python之sklearn-分类算法-3.5 模型的保存与加载

一，sklearn模型的保存和加载API

from sklearn.externals import joblib

• 保存：joblib.dump(rf,“test.pkl”)
• 加载：estimator = joblib.load(‘test.pkl’)

二，线性回归模型的保存加载案例

1,保存模型

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report,roc_auc_score
from sklearn.externals import joblib

def logisticregression():
    '''逻辑回归癌症预测'''
    # 确定数据columns数值
    columns = ["Sample code number","Clump Thickness","Uniformity of Cell Size","Uniformity of Cell Shape","Marginal Adhesion","Single Epithelial Cell Size","Bare Nuclei","Bland Chromatin","Normal Nucleoli","Mitoses","Class"]
    data = pd.read_csv("breast-cancer-wisconsin.data",names=columns)

    # 去掉缺失值
    data.replace(to_replace="?",value=np.nan,inplace=True)
    data.dropna(axis=0,inplace=True,how="any")

    # 提取目标值
    target = data["Class"]

    # 提取特征值
    data = data.drop(["Sample code number"],axis=1).iloc[:,:-1]

    # 切割训练集和测试集
    x_train,x_test,y_train,y_test = train_test_split(data,target,test_size=0.3)

    # 进行标准化
    std = StandardScaler()
    x_train = std.fit_transform(x_train)
    x_test = std.fit_transform(x_test)

    # 逻辑回归进行训练和
    lr = LogisticRegression()
    lr.fit(x_train,y_train)

    # 得到训练集返回数据
    # print("逻辑回归权重：",lr.coef_)
    # print("逻辑回归偏置：",lr.intercept_)

    # 保存训练模型
    joblib.dump(lr, "test.pkl")

if __name__ == '__main__':
    logisticregression()

2，加载模型

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report,roc_auc_score
from sklearn.externals import joblib

def logisticregression():
    '''逻辑回归癌症预测'''
    # 确定数据columns数值
    columns = ["Sample code number","Clump Thickness","Uniformity of Cell Size","Uniformity of Cell Shape","Marginal Adhesion","Single Epithelial Cell Size","Bare Nuclei","Bland Chromatin","Normal Nucleoli","Mitoses","Class"]
    data = pd.read_csv("breast-cancer-wisconsin.data",names=columns)

    # 去掉缺失值
    data.replace(to_replace="?",value=np.nan,inplace=True)
    data.dropna(axis=0,inplace=True,how="any")

    # 提取目标值
    target = data["Class"]

    # 提取特征值
    data = data.drop(["Sample code number"],axis=1).iloc[:,:-1]

    # 切割训练集和测试集
    x_train,x_test,y_train,y_test = train_test_split(data,target,test_size=0.3)

    # 进行标准化
    std = StandardScaler()
    x_train = std.fit_transform(x_train)
    x_test = std.fit_transform(x_test)

    lr = joblib.load("test.pkl")

    # 逻辑回归测试集预测结果
    pre_result = lr.predict(x_test)
    # print(pre_result)

    # 逻辑回归预测准确率
    sore = lr.score(x_test,y_test)
    print(sore)

    # 精确率(Precision)与召回率(Recall)
    report = classification_report(y_test,pre_result,target_names=["良性","恶性"])
    print(report)

    # 查看AUC指标
    y_test = np.where(y_test>2.5,1,0)
    print(y_test)
    auc_score = roc_auc_score(y_test,pre_result)
    print(auc_score)

if __name__ == '__main__':
    logisticregression()