main.py 文件源码

def testModelFit(arma_mod30, dta):
    # does our model fit the theory?
    residuals = arma_mod30.resid
    sm.stats.durbin_watson(residuals.values)
    # NOTE: Durbin Watson Test Statistic approximately equal to 2*(1-r)
    #       where r is the sample autocorrelation of the residuals.
    #       Thus, for r == 0, indicating no serial correlation,
    #       the test statistic equals 2. This statistic will always be
    #       between 0 and 4. The closer to 0 the statistic, the more evidence
    #       for positive serial correlation. The closer to 4, the more evidence
    #       for negative serial correlation.

    # plot the residuals so we can see if there are any areas in time which
    # are poorly explained.
    fig = plt.figure(figsize=(12,8))
    ax = fig.add_subplot(111)
    ax = arma_mod30.resid.plot(ax=ax);

    plt.savefig(FIG_DIR+'residualsVsTime.png', bbox_inches='tight')
#    plt.show()

    # tests if samples are different from normal dist.
    k2, p = stats.normaltest(residuals)
    print ("residuals skew (k2):" + str(k2) +
           " fit w/ normal dist (p-value): " + str(p))

    # plot residuals
    fig = plt.figure(figsize=(12,8))
    ax = fig.add_subplot(211)
    fig = qqplot(residuals, line='q', ax=ax, fit=True)

    ax2 = fig.add_subplot(212)
    # resid_dev = residuals.resid_deviance.copy()
    # resid_std = (resid_dev - resid_dev.mean()) / resid_dev.std()
    plt.hist(residuals, bins=25);
    plt.title('Histogram of standardized deviance residuals');
    plt.savefig(FIG_DIR+'residualsNormality.png', bbox_inches='tight')

    # plot ACF/PACF for residuals
    plotACFAndPACF(residuals, 'residualsACFAndPACF.png')

    r,q,p = sm.tsa.acf(residuals.values.squeeze(), qstat=True)
    data = np.c_[range(1,41), r[1:], q, p]
    table = pandas.DataFrame(data, columns=['lag', "AC", "Q", "Prob(>Q)"])
    print(table.set_index('lag'))

    # sameple data indicates a lack of fit.