Пример #1
0
def store_results(dm, area, sex, year):
    types_to_plot = 'p i r rr'.split()

    graphics.plot_convergence_diag(dm.vars)
    pl.clf()
    for i, t in enumerate(types_to_plot):
        pl.subplot(len(types_to_plot), 1, i + 1)
        graphics.plot_data_bars(dm.model.get_data(t))
        pl.plot(range(101),
                dm.emp_priors[t, 'mu'],
                linestyle='dashed',
                color='grey',
                label='Emp. Prior',
                linewidth=3)
        pl.plot(range(101), dm.true[t], 'b-', label='Truth', linewidth=3)
        pl.plot(range(101),
                dm.posteriors[t].mean(0),
                'r-',
                label='Estimate',
                linewidth=3)

        pl.errorbar(range(101),
                    dm.posteriors[t].mean(0),
                    yerr=1.96 * dm.posteriors[t].std(0),
                    fmt='r-',
                    linewidth=1,
                    capsize=0)

        pl.ylabel(t)
        graphics.expand_axis()

    pl.legend(loc=(0., -.95), fancybox=True, shadow=True)
    pl.subplots_adjust(hspace=0, left=.1, right=.95, bottom=.2, top=.95)
    pl.xlabel('Age (Years)')
    pl.show()

    model = dm
    model.mu = pandas.DataFrame()
    for t in types_to_plot:
        model.mu = model.mu.append(pandas.DataFrame(
            dict(true=dm.true[t],
                 mu_pred=dm.posteriors[t].mean(0),
                 sigma_pred=dm.posteriors[t].std(0))),
                                   ignore_index=True)
    data_simulation.add_quality_metrics(model.mu)
    print '\nparam prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
        model.mu['abs_err'].mean(),
        pl.median(pl.absolute(
            model.mu['rel_err'].dropna())), model.mu['covered?'].mean())
    print

    data_simulation.initialize_results(model)
    data_simulation.add_to_results(model, 'mu')
    data_simulation.finalize_results(model)

    print model.results

    return model
Пример #2
0
def validate_prior_similarity():
    #dm = dismod3.load_disease_model(20945)
    #dm.model = data.ModelData.from_gbd_jsons(json.loads(dm.to_json()))
    #t = 'i'
    #area, sex, year = 'europe_eastern', 'male', 2005

    dm = dismod3.load_disease_model(20928)
    dm.model = data.ModelData.from_gbd_jsons(json.loads(dm.to_json()))
    t = 'p'
    area, sex, year = 'sub-saharan_africa_central', 'male', 2005

    # select data that is about areas in this region, recent years, and sex of male or total only
    model = dm.model
    subtree = nx.traversal.bfs_tree(model.hierarchy, area)
    relevant_rows = [i for i, r in model.input_data.T.iteritems() \
                         if (r['area'] in subtree or r['area'] == 'all')\
                         and ((year == 2005 and r['year_end'] >= 1997) or r['year_start'] <= 1997) \
                         and r['sex'] in [sex, 'total']]
    model.input_data = model.input_data.ix[relevant_rows]

    # replace area 'all' with area
    model.input_data['area'][model.input_data['area'] == 'all'] = area


    for het in 'Slightly Moderately Very'.split():
        dm.model.parameters[t]['parameter_age_mesh'] = [0, 15, 20, 25, 35, 45, 55, 65, 75, 100]
        dm.model.parameters[t]['heterogeneity'] = het
        setup_regional_model(dm, area, sex, year)

        dm.vars = {}
        dm.vars[t] = data_model.data_model(t, dm.model, t,
                                           root_area=area, root_sex=sex, root_year=year,
                                           mu_age=None,
                                           mu_age_parent=dm.emp_priors[t, 'mu'],
                                           sigma_age_parent=dm.emp_priors[t, 'sigma'],
                                           rate_type=(t == 'rr') and 'log_normal' or 'neg_binom')

        fit_model.fit_data_model(dm.vars[t], iter=10050, burn=5000, thin=50, tune_interval=100)

        #2graphics.plot_one_effects(dm.vars[t], t, dm.model.hierarchy)
        #pl.title(het)

        graphics.plot_convergence_diag(dm.vars[t])
        pl.title(het)

        #graphics.plot_one_ppc(dm.vars[t], t)
        #pl.title(het)

        graphics.plot_one_type(dm.model, dm.vars[t], dm.emp_priors, t)
        pl.title(het)

    pl.show()
    return dm
Пример #3
0
def store_results(dm, area, sex, year):
    types_to_plot = 'p i r rr'.split()

    graphics.plot_convergence_diag(dm.vars)
    pl.clf()
    for i, t in enumerate(types_to_plot):
        pl.subplot(len(types_to_plot), 1, i+1)
        graphics.plot_data_bars(dm.model.get_data(t))
        pl.plot(range(101), dm.emp_priors[t, 'mu'], linestyle='dashed', color='grey', label='Emp. Prior', linewidth=3)
        pl.plot(range(101), dm.true[t], 'b-', label='Truth', linewidth=3)
        pl.plot(range(101), dm.posteriors[t].mean(0), 'r-', label='Estimate', linewidth=3)

