Python cluster.AffinityPropagation类代码示例

	def clustering(self):
		# Calculate similarity matrix
		X = self.create_tfidf_vector()
		X = X.toarray()
		pca = PCA(n_components=300, copy=False)
		X = pca.fit(X).transform(X)
		S = cosine_similarity(X, X)
		# Run affinity propogation
		af = AffinityPropagation()
		af.fit(S)
		# Formulate result
		tmp_clusters = defaultdict(list)
		goal_clusters = defaultdict(list)
		cluster_centers_indices = af.cluster_centers_indices_
		labels = af.labels_
		count = 0
		for label in labels:
			tmp_clusters[\
				self.goal_list[cluster_centers_indices[label]]].append(\
				self.goal_list[count])
			count += 1
		# 2nd-layer clutering of each cluster
		for goal, item_list in tmp_clusters.items():
			subclusters = self.subcluster_by_editdistance(goal, item_list)
			for subgoal, items in subclusters.items():
				goal_clusters[subgoal] = items
		return goal_clusters

def main():
    '''
        >>> main() # stuff happens
    '''

    args = parse_args()
    setup_logging(args.log, verbose=args.verbose)

    chunks = sequence_chunk_generator(args.fasta_file,
                                      chunk_size=args.chunk_size)

    hasher = HashingVectorizer(analyzer='char',
                               n_features = 2 ** 18,
                               ngram_range=(args.ngram_min, args.ngram_max),
                               )

    estimator = AffinityPropagation()

    for chunk in chunks:

        logging.info('hashing chunk')
        chunk_vector = hasher.transform([ str(i.seq) for i in chunk ])

        logging.info('clustering')

        estimator.fit(chunk_vector)

        logging.info('got %s clusters' % len(set(estimator.labels_)))

def clusterSimilarityWithSklearnAPC(data_file,damping=0.9,max_iter=200,convergence_iter=15,preference='min'):
    """
    Compare Sparse Affinity Propagation (SAP) result with SKlearn Affinity Propagation (AP) Clustering result.
    Please note that convergence condition for Sklearn AP is "no change in the number of estimated clusters",
    for SAP the condition is "no change in the cluster assignment". 
    So SAP may take more iterations and the there will be slightly difference in final cluster assignment (exemplars for each sample).
    """
    # loading data
    simi_mat=loadMatrix(data_file)
    simi_mat_dense=simi_mat.todense()

    # get preference
    if preference=='min':
        preference=np.min(simi_mat_dense)
    elif preference=='median':
        preference=np.median(simi_mat_dense)
    
    print('{0}, start SKlearn Affinity Propagation'.format(datetime.now()))
    af=AffinityPropagation(damping=damping, preference=preference, affinity='precomputed',verbose=True)
    af.fit(simi_mat_dense)
    cluster_centers_indices,labels = af.cluster_centers_indices_,af.labels_
    sk_exemplars=np.asarray([cluster_centers_indices[i] for i in labels])
    print('{0}, start Fast Sparse Affinity Propagation Cluster'.format(datetime.now()))
    sap=SAP(preference=preference,convergence_iter=convergence_iter,max_iter=max_iter,damping=damping,verboseIter=100)
    sap_exemplars=sap.fit_predict(simi_mat_dense)
    
    # Caculate similarity between sk_exemplars and sap_exemplars
    exemplars_similarity=sparseAP_cy.arrSamePercent(np.array(sk_exemplars), np.array(sap_exemplars))
    
    return exemplars_similarity

 def clusterAffinityPropagation(self):
     """
     Cluster the embeddings with affinity propagation
     :return:
     """
     affin = AffinityPropagation()
     affin.fit(self.emb1.m)
     aflabels1 = affin.labels_
     afclusters1 = dict()
     word2cluster1 = dict()
     for i,l in enumerate(aflabels1):
         points = afclusters1.setdefault(l,list())
         points.append(self.emb1.rd[i])
     for l,c in afclusters1.items():
         for w in c:
             word2cluster1[w] = l
     self.cluster1 = afclusters1
     self.word2cluster1 = word2cluster1
     affin.fit(self.emb2.m)
     aflabels2 = affin.labels_
     afclusters2 = dict()
     word2cluster2 = dict()
     for i,l in enumerate(aflabels2):
         points = afclusters2.setdefault(l,list())
         points.append(self.emb2.rd[i])
     for l,c in afclusters2.items():
         for w in c:
             word2cluster2[w] = l
     self.cluster2 = afclusters2
     self.word2cluster2 = word2cluster2

    def classify_core(self, N_CLUSTERS, clusterType, data_for_trial_type, begin_time, end_time):

