Python statsmodels.api 模块，qqplot() 实例源码

def tsplot(y, lags=None, figsize=(10, 8), style='bmh'):
    if not isinstance(y, pd.Series):
        y = pd.Series(y)
    with plt.style.context(style):
        fig = plt.figure(figsize=figsize)
        # mpl.rcParams['font.family'] = 'Ubuntu Mono'
        layout = (3, 2)
        ts_ax = plt.subplot2grid(layout, (0, 0), colspan=2)
        acf_ax = plt.subplot2grid(layout, (1, 0))
        pacf_ax = plt.subplot2grid(layout, (1, 1))
        qq_ax = plt.subplot2grid(layout, (2, 0))
        pp_ax = plt.subplot2grid(layout, (2, 1))

        y.plot(ax=ts_ax)
        ts_ax.set_title('Time Series Analysis Plots')
        smt.graphics.plot_acf(y, lags=lags, ax=acf_ax, alpha=0.5)
        smt.graphics.plot_pacf(y, lags=lags, ax=pacf_ax, alpha=0.5)
        sm.qqplot(y, line='s', ax=qq_ax)
        qq_ax.set_title('QQ Plot')
        scs.probplot(y, sparams=(y.mean(), y.std()), plot=pp_ax)

        plt.tight_layout()
    return

def plot_resid(model, x):
    '''
        Given a trained StatsModel linear regression model, plot the residual error
        in a scatter plot as well as a qqplot

        model: a trained StatsModel linear regression model.
        x: the input data which was used to train the model.

        returns: the figure upon which the residuals were drawn
    '''
    fig, ax_list = plt.subplots(1, 2)

    y_hat = model.predict(x)
    resid = model.outlier_test()['student_resid']

    ax_list[0].scatter(y_hat, resid, alpha=.2)
    ax_list[0].axhline(0, linestyle='--')
    sm.qqplot(resid, line='s', ax=ax_list[1])

    fig.tight_layout()
    return fig

def cross_section_qqplot(data, factor_name, date):
    '''
    ??
    --------------------------------
    data:DataFrame(index:[Date,IDs],factor1,factor2,...)
    factor_name:str
    date?str
    '''
    ax = plt.gca()
    plot_data = data.ix[(date,), factor_name].values
    fig = sm.qqplot(plot_data, line='45', fit=True,ax=ax)
    plt.show()

    return ax

# ??4
# ic ???

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 _____________________