python实现ID3 决策树
素材
AllElectronics.csv
代码实现
import csvfrom sklearn import treefrom sklearn import preprocessingfrom sklearn.feature_extraction import DictVectorizer allElectronicsData = open(r'AllElectronics.csv', 'r') #reader = csv.reader(allElectronicsData) # 迭代器headers = next(reader)print("reader:"+str(reader))print("headers:"+str(headers))featureList = []labelList = []for row in reader:print(row)labelList.append((row[len(row) - 1])) # 把预测项作为labelList的元素rowDict = {}for i in range(1, len(row) - 1): # 从1开始是因为要防止读取RIDrowDict[headers[i]] = row[i]featureList.append(rowDict)print("labelList:"+str(labelList))print("featureList:"+str(featureList)) # 列表里面含有字典vec = DictVectorizer() # 符号化将字典转换成0、1字符dummyX = vec.fit_transform(featureList).toarray() # 将featureList转化成0、1字符print('dummyX:'+str(dummyX))print("feature_names:"+str(vec.get_feature_names())) # 打印每一个特征值用键值对合并表示print("labelList:"+str(labelList))lb = preprocessing.LabelBinarizer() # 二值化dummyY = lb.fit_transform(labelList) # 将labelList中相反的值转化成0,1字符print("dummyY:"+str(dummyY))clf = tree.DecisionTreeClassifier(criterion='entropy') # 按信息熵来使用决策树ID3算法clf = clf.fit(dummyX, dummyY) # 按dummyX,dummyY拟合print("clf:"+str(dummyY))with open("allElectronicInformationGainOri.dot", 'w') as f:f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file=f)# 把clf写入并生成allElectronicInformationGainOri.dot文件oneRowX = dummyX[0, :] # 获取训练集的第一行数据print("oneRowX:", str(oneRowX))newRowX = oneRowX newRowX[0] = 1newRowX[2] = 0# 修改newRowX的并作为测试集print("newRowX:" + str(newRowX))predictedY = clf.predict([newRowX]) # 测试print("predictedY:" + str(predictedY))
输出
声明:本文来自网络,不代表【好得很程序员自学网】立场,转载请注明出处:http://haodehen.cn/did127595