        pl.errorbar(range(101), dm.posteriors[t].mean(0), yerr=1.96*dm.posteriors[t].std(0), fmt='r-', linewidth=1, capsize=0)

        pl.ylabel(t)
        graphics.expand_axis()
    
    pl.legend(loc=(0.,-.95), fancybox=True, shadow=True)
    pl.subplots_adjust(hspace=0, left=.1, right=.95, bottom=.2, top=.95)
    pl.xlabel('Age (Years)')
    pl.show()

    model = dm
    model.mu = pandas.DataFrame()
    for t in types_to_plot:
        model.mu = model.mu.append(pandas.DataFrame(dict(true=dm.true[t],
                                                         mu_pred=dm.posteriors[t].mean(0),
                                                         sigma_pred=dm.posteriors[t].std(0))),
                                   ignore_index=True)
    data_simulation.add_quality_metrics(model.mu)
    print '\nparam prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.mu['abs_err'].mean(),
                                                                         pl.median(pl.absolute(model.mu['rel_err'].dropna())),
                                                                         model.mu['covered?'].mean())
    print

    data_simulation.initialize_results(model)
    data_simulation.add_to_results(model, 'mu')
    data_simulation.finalize_results(model)

    print model.results

    return model
Пример #4
0
                predict_sex,
                predict_year,
                True,  # population weighted averages
                model.vars[t],
                lower,
                upper)
    try:
        graphics.plot_fit(model, vars, emp_priors, {})
        pl.savefig(dir + '/image/posterior-%s+%s+%s.png' %
                   (predict_area, predict_sex, predict_year))
    except Exception, e:
        print 'Error generating output graphics'
        print e

    try:
        graphics.plot_convergence_diag(vars)
        pl.savefig(dir + '/image/posterior-%s+%s+%s-convergence.png' %
                   (predict_area, predict_sex, predict_year))
    except Exception, e:
        print 'Error generating output graphics'
        print e

    dm.vars, dm.model, dm.emp_priors = model.vars, model, emp_priors
    for t in 'i r f p rr pf X m_with smr'.split():
        if t not in dm.vars:
            continue
        print 'saving tables for', t
        if 'data' in dm.vars[t] and 'p_pred' in dm.vars[t]:
            stats = dm.vars[t]['p_pred'].stats(batches=5)
            dm.vars[t]['data']['mu_pred'] = stats['mean']
            dm.vars[t]['data']['sigma_pred'] = stats['standard deviation']
Пример #5
0
def validate_prior_similarity():
    #dm = dismod3.load_disease_model(20945)
    #dm.model = data.ModelData.from_gbd_jsons(json.loads(dm.to_json()))
    #t = 'i'
    #area, sex, year = 'europe_eastern', 'male', 2005

    dm = dismod3.load_disease_model(20928)
    dm.model = data.ModelData.from_gbd_jsons(json.loads(dm.to_json()))
    t = 'p'
    area, sex, year = 'sub-saharan_africa_central', 'male', 2005

    # select data that is about areas in this region, recent years, and sex of male or total only
    model = dm.model
    subtree = nx.traversal.bfs_tree(model.hierarchy, area)
    relevant_rows = [i for i, r in model.input_data.T.iteritems() \
                         if (r['area'] in subtree or r['area'] == 'all')\
                         and ((year == 2005 and r['year_end'] >= 1997) or r['year_start'] <= 1997) \
                         and r['sex'] in [sex, 'total']]
    model.input_data = model.input_data.ix[relevant_rows]

    # replace area 'all' with area
    model.input_data['area'][model.input_data['area'] == 'all'] = area

    for het in 'Slightly Moderately Very'.split():
        dm.model.parameters[t]['parameter_age_mesh'] = [
            0, 15, 20, 25, 35, 45, 55, 65, 75, 100
        ]
        dm.model.parameters[t]['heterogeneity'] = het
        setup_regional_model(dm, area, sex, year)

        dm.vars = {}
        dm.vars[t] = data_model.data_model(
            t,
            dm.model,
            t,
            root_area=area,
            root_sex=sex,
            root_year=year,
            mu_age=None,
            mu_age_parent=dm.emp_priors[t, 'mu'],
            sigma_age_parent=dm.emp_priors[t, 'sigma'],
            rate_type=(t == 'rr') and 'log_normal' or 'neg_binom')

        fit_model.fit_data_model(dm.vars[t],
                                 iter=10050,
                                 burn=5000,
                                 thin=50,
                                 tune_interval=100)

        #2graphics.plot_one_effects(dm.vars[t], t, dm.model.hierarchy)
        #pl.title(het)

        graphics.plot_convergence_diag(dm.vars[t])
        pl.title(het)

