发表于   |   分类于
相关博客： http://www.360doc.com/content/14/1109/12/20290918_423780183.shtml from numpy import * import matplotlib.pyplot as plt def loadSimpData(): datMat = matrix([ [1., 2.1], [2., 1.1], [1.3, 1.], [1., 1.], [2., 1.] ]) classLabels = [1.0, 1.0, -1.0, -1.0, 1.0] return datMat, classLabels #弱分类器分类，返回致函1/-1的numpy数组 def stumpClassify(dataMatrix, dimen, threshVal, threshIneq): retArray = ones((shape(dataMatrix)[0], 1)) if threshIneq == & ...
阅读全文 »

发表于   |   分类于
svm实现相关博客： http://www.cnblogs.com/dreamvibe/p/4349886.html http://blog.csdn.net/macyang/article/details/38782399/ from numpy import * #文件操作 def loadDataSet(fileName): dataMat = []; labelMat = [] fr = open(fileName) for line in fr.readlines(): lineArr = line.strip().split('\t') dataMat.append([float(lineArr[0]), float(lineArr[1])]) labelMat.append(float(lineArr[2])) return dataMat,labelMat #随机选择另一个α优化 def selectJrand(i,m): j=i while (j ...
阅读全文 »

发表于   |   分类于
from numpy import * def loadDataSet(): dataMat = []; labelMat = [] fr = open('testSet.txt') for line in fr.readlines(): lineArr = line.strip().split() dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])]) labelMat.append(int(lineArr[2])) return dataMat, labelMat def sigmoid(inX): return 1.0/(1+exp(-inX)) #梯度上升算法，运算次数多，准确度高 def gradAscent(dataMatIn, classLabels): dataMatrix = mat(dataMatIn) labelMat = mat(classLabels).transpose ...
阅读全文 »

发表于   |   分类于
下面的例子是用于文本分析 import operator import numpy as np import feedparser as fp def loadDataSet():#0表示非侮辱言论，1表示侮辱言论 postingList = [['my', 'dog', 'has', 'flea', 'problems', 'helo', 'please'], ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'], ['my', &a ...
阅读全文 »

发表于   |   分类于
决策树算法from math import log import operator def createDataSet(): dataSet = [[1,0,'yes'], [1,0,'yes'], [0,1,'no'], [0,1,'no'], [1,0,'no']] labels = ['no surfacing','flippers']#对应1,0的标签 return dataSet, labels def calcShannonEnt(dataSet):#计算香农熵的期望值 numEntries = len(dataSet) labelCounts = {} for featVec in dataSet: currentLabel = featVec ...
阅读全文 »