from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn import preprocessing
from sklearn.externals.six import StringIO

# Read in the csv file and put features into list of dict and list of class label
allElectronicsData = open(r'/home/zhoumiao/MachineLearning/01decisiontree/AllElectronics.csv', 'rb')
reader = csv.reader(allElectronicsData)
headers = reader.next()

print(headers)
# featureList存放特徵屬性，轉換成多維：舉例子“身高屬性”的取值“高”“矮”{1.0,0.0}，
# 若沒有序關係，假定有k個屬性值，則通常轉化成k維向量，
# 例如屬性”瓜類“的取值“西瓜”“南瓜”“黃瓜”可轉化為（0,0,1）（0,1,0）（1,0,0）。
featureList = []
# labelList存放標籤屬性
labelList = []

for row in reader:
# 讀入標籤
    labelList.append(row[len(row)-1])
	# 新增字典，將屬性新增到字典中
    rowDict = {}
    for i in range(1, len(row)-1):
        rowDict[headers[i]] = row[i]
    # 將字典存放到特徵屬性當中
	featureList.append(rowDict)

print(featureList)

# Vetorize features
vec = DictVectorizer()
# python的模組，將字典轉換成上面的屬性形式
dummyX = vec.fit_transform(featureList) .toarray()

print("dummyX: " + str(dummyX))
print(vec.get_feature_names())

print("labelList: " + str(labelList))

# vectorize class labels
lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)
print("dummyY: " + str(dummyY))

# Using decision tree for classification
# clf = tree.DecisionTreeClassifier()
# sklearn的決策樹使用
clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(dummyX, dummyY)
print("clf: " + str(clf))


# Visualize model
# 運用graphviz將決策樹寫到文件中
with open("allElectronicInformationGainOri.dot", 'w') as f:
    f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file=f)

# 去除第一行
oneRowX = dummyX[0, :]
print("oneRowX: " + str(oneRowX))

# 修改第一行的資料，然後進行預測
newRowX = oneRowX
newRowX[0] = 1
newRowX[2] = 0
print("newRowX: " + str(newRowX))

predictedY = clf.predict(newRowX)
print("predictedY: " + str(predictedY))