        #graphics.plot_one_ppc(dm.vars[t], t)
        #pl.title(het)

        graphics.plot_one_type(dm.model, dm.vars[t], dm.emp_priors, t)
        pl.title(het)

    pl.show()
    return dm
Пример #6
0
def validate_age_pattern_model_sim(N=500, delta_true=.15, pi_true=quadratic):
    ## generate simulated data
    a = pl.arange(0, 101, 1)
    pi_age_true = pi_true(a)

    model = data_simulation.simple_model(N)
    model.parameters['p']['parameter_age_mesh'] = range(0, 101, 10)

    age_list = pl.array(mc.runiform(0, 100, size=N), dtype=int)
    p = pi_age_true[age_list]
    n = mc.runiform(100, 10000, size=N)

    model.input_data['age_start'] = age_list
    model.input_data['age_end'] = age_list
    model.input_data['effective_sample_size'] = n
    model.input_data['true'] = p
    model.input_data['value'] = mc.rnegative_binomial(n*p, delta_true*n*p) / n

    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p', 'all', 'total', 'all', None, None, None)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=10000, burn=5000, thin=25, tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)
    graphics.plot_one_type(model, model.vars['p'], {}, 'p')
    pl.plot(a, pi_age_true, 'r:', label='Truth')
    pl.legend(fancybox=True, shadow=True, loc='upper left')

    pl.show()

    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats()['standard deviation']
    data_simulation.add_quality_metrics(model.input_data)

    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    data_simulation.add_quality_metrics(model.delta)

    print 'delta'
    print model.delta

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.input_data['abs_err'].mean(),
                                                     pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
                                                                       model.input_data['covered?'].mean())

    model.mu = pandas.DataFrame(dict(true=pi_age_true,
                                     mu_pred=model.vars['p']['mu_age'].stats()['mean'],
                                     sigma_pred=model.vars['p']['mu_age'].stats()['standard deviation']))
    data_simulation.add_quality_metrics(model.mu)

    model.results = dict(param=[], bias=[], mare=[], mae=[], pc=[])
    data_simulation.add_to_results(model, 'delta')
    data_simulation.add_to_results(model, 'mu')
    data_simulation.add_to_results(model, 'input_data')
    model.results = pandas.DataFrame(model.results, columns='param bias mae mare pc'.split())

    print model.results

    return model
Пример #7
0
                upper=pl.inf
            posteriors[t] = covariate_model.predict_for(model,
                                                        model.parameters.get(t, {}),
                                                        predict_area, predict_sex, predict_year,
                                                        predict_area, predict_sex, predict_year,
                                                        True,  # population weighted averages
                                                        model.vars[t], lower, upper)
    try:
        graphics.plot_fit(model, vars, emp_priors, {})
        pl.savefig(dir + '/image/posterior-%s+%s+%s.png'%(predict_area, predict_sex, predict_year))
    except Exception, e:
        print 'Error generating output graphics'
        print e

    try:
        graphics.plot_convergence_diag(vars)
        pl.savefig(dir + '/image/posterior-%s+%s+%s-convergence.png'%(predict_area, predict_sex, predict_year))
    except Exception, e:
        print 'Error generating output graphics'
        print e

    dm.vars, dm.model, dm.emp_priors = model.vars, model, emp_priors
    for t in 'i r f p rr pf X m_with smr'.split():
        if t not in dm.vars:
            continue
        print 'saving tables for', t
        if 'data' in dm.vars[t] and 'p_pred' in dm.vars[t]:
            stats = dm.vars[t]['p_pred'].stats(batches=5)
            dm.vars[t]['data']['mu_pred'] = stats['mean']
            dm.vars[t]['data']['sigma_pred'] = stats['standard deviation']
Пример #8
0
def validate_covariate_model_fe(N=100,
                                delta_true=3,
                                pi_true=.01,
                                beta_true=[.5, -.5, 0.],
                                replicate=0):
    # set random seed for reproducibility
    mc.np.random.seed(1234567 + replicate)

    ## generate simulated data
    a = pl.arange(0, 100, 1)
    pi_age_true = pi_true * pl.ones_like(a)

    model = data.ModelData()
    model.parameters['p']['parameter_age_mesh'] = [0, 100]
    model.input_data = pandas.DataFrame(index=range(N))
    initialize_input_data(model.input_data)

    # add fixed effect to simulated data
    X = mc.rnormal(0., 1.**-2, size=(N, len(beta_true)))
    Y_true = pl.dot(X, beta_true)

    for i in range(len(beta_true)):
        model.input_data['x_%d' % i] = X[:, i]
    model.input_data['true'] = pi_true * pl.exp(Y_true)

    model.input_data['effective_sample_size'] = mc.runiform(100, 10000, N)

    n = model.input_data['effective_sample_size']
    p = model.input_data['true']
    model.input_data['value'] = mc.rnegative_binomial(n * p, delta_true) / n

    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p', 'all', 'total',
                                            'all', None, None, None)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'],
                                                     iter=10000,
                                                     burn=5000,
                                                     thin=5,
                                                     tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)

    pl.show()

