import numpy as np

Author: DeepInDeeper

.gitignore

@@ -16,6 +16,7 @@ out
 *.obj
 .ipynb_checkpoints
 */.ipynb_checkpoints
+*/**/.ipynb_checkpoints
 
 # Compiled Dynamic libraries
 *.so

K-Means/K-Means-sklearn.ipynb

@@ -0,0 +1,75 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## K-Means 聚类算法 "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "import numpy as np\n",
+    "from scipy import io as spio\n",
+    "from matplotlib import pyplot as plt\n",
+    "from sklearn.cluster import KMeans\n",
+    "import matplotlib as mpl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = spio.loadmat(\"data.mat\")\n",
+    "X = data[\"X\"]\n",
+    "model = KMeans(n_clusters=3).fit(X)\n",
+    "centroids = model.cluster_centers_ \n",
+    "print centroids"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def draw(X,center):\n",
+    "    plt.figure(figsize=(8,8)) \n",
+    "    plt.scatter(X[:,0], X[:,1])     # 原数据的散点图\n",
+    "    plt.plot(center[:,0],center[:,1],'r^',markersize=10)  # 聚类中心\n",
+    "\n",
+    "draw(X,centroids)  \n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [Root]",
+   "language": "python",
+   "name": "Python [Root]"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

K-Means/K-Means.ipynb

@@ -8,7 +8,7 @@
 def kMenas():
     data = spio.loadmat("data.mat")
     X = data['X']   
-    model = KMeans(n_clusters=3).fit(X) # n_clusters指定3类，拟合数据
+    model = KMeans(n_clusters=3).fit(X)  # n_clusters指定3类，拟合数据
     centroids = model.cluster_centers_  # 聚类中心
 
     plt.scatter(X[:,0], X[:,1])     # 原数据的散点图

K-Means/K-Means_scikit-learn.py

@@ -11,7 +11,7 @@
 
 def KMeans():
     '''二维数据聚类过程演示'''
-    print u'聚类过程展示...\n'
+    print (u'聚类过程展示...\n')
     data = spio.loadmat("data.mat")
     X = data['X']
     K = 3   # 总类数
@@ -21,7 +21,7 @@ def KMeans():
     '''
     图片压缩
     '''
-    print u'K-Means压缩图片\n'
+    print (u'K-Means压缩图片\n')
     img_data = misc.imread("bird.png")  # 读取图片像素数据
     img_data = img_data/255.0             # 像素值映射到0-1
     img_size = img_data.shape
@@ -31,21 +31,21 @@ def KMeans():
     max_iters = 5
     initial_centroids = kMeansInitCentroids(X,K)
     centroids,idx = runKMeans(X, initial_centroids, max_iters, False)
-    print u'\nK-Means运行结束\n'
-    print u'\n压缩图片...\n'
+    print (u'\nK-Means运行结束\n')
+    print (u'\n压缩图片...\n')
     idx = findClosestCentroids(X, centroids)
     X_recovered = centroids[idx,:]
     X_recovered = X_recovered.reshape(img_size[0],img_size[1],3)
 
-    print u'绘制图片...\n'
+    print (u'绘制图片...\n')
     plt.subplot(1,2,1)
     plt.imshow(img_data)
     plt.title(u"原先图片",fontproperties=font)
     plt.subplot(1,2,2)
     plt.imshow(X_recovered)
     plt.title(u"压缩图像",fontproperties=font)
     plt.show()
-    print u'运行结束！'
+    print (u'运行结束！')
 
 
 # 找到每条数据距离哪个类中心最近    
@@ -86,7 +86,7 @@ def runKMeans(X,initial_centroids,max_iters,plot_process):
     idx = np.zeros((m,1))           # 每条数据属于哪个类
 
     for i in range(max_iters):      # 迭代次数
-        print u'迭代计算次数：%d'%(i+1)
+        print (u'迭代计算次数：%d'%(i+1))
         idx = findClosestCentroids(X, centroids)
         if plot_process:    # 如果绘制图像
             plt = plotProcessKMeans(X,centroids,previous_centroids) # 画聚类中心的移动过程
@@ -120,4 +120,3 @@ def kMeansInitCentroids(X,K):
 
 if __name__ == "__main__":
     KMeans()
-