寫在開頭的話：在學習《機器學習實戰》的過程中發現書中很多代碼並沒有註釋，這對新入門的同學是一個挑戰，特此貼出我對代碼做出的註釋，僅供參考，歡迎指正。
1、K-均值聚類算法
#coding:gbk
from numpy import *
#作用：從文件中導入數據集
#輸入：文件名
#輸出：數據集
def loadDataSet(fileName): #general function to parse tab -delimited floats
dataMat = [] #assume last column is target value
fr = open(fileName)
for line in fr.readlines():
curLine = line.strip().split('\t')
fltLine = map(float,curLine) #map all elements to float()
dataMat.append(fltLine)
return dataMat
#作用：計算兩個向量的歐式距離
#輸入：向量A，向量B
#輸出：向量間的歐式距離
def distEclud(vecA, vecB):
return sqrt(sum(power(vecA - vecB, 2)))
#作用：爲給定數據集構建一個包含k個隨機質心的集合
#輸入：數據集，隨機質心數
#輸出：包含k個隨機質心的集合
def randCent(dataSet, k):
n = shape(dataSet)[1]
centroids = mat(zeros((k, n)))
for j in range(n):
minJ = min(dataSet[:, j])
rangeJ = float(max(dataSet[:, j]) - minJ)
centroids[:, j] = minJ + rangeJ * random.rand(k, 1)
return centroids
#作用：k-均值算法
#輸入：數據集，簇數目，距離計算方法，質心集合創造方法
#輸出：簇質心集合，簇分配結果矩陣
def kMeans(dataSet, k, distMeas = distEclud, createCent = randCent):
m = shape(dataSet)[0]
#簇分配結果矩陣，包含兩列，一列記錄簇索引值，第二列存儲誤差
clusterAssment = mat(zeros((m, 2)))
centroids = createCent(dataSet, k)
clusterChanged = True
while clusterChanged:
clusterChanged = False
#對每個樣本，尋找最近的質心
for i in range(m):
minDist = inf
minIndex = -1#從屬簇的索引值
for j in range(k):
distJI = distMeas(centroids[j, :], dataSet[i, :])
if distJI < minDist:
minDist = distJI
minIndex = j
#只要有數據點的簇分配結果發生改變，clusterChanged = True
if clusterAssment[i, 0] != minIndex:
clusterChanged = True
clusterAssment[i, :] = minIndex, minDist ** 2
#print centroids
#遍歷所有質心並更新它們的取值
for cent in range(k):
ptsInClust = dataSet[nonzero(clusterAssment[:, 0].A == cent)[0]]
centroids[cent, :] = mean(ptsInClust, axis = 0)#axis = 0表示沿矩陣的列方向進行均值計算
return centroids, clusterAssment2、二分K-均值聚類算法
#作用：二分k-均值聚類算法
#輸入：數據集，簇數目，距離計算方法
#輸出：簇質心集合，簇分配結果矩陣
def biKmeans(dataSet, k, distMeas = distEclud):
m = shape(dataSet)[0]#數據點個數
clusterAssment = mat(zeros((m, 2)))#簇分配結果矩陣，包含兩列，一列記錄簇索引值，第二列存儲誤差
centroid0 = mean(dataSet, axis = 0).tolist()[0]#計算整個數據集的質心
centList = [centroid0]#使用列表保留所有簇的質心，將初始簇的質心壓入
#遍歷數據集中所有的點來計算每個點到質心的誤差值
for j in range(m):
clusterAssment[j, 1] = distMeas(mat(centroid0), dataSet[j, :]) ** 2
#不停對簇進行劃分，直到得到想要的簇數目爲止
while (len(centList) < k):
lowestSSE = inf
#遍歷已有的簇來決定最佳的簇進行劃分
for i in range(len(centList)):
#只有第i個簇的數據集
ptsInCurrCluster = dataSet[nonzero(clusterAssment[:, 0].A == i)[0], :]
#對第i個簇一分爲二
centroidMat, splitClustAss = kMeans(ptsInCurrCluster, 2, distMeas)
#對第i個簇劃分後得到的誤差平方和
sseSplit = sum(splitClustAss[:, 1])
#除了第i個簇的數據集的誤差平方和
sseNotSplit = sum(clusterAssment[nonzero(clusterAssment[:, 0].A != i)[0], 1])
print "sseSplit, and notSplit: ", sseSplit, sseNotSplit
#如果劃分後的簇有最小的總誤差
if (sseSplit + sseNotSplit) < lowestSSE:
bestCentToSplit = i
bestNewCents = centroidMat
bestClustAss = splitClustAss.copy()
lowestSSE = sseSplit +sseNotSplit
#將新的二分好的簇的第二個的索引值設爲cenList + 1，即現有的centList後的一個
bestClustAss[nonzero(bestClustAss[:, 0].A == 1)[0], 0] = len(centList)
#將新的二分好的簇的第二個的索引值設爲bestCentToSplit，即要二分的簇
bestClustAss[nonzero(bestClustAss[:, 0].A == 0)[0], 0] = bestCentToSplit
print 'the bestCentToSplit is: ', bestCentToSplit
print 'the len of bestClustAss is: ', len(bestClustAss)
#均需要加tolist()[0]，否則後面會出錯誤
centList[bestCentToSplit] = bestNewCents[0, :].tolist()[0]#將i個簇換成新的二分好的簇的第一個
centList.append(bestNewCents[1, :].tolist()[0])#將新的二分好的簇的第二個壓入列表
clusterAssment[nonzero(clusterAssment[:, 0].A == bestCentToSplit)[0], :] = bestClustAss#更新簇的分配結果
#print centList
return mat(centList), clusterAssment3、對地圖上的點進行聚類
import urllib
import json
#作用：對地址進行地理編碼
#輸入：地址，城市
#輸出：地理編碼
def geoGrab(stAddress, city):
apiStem = 'http://where.yahooapis.com/geocode?'