    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats(
    )['standard deviation']
    add_quality_metrics(model.input_data)

    model.beta = pandas.DataFrame(index=model.vars['p']['X'].columns)
    model.beta['true'] = 0.
    for i in range(len(beta_true)):
        model.beta['true']['x_%d' % i] = beta_true[i]

    model.beta['mu_pred'] = [
        n.stats()['mean'] for n in model.vars['p']['beta']
    ]
    model.beta['sigma_pred'] = [
        n.stats()['standard deviation'] for n in model.vars['p']['beta']
    ]
    add_quality_metrics(model.beta)

    print '\nbeta'
    print model.beta

    model.results = dict(param=[], bias=[], mare=[], mae=[], pc=[])
    add_to_results(model, 'beta')

    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    add_quality_metrics(model.delta)

    print 'delta'
    print model.delta
    add_to_results(model, 'delta')

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
        model.input_data['abs_err'].mean(),
        pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
        model.input_data['covered?'].mean())
    print 'effect prediction MAE: %.3f, coverage: %.2f' % (
        pl.median(pl.absolute(model.beta['abs_err'].dropna())),
        model.beta.dropna()['covered?'].mean())
    add_to_results(model, 'input_data')
    add_to_results(model, 'beta')

    model.results = pandas.DataFrame(model.results)
    return model
Пример #9
0
def validate_covariate_model_dispersion(N=1000, delta_true=.15, pi_true=.01, zeta_true=[.5, -.5, 0.]):
    ## generate simulated data
    a = pl.arange(0, 100, 1)
    pi_age_true = pi_true * pl.ones_like(a)

    model = data.ModelData()
    model.parameters['p']['parameter_age_mesh'] = [0, 100]
    model.input_data = pandas.DataFrame(index=range(N))
    initialize_input_data(model.input_data)

    Z = mc.rbernoulli(.5, size=(N, len(zeta_true))) * 1.0
    delta = delta_true * pl.exp(pl.dot(Z, zeta_true))
    for i in range(len(zeta_true)):
        model.input_data['z_%d'%i] = Z[:,i]

    model.input_data['true'] = pi_true

    model.input_data['effective_sample_size'] = mc.runiform(100, 10000, N)

    n = model.input_data['effective_sample_size']
    p = model.input_data['true']
    model.input_data['value'] = mc.rnegative_binomial(n*p, delta*n*p) / n


    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p', 'all', 'total', 'all', None, None, None)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=10000, burn=5000, thin=5, tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)

    pl.show()


    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats()['standard deviation']
    add_quality_metrics(model.input_data)


    model.zeta = pandas.DataFrame(index=model.vars['p']['Z'].columns)
    model.zeta['true'] = zeta_true
    
    model.zeta['mu_pred'] = model.vars['p']['zeta'].stats()['mean']
    model.zeta['sigma_pred'] = model.vars['p']['zeta'].stats()['standard deviation']
    add_quality_metrics(model.zeta)

    print '\nzeta'
    print model.zeta
    
    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    add_quality_metrics(model.delta)

    print 'delta'
    print model.delta

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.input_data['abs_err'].mean(),
                                                     pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
                                                                       model.input_data['covered?'].mean())
    print 'effect prediction MAE: %.3f, coverage: %.2f' % (pl.median(pl.absolute(model.zeta['abs_err'].dropna())),
                                                           model.zeta.dropna()['covered?'].mean())


    model.results = dict(param=[], bias=[], mare=[], mae=[], pc=[])
    add_to_results(model, 'delta')
    add_to_results(model, 'input_data')
    add_to_results(model, 'zeta')
    model.results = pandas.DataFrame(model.results, columns='param bias mae mare pc'.split())

    return model
Пример #10
0
def validate_covariate_model_re(N=500,
                                delta_true=.15,
                                pi_true=.01,
                                sigma_true=[.1, .1, .1, .1, .1],
                                ess=1000):
    ## set simulation parameters
    import dismod3
    import simplejson as json
    model = data.ModelData.from_gbd_jsons(
        json.loads(dismod3.disease_json.DiseaseJson().to_json()))
    model.parameters['p']['parameter_age_mesh'] = [0, 100]
    model.parameters['p'][
        'heterogeneity'] = 'Slightly'  # ensure heterogeneity is slightly

    area_list = []
    for sr in sorted(model.hierarchy.successors('all')):
        area_list.append(sr)
        for r in sorted(model.hierarchy.successors(sr)):
            area_list.append(r)
            area_list += sorted(model.hierarchy.successors(r))[:5]
    area_list = pl.array(area_list)

    ## generate simulation data
    model.input_data = pandas.DataFrame(index=range(N))
    initialize_input_data(model.input_data)

    alpha = alpha_true_sim(model, area_list, sigma_true)

