Edwards_June的专栏

源码有问题,贴出修改后可运行代码：def loadDataSet(): return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]] def createC1(dataSet): C1 = [] for transaction in dataSet: for item in transaction:

from math import log import operator # 计算数据集的熵 def calsShannonEnt(dataSet): numEntries = len(dataSet) labelCounts = {} for featVec in dataSet: currentLabel = featVec[-1]

代码链接： from numpy import * def loadDataSet(): dataMat = [] labelMat = [] fr = open('testSet.txt') for line in fr.readlines(): lineArr = line.strip().split() dataM

代码链接：   from numpy import * def loadDataSet(fileName): dataMat = [] fr = open(fileName) m = len(fr.readline().split('\t')) for line in fr.readlines(): curLine = line.strip(

代码链接： from numpy import * def loadDataSet(fileName, delim='\t'): fr = open(fileName) stringArr = [line.strip().split(delim) for line in fr.readlines()] datArr = [] for line in s

代码链接： from numpy import * def loadDataSet(fileName): numFeat = len(open(fileName).readline().split('\t')) - 1 dataMat = [] labelMat = [] fr = open(fileName) for line in fr.r

代码链接：http://download.youkuaiyun.com/detail/edwards_june/9856050 from numpy import * def loadDataSet(fileName): dataMat = [] labelMat = [] fr = open(fileName) for line in fr.readlines(

代码链接：http://download.youkuaiyun.com/detail/edwards_june/9856048 from numpy import * # 词表到向量的转换函数 def loadDataSet(): postingList = [['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],

学习《机器学习实战》一书时写的代码： from numpy import * def loadSimpData():     datMat = matrix([[1., 2.1],                      [2., 1.1],                      [1.3, 1.],                      [1., 1.],

from array import array from os import listdir from numpy import * import operator def createDataSet():         group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])         labels = ['A','A','