lasso.py 文件源码

def regression(filename):
    from sklearn.linear_model import LinearRegression
    from sklearn import metrics

    X,y = loadDataSet(filename)
    print(filename,X.shape)
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1, test_size=0.25)
    linreg = LinearRegression()
    linreg.fit(X_train, y_train)

#    print(linreg.intercept_, linreg.coef_)
    # pair the feature names with the coefficients
    feature_cols = ['????', '????', '??????','?????','??????','???????','???????','?????????','??????']
#    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=3)
    print('scores:',scores)  
    print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))

    res = pd.DataFrame(linreg.coef_.T[:len(feature_cols)].T,columns=feature_cols,index=[filename.split('.')[0]])
#    res = pd.DataFrame(linreg.coef_,index=[filename.split('.')[0]])
    return (res)

#files = ['201603.xlsx','201604.xlsx','201605.xlsx','?????3?.xlsx','?????4?.xlsx','?????5?.xlsx','?????6?.xlsx']
#files = ['?????3?.xlsx','?????4?.xlsx','?????5?.xlsx','?????6?.xlsx','201703_06.xlsx']
#files = ['201703_06.xlsx']