python sklearn库集成_python机器学习sklearn库：从头到尾

一,简单示例

1.数据准备

from sklearn import datasets

from sklearn.model_selection import train_test_split

iris=datasets.load_iris()

2.将特征与标签分开

x,y=datasets.load_iris(return_X_y=True)

x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)

3.建立模型

from sklearn.neighbors import KNeighborsClassifier

knn=KNeighborsClassifier()

4.训练

knn.fit(x_train,y_train)

KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',

metric_params=None, n_jobs=None, n_neighbors=5, p=2,

weights='uniform')

5.测试

acc=knn.score(x_test,y_test)

print(acc)

0.9333333333333333

二,线性回归与交叉验证

from sklearn.datasets import fetch_california_housing

from sklearn.linear_model import LinearRegression,Lasso,Ridge,ElasticNet

from sklearn.model_selection import cross_val_score

x,y=fetch_california_housing(return_X_y=True)

lr=LinearRegression()

loss=-cross_val_score(lr,x,y,cv=5,scoring='neg_mean_squared_error').mean()

print(y.min(),y.max())

print(loss)

0.14999 5.00001

0.5582901717686815

Lasso(L1正则化)，Ridge(L2正则化)，ElasticNet(L1和L2正则化都有)

lasso=Lasso(alpha=0.01)

loss1=-cross_val_score(lasso,x,y,cv=5,scoring='neg_mean_squared_error').mean()

ridge=Ridge(alpha=0.01)

loss2=-cross_val_score(ridge,x,y,cv=5,scoring='neg_mean_squared_error').mean()

elasticnet=ElasticNet(alpha=0.01)

loss3=-cross_val_score(elasticnet,x,y,cv=5,scoring='neg_mean_squared_error').mean()

print(loss1,loss2,loss3)

0.564023420597941 0.558290056170532 0.5603421342140549

三,逻辑回归与学习曲线

from sklearn.datasets import load_breast_cancer

from sklearn.linear_model impor