sklearn-LR_prov.py 文件源码

def regression(filename):
    from sklearn.cross_validation import train_test_split
    print(filename)
    X,y = loadDataSet(filename)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1)
    from sklearn.linear_model import LinearRegression
    from sklearn import metrics
    linreg = LinearRegression()
    linreg.fit(X_train, y_train)

#    print(linreg.intercept_, linreg.coef_)
    # pair the feature names with the coefficients
    feature_cols = ['????', '????', '??????','?????','??????','???????','???????','?????????','??????']
    #print(feature_cols, linreg.coef_)
    #zip(feature_cols, linreg.coef_)
    y_pred = linreg.predict(X_test)

    print("MAE:",metrics.mean_absolute_error(y_test, y_pred))
    print("MSE:",metrics.mean_squared_error(y_test, y_pred))
    print('RMSE:',np.sqrt(metrics.mean_squared_error(y_test, y_pred)))
    scores = cross_val_score(linreg, X, y,cv=5)
#    print(filename)
    print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))

    res = pd.DataFrame(linreg.coef_,columns=feature_cols,index=[filename])
    return (res)

#files = ['?????3?.xlsx','?????4?.xlsx','?????5?.xlsx','?????6?.xlsx']