        BEGIN_TIME_FRAME = begin_time*self.griddy.TIME_GRID_SPACING
        END_TIME_FRAME = end_time*self.griddy.TIME_GRID_SPACING

        data = data_for_trial_type[:,BEGIN_TIME_FRAME:END_TIME_FRAME,self.griddy.VEL_X]

        labels = None
        if clusterType == 'kmeans':
            kmeans = KMeans(n_clusters=N_CLUSTERS)
            kmeans.fit(data)
            labels = kmeans.labels_
        elif clusterType == 'affinity_propagation':
            ap = AffinityPropagation(damping=0.75)
            ap.fit(data)
            labels = ap.labels_
            N_CLUSTERS = np.max(self.labels)+1
        elif clusterType == 'DBSCAN':
            dbscan = DBSCAN()
            dbscan.fit(data)
            labels = dbscan.labels_
            N_CLUSTERS = np.max(labels)+1
            print 'N_CLUSTERS=' + str(N_CLUSTERS)
        elif clusterType == 'AgglomerativeClustering':
            ac = AgglomerativeClustering(n_clusters=N_CLUSTERS)
            ac.fit(data)
            labels = ac.labels_
        else:
            print 'ERROR: clusterType: ' + clusterType + ' is not recognized'

        return (labels, N_CLUSTERS)

def cluster(mat, doc_indices):
    X = mat[:, doc_indices].T
    # Other clustering algorithms can easily be swapped in:
    # http://scikit-learn.org/stable/modules/classes.html#module-sklearn.cluster
    clust = AffinityPropagation()
    clust.fit(X)
    return zip(doc_indices,  clust.labels_)

def cluster(scope):
    # Setup data
    df = pd.read_sql('playtype_data', db_engine)

    # Manipulate data into scope
    if scope == 'Team':
        df = df.drop('Player', 1).groupby('Team', as_index=False).mean()
    elif scope == 'Player':
        df = df.drop('Team', 1)
    else:
        raise Exception('This is never supposed to happen')

    # Normalize the data
    df[FEATURES] = (df[FEATURES] - df[FEATURES].mean()) / (df[FEATURES].max() - df[FEATURES].min())

    # Run clustering
    clstr = AffinityPropagation()
    clstr.fit(df[FEATURES])

    # Clump results
    df['cluster'] = clstr.labels_
    df = df.sort('cluster')

    # Convert results to JSON for frontend
    return clusters_to_json(df, scope)

def affinity_propagation_cluster_analysis(x,y,preference):
    # NOT WORKING BECAUSE I DONT REALLY UNDERSTAND WHAT IT DOES...
    # ADAPTED FROM:
    # http://scikit-learn.org/stable/auto_examples/cluster/plot_affinity_propagation.html#example-cluster-plot-affinity-propagation-py
    X = np.hstack((x.reshape((x.shape[0],1)),y.reshape((y.shape[0],1))))
    af = AffinityPropagation()
    af = af.fit(X)
    cluster_centers_indices = af.cluster_centers_indices_
    labels = af.labels_
    
    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 = X[cluster_centers_indices[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])
        for j in X[my_members]:
            plt.plot([cluster_center[0], x[0]], [cluster_center[1], x[1]],c=colors[i],linestyle='--')
    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 cluster(self, feat_mtx, df_lm_allusers):
        # clustering artists based on AffinityPropogation
        start = time.time()
        af = AffinityPropagation()
        af.fit(feat_mtx)
        self.labels = af.labels_
        self.af = af

        # adding cluster labels to least misery dataframe and sorting by rank and cluster
        #df_least_misery_clustered = self.df_least_misery.copy() --> changing to df_lm_allusers
        print 'number of labels: ', len(self.labels)
        print 'labels', self.labels
        
