python编程实践小结2016-04-11

本文小结最近python编程中解决的几个问题。

这些问题大部分是不同版本python的函数差异。

列表：

1、python的对象序列化模块是pickle.

2、读写文件过程中，主要读写的方式'w'、'wb'，'r'、'rb'，不同版本python的函数对参数的要求不同。

3、函数isinstance(secondDict[key], dict) 作用等价于type(secondDict[key]).__name__=='dict'。都是判断是不是字典类型。

4、字典dictionary的函数key()在python2.x返回列表，在python3.x返回dict对象。注意甄别。

5、调用dictionary时，Pydev无法智能提示字典的函数key()。不知什么原因，以后注意。

5、查看python函数的详细定义时，一般java工程中，按F3即可。但Pydev中，总是跳出一个选择列表，对于刚接触python，不懂各个模块功能的人来说，确实痛苦。

6、python开发文件.py中，加入中文字符就会乱码，编译运行都会失败。

解决办法：1、#!/usr/bin/env python。# coding=utf-8

    2、# -*- coding: utf-8 -*-

7、import时，引入一个函数时，可以form os import listdir；引入某个包所有函数，可以from numpy import *；引入某个包或者.py文件，import operator.

8、with open() as file，经常用于打开文件。

利用香农熵构建决策树，并进行分类，以及存储调用决策树的python源码如下：

#!/usr/bin/env python
# coding=utf-8

'''
Created on Oct 12, 2010
Decision Tree Source Code for Machine Learning in Action Ch. 3
@author: Peter Harrington
'''
from math import log
import operator

#创建数据集
def createDataSet():
    dataSet = [[1, 1, 'yes'],
               [1, 1, 'yes'],
               [1, 0, 'no'],
               [0, 1, 'no'],
               [0, 1, 'no']]
    labels = ['no surfacing','flippers']
    #change to discrete values
    return dataSet, labels

#计算样本集的香农熵
def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet: #the the number of unique elements and their occurance
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] = 0
        labelCounts[currentLabel] += 1
    shannonEnt = 0.0
    for key in labelCounts:     #计算数据集的熵，依据是否为鱼类
        prob = float(labelCounts[key])/numEntries
        shannonEnt -= prob * log(prob,2) #log base 2
    return shannonEnt
    
#返回数据集中所有axis的属性值==value的数据
def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]     #chop out axis used for splitting 返回从开始到axis的元素，不包括axis元素
            reducedFeatVec.extend(featVec[axis+1:]) #list末尾添加另一个list
            retDataSet.append(reducedFeatVec)
    return retDataSet
    
#计算最好的数据集划分方式
def chooseBestFeatureToSplit(dataSet):
    numFeatures = len(dataSet[0]) - 1      #the last column is used for the labels
    baseEntropy = calcShannonEnt(dataSet)  #最初熵值
    bestInfoGain = 0.0; bestFeature = -1
    for i in range(numFeatures):        #iterate over all the features
        featList = [example[i] for example in dataSet]#create a list of all the examples of this feature
        uniqueVals = set(featList)       #get a set of unique values
        newEntropy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet, i, value)        #按第i个属性值，value值进行划分
            prob = len(subDataSet)/float(len(dataSet))          #子集概率
            newEntropy += prob * calcShannonEnt(subDataSet)     #熵值
        infoGain = baseEntropy - newEntropy     #calculate the info gain; ie reduction in entropy
        if (infoGain > bestInfoGain):       #compare this to the best gain so far
            bestInfoGain = infoGain         #if better than current best, set to best
            bestFeature = i
    return bestFeature                      #returns an integer

#返回次数最多的分类名称
def majorityCnt(classList):
    classCount={}
    for vote in classList:
        if vote not in classCount.keys(): classCount[vote] = 0
        classCount[vote] += 1
    sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

#创建决策树
def createTree(dataSet,labels):
    classList = [example[-1] for example in dataSet]        #分类名称
    if classList.count(classList[0]) == len(classList):     #类型一致，则返回分类名称
        return classList[0]         #stop splitting when all of the classes are equal
    if len(dataSet[0]) == 1:        #stop splitting when there are no more features in dataSet
        return majorityCnt(classList)                       #遍历完所有特征值，返回剩下数据中，出现最多的分类名称
    bestFeat = chooseBestFeatureToSplit(dataSet)    #返回最佳特征值序号              
    bestFeatLabel = labels[bestFeat]                #去除特征值名称
    myTree = {bestFeatLabel:{}}         #嵌套字典表示决策树
    del(labels[bestFeat])                                   #删除已选择标签
    featValues = [example[bestFeat] for example in dataSet]
    uniqueVals = set(featValues)
    for value in uniqueVals:
        subLabels = labels[:]       #copy all of labels, so trees don't mess up existing labels
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels)
    return myTree                            
    
#利用决策树进行分类
def classify(inputTree,featLabels,testVec):     #参数：决策树、特征向量、测试向量
    firstStr = list(inputTree.keys())[0]        #第一层决策
    secondDict = inputTree[firstStr]            #第一层key对应到的value
    featIndex = featLabels.index(firstStr)      #特征值对应的索引
    key = testVec[featIndex]                    #测试向量key
    valueOfFeat = secondDict[key]               #测试向量key对应的value
    if isinstance(valueOfFeat, dict):           #value还是dict
        classLabel = classify(valueOfFeat, featLabels, testVec)
    else: classLabel = valueOfFeat              #value不是dict
    return classLabel

#存储决策树到文件
def storeTree(inputTree,filename):
    import pickle       #序列化对象
    fw = open(filename,'wb')        #注意打开方式'w'与'wb'区别
    pickle.dump(inputTree, fw)
    fw.close()
    
#加载文件中的决策树
def grabTree(filename):
    import pickle
    fr = open(filename, 'rb')
    return pickle.load(fr)
    
dataSet, labels = createDataSet()
print('the dataSet is: %s'%dataSet)
print('the labels is: %s'%labels)

shannonEntropy = calcShannonEnt(dataSet)
print('the shannonEntropy is: %.10f'%shannonEntropy)

bestFeature = chooseBestFeatureToSplit(dataSet)
print('the best feature is: %d'%bestFeature)

import ch03_treePlotter
myTree = ch03_treePlotter.retrieveTree(0)
classLabel = classify(myTree, labels, [1,0])
print ('the classify result is: %s'%classLabel)

storeTree(myTree, 'decisiontree\\decisionTree.txt')
tree = grabTree('decisiontree\\decisionTree.txt')
ok = 1