    # choose observed prevalence values
    model.input_data['effective_sample_size'] = ess

    model.input_data['area'] = area_list[mc.rcategorical(
        pl.ones(len(area_list)) / float(len(area_list)), N)]

    model.input_data['true'] = pl.nan
    for i, a in model.input_data['area'].iteritems():
        model.input_data['true'][i] = pi_true * pl.exp(
            pl.sum([
                alpha[n] for n in nx.shortest_path(model.hierarchy, 'all', a)
                if n in alpha
            ]))

    n = model.input_data['effective_sample_size']
    p = model.input_data['true']
    model.input_data['value'] = mc.rnegative_binomial(n * p,
                                                      delta_true * n * p) / n

    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p', 'all', 'total',
                                            'all', None, None, None)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'],
                                                     iter=20000,
                                                     burn=10000,
                                                     thin=10,
                                                     tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)

    pl.show()

    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats(
    )['standard deviation']
    add_quality_metrics(model.input_data)

    model.alpha = pandas.DataFrame(
        index=[n for n in nx.traversal.dfs_preorder_nodes(model.hierarchy)])
    model.alpha['true'] = pandas.Series(dict(alpha))
    model.alpha['mu_pred'] = pandas.Series(
        [n.stats()['mean'] for n in model.vars['p']['alpha']],
        index=model.vars['p']['U'].columns)
    model.alpha['sigma_pred'] = pandas.Series(
        [n.stats()['standard deviation'] for n in model.vars['p']['alpha']],
        index=model.vars['p']['U'].columns)
    add_quality_metrics(model.alpha)

    print '\nalpha'
    print model.alpha.dropna()

    model.sigma = pandas.DataFrame(dict(true=sigma_true))
    model.sigma['mu_pred'] = [
        n.stats()['mean'] for n in model.vars['p']['sigma_alpha']
    ]
    model.sigma['sigma_pred'] = [
        n.stats()['standard deviation'] for n in model.vars['p']['sigma_alpha']
    ]
    add_quality_metrics(model.sigma)

    print 'sigma_alpha'
    print model.sigma

    model.results = dict(param=[], bias=[], mare=[], mae=[], pc=[])
    add_to_results(model, 'sigma')

    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    add_quality_metrics(model.delta)

    print 'delta'
    print model.delta
    add_to_results(model, 'delta')

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
        model.input_data['abs_err'].mean(),
        pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
        model.input_data['covered?'].mean())
    print 'effect prediction MAE: %.3f, coverage: %.2f' % (
        pl.median(pl.absolute(model.alpha['abs_err'].dropna())),
        model.alpha.dropna()['covered?'].mean())
    add_to_results(model, 'input_data')
    add_to_results(model, 'alpha')

    model.results = pandas.DataFrame(model.results)
    return model
def validate_ai_re(N=500,
                   delta_true=.15,
                   sigma_true=[.1, .1, .1, .1, .1],
                   pi_true=quadratic,
                   smoothness='Moderately',
                   heterogeneity='Slightly'):
    ## generate simulated data
    a = pl.arange(0, 101, 1)
    pi_age_true = pi_true(a)

    import dismod3
    import simplejson as json
    model = data.ModelData.from_gbd_jsons(
        json.loads(dismod3.disease_json.DiseaseJson().to_json()))
    gbd_hierarchy = model.hierarchy

    model = data_simulation.simple_model(N)
    model.hierarchy = gbd_hierarchy

    model.parameters['p']['parameter_age_mesh'] = range(0, 101, 10)
    model.parameters['p']['smoothness'] = dict(amount=smoothness)
    model.parameters['p']['heterogeneity'] = heterogeneity

    age_start = pl.array(mc.runiform(0, 100, size=N), dtype=int)
    age_end = pl.array(mc.runiform(age_start, 100, size=N), dtype=int)

    age_weights = pl.ones_like(a)
    sum_pi_wt = pl.cumsum(pi_age_true * age_weights)
    sum_wt = pl.cumsum(age_weights * 1.)
    p = (sum_pi_wt[age_end] - sum_pi_wt[age_start]) / (sum_wt[age_end] -
                                                       sum_wt[age_start])

    # correct cases where age_start == age_end
    i = age_start == age_end
    if pl.any(i):
        p[i] = pi_age_true[age_start[i]]

    model.input_data['age_start'] = age_start
    model.input_data['age_end'] = age_end
    model.input_data['effective_sample_size'] = mc.runiform(100, 10000, size=N)

    from validate_covariates import alpha_true_sim
    area_list = pl.array([
        'all', 'super-region_3', 'north_africa_middle_east', 'EGY', 'KWT',
        'IRN', 'IRQ', 'JOR', 'SYR'
    ])
    alpha = alpha_true_sim(model, area_list, sigma_true)
    print alpha

    model.input_data['true'] = pl.nan

    model.input_data['area'] = area_list[mc.rcategorical(
        pl.ones(len(area_list)) / float(len(area_list)), N)]

    for i, a in model.input_data['area'].iteritems():
        model.input_data['true'][i] = p[i] * pl.exp(
            pl.sum([
                alpha[n] for n in nx.shortest_path(model.hierarchy, 'all', a)
                if n in alpha
            ]))
    p = model.input_data['true']

    n = model.input_data['effective_sample_size']
    model.input_data['value'] = mc.rnegative_binomial(n * p,
                                                      delta_true * n * p) / n

