How to use the emcee.autocorr function in emcee

def get_autocorr_time(self, window=50):
        """
        Compute an estimate of the autocorrelation time for each parameter
        (length: ``dim``).

        :param window: (optional)
            The size of the windowing function. This is equivalent to the
            maximum number of lags to use. (default: 50)

        """
        return autocorr.integrated_time(self.chain, axis=0, window=window)

def get_autocorr_time(self, window=50):
        """
        Compute an estimate of the autocorrelation time for each parameter
        (length: ``dim``).

        :param window: (optional)
            The size of the windowing function. This is equivalent to the
            maximum number of lags to use. (default: 50)

        """
        return autocorr.integrated_time(self.chain, axis=0, window=window)

f'+{ang_percen[2]-ang_percen[1]:.2f})')

        print(f'Contrast (mag) = {mag_percen[1]:.2f} '
              f'(-{mag_percen[1]-mag_percen[0]:.2f} '
              f'+{mag_percen[2]-mag_percen[1]:.2f})')

        history = f'walkers = {self.m_nwalkers}, steps = {self.m_nsteps}'
        self.m_chain_out_port.copy_attributes(self.m_image_in_port)
        self.m_chain_out_port.add_history('MCMCsamplingModule', history)

        mean_accept = np.mean(sampler.acceptance_fraction)
        print(f'Mean acceptance fraction: {mean_accept:.3f}')
        self.m_chain_out_port.add_attribute('ACCEPTANCE', mean_accept, static=True)

        try:
            autocorr = emcee.autocorr.integrated_time(sampler.get_chain())
            print(f'Integrated autocorrelation time = {autocorr}')

        except emcee.autocorr.AutocorrError:
            autocorr = [np.nan, np.nan, np.nan]
            print('The chain is too short to reliably estimate the autocorrelation time. [WARNING]')

        self.m_chain_out_port.add_attribute('AUTOCORR_0', autocorr[0], static=True)
        self.m_chain_out_port.add_attribute('AUTOCORR_1', autocorr[1], static=True)
        self.m_chain_out_port.add_attribute('AUTOCORR_2', autocorr[2], static=True)

        self.m_chain_out_port.close_port()

f'(-{mag_percen[1]-mag_percen[0]:.2f} '
              f'+{mag_percen[2]-mag_percen[1]:.2f})')

        history = f'walkers = {self.m_nwalkers}, steps = {self.m_nsteps}'
        self.m_chain_out_port.copy_attributes(self.m_image_in_port)
        self.m_chain_out_port.add_history('MCMCsamplingModule', history)

        mean_accept = np.mean(sampler.acceptance_fraction)
        print(f'Mean acceptance fraction: {mean_accept:.3f}')
        self.m_chain_out_port.add_attribute('ACCEPTANCE', mean_accept, static=True)

        try:
            autocorr = emcee.autocorr.integrated_time(sampler.get_chain())
            print(f'Integrated autocorrelation time = {autocorr}')

        except emcee.autocorr.AutocorrError:
            autocorr = [np.nan, np.nan, np.nan]
            print('The chain is too short to reliably estimate the autocorrelation time. [WARNING]')

        self.m_chain_out_port.add_attribute('AUTOCORR_0', autocorr[0], static=True)
        self.m_chain_out_port.add_attribute('AUTOCORR_1', autocorr[1], static=True)
        self.m_chain_out_port.add_attribute('AUTOCORR_2', autocorr[2], static=True)

        self.m_chain_out_port.close_port()

def check_convergence(samples):
    tau = emcee.autocorr.integrated_time(samples, tol=0)
    num = samples.shape[0] * samples.shape[1]
    converged = np.all(tau * target_n_eff < num)
    converged &= np.all(len(samples) > 50 * tau)
    return converged, num / tau

def _interpret_thin(self, thin):
        if thin == 'acor':
            try:
                thin = self.autocorrelation
            except emcee.autocorr.AutocorrError:
                # we seem to need to change the warning filter here, we have
                # warnings as errors set elsewhere in the tests but somehow we
                # can't set it back in a test specifically, I think because the
                # warning -> error inside an except clause causes more
                # problems. So for now just manually set the warnings filter
                # here. would probably be good to do something better here
                # eventually -tgd 2016-09-16
                with warnings.catch_warnings():
                    warnings.simplefilter("always")
                    warnings.warn("Chain is too short for autocorrelation thinning, using whole chain")
                thin = 1
        elif thin is None:
            thin = 1
        if thin < 1:
            thin = 1
        else:

# Equation 24: varhat+(z) in Ford 2006
    varz = (nsteps-1.0)/bz + varianceofmeans

    # Equation 25: Rhat(z) in Ford 2006
    gelmanrubin = np.sqrt(varEstimate/withinChainVariances)

    # Equation 26: T(z) in Ford 2006
    vbz = varEstimate / bz
    tz = nchains*nsteps*vbz[vbz < 1]
    if tz.size == 0:
        tz = [-1]

    chains = np.dstack(chains)
    chains = np.swapaxes(chains, 0, 2)

    autocorrelation = emcee.autocorr.integrated_time(chains, tol = 0)

    afactor = np.divide(chains.shape[0], autocorrelation)

    archange = np.divide(np.abs(np.subtract(autocorrelation, oldautocorrelation)), oldautocorrelation)

    # well-mixed criteria
    ismixed = min(tz) > minTz and max(gelmanrubin) < maxGR and \
              np.amin(afactor) > minAfactor and np.amax(archange) < maxArchange

    return (ismixed, afactor, archange, autocorrelation, gelmanrubin, tz)