params = {}
params['flags'] = 'J'#將返回類型設爲JSON
params['appid'] = 'ppp68N8t'
params['location'] = '%s %s' % (stAddress, city)
url_params = urllib.urlencode(params)#將創建的字典轉換爲可以通過URL進行傳遞的字符串格式
yahooApi = apiStem + url_params
print yahooApi#打印輸出的URL
c = urllib.urlopen(yahooApi)#打開URL
return json.loads(c.read())#讀取返回值
from time import sleep
#作用：服務器不存在，失敗
#輸入：
#輸出：
def massPlaceFind(fileName):
fw = open('places.txt', 'w')
for line in open(fileName).readlines():
line = line.strip()
lineArr = line.split('\t')
retDict = geoGrab(lineArr[1], lineArr[2])
if retDict['ResultSet']['Error'] == 0:
lat = float(retDict['ResultSet']['Result'][0]['latitude'])#維度
lng = float(retDict['ResultSet']['Result'][0]['longitude'])#經度
print "%s\t%f\t%f" % (lineArr[0], lat, lng)
fw.write('%s\t%f\t%f\n' % (line, lat, lng))
else:
print "error fetching"
sleep(1)
fw.close()
def distSLC(vecA, vecB):
a = sin(vecA[0, 1] * pi / 180) * sin(vecB[0, 1] * pi / 180)
b = cos(vecA[0, 1] * pi / 180) * cos(vecB[0, 1] * pi / 180) * cos(pi * (vecB[0, 0] -vecA[0, 0]) / 180)
return arccos(a + b) * 6371.0
import matplotlib
import matplotlib.pyplot as plt
def clusterClubs(numClust = 5):
datList = []#表示每個地點的經度、維度
for line in open('places.txt').readlines():
lineArr = line.split('\t')
datList.append([float(lineArr[4]), float(lineArr[3])])
datMat = mat(datList)
#二分k-均值聚類算法
myCentroids, clustAssing = biKmeans(datMat, numClust, distMeas = distSLC)
fig = plt.figure()
rect = [0.1, 0.1, 0.8, 0.8]
scatterMarkers = ['s', 'o', '^', '8', 'p', 'd', 'v', 'h', '>', '<']
axprops = dict(xticks = [], yticks = [])
ax0 = fig.add_axes(rect, label = 'ax0', **axprops)
imgP = plt.imread('Portland.png')
ax0.imshow(imgP)
ax1 = fig.add_axes(rect, label = 'ax1', frameon = False)
#ax1.scatter(myCentroids[:, 0].flatten().A[0], myCentroids[:, 1].flatten().A[0], marker='+', s=300)
#繪製座標點
for i in range(numClust):
ptsInCurrCluster = datMat[nonzero(clustAssing[:, 0].A == i)[0], :]
markerStyle = scatterMarkers[i % len(scatterMarkers)]
ax1.scatter(ptsInCurrCluster[:, 0].flatten().A[0], ptsInCurrCluster[:, 1].flatten().A[0], \
marker = markerStyle, s = 90)
#myCentroids = mat(myCentroids)
#print myCentroids
#繪製簇中心
ax1.scatter(myCentroids[:, 0].flatten().A[0], myCentroids[:, 1].flatten().A[0], marker = '+', s = 300)
plt.show()