【072】模型的使用和保存

最新推荐文章于 2021-12-02 10:31:32 发布

小麦粒

最新推荐文章于 2021-12-02 10:31:32 发布

阅读量525

点赞数

本文链接：https://blog.csdn.net/u010986753/article/details/105926551

版权

本文介绍了Python中岭回归和线性回归的建模过程，并详细讲解了如何在实际应用中使用和保存模型。作者小婷儿专注于数据分析、数据挖掘和机器学习技术，分享了学习笔记和相关资源。

摘要由CSDN通过智能技术生成

内容目录

一、岭回归建模二、线性回归建模三、模型使用joblib原文见公众号：python宝

一、岭回归

from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Ridge
from sklearn.metrics import mean_squared_error
from sklearn.externals import joblib


def linear3():

    #岭回归对波士顿房价进行预测
    #1、加载数据
    boston = load_boston()
    print("特征数量：\n", boston.data.shape)

    #2 、划分数据集
    x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)

    # 3、标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)

    # 4、预估器
    estimator = Ridge(alpha=0.5, max_iter=10000)
    estimator.fit(x_train, y_train)

    # 保存模型
    joblib.dump(estimator, ".\my_ridge.pkl")
    # 加载模型
    # estimator = joblib.load("my_ridge.pkl")

    # 5、得出模型
    print("岭回归-权重系数为：\n", estimator.coef_)
    print("岭回归-偏置为：\n", estimator.intercept_)

    # 6、模型评估
    y_predict = estimator.predict(x_test)
    print("预测房价：\n", y_predict)
    error = mean_squared_error(y_test, y_predict)
    print("岭回归-均方误差为：\n", error)

    return None


if __name__ == "__main__":
    linear3()

特征数量：
 (506, 13)
岭回归-权重系数为：
 [-0.64193209  1.13369189 -0.07675643  0.74427624 -1.93681163  2.71424838
 -0.08171268 -3.27871121  2.45697934 -1.81200596 -1.74659067  0.87272606
 -3.90544403]
岭回归-偏置为：
 22.62137203166228
预测房价：
 [28.22536271 31.50554479 21.13191715 32.65799504 20.02127243 19.07245621
 21.10832868 19.61646071 19.63294981 32.85629282 20.99521805 27.5039205
 15.55295503 19.79534148 36.87534254 18.80312973  9.39151837 18.50769876
 30.66823994 24.3042416  19.08011554 34.10075629 29.79356171 17.51074566
 34.89376386 26.53739131 34.68266415 27.42811508 19.08866098 14.98888119
 30.85920064 15.82430706 37.18223651  7.77072879 16.25978968 17.17327251
  7.44393003 19.99708381 40.57013125 28.94670553 25.25487557 17.75476957
 38.77349313  6.87948646 21.78603146 25.27475292 20.4507104  20.47911411
 17.25121804 26.12109499  8.54773286 27.48936704 30.58050833 16.56570322
  9.40627771 35.52573005 32.2505845  21.8734037  17.61137983 22.08222631
 23.49713296 24.09419259 20.15174912 38.49803353 24.63926151 19.77214318
 13.95001219  6.7578343  42.03931243 21.92262496 16.89673286 22.59476215
 40.75560357 21.42352637 36.88420001 27.18201696 21.03801678 20.39349944
 25.35646095 22.27374662 31.142768   20.39361408 23.99587493 31.54490413
 26.76213545 20.8977756  29.0705695  21.99584672 26.30581808 20.10938421
 25.47834262 24.08620166 19.90788343 16.41215513 15.26575844 18.40106165
 24.82285704 16.61995784 20.87907604 26.70640134 20.75218143 17.88976552
 24.27287641 23.36686439 21.57861455 36.78815164 15.88447635 21.47747831
 32.80013402 33.71367379 20.61690009 26.83175792 22.69265611 17.38149366
 21.67395385 21.67101719 27.6669245  25.06785897 23.73251233 14.65355067
 15.19441045  3.81755887 29.1743764  20.68219692 22.33163756 28.01411044
 28.55668351]
岭回归-均方误差为：
 20.64177160618091

二、线性回归

from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Ridge,LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.externals import joblib
from sklearn.metrics import confusion_matrix,roc_curve, auc, recall_score, classification_report


def linear3():

    #岭回归对波士顿房价进行预测
    #1、加载数据
    boston = load_boston()
    print("特征数量：\n", boston.data.shape)

    #2 、划分数据集
    x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)

    # 3、标准化
    transfer = StandardScaler()
    x_train = transfer.fit_transform(x_train)
    x_test = transfer.transform(x_test)

    # 4、预估器
    estimator = LinearRegression()
    estimator.fit(x_train, y_train)

    # 保存模型
    joblib.dump(estimator, ".\my_Line.pkl")
    # 加载模型
    # estimator = joblib.load("my_Line.pkl")

    # 5、模型评估
    y_predict = estimator.predict(x_test)
    # 训练集的混淆矩阵
    error = mean_squared_error(y_test, y_predict)
    print("线性-均方误差为：\n", error)

    return None


if __name__ == "__main__":
    linear3()

特征数量：
 (506, 13)
线性-均方误差为：
 20.6275137630954

三、模型使用

from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Ridge,LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.externals import joblib
import numpy as np

np.set_printoptions(suppress=True)

boston = load_boston()

x_train, x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=22)
type(x_test[1])
type(x_test)
# 加载模型
estimator = joblib.load(".\my_Line.pkl")
transfer = StandardScaler()
a = np.array([[6.6420e-02, 0.0000e+00, 4.0500e+00, 0.0000e+00, 5.1000e-01,
       6.8600e+00, 7.4400e+01, 2.9153e+00, 5.0000e+00, 2.9600e+02,
       1.6600e+01, 3.9127e+02, 6.9200e+00]])
a = transfer.fit_transform(a)
pre1 = estimator.predict(a)
true1 = y_test[1]
print(pre1,true1)