因為最近實習的需要，所以用python里的sklearn包重新寫了一次決策樹
工具：sklearn，http://www.lfd.uci.edu/~gohlke/pythonlibs/#numpy；將dot文件轉化為pdf格式（是為了將形成的決策樹可視化）graphviz-2.38，下載解壓之后將其中的bin文件的目錄添加進環境變量
源代碼如下：
from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn import preprocessing
from sklearn.externals.six import StringIO
from xml.sax.handler import feature_external_ges
from numpy.distutils.fcompiler import dummy_fortran_file
# Read in the csv file and put features into list of dict and list of class label
allElectronicsData = open(r'E:/DeepLearning/resources/AllElectronics.csv', 'rt')
reader = csv.reader(allElectronicsData)
headers = next(reader)
featureList = []
lableList = []
for row in reader:
lableList.append(row[len(row)-1])
rowDict = {}
#不包括len(row)-1
for i in range(1,len(row)-1):
rowDict[headers[i]] = row[i]
featureList.append(rowDict)
print(featureList)
vec = DictVectorizer()
dummX = vec.fit_transform(featureList).toarray()
print(str(dummX))
lb = preprocessing.LabelBinarizer()
dummY = lb.fit_transform(lableList)
print(str(dummY))
#entropy=>ID3
clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(dummX, dummY)
print("clf:"+str(clf))
#可視化tree
with open("resultTree.dot",'w')as f:
f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(),out_file = f)
#對於新的數據怎樣來查看它的分類
oneRowX = dummX[0,:]
print("oneRowX: "+str(oneRowX))
newRowX = oneRowX
newRowX[0] = 1
newRowX[2] = 0
predictedY = clf.predict(newRowX)
print("predictedY: "+ str(predictedY))
這里的AllElectronics.csv，形式如下圖所示：
今天早上好不容易將jdk、eclipse以及pydev裝進linux，但是，但是，但是，想裝numpy的時候，總是報錯，發現是沒有gcc，然后又去裝gcc，真是醉了，到現在gcc還是沒有裝成功，再想想法子，實在不行過段時間去問大神