使用Sklearn机器学习库对Iris进行训练和测试

from sklearn.linear_model import LogisticRegression
import pandas as pd
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
import pandas as pd
import numpy as np
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import classification_report
from sklearn.preprocessing import OneHotEncoder

df = pd.read_csv('D:\\DEV_DATA\\AI\\Iris\\iris_origin.csv',
                     names=['sepal length', 'sepal width', 'petal length', 'petal width', 'class'])

#setosa为正类，其他为负类
#df['class']=df['class'].apply(lambda v: 1 if v == 'setosa' else 0)
x = df.ix[:, :4]
y = df.ix[:, 4]

#特征缩放，标准化处理
sc = StandardScaler()
X_train, X_test, Y_train, Y_test = train_test_split(x, y, test_size=0.3)
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)

lr = LogisticRegression(C=1000.0, random_state=0)
lr.fit(X_train_std, Y_train)

print(Y_test)
predict = lr.predict(X_test_std)
print(lr.score(X_test_std,Y_test))
print(classification_report(Y_test, predict))
print('---------------------')


x = sc.transform([[6.5,2.8,4.6,1.5]])

y = lr.predict(x)
print(y)