# 通過卡方檢驗選定資料特徵
import pandas
from pandas import read_csv
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
# 匯入資料
iris =pandas.read_csv('http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
 
,header=None)
iris.columns=['SepalLengthCm','SepalWidthCm','PetalLengthCm','PetalWidthCm','Species'] 

# 將資料分為輸入資料和輸出結果
arrary = iris.values
X =arrary[:,0:4]

le = LabelEncoder()
le.fit(iris['Species'])   
Y = le.transform(iris['Species']) # 對花的類別進行編號處理
# 分為測試集和訓練集
test_size = 0.33
seed = 6
X_train, X_test
 
, Y_traing, Y_test = train_test_split(X, Y, test_size=test_size, random_state=seed)
# 選擇模型
model = LogisticRegression()
# 進行訓練
model.fit(X_train, Y_traing)
# 用測試集檢視訓練結果
result = model.score(X_test, Y_test)
print("演算法評估結果：%.3f%%" % (result * 100))