Z = set(Y) M = [[z,Y.count(z)] for z in Z] M.sort() M.reverse() X = [data[0] for data in M] Y = [data[1] for data in M] ''' #Y = [sum(Y[:i]) / float(len(gps_data)) for i in range(1,len(M) + 1,1)] ''' plt.bar(X, Y, width=0.25) plt.show() ''' #pylab.plot(X,Y,'o') #pylab.show() labels, centers = sciencecluster.science_cluster(numpy.array(gps_data), cutoff_distance=0.0000001) save_gps_data(gps_data, labels) ''' eps = 0.00001 min_samples = 15 metric = 'euclidean' core_samples, labels = sklearn.cluster.dbscan(numpy.array(gps_data), metric=metric, eps=eps,min_samples=min_samples) print labels[:100] ''' ''' X = [data[0] for data in gps_data] Y = [data[1] for data in gps_data] ax1 = pylab.subplot(211) ax2 = pylab.subplot(212) pylab.sca(ax1) for i in range(len(X)):
def science_cluster(gps_data,number,show = False): labels,centers = sciencecluster.science_cluster(numpy.array(gps_data),num = number,cutoff_distance = 0.000005,experience = 0.000811,show = show) #0.0003 \\0.0001 return centers,labels
Z = set(Y) M = [[z,Y.count(z)] for z in Z] M.sort() M.reverse() X = [data[0] for data in M] Y = [data[1] for data in M] ''' #Y = [sum(Y[:i]) / float(len(gps_data)) for i in range(1,len(M) + 1,1)] ''' plt.bar(X, Y, width=0.25) plt.show() ''' #pylab.plot(X,Y,'o') #pylab.show() labels,centers = sciencecluster.science_cluster(numpy.array(gps_data),cutoff_distance = 0.0000001) save_gps_data(gps_data,labels) ''' eps = 0.00001 min_samples = 15 metric = 'euclidean' core_samples, labels = sklearn.cluster.dbscan(numpy.array(gps_data), metric=metric, eps=eps,min_samples=min_samples) print labels[:100] ''' ''' X = [data[0] for data in gps_data] Y = [data[1] for data in gps_data] ax1 = pylab.subplot(211) ax2 = pylab.subplot(212) pylab.sca(ax1) for i in range(len(X)):