        # print 'least misery clustered length', len(df_least_misery_clustered)
        
        df_least_misery_clustered = df_lm_allusers.copy()
        print 'len df least misery: ', len(df_least_misery_clustered)
        
        df_least_misery_clustered['cluster'] = self.labels
        df_least_misery_clustered[['cluster', self.score_col]] = df_least_misery_clustered[['cluster', self.score_col]].astype(float)
        ''' will do different sorting if not using rank '''
        # now set to false as looking for highest score
        df_least_misery_clustered = df_least_misery_clustered.sort(['cluster', self.score_col], ascending = False)
        self.df_least_misery_clustered = df_least_misery_clustered
        end = time.time()
        print 'clustering completed in: ', end - start  
        return df_least_misery_clustered

def cluster_trajectories( curves ):
    """Given a list of curves, cluster_trajectories will cluster them."""
    n_curves = len(curves)
    X_2B_clstrd = np.zeros( (n_curves, 4) )
    X_2B_clstrd[:,0] = np.array( [ curves[k][0, 0] for k in range(n_curves) ] )
    X_2B_clstrd[:,1] = np.array( [ curves[k][1, 0] for k in range(n_curves) ] )
    X_2B_clstrd[:,2] = np.array( [ curves[k][0,-1] for k in range(n_curves) ] )
    X_2B_clstrd[:,3] = np.array( [ curves[k][1,-1] for k in range(n_curves) ] )
        
    for col in range( 4 ):
        X_2B_clstrd[:,col] /=  X_2B_clstrd[:,col].std()
        
    def distance_metric(a,b):
        #A distance metric on R^4 modulo the involution
        #(x0,x2,x3,x4) -> (x3,x4,x1,x2)
        d = lambda a,b : np.sqrt( np.sum( (a-b)**2 ) )
        T = lambda x: np.array([x[2],x[3],x[0],x[1]])
        return min( d(a,b) , d(T(a),b) )
    from sklearn.cluster import AffinityPropagation
    clusterer = AffinityPropagation(affinity='precomputed', convergence_iter=100)
    aff = np.zeros((n_curves, n_curves))
    for i in range(n_curves):
        for j in range(i+1,n_curves):
            aff[i,j] = np.exp(-distance_metric( X_2B_clstrd[i], X_2B_clstrd[j])**2)
            aff[j,i] = aff[i,j]

    #clusterer.Affinity = aff
    cluster_labels = clusterer.fit_predict(aff)
    out = []
    for label in set( cluster_labels):
        cluster = map( lambda k: curves[k] , filter( lambda k: cluster_labels[k] == label , range( n_curves) ) )
        out.append( cluster )
    return map( align_cluster, out)

def loadKmeansData(dataArrayTest,dataArrayTrain,k,m='load'):
    if m=='load':
        centroidRead=open('centroid','r')
        labelClusterRead=open('labelCluster','r')
        labelPreRead=open('labelPre','r')
        centroid=pickle.load(centroidRead)
        labelCluster=pickle.load(labelClusterRead)
        labelPre=pickle.load(labelPreRead)
    else:
        dataArrayTestNorm = preprocessing.normalize(dataArrayTest)
        dataArrayTrainNorm = preprocessing.normalize(dataArrayTrain)
        #clf=MiniBatchKMeans(init='k-means++', n_clusters=k, n_init=10)
        clf=AffinityPropagation()
        #clf=DBSCAN(min_samples=30)
        pre=clf.fit(dataArrayTrainNorm)


        centroid=pre.cluster_centers_
        centroidWrite=open('centroid','w')
        #pickle.dump(centroid,centroidWrite)

        labelCluster=pre.labels_
        labelClusterWrite=open('labelCluster','w')
        #pickle.dump(labelCluster,labelClusterWrite)

        labelPre=clf.predict(dataArrayTestNorm)
        labelPreWrite=open('labelPre','w')
        #pickle.dump(labelPre,labelPreWrite)

    return centroid,labelCluster,labelPre

def clusterise_data(data_obj):
    """ Assigns a cluster label to each days present in the data received 
        using three different algorithms: MeanShift, Affinity Propagation, 
        or KMeans. 
        @param data_obj: List of dictionaries
    """
    L = len(data_obj)
    
