Python cluster.vq函数代码示例

	def find_grid(self,inp):
		dx,dy = [],[]
		outx,outy = [],[]
		for i in inp:
			dy.append([i[2],0])
		data = np.vstack(dy)
		centroids,_ = kmeans(data,self.Ny)
		idx,_ = vq(data,centroids)
		for ii in range(0,self.Ny):
			mini = np.min(data[idx==ii,0])
			maxi = np.max(data[idx==ii,0])
			outy.append([mini,maxi])
		outy = sorted(outy[:],key=lambda s:s[1])  
		dx = []
		for i in inp:
			dx.append([i[1],0])
		data = np.vstack(dx)
		centroids,_ = kmeans(data,self.Nx)
		idx,_ = vq(data,centroids)
		for ii in range(0,self.Nx):
			mini = np.min(data[idx==ii,0])
			maxi = np.max(data[idx==ii,0])
			outx.append([mini,maxi])
		outx = sorted(outx[:],key=lambda s:s[1])
		
		out = []
		for y in range(0,len(outy)):
			for x in range(0,len(outx)):
				k = 0
				for k in range(0,len(inp)):
					if (inp[k][1]>=outx[x][0]) and (inp[k][1]<=outx[x][1]) and (inp[k][2]>=outy[y][0]) and (inp[k][2]<=outy[y][1]):
						out.append(inp[k])
					else:
						k+=1
		return out

def compare(m, Nobs, Ncodes, Nfeatures):
    obs = RandomArray.normal(0., 1., (Nobs, Nfeatures))
    codes = RandomArray.normal(0., 1., (Ncodes, Nfeatures))
    import scipy.cluster.vq
    scipy.cluster.vq
    print 'vq with %d observation, %d features and %d codes for %d iterations' % \
           (Nobs,Nfeatures,Ncodes,m)
    t1 = time.time()
    for i in range(m):
        code, dist = scipy.cluster.vq.py_vq(obs, codes)
    t2 = time.time()
    py = (t2 - t1)
    print ' speed in python:', (t2 - t1) / m
    print code[:2], dist[:2]

    t1 = time.time()
    for i in range(m):
        code, dist = scipy.cluster.vq.vq(obs, codes)
    t2 = time.time()
    print ' speed in standard c:', (t2 - t1) / m
    print code[:2], dist[:2]
    print ' speed up: %3.2f' % (py / (t2 - t1))

    # load into cache
    b = vq(obs, codes)
    t1 = time.time()
    for i in range(m):
        code, dist = vq(obs, codes)
    t2 = time.time()
    print ' speed inline/blitz:', (t2 - t1) / m
    print code[:2], dist[:2]
    print ' speed up: %3.2f' % (py / (t2 - t1))

    # load into cache
    b = vq2(obs, codes)
    t1 = time.time()
    for i in range(m):
        code, dist = vq2(obs, codes)
    t2 = time.time()
    print ' speed inline/blitz2:', (t2 - t1) / m
    print code[:2], dist[:2]
    print ' speed up: %3.2f' % (py / (t2 - t1))

    # load into cache
    b = vq3(obs, codes)
    t1 = time.time()
    for i in range(m):
        code, dist = vq3(obs, codes)
    t2 = time.time()
    print ' speed using C arrays:', (t2 - t1) / m
    print code[:2], dist[:2]
    print ' speed up: %3.2f' % (py / (t2 - t1))

def getBOVW(sift_key):
    global codebook
    new_line = ""
    sift_key_points = []

    lines = sift_key.readlines()
    lines = lines[1:]
    for i in range(len(lines)):
        if (i % 8) == 0:
            if new_line != "":
                new_line = new_line.strip()
                tokens = new_line.split()
                tokens = map(int, tokens)
                sift_key_points.append(tokens)
            new_line = ""
        else:
            new_line += (lines[i].strip() + ' ')

    sift_key_points = np.array(sift_key_points)
    codebook = np.array(codebook)
    idx, _ = vq(sift_key_points, codebook)

    BOVW = []
    for i in range(k):
        BOVW.append(list(idx).count(i+1)/ len(sift_key_points))

    return BOVW

    def BOWMatch(self, indexPath):
        '''the query's score against an individual index'''
        # start = time.time()
        query_des_list = []
        im_features, image_paths, idf, numWords, voc = joblib.load(indexPath)
        numWords = self.numWords

        desc = cv2.xfeatures2d.SIFT_create()
        # Extract the descriptors from the query 
        query = self.image
        kp, des = desc.detectAndCompute(query, None)
        query_des_list.append((query, des))

