sklearn之决策树

from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import preprocessing
from sklearn import tree
from sklearn.externals.six import StringIO
allEctronicsData = open(r'E:\workspace\first\src\test\c.csv', 'rb')
reader = csv.reader(allEctronicsData);
headers = reader.next();
featureList = [];
labelList = [];
for row in reader:
    labelList.append(row[len(row) - 1])
    rowDict = {};
    for i in range(1, len(row)-1):
        rowDict[headers[i]] = row[i];
    
    featureList.append(rowDict);
print(featureList)
vec = DictVectorizer();
dumpyX = vec.fit_transform(featureList).toarray()
print(vec.feature_names_)
lb = preprocessing.LabelBinarizer()
dumpyY = lb.fit_transform(labelList)
print(str(dumpyY))


clf = tree.DecisionTreeClassifier(criterion = 'entropy')
clf = clf.fit(dumpyX, dumpyY)
print(str(clf))
with open("allEctronicsDataAllInfo.dot", 'w') as f:
    f = tree.export_graphviz(clf, feature_names = vec.get_feature_names(), out_file = f)