    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p',
                                            'north_africa_middle_east',
                                            'total', 'all', None, None, None)
    #model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=1005, burn=500, thin=5, tune_interval=100)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'],
                                                     iter=10000,
                                                     burn=5000,
                                                     thin=25,
                                                     tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)
    graphics.plot_one_type(model, model.vars['p'], {}, 'p')
    pl.plot(range(101), pi_age_true, 'r:', label='Truth')
    pl.legend(fancybox=True, shadow=True, loc='upper left')

    pl.show()

    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats(
    )['standard deviation']
    data_simulation.add_quality_metrics(model.input_data)

    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    data_simulation.add_quality_metrics(model.delta)

    model.alpha = pandas.DataFrame(
        index=[n for n in nx.traversal.dfs_preorder_nodes(model.hierarchy)])
    model.alpha['true'] = pandas.Series(dict(alpha))
    model.alpha['mu_pred'] = pandas.Series(
        [n.stats()['mean'] for n in model.vars['p']['alpha']],
        index=model.vars['p']['U'].columns)
    model.alpha['sigma_pred'] = pandas.Series(
        [n.stats()['standard deviation'] for n in model.vars['p']['alpha']],
        index=model.vars['p']['U'].columns)
    model.alpha = model.alpha.dropna()
    data_simulation.add_quality_metrics(model.alpha)

    model.sigma = pandas.DataFrame(dict(true=sigma_true))
    model.sigma['mu_pred'] = [
        n.stats()['mean'] for n in model.vars['p']['sigma_alpha']
    ]
    model.sigma['sigma_pred'] = [
        n.stats()['standard deviation'] for n in model.vars['p']['sigma_alpha']
    ]
    data_simulation.add_quality_metrics(model.sigma)

    print 'delta'
    print model.delta

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
        model.input_data['abs_err'].mean(),
        pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
        model.input_data['covered?'].mean())

    model.mu = pandas.DataFrame(
        dict(true=pi_age_true,
             mu_pred=model.vars['p']['mu_age'].stats()['mean'],
             sigma_pred=model.vars['p']['mu_age'].stats()
             ['standard deviation']))
    data_simulation.add_quality_metrics(model.mu)

    data_simulation.initialize_results(model)
    data_simulation.add_to_results(model, 'delta')
    data_simulation.add_to_results(model, 'mu')
    data_simulation.add_to_results(model, 'input_data')
    data_simulation.add_to_results(model, 'alpha')
    data_simulation.add_to_results(model, 'sigma')
    data_simulation.finalize_results(model)

    print model.results

    return model
Пример #12
0
def validate_consistent_re(N=500, delta_true=.15, sigma_true=[.1,.1,.1,.1,.1], 
                           true=dict(i=quadratic, f=constant, r=constant)):
    types = pl.array(['i', 'r', 'f', 'p'])

    ## generate simulated data
    model = data_simulation.simple_model(N)
    model.input_data['effective_sample_size'] = 1.
    model.input_data['value'] = 0.
    # coarse knot spacing for fast testing
    for t in types:
        model.parameters[t]['parameter_age_mesh'] = range(0, 101, 20)

    sim = consistent_model.consistent_model(model, 'all', 'total', 'all', {})
    for t in 'irf':
        for i, k_i in enumerate(sim[t]['knots']):
            sim[t]['gamma'][i].value = pl.log(true[t](k_i))

    age_start = pl.array(mc.runiform(0, 100, size=N), dtype=int)
    age_end = pl.array(mc.runiform(age_start, 100, size=N), dtype=int)

    data_type = types[mc.rcategorical(pl.ones(len(types), dtype=float) / float(len(types)), size=N)]


    a = pl.arange(101)
    age_weights = pl.ones_like(a)
    sum_wt = pl.cumsum(age_weights)

    p = pl.zeros(N)
    for t in types:
        mu_t = sim[t]['mu_age'].value
        sum_mu_wt = pl.cumsum(mu_t*age_weights)
    
        p_t = (sum_mu_wt[age_end] - sum_mu_wt[age_start]) / (sum_wt[age_end] - sum_wt[age_start])

        # correct cases where age_start == age_end
        i = age_start == age_end
        if pl.any(i):
            p_t[i] = mu_t[age_start[i]]