        # Stack query descriptors in a numpy array
        query_descriptors = query_des_list[0][1]

        # Calculate histogram of Features for the Query 
        test_features = np.zeros((1, numWords), "float32")
        words, distance = vq(query_descriptors, voc)
        for w in words:
            test_features[0][w] += 1 

        # Perform Tf-idf vectorization for the Query
        test_features = test_features * idf
        test_features = preprocessing.normalize(test_features, norm='l2')

        score = np.dot(test_features, im_features.T)
        return score

def detectPupilKMeans(gray,K=2,distanceWeight=2,reSize=(40,40)):
	''' Detects the pupil in the image, gray, using k-means
			gray              : grays scale image
			K                 : Number of clusters
			distanceWeight    : Defines the weight of the position parameters
			reSize            : the size of the image to do k-means on
		'''
	#Resize for faster performance
	smallI = cv2.resize(gray, reSize)
	M,N = smallI.shape
	#Generate coordinates in a matrix
	X,Y = np.meshgrid(range(M),range(N))
	#Make coordinates and intensity into one vectors
	z = smallI.flatten()
	x = X.flatten()
	y = Y.flatten()
	O = len(x)
	#make a feature vectors containing (x,y,intensity)
	features = np.zeros((O,3))
	features[:,0] = z;
	features[:,1] = y/distanceWeight; #Divide so that the distance of position weighs less than intensity
	features[:,2] = x/distanceWeight;
	features = np.array(features,'f')
	# cluster data
	centroids,variance = kmeans(features,K)
	#use the found clusters to map
	label,distance = vq(features,centroids)
	# re-create image from
	labelIm = np.array(np.reshape(label,(M,N)))
	f = figure(1)
	imshow(labelIm)
	f.canvas.draw()
	f.show()

def buildHistogramForVideo(pathToVideo, vocabulary):
    frames = os.listdir(pathToVideo)
    size = len(vocabulary)

    stackOfHistogram = np.zeros(size).reshape(1, size)
    for frame in frames:
        # build histogram for this frame
        completePath = pathToVideo +"/"+ frame
        lines = open(completePath, "r").readlines()

        print completePath

        frameFeatures = np.zeros(128).reshape(1, 128)
        for line in lines[1:]:
            data = line.split(" ")
            feature = data[4:]

            for i in range(len(feature)):
                item = int(feature[i])
                feature[i] = item

            feature = normalizeSIFT(feature)
            frameFeatures = np.vstack((frameFeatures, feature))

        frameFeatures = frameFeatures[1:]
        codes, distance = vq(frameFeatures, vocabulary)

        histogram = np.zeros(size)
        for code in codes:
            histogram[code] += 1

        stackOfHistogram = np.vstack((stackOfHistogram, histogram.reshape(1,size)))

    return stackOfHistogram[1:]

def predictor(im, w, queue):
    global fea_det
    global step_size
    global k
    global voc
    global clf
    global classes_names
    global stdSlr
    global image_paths
    best = 0
    for (x_pt, y_pt, window) in sliding_window(im, stepSize=16, windowSize=(w,w)):
        if window.shape[0] != w or window.shape[1] != w:
            continue
        kpts = [cv2.KeyPoint(x, y, step_size) for y in range(0, window.shape[0], step_size)
                                              for x in range(0, window.shape[1], step_size)]
        (kpts, des) = fea_det.compute(window, kpts) # compute dense descriptors
        des = whiten(des)
        test_features = np.zeros((len(image_paths), k), "float32")
        words, L2distance = vq(des, voc)
        for wd in words:
            test_features[0][wd] += 1
        nbr_occurences = np.sum( (test_features > 0) * 1, axis = 0)
        idf = np.array(np.log((1.0*len(image_paths)+1) / (1.0*nbr_occurences + 1)), 'float32')
        test_features = stdSlr.transform(test_features)
        probs = np.array(clf.predict_proba(test_features))
        ind = np.argmax(probs)
        max_prob = np.max(probs)
        if max_prob > best:
            predictions = (classes_names[ind], max_prob)
            best = max_prob
            #print(predictions)
    queue.put(predictions)

def classify(im):
    if im == None:
        print "No such file {}\nCheck if the file exists".format(image_path)
        return -1

    # Load the classifier, class names, scaler, number of clusters and vocabulary
    clf, classes_names, stdSlr, k, voc = joblib.load("bow.pkl")

    sift = cv2.xfeatures2d.SIFT_create()

    kpts, des = sift.detectAndCompute(im, None)

    test_features = np.zeros((1, k), "float32")

