regression_modeling.py 文件源码

def basic_linear(wine_set):
    scat0 = seaborn.regplot(x="volatile_acidity", y="quality", fit_reg=True, data=wine_set)
    plt.xlabel("Amount of volatile acidity in wine")
    plt.ylabel("Quality level of wine (0-10 scale)")
    plt.title("Association between the amount of volatile acidity in wine and the quality of wine")
    plt.show()

    # ----------- centering the explanatory variable by subrtacting the mean
    f_acidity_mean = wine_set["volatile_acidity"].mean()
    print("mean of the volatile acidity variable = ", f_acidity_mean)
    wine_set["volatile_acidity"] = wine_set["volatile_acidity"] - f_acidity_mean
    print("mean of the volatile acidity variable after normalization = ", wine_set["volatile_acidity"].mean())

    print ("\nOLS regression model for the association between the amount of volatile acidity in wine and the quality of wine:")
    model1 = smf.ols(formula="quality ~ volatile_acidity", data=wine_set)
    results1 = model1.fit()
    print(results1.summary())


# call(basic_linear)


# #___________________________________ Multiple Regression___________________________________________