        # copy part into p
        p[data_type==t] = p_t[data_type==t]


    # add covariate shifts
    import dismod3
    import simplejson as json
    gbd_model = data.ModelData.from_gbd_jsons(json.loads(dismod3.disease_json.DiseaseJson().to_json()))
    model.hierarchy = gbd_model.hierarchy

    from validate_covariates import alpha_true_sim
    area_list = pl.array(['all', 'super-region_3', 'north_africa_middle_east', 'EGY', 'KWT', 'IRN', 'IRQ', 'JOR', 'SYR'])
    alpha = {}
    for t in types:
        alpha[t] = alpha_true_sim(model, area_list, sigma_true)
    print json.dumps(alpha, indent=2)

    model.input_data['area'] = area_list[mc.rcategorical(pl.ones(len(area_list)) / float(len(area_list)), N)]
    
    for i, a in model.input_data['area'].iteritems():
        t = data_type[i]
        p[i] = p[i] * pl.exp(pl.sum([alpha[t][n] for n in nx.shortest_path(model.hierarchy, 'all', a) if n in alpha]))

    n = mc.runiform(100, 10000, size=N)

    model.input_data['data_type'] = data_type
    model.input_data['age_start'] = age_start
    model.input_data['age_end'] = age_end
    model.input_data['effective_sample_size'] = n
    model.input_data['true'] = p
    model.input_data['value'] = mc.rnegative_binomial(n*p, delta_true) / n

    # coarse knot spacing for fast testing
    for t in types:
        model.parameters[t]['parameter_age_mesh'] = range(0, 101, 20)

    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars = consistent_model.consistent_model(model, 'all', 'total', 'all', {})
    #model.map, model.mcmc = fit_model.fit_consistent_model(model.vars, iter=101, burn=0, thin=1, tune_interval=100)
    model.map, model.mcmc = fit_model.fit_consistent_model(model.vars, iter=10000, burn=5000, thin=25, tune_interval=100)

    graphics.plot_convergence_diag(model.vars)

    graphics.plot_fit(model, model.vars, {}, {})
    for i, t in enumerate('i r f p rr pf'.split()):
        pl.subplot(2, 3, i+1)
        pl.plot(range(101), sim[t]['mu_age'].value, 'w-', label='Truth', linewidth=2)
        pl.plot(range(101), sim[t]['mu_age'].value, 'r-', label='Truth', linewidth=1)

    pl.show()

    model.input_data['mu_pred'] = 0.
    model.input_data['sigma_pred'] = 0.
    for t in types:
        model.input_data['mu_pred'][data_type==t] = model.vars[t]['p_pred'].stats()['mean']
        model.input_data['sigma_pred'][data_type==t] = model.vars[t]['p_pred'].stats()['standard deviation']
    data_simulation.add_quality_metrics(model.input_data)

    model.delta = pandas.DataFrame(dict(true=[delta_true for t in types if t != 'rr']))
    model.delta['mu_pred'] = [pl.exp(model.vars[t]['eta'].trace()).mean() for t in types if t != 'rr']
    model.delta['sigma_pred'] = [pl.exp(model.vars[t]['eta'].trace()).std() for t in types if t != 'rr']
    data_simulation.add_quality_metrics(model.delta)

    model.alpha = pandas.DataFrame()
    model.sigma = pandas.DataFrame()
    for t in types:
        alpha_t = pandas.DataFrame(index=[n for n in nx.traversal.dfs_preorder_nodes(model.hierarchy)])
        alpha_t['true'] = pandas.Series(dict(alpha[t]))
        alpha_t['mu_pred'] = pandas.Series([n.stats()['mean'] for n in model.vars[t]['alpha']], index=model.vars[t]['U'].columns)
        alpha_t['sigma_pred'] = pandas.Series([n.stats()['standard deviation'] for n in model.vars[t]['alpha']], index=model.vars[t]['U'].columns)
        alpha_t['type'] = t
        model.alpha = model.alpha.append(alpha_t.dropna(), ignore_index=True)

        sigma_t = pandas.DataFrame(dict(true=sigma_true))
        sigma_t['mu_pred'] = [n.stats()['mean'] for n in model.vars[t]['sigma_alpha']]
        sigma_t['sigma_pred'] = [n.stats()['standard deviation'] for n in model.vars[t]['sigma_alpha']]
        model.sigma = model.sigma.append(sigma_t.dropna(), ignore_index=True)

    data_simulation.add_quality_metrics(model.alpha)
    data_simulation.add_quality_metrics(model.sigma)


    print 'delta'
    print model.delta

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.input_data['abs_err'].mean(),
                                                     pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
                                                                       model.input_data['covered?'].mean())

    model.mu = pandas.DataFrame()
    for t in types:
        model.mu = model.mu.append(pandas.DataFrame(dict(true=sim[t]['mu_age'].value,
                                                         mu_pred=model.vars[t]['mu_age'].stats()['mean'],
                                                         sigma_pred=model.vars[t]['mu_age'].stats()['standard deviation'])),
                                   ignore_index=True)
    data_simulation.add_quality_metrics(model.mu)
    print '\nparam prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.mu['abs_err'].mean(),
                                                                         pl.median(pl.absolute(model.mu['rel_err'].dropna())),
                                                                         model.mu['covered?'].mean())
    print


    data_simulation.initialize_results(model)
    data_simulation.add_to_results(model, 'delta')
    data_simulation.add_to_results(model, 'mu')
    data_simulation.add_to_results(model, 'input_data')
    data_simulation.add_to_results(model, 'alpha')
    data_simulation.add_to_results(model, 'sigma')
    data_simulation.finalize_results(model)

    print model.results

    return model
Пример #13
0
def validate_consistent_model_sim(N=500,
                                  delta_true=.5,
                                  true=dict(i=quadratic,
                                            f=constant,
                                            r=constant)):
    types = pl.array(['i', 'r', 'f', 'p'])