    #Simply converts data_obj to a 2D list for computation
    List2D = [[None for _ in range(4)] for _ in range(L-1)]
    for i in range(L-1): #don't include current day
        #wake_up and sleep_duration are the most important factors
        List2D[i][0] = 5 * data_obj[i]["wake_up"]
        List2D[i][1] = 1 * data_obj[i]["sleep"]
        List2D[i][2] = 5 * data_obj[i]["sleep_duration"]
        List2D[i][3] = 0.5 * data_obj[i]["activity"]
    points = NumpyArray(List2D) #converts 2D list to numpyarray
        
    if ALGO == "Affinity Propagation":
        labels = AffinityPropagation().fit_predict(points)
    elif ALGO == "KMeans":
        labels= KMeans(init='k-means++', n_clusters=5, n_init=10)   .fit_predict(points)
    elif ALGO == "MeanShift":
        bandwidth = estimate_bandwidth(points, quantile=0.2, n_samples=20)
        labels = MeanShift(bandwidth=bandwidth, bin_seeding=True).fit_predict(points)
    else:
        raise Exception("Algorithm not defined: "+str(ALGO))
        
    for i in range(L-1):
        data_obj[i]["cluster"] = labels[i]
    for unique_label in remove_duplicates(labels):
        debug_print(ALGO+": Cluster "+str(unique_label)+" contains "+str(labels.tolist().count(unique_label))+" data points")
    debug_print(ALGO+": Silhouette coefficient"+ str(metrics.silhouette_score(points, labels, metric='euclidean')*100)+"%")

def execute(args):
  ##############################################################################
  if len(args) < 1:
    usage()
    sys.exit()

  names, labels_true, X = parse(args[0])
  indices = [int(i) for i in args[1:]]
  relevant_names = names[1:]
  if len(indices) > 0:
    X = np.asarray([[sample[i] for i in indices] for sample in X])
    relevant_names = [relevant_names[i] for i in indices]
  print "Clustering on", str(relevant_names) + "..."

  
  ##############################################################################
  # Compute Affinity Propagation
  af = AffinityPropagation(preference=-50)
  # cluster_centers_indices = af.cluster_centers_indices_
  # labels = af.labels_
  # 
  # n_clusters_ = len(cluster_centers_indices)

  y_pred = af.fit_predict(X)
  if y_pred is None or len(y_pred) is 0 or type(y_pred[0]) is np.ndarray:
    return 0
  counts = get_cluster_counts(labels_true, y_pred)
  print counts

def affinity_propagation(crime_rows, column_names):
    """
        damping : float, optional, default: 0.5
            Damping factor between 0.5 and 1.
        convergence_iter : int, optional, default: 15
            Number of iterations with no change in the number of estimated 
            clusters that stops the convergence.
        max_iter : int, optional, default: 200
            Maximum number of iterations.
        preference : array-like, shape (n_samples,) or float, optional
            Preferences for each point - points with larger values of preferences 
            are more likely to be chosen as exemplars. 
            The number of exemplars, ie of clusters, is influenced by the input 
            preferences value. If the preferences are not passed as arguments, 
            they will be set to the median of the input similarities.
        affinity : string, optional, default=``euclidean``
            Which affinity to use. At the moment precomputed and euclidean are 
            supported. euclidean uses the negative squared euclidean distance 
            between points.
    """
    crime_xy = [crime[0:2] for crime in crime_rows]
    crime_info = [crime[2:] for crime in crime_rows]
    print("Running Affinity Propagation")
    # TODO: Parameterize this
    affinity_prop = AffinityPropagation()
    #affinity_propagation_labels = affinity_prop.fit_predict(crime_xy)
    affinity_prop.fit(random_sampling(crime_xy, num_samples=5000))
    affinity_propagation_labels = affinity_prop.predict(crime_xy)
    print("formatting....")
    return _format_clustering(affinity_propagation_labels, crime_xy, crime_info, 
            column_names)

def affinity_propagation(feature_matrix):
    
    sim = feature_matrix * feature_matrix.T
    sim = sim.todense()
    ap = AffinityPropagation()
    ap.fit(sim)
    clusters = ap.labels_          
    return ap, clusters