regression_modeling.py 文件源码

def mult_regression(wine_set):
    # center quantitative IVs for regression analysis
    w = wine_set['quality']
    wine_set = wine_set - wine_set.mean()
    wine_set['quality'] = w

    print ("OLS multivariate regression model")
    # first i have run with all columns; than chose the most significant for each wine set and rerun:

    if len(wine_set) < 2000:
        # for red
        model1 = smf.ols(
            formula="quality ~ volatile_acidity + chlorides + pH + sulphates + alcohol",
            data=wine_set)
    else:
        # for white
        model1 = smf.ols(
            formula="quality ~ volatile_acidity + density + pH + sulphates + alcohol",
            data=wine_set)

    results1 = model1.fit()
    print(results1.summary())

    # q-q plot for normality
    qq = sm.qqplot(results1.resid, line = 'r')
    plt.show()

    # plot of residuals
    stdres = pd.DataFrame(results1.resid_pearson)
    plt.plot(stdres, 'o', ls = 'None')
    l = plt.axhline(y=0, color = 'r')
    plt.ylabel('Standardized redisual')
    plt.xlabel('Observation number')
    plt.show()

    # # diagnostic plots
    # figure1 = plt.figure(figsize=(12, 8))
    # figure1 = sm.graphics.plot_regress_exog(results1, "alcohol", fig = figure1)
    # plt.show()
    #
    # figure1 = plt.figure(figsize=(12, 8))
    # figure1 = sm.graphics.plot_regress_exog(results1, "sulphates", fig = figure1)
    # plt.show()

    # leverage plot
    figure1 = sm.graphics.influence_plot(results1, size=8)
    plt.show()

# call(mult_regression)


# ____________________________ Logistic Regression _____________________