster-plot-mean-shift-py
    # The following bandwidth can be automatically detected using
    X = np.hstack((x.reshape((x.shape[0],1)),y.reshape((y.shape[0],1))))
    bandwidth = estimate_bandwidth(X, quantile=quantile, n_samples=n_samples)
    
    ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
    ms.fit(X)
    labels = ms.labels_
    cluster_centers = ms.cluster_centers_
    
    labels_unique = np.unique(labels)
    n_clusters_ = len(labels_unique)
    
    #print("number of estimated clusters : %d" % n_clusters_)
    colors = 'bgrcmykbgrcmykbgrcmykbgrcmykbgrcmykbgrcmykbgrcmyk' #cycle('bgrcmykbgrcmykbgrcmykbgrcmyk')
    for i in xrange(len(np.unique(labels))):
        my_members = labels == i
        cluster_center = cluster_centers[i]
        plt.scatter(X[my_members, 0], X[my_members, 1],s=90,c=colors[i],alpha=0.7)
        plt.scatter(cluster_center[0], cluster_center[1],marker='+',s=280,c=colors[i])
    tolx = (X[:,0].max()-X[:,0].min())*0.03
    toly = (X[:,1].max()-X[:,1].min())*0.03
    plt.xlim(X[:,0].min()-tolx,X[:,0].max()+tolx)
    plt.ylim(X[:,1].min()-toly,X[:,1].max()+toly)
    plt.show()
    return labels

def simplify_data1(x):
	X = np.array(zip(x,np.zeros(len(x))), dtype=np.float)
	bandwidth = estimate_bandwidth(X, quantile=0.2)
	ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
	ms.fit(X)
	labels = ms.labels_
	cluster_centers = ms.cluster_centers_
	labels_unique = np.unique(labels)
	n_clusters_ = len(labels_unique)
	#print n_clusters_
	#exit()
	start=0
	value=0
	print x
	for k in range(n_clusters_):
	    my_members = labels == k
	    print "cluster {0}: {1}".format(k, X[my_members, 0]),np.average(X[my_members, 0])
	    value=np.average(X[my_members, 0])
	    val2=0
	    for i in xrange(start,start+len(X[my_members, 0])):
		val2+=X[i][0]
		print val2,X[i][0],i
		X[i][0]=value
	    print "FINAL",val2/len(X[my_members, 0])
	    start+=len(X[my_members, 0])
	return X[:,0]

def Mean_Shift(path):
    #importer les donnees
    data=pandas.read_csv(filepath_or_buffer=path,delimiter=',',encoding='utf-8')  
    data.drop_duplicates()
    print (data)
    #lire les donnees
    values=data[['latitude', 'longitude']].values
    print("printing values")
    print (values)
    #Mean shift
    print ("Clustering data Meanshift algorithm")
    bandwidth = estimate_bandwidth(values, quantile=0.003, n_samples=None)
    #ms = MeanShift(bandwidth=bandwidth, bin_seeding=True, min_bin_freq=20, cluster_all=False)
    ms = MeanShift(bandwidth=bandwidth, bin_seeding=True,min_bin_freq=25,cluster_all=False)
    ms.fit(values)
    data['cluster'] = ms.labels_
    data = data.sort(columns='cluster')
    data = data[(data['cluster'] != -1)]
    print (data['cluster'])
    data['cluster'] = data['cluster'].apply(lambda x:"cluster" +str(x))
    labels_unique = np.unique(ms.labels_).tolist()
    del labels_unique[0]
    # Filtering clusters centers according to data filter
    cluster_centers = DataFrame(ms.cluster_centers_, columns=['latitude', 'longitude'])
    cluster_centers['cluster'] = labels_unique
    print (cluster_centers)
    n_centers_ = len(cluster_centers)
    print("number of clusters is :%d" % n_centers_)
    # print ("Exporting clusters to {}...'.format(clusters_file)")
    data.to_csv(path_or_buf="output/points.csv", cols=['user','latitude','longitude','cluster','picture','datetaken'], encoding='utf-8')
    #print ("Exporting clusters centers to {}...'.format(centers_file)")
    cluster_centers['cluster'] = cluster_centers['cluster'].apply(lambda x:"cluster" +str(x))
    cluster_centers.to_csv(path_or_buf="output/centers.csv", cols=['latitude', 'longitude','cluster'], encoding='utf-8')
    plot_meanshift(data, cluster_centers, n_centers_)
    return 0

def meanShift(points):
  # perform meanshift clustering of data
  meanshift = MeanShift()
  meanshift.fit(points.T)
  labels = meanshift.labels_
  centers = meanshift.cluster_centers_
  return np.array(labels)

def ms_algo(X, bandwidth=None):
    if(bandwidth==None):
        n_samples = X.shape[0]
        bandwidth = estimate_bandwidth(X, quantile=0.2, n_samples=n_samples)

    # Apply the meanshit algorithm from sklearn library
    ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
    ms.fit(X)

    # collect from the meanshift algorithm the labels and the centers of the clusters
    labels = ms.labels_
    cluster_centers = ms.cluster_centers_


    labels_unique = np.unique(labels)
    n_clusters_ = len(labels_unique) #Number of clusters

    # Print section
    print("The number of clusters is: %d" % n_clusters_)

    print("The centers are:")
    for i in range(n_clusters_):
        print i,
        print cluster_centers[i]

    return cluster_centers    

def find_clusters(feature, items, bandwidth=None, min_bin_freq=None, cluster_all=True, n_jobs=1):
    """
    Cluster list of items based on feature using meanshift algorithm (Binning).