    # words, distance = vq(des_list[0][1],voc)
    words, distance = vq(des, voc)
    for w in words:
        test_features[0][w] += 1

    # Perform tf-idf vectorization
    nbr_occurences = np.sum((test_features > 0) * 1, axis=0)
    idf = np.array(np.log((1.0 * 1 + 1) / (1.0 * nbr_occurences + 1)), "float32")

    # Scale the features
    test_features = stdSlr.transform(test_features)

    # Perform the predictions
    predictions = [classes_names[i] for i in clf.predict(test_features)]
    return predictions

def k_mean_plot_AMN(c,folder, list_vectors_ANM):
    """Creates a k-means clustering mainly for dcds trayectories cluster"""
    for i in list_vectors_ANM:
	# DEFINE ONE VAR (fixed number of variables = number of PDB-DCD pairs = 4 in our case)
        var1 = list_vectors_ANM[0]
        var2 = list_vectors_ANM[1]
        var3 = list_vectors_ANM[2]
        var4 = list_vectors_ANM[3]

        features = np.array([])
	features=np.append(features,var1)
	features=np.append(features,var2)
	features=np.append(features,var3)
	features=np.append(features,var4)
	
        centroids,variance = kmeans(features,c)
        code,distance = vq(features,centroids)
	
        for j in range(len(var1)-1):
            pylab.plot([p[j] for p in var1],[p[j+1] for p in var1],'*')
            pylab.plot([p[j] for p in var2],[p[j+1] for p in var2],'r*') 
            pylab.plot([p[j] for p in var3],[p[j+1] for p in var3],'y*') 
            pylab.plot([p[j] for p in var4],[p[j+1] for p in var4],'g*') 
        #~ pylab.plot([p[0] for p in centroids],[p[1] for p in centroids],'go') 
        pylab.plot(centroids,centroids,'go') 
    pylab.savefig("./"+folder+"/kmeans_ANMnalysis.png")

def GetPupilKMeans(gray, K = 2, distanceWeight = 2, reSize = (40,40)):
	
	smallI = cv2.resize(gray, reSize)
	
	M,N = smallI.shape

	X,Y = np.meshgrid(range(M), range(N))

	z = smallI.flatten()
	x = X.flatten()
	y = Y.flatten()
	O = len(x)

	features = np.zeros((O, 3))
	features[:,0] = z
	features[:,1] = y / distanceWeight
	features[:,2] = x / distanceWeight

	features = np.array(features, 'f')

	centroids, variance = kmeans(features, K)
	print(centroids)
	label, distance = vq(features, centroids)

	labelIm = np.array(np.reshape(label, (M, N)))

	f = figure(1)
	imshow(labelIm)
	f.canvas.draw()
	f.show()

def detectPupilKMeans(gray,K=4,distanceWeight=1,reSize=(30,30)):
    smallI = cv2.resize(gray, reSize)
    M,N = smallI.shape
    X,Y = np.meshgrid(range(M),range(N))

    z = smallI.flatten()
    x = X.flatten()
    y = Y.flatten()
    O = len(x)

    #make a feature vectors containing (x,y,intensity)
    features = np.zeros((O,3))
    features[:,0] = z;
    features[:,1] = y/distanceWeight; #Divide so that the distance of position weighs less

    features[:,2] = x/distanceWeight;
    features = np.array(features,'f')
    # cluster data
    centroids,variance = kmeans(features,K)
    #use the found clusters to map
    label,distance = vq(features,centroids)
    # re-create image from
    labelIm = np.array(np.reshape(label,(M,N)))

    # Find the lowest valued class
    thr = 255
    for i in range(K):
        if(centroids[i][0] < thr):
            thr = centroids[i][0]

    return thr

def cluster(S,k,ndim):
    """ Spectral clustering from a similarity matrix."""
    
