k-means python实现及数据.zip

import numpy as np import matplotlib.pyplot as plt # 返回距离样本最近的质心的下标索引 def group_one(sample, centers): distance_vect = np.sum((sample-centers)**2, axis=1) return np.argmin(distance_vect) # 将所有样本分组到k个质心，返回二维列表[[属于分组1的样本][属于分组2的样本]...] def group_all(data, k, centers): # 这里使用二维列表，而不是ndarray的原因在于，每个分组的大小，也就是样本的个数是不确定的 # 而array是确定大小的，强行转换这里会变成列表对象的数组，效率低下且更容易出错 # 如果有更好的做法欢迎交流 groups = [] for index in range(k): groups.append([]) # 对每一个样本进行分组 for sample in data: index = group_one(sample, centers) groups[index].append(sample.tolist()) return groups # 根据样本分组，更新每个质心的位置 def update_centers(data, k, groups): centers = np.zeros((k, data.shape[1])) for index in range(k): centers[index] = np.mean(np.array(groups[index]), axis=0) return centers # 检测与上一次迭代的更新差值 def iter_diff(old_centers, new_centers): return np.sum(np.abs(old_centers - new_centers)) # 生成随机质心 def rand_center(data, k): # 共k个质心，data.shape[1]是每个数据样本的维度，质心的维度应与样本的维度一致。 centers = np.random.rand(k, data.shape[1]) # rand随机的范围是零到一，要适用于样本的范围需要进行缩放 # 这里使用样本在该维度的最大值作为每个维度上的缩放倍数 scale = np.max(data, axis=0) centers *= scale return centers # 迭代主体函数 def classify(data, k, threshold, max_iter=0): centers = rand_center(data, k) loss = float("inf") iter_count = 0 # 当loss小于阈值，或迭代次数大于指定最大次数时（若不指定则只判断loss足够低）终止 while loss > threshold and ((max_iter == 0) or iter_count < max_iter): groups = group_all(data, k, centers) old_centers = centers centers = update_centers(data, k, groups) loss = iter_diff(old_centers, centers) iter_count += 1 print("iter_%d : loss=%f" % (iter_count, loss)) return centers, groups # 绘图 def paint_result(data, centers, k, groups, debug=False): c = [] flatten_group = [] for index in range(k): for item in groups[index]: c.append(index) flatten_group.append(item) groups = np.array(flatten_group) if debug: plt.scatter(groups[:, 0], groups[:, 1]) else: plt.scatter(groups[:, 0], groups[:, 1],c=c) plt.scatter(centers[:, 0], centers[:, 1], color="red") plt.show() def main(): data = np.loadtxt("d:/data.csv", delimiter=",") data.resize((500, 2)) center, groups = classify(data, 3, 0, 0) paint_result(data, center, 3, groups) if __name__ == '__main__': main()