FCM_iris.rar_fcm python_fcm算法 _iris_python_聚类

# coding: utf-8 # In[1]: import numpy as np from scipy.spatial.distance import cdist import sklearn.datasets as ds import math import matplotlib.pyplot as plt from sklearn import metrics # In[2]: def Nmi(xx, U, culster_number, target=None): print("this is NMI!") data = np.array(xx.data.T) S,N = data.shape # print(data.shape) R = np.zeros((N,1)) # print(R) for i in range(0,N): for j in range(0,culster_number): k = int(R[i][0]) if U[i][k]<U[i][j]: R[i][0] = j R = R.reshape(1,N) ssr,nnr= R.shape if target is None: Q = xx.target else: target = np.array(target) Q = target Q = Q.reshape(1,N) # print(Q) ssq,nnq = Q.shape # print("Q.shape=%s"%str(Q.shape)) tmp, total = Q.shape Q_i = np.unique(Q) Q_i = np.array([Q_i]) Q_c = len(Q_i[0]) R_i = np.unique(R) R_i = np.array([R_i]) R_c = len(R_i[0]) idQ = (np.tile(Q, (Q_c,1)).reshape(Q_c*ssq,1*nnq) == np.tile(Q_i.T, (1,total)).reshape(Q_c*ssq,1*nnq))+0.0 idR = (np.tile(R, (R_c,1)).reshape(R_c*ssr,1*nnr) == np.tile(R_i.T, (1,total)).reshape(R_c*ssr,1*nnr))+0.0 idQR = idQ.dot(idR.T) # print("idQR.shape=%s"%str(idQR.shape)) print(idQR) Sq = np.zeros((Q_c,1)) Sr = np.zeros((R_c,1)) for i in range(0,Q_c): for j in range(0,total): if idQ[i][j]==1: Sq[i][0]=Sq[i][0]+1 for i in range(0,R_c): for j in range(0,total): if idR[i][j]==1: Sr[i][0]=Sr[i][0]+1 Pq = np.zeros((Q_c,1)) Pr = np.zeros((R_c,1)) for i in range(0,Q_c): Pq[i][0] = Sq[i][0]/total for i in range(0,R_c): Pr[i][0] = Sr[i][0]/total Pqr = idQR/total # print("-------Pqr_--------") # print(Pqr) #计算熵值 Hq = 0 Hr = 0 for i in range(0,Q_c): Hq = Hq+Pq[i][0]*math.log(Pq[i][0],2) for i in range(0,R_c): Hr = Hr+Pr[i][0]*math.log(Pr[i][0],2) # 计算结果 校验值:1.339261208514355 MI = 0 for i in range(0,Q_c): for j in range(0,R_c): MI = MI+Pqr[i][j]*math.log((Pqr[i][j]/(Pq[i][0]*Pr[j][0])+2.2204e-16),2)#eps=2.2204e-16 1.275 1.339261208514355 NMI = MI/((Hq*Hr)**(1./2.)) print("NMI=%lf"%NMI) return NMI # In[3]: def plot(self, v, u, c, labels=None): # plt.ion() print("-"*30+"begin drawing ... ...") # plt.figure(1) ax = plt.subplots()[1] # Plot assigned clusters, for each data point in training set # print("u:%s"%str(u.shape)) cluster_membership = np.argmax(u, axis=0) # print("cluster_membership:%s"%str(cluster_membership.shape)) marker_lab = ['*', 'x', 'o'] color_lab = ['bs', 'rs', 'gs'] for j in range(c): ax.scatter( self[2][cluster_membership == j], self[3][cluster_membership == j], alpha = 0.8, marker = marker_lab[j], edgecolors = "none") # Mark the center of each fuzzy cluster k = 0 for pt in v: ax.plot(pt[2], pt[3], color_lab[k]) k += 1 # ax.legend() ax.grid(True) # plt.pause(2) #显示秒数 # plt.close() plt.show() # In[4]: def _object(u, d, m): d2 = d ** 2 um = u ** m j = np.sum(um*d2) return j # In[5]: def _fcm_criterion(d, m, metric): exp = -2. / (m - 1) d2 = d ** exp ds = np.sum(d2, axis=0, keepdims=1) u = d2 / ds # print("_fcm_criterion-->d2:{},ds:{},u:{}".format(d2.shape, ds.shape, u.shape)) return