    :param feature: key used to retrieve item to cluster on
    :param items:
    :param bandwidth:
    :param min_bin_freq:
    :param cluster_all:
    :return:
    """
    x = [item[feature] for item in items]
    X = np.array(list(zip(x, np.zeros(len(x)))), dtype=np.float)
    ms = MeanShift(bandwidth=bandwidth, min_bin_freq=min_bin_freq, cluster_all=cluster_all, n_jobs=n_jobs)
    ms.fit(X)

    labels = ms.labels_
    labels_unique = np.unique(labels)

    n_clusters_ = len(labels_unique)

    clusters = []

    for k in range(n_clusters_):
        if k != -1:
            my_members = labels == k
            cluster_center = np.median(X[my_members, 0])
            cluster_sd = np.std(X[my_members, 0])
            clusters.append({
                'center': cluster_center,
                'sd': cluster_sd,
                'items': X[my_members, 0]
            })

    return clusters

def do_meanshift(s_path, band1, band2, band3, band4, colour1, colour2,
                 make_plot):
    '''Meanshift clustering to determine the number of clusters in the
        data, which is passed to KMEANS function'''
    # Truncate data
    X = np.vstack([colour1, colour2]).T
    '''Compute clustering with MeanShift'''
    # Scale data because meanshift generates circular clusters
    X_scaled = preprocessing.scale(X)
    # The following bandwidth can be automatically detected using
    # the routine estimate_bandwidth(X). Bandwidth can also be set manually.
    bandwidth = estimate_bandwidth(X)
    #bandwidth = 0.65
    # Meanshift clustering
    ms = MeanShift(bandwidth=bandwidth, bin_seeding=True, cluster_all=False)
    ms.fit(X_scaled)
    labels_unique = np.unique(ms.labels_)

    objects = ms.labels_[ms.labels_ >= 0]
    n_clusters = len(labels_unique[labels_unique >= 0])
    # Make plot
    if "meanshift" in make_plot:
        make_ms_plots(s_path, colour1, colour2, n_clusters, X, ms,
                      band1, band2, band3, band4, objects)
    return(n_clusters, bandwidth)

def make(filename, precision):
    with open('test.geojson') as f:
        data = json.load(f)

    features = data['features']
    points = [
        geo['geometry']["coordinates"]
        for geo in features if pred(geo)
    ]
    print points
    ar_points = array(points).reshape(len(points) * 2, 2)
    print ar_points
    bandwidth = estimate_bandwidth(ar_points) / precision
    cluster = MeanShift(bandwidth=bandwidth)
    cluster.fit(ar_points)
    labels = cluster.labels_
    cluster_centers = cluster.cluster_centers_
    print 'clusters:', len(unique(labels))

    for i, geo in enumerate(filter(pred, features)):
        geo['geometry']["coordinates"] = [
            list(cluster_centers[labels[i*2 + j]])
            for j in range(2)
        ]

    with open(filename, 'w') as f:
        json.dump(data, f)

 def centers_y_clusters(self,graph_db,nodes,consulta,cyprop):
     group = []
     todo = []
     rr = []
     for n in nodes:
         tiene = neo4j.CypherQuery(graph_db, consulta+" where id(n) ="+str(n.id)+" return count(distinct(e))"+cyprop+" as cuenta").execute()
         for r in tiene:
             todo.append([r.cuenta])
             rr.append(r.cuenta)
         
     ms = MeanShift(bin_seeding=True)
     ms.fit(np.asarray(todo))
     labels = ms.labels_
     cluster_centers = sorted(ms.cluster_centers_ , key=lambda x: x[0])
     for idx,cl in enumerate(cluster_centers):
         cluster_centers[idx] = float(cl[0])
     for u in cluster_centers:
         group.append([])
     for n in nodes:
         tiene = neo4j.CypherQuery(graph_db, consulta+" where id(n) ="+str(n.id)+" return count(distinct(e))"+cyprop+" as cuenta").execute()
         for r in tiene:
             valor = r.cuenta
         for idx,v in enumerate(cluster_centers):
             if idx == 0:
                 temp1 = -9999
             else:
                 temp1 = (cluster_centers[idx-1] + cluster_centers[idx])/2
             if idx == len(cluster_centers) - 1:
                 temp2 = 99999
             else:
                 temp2 = (cluster_centers[idx+1] + cluster_centers[idx])/2
             if temp1 <= valor < temp2:
                 group[idx].append(n)
     return cluster_centers, group