    # check for symmetry
    if sum(abs(S-S.T)) > 1e-10:
        print 'not symmetric'
    
    # create Laplacian matrix
    rowsum = sum(abs(S),axis=0)
    D = diag(1 / sqrt(rowsum + 1e-6))
    L = dot(D,dot(S,D))
    
    # compute eigenvectors of L
    U,sigma,V = linalg.svd(L,full_matrices=False)
    
    # create feature vector from ndim first eigenvectors
    # by stacking eigenvectors as columns
    features = array(V[:ndim]).T

    # k-means
    features = whiten(features)
    centroids,distortion = kmeans(features,k)
    code,distance = vq(features,centroids)
        
    return code,V

def buildVLADForEachImageAtDifferentLevels(descriptorsOfImage, level):

    # Set width and height
    width = descriptorsOfImage.width
    height = descriptorsOfImage.height
    # calculate width and height step
    widthStep = int(width / 2)
    heightStep = int(height / 2)

    descriptors = descriptorsOfImage.descriptors

    # level 1, a list with size = 4 to store histograms at different location
    VLADOfLevelOne = np.zeros((4, k, dim))
    for descriptor in descriptors:
        x = descriptor.x
        y = descriptor.y
        boundaryIndex = int(x / widthStep)  + int(y / heightStep)

        feature = descriptor.descriptor
        shape = feature.shape[0]
        feature = feature.reshape(1, shape)

        codes, distance = vq(feature, k_means.cluster_centers_)
        
        VLADOfLevelOne[boundaryIndex][codes[0]] += np.array(feature).reshape(shape) - k_means.cluster_centers_[codes[0]]
    
    
    for i in xrange(4):
        # Square root norm
        VLADOfLevelOne[i] = np.sign(VLADOfLevelOne[i]) * np.sqrt(np.abs(VLADOfLevelOne[i]))
        # Local L2 norm
        vector_norm = np.linalg.norm(VLADOfLevelOne[i], axis = 1)
        vector_norm[vector_norm < 1] = 1
        
        VLADOfLevelOne[i] /= vector_norm[:, None]
    
    # level 0
    VLADOfLevelZero = VLADOfLevelOne[0] + VLADOfLevelOne[1] + VLADOfLevelOne[2] + VLADOfLevelOne[3]
    # Square root norm
    VLADOfLevelZero = np.sign(VLADOfLevelZero) * np.sqrt(np.abs(VLADOfLevelZero))
    # Local L2 norm
    vector_norm = np.linalg.norm(VLADOfLevelZero, axis = 1)
    vector_norm[vector_norm < 1] = 1
    
    VLADOfLevelZero /= vector_norm[:, None]
    
    if level == 0:
        return VLADOfLevelZero

    elif level == 1:
        tempZero = VLADOfLevelZero.flatten() * 0.5
        tempOne = VLADOfLevelOne.flatten() * 0.5
        result = np.concatenate((tempZero, tempOne))
        # Global L2 norm
        norm = np.linalg.norm(result)
        if norm > 1.0:
            result /= norm
        return result
    else:
        return None

  def project(self,descriptors):
    """ 記述子をボキャブラリに射影して、
        単語のヒストグラムを作成する """
    #drawing = zeros((1000,1000))    
    dic = {}
    # ビジュアルワードのヒストグラム
    imhist = zeros((self.nbr_words))
    words,distance = vq(descriptors,self.voc)
    """
    tmp = list(set(words)) # 重複を排除したwordsを取得
    words = np.array(words)
    index = []
    for t in tmp:
      tmp_d = []
      index.append( np.where( words == t)[0] )
      for i in index:
        tmp_d.append([pointors[i,:]])
      dic[t] = tmp_d
      tmp_d = np.array(dic[t])
      dic[t] = np.sort(tmp_d, axis = 0)
      print dic[t]
      cv2.drawContours(drawing,dic[t],0,(0,255 -t,0),2)
    
    cv2.imshow( "Result", drawing )
    cv2.waitKey()  
    cv2.destroyAllWindows()
    """
    for w in words:
      imhist[w] += 1

    return imhist

def clusterDataSpec(data, k, algorithm):
    '''
    Cluster the given data into a number of clusters determined by BIC.
    @param data: 2D numpy array holding our data.
    @param algorithm: 
    @raise LogicalError if algorithm is other than "k-means" or "GMM"
    @return The predicted labels (clusters) for every example.
    '''
    
    if algorithm not in ["k-means", "GMM"]:
        raise LogicalError, "Method %s: Clustering is made only through K-means or GMM." %(stack()[0][3])
    
    print "Clustering for k=%d." %(k) 
    if algorithm == "k-means":
        whiten(data)
        codebook, _distortion = kmeans(data, k, 10) # 10 iterations only to make it faster
    else:
        g = GMM(n_components=k,thresh = 1e-05, covariance_type='diag', n_iter=10)
        g.fit(data)
            
    #print "Optimal number of clusters according to BIC: %d." %(optimalK)
    
    # Return predicted labels
    if algorithm == "k-means":
        return vq(data, codebook)[0] # predictions on the same data
    else:
        return g.predict(data) # predictions on the same data