机器学习基础100天---day03 多元线性回归

刺骨的言语ヽ痛彻心扉 2022-05-12 04:16 145阅读 0赞

> R&D Spend,Administration,Marketing Spend,State,Profit  
> 165349.2,136897.8,471784.1,New York,192261.83  
> 162597.7,151377.59,443898.53,California,191792.06  
> 153441.51,101145.55,407934.54,Florida,191050.39  
> 144372.41,118671.85,383199.62,New York,182901.99  
> 142107.34,91391.77,366168.42,Florida,166187.94  
> 131876.9,99814.71,362861.36,New York,156991.12  
> 134615.46,147198.87,127716.82,California,156122.51  
> 130298.13,145530.06,323876.68,Florida,155752.6  
> 120542.52,148718.95,311613.29,New York,152211.77  
> 123334.88,108679.17,304981.62,California,149759.96  
> 101913.08,110594.11,229160.95,Florida,146121.95  
> 100671.96,91790.61,249744.55,California,144259.4  
> 93863.75,127320.38,249839.44,Florida,141585.52  
> 91992.39,135495.07,252664.93,California,134307.35  
> 119943.24,156547.42,256512.92,Florida,132602.65  
> 114523.61,122616.84,261776.23,New York,129917.04  
> 78013.11,121597.55,264346.06,California,126992.93  
> 94657.16,145077.58,282574.31,New York,125370.37  
> 91749.16,114175.79,294919.57,Florida,124266.9  
> 86419.7,153514.11,0,New York,122776.86  
> 76253.86,113867.3,298664.47,California,118474.03  
> 78389.47,153773.43,299737.29,New York,111313.02  
> 73994.56,122782.75,303319.26,Florida,110352.25  
> 67532.53,105751.03,304768.73,Florida,108733.99  
> 77044.01,99281.34,140574.81,New York,108552.04

#_*_coding:utf-8_*_
    
    import pandas as pd
    import numpy as np
    
    dataset = pd.read_csv('../data/50_Startups.csv')
    
    X = dataset.iloc[ : , :-1].values
    Y = dataset.iloc[ : , 4].values
    #抽取类别数据，转换成虚拟变量
    city = dataset.iloc[ : , 3].values
    from sklearn.preprocessing import LabelEncoder,OneHotEncoder
    labelencoder = LabelEncoder()
    X[: , 3] = labelencoder.fit_transform(X[ : , 3])
    onehotencoder = OneHotEncoder(categorical_features = [3])
    X = onehotencoder.fit_transform(X).toarray()
    
    #躲避虚拟变量陷阱       排除多个变量之间相互关联
    
    X = X[:,1:]
    
    from sklearn.model_selection import train_test_split
    
    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size= 0.25 ,random_state=0)
    
    from sklearn.linear_model import LinearRegression
    
    model = LinearRegression()
    model.fit(X_train,Y_train)
    
    y_pred = model.predict(X_test)
    print(y_pred)
    print('train score: {}'.format(model.score(X_train,Y_train)))
    print('test score: {}'.format(model.score(X_test,Y_test)))

[更多请参考大神GitHub][GitHub]

[GitHub]: https://github.com/MLEveryday/100-Days-Of-ML-Code