머신러닝 노트1: 결정목

분석 데이터
분석 데이터 csv 파일.
프로젝트는 RID,age(나이),income(수입),student(학생),credit신용도buys_구매 결과

sklearn을 분석하기 위해서는 전환이 필요합니다.

from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import preprocessing
from sklearn import tree
from sklearn.externals.six import StringIO
with open('test_data.csv') as f:
f_csv = csv.reader(f)
headers = next(f_csv)
# csvデータを分析データに転換用
labelList = [] # 結果データ
featureList = [] # 属性データ

for row in f_csv:
    labelList.append(row[len(row) - 1])
    rowDict = {}
    for i in range(1, len(row) - 1):
        rowDict[headers[i]] = row[i]
    featureList.append(rowDict)

print(labelList)
print(featureList)

# sklearnの分析データに転換する
vec = DictVectorizer()
dummyX = vec.fit_transform(featureList).toarray()

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

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

# sklearnの結果データに転換する
lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)
print("dummyY: " + str(dummyY))

# 計算方法を決まり、treeを構築する
clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(dummyX, dummyY)
print("clf:" + str(clf))

with open("test.dot", 'w') as f2:
    # 結果データを出力する
    f2 = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file = f2)
    # dot ファイルからpdfに転換 コマンド: dot -T pdf test.dot -o output.pdf

# 仮に予想データを作成する
oneRowX = dummyX[0, :]
print("oneRowX:" + str(oneRowX))

newRowX = oneRowX
newRowX[0] = 1
newRowX[2] = 0 
print("newRowX:" + str(newRowX))

#予想データの結果
predictedY = clf.predict(newRowX)
print("predictedY:" + str(predictedY))