推到省略:
鸢尾花数据集采用逻辑回归进行分类:
from sklearn.datasets import load_iris #导入数据集模块
from sklearn.linear_model import LogisticRegression #导入逻辑回归算法类
from sklearn.model_selection import train_test_split #导入数据分割方法
from sklearn.metrics import accuracy_score #导入精确度方法
dataset=load_iris() #调用方法
x=dataset.data[0:100,:] #获取前100行
# print(x)
y=dataset.target[0:100] #获取前100行
# print(y)
X_train, X_test, y_train, y_test = train_test_split(x,y,test_size=0.3,random_state=6) #分割数据集
logistic_model=LogisticRegression() #调用逻辑回归方法
logistic_model.fit(X_train,y_train) #训练数据
y_pred=logistic_model.predict(X_test) #测试数据
print(accuracy_score(y_test,y_pred)) #获得精度
print(logistic_model.predict_proba(X_test)) #可以得到预测为0 1 的概率
"""
[[0.97427443 0.02572557]
[0.9641451 0.0358549 ]
[0.97639496 0.02360504]
[0.96718815 0.03281185]
"""