u def _update_clusters(x, u, m): um = u **m ux = um.dot(x.T) us = np.atleast_2d(um.sum(axis=1)).T # print("_update_clusters-->um:{},ux:{},us:{}".format(um.shape, ux.shape, us.shape)) v = ux / us # print("_update_clusters-->v:{}".format(v.shape)) return v def cmean(x, c, m, e, max_iterations, v0=None, metric="euclidean" ): # Num Features, Datapoints S, N = x.shape # Initialize the cluster centers # If the user doesn't provide their own starting points, if v0 is None: # Pick random values from dataset xt = x.T np.random.seed(1) v0 = xt[np.random.choice(xt.shape[0], c, replace=False), :] v = np.empty((max_iterations, c, S)) v[0] = np.array(v0) # Membership Matrix Each Data Point in eah cluster u = np.zeros((max_iterations, c, N)) j = np.zeros(max_iterations, dtype="float64") t = 0 while t < max_iterations - 1: d = cdist(x.T, v[t], metric=metric).T # Sanitize Distances (Avoid Zeroes) d = np.fmax(d, np.finfo(x.dtype).eps) # u updata u[t] = _fcm_criterion(d, m, metric) # v updata v[t + 1] = _update_clusters(x, u[t], m) j[t + 1] = _object(u[t], d, m) # Stopping Criteria if np.linalg.norm(j[t + 1] - j[t]) < e: break t += 1 return v[t], v[0], u[t - 1], u[0], t, j # In[6]: fuzzifier = 1.5 error = 0.0001 maxiter = 100 c = 3 # np.random.seed(100) # In[12]: iris0 = ds.load_iris() labels = iris0.target_names target = iris0.target iris = np.array(iris0.data).T # v, v0, u, u0, d, t = cmeans.fcm(iris, c, fuzzifier, error, maxiter) v, v0, u, u0, t, j= cmean(iris, c, fuzzifier, error, maxiter) iris = iris.T print("Iris") print(v) Nmi(iris0, u.T, c) u_max = np.argmax(u, axis=0) print(metrics.normalized_mutual_info_score(u_max, target)) # print(v) # print(t) # for i in range(t+3): # print("%3f"%j[i]) # In[8]: plot(iris.T, v, u, c ) # In[15]: import sklearn.datasets as ds from matplotlib import pyplot as plt from mpl_toolkits.mplot3d import Axes3D def plot_3D(self, v, u, cluster, a, b, c,labels=None): feature_a = a feature_b = b feature_c = c # plt.ion() print("-"*30+"begin drawing ... ...") # plt.figure(1) # ax = plt.subplots()[1] ax = plt.subplot(111, projection='3d') # 创建一个三维的绘图工程 # Plot assigned clusters, for each data point in training set # print("u:%s"%str(u.shape)) cluster_membership = np.argmax(u, axis=0) # print("cluster_membership:%s"%str(cluster_membership.shape)) marker_lab = ['^', 'x', 'o', 'd', '*', 'h', '.'] color_lab = ['bs', 'rs', 'gs', 'ys', 'ks', 'ms', 'cs'] for j in range(cluster): ax.scatter( self[feature_a][cluster_membership == j], self[feature_b][cluster_membership == j], self[feature_c][cluster_membership == j], alpha = 0.5, marker = marker_lab[j], # edgecolors = "none" ) # Mark the center of each fuzzy cluster k = 0 for pt in v: # ax.scatter(pt[feature_a], pt[feature_b], pt[feature_c], color_lab[k]) ax.scatter(pt[feature_a], pt[feature_b], pt[feature_c], "rs") k += 1 # ax.legend() ax.grid(True) # plt.pause(2) #显示秒数 # plt.close() plt.show() plot_3D(iris.T, v, u, c, 1, 0, 2)