    ## generate simulated data
    model = data_simulation.simple_model(N)
    model.input_data['effective_sample_size'] = 1.
    model.input_data['value'] = 0.

    for t in types:
        model.parameters[t]['parameter_age_mesh'] = range(0, 101, 20)

    sim = consistent_model.consistent_model(model, 'all', 'total', 'all', {})
    for t in 'irf':
        for i, k_i in enumerate(sim[t]['knots']):
            sim[t]['gamma'][i].value = pl.log(true[t](k_i))

    age_start = pl.array(mc.runiform(0, 100, size=N), dtype=int)
    age_end = pl.array(mc.runiform(age_start, 100, size=N), dtype=int)

    data_type = types[mc.rcategorical(pl.ones(len(types), dtype=float) /
                                      float(len(types)),
                                      size=N)]

    a = pl.arange(101)
    age_weights = pl.ones_like(a)
    sum_wt = pl.cumsum(age_weights)

    p = pl.zeros(N)
    for t in types:
        mu_t = sim[t]['mu_age'].value
        sum_mu_wt = pl.cumsum(mu_t * age_weights)

        p_t = (sum_mu_wt[age_end] - sum_mu_wt[age_start]) / (sum_wt[age_end] -
                                                             sum_wt[age_start])

        # correct cases where age_start == age_end
        i = age_start == age_end
        if pl.any(i):
            p_t[i] = mu_t[age_start[i]]

        # copy part into p
        p[data_type == t] = p_t[data_type == t]
    n = mc.runiform(100, 10000, size=N)

    model.input_data['data_type'] = data_type
    model.input_data['age_start'] = age_start
    model.input_data['age_end'] = age_end
    model.input_data['effective_sample_size'] = n
    model.input_data['true'] = p
    model.input_data['value'] = mc.rnegative_binomial(n * p,
                                                      delta_true * n * p) / n

    # coarse knot spacing for fast testing
    for t in types:
        model.parameters[t]['parameter_age_mesh'] = range(0, 101, 20)

    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars = consistent_model.consistent_model(model, 'all', 'total',
                                                   'all', {})
    model.map, model.mcmc = fit_model.fit_consistent_model(model.vars,
                                                           iter=10000,
                                                           burn=5000,
                                                           thin=25,
                                                           tune_interval=100)

    graphics.plot_convergence_diag(model.vars)

    graphics.plot_fit(model, model.vars, {}, {})
    for i, t in enumerate('i r f p rr pf'.split()):
        pl.subplot(2, 3, i + 1)
        pl.plot(a, sim[t]['mu_age'].value, 'w-', label='Truth', linewidth=2)
        pl.plot(a, sim[t]['mu_age'].value, 'r-', label='Truth', linewidth=1)

    #graphics.plot_one_type(model, model.vars['p'], {}, 'p')
    #pl.legend(fancybox=True, shadow=True, loc='upper left')

    pl.show()

    model.input_data['mu_pred'] = 0.
    model.input_data['sigma_pred'] = 0.
    for t in types:
        model.input_data['mu_pred'][
            data_type == t] = model.vars[t]['p_pred'].stats()['mean']
        model.input_data['sigma_pred'][data_type == t] = model.vars['p'][
            'p_pred'].stats()['standard deviation']
    data_simulation.add_quality_metrics(model.input_data)

    model.delta = pandas.DataFrame(
        dict(true=[delta_true for t in types if t != 'rr']))
    model.delta['mu_pred'] = [
        pl.exp(model.vars[t]['eta'].trace()).mean() for t in types if t != 'rr'
    ]
    model.delta['sigma_pred'] = [
        pl.exp(model.vars[t]['eta'].trace()).std() for t in types if t != 'rr'
    ]
    data_simulation.add_quality_metrics(model.delta)

    print 'delta'
    print model.delta

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
        model.input_data['abs_err'].mean(),
        pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
        model.input_data['covered?'].mean())

    model.mu = pandas.DataFrame()
    for t in types:
        model.mu = model.mu.append(pandas.DataFrame(
            dict(true=sim[t]['mu_age'].value,
                 mu_pred=model.vars[t]['mu_age'].stats()['mean'],
                 sigma_pred=model.vars[t]['mu_age'].stats()
                 ['standard deviation'])),
                                   ignore_index=True)
    data_simulation.add_quality_metrics(model.mu)
    print '\nparam prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
        model.mu['abs_err'].mean(),
        pl.median(pl.absolute(
            model.mu['rel_err'].dropna())), model.mu['covered?'].mean())
    print

    data_simulation.initialize_results(model)
    data_simulation.add_to_results(model, 'delta')
    data_simulation.add_to_results(model, 'mu')
    data_simulation.add_to_results(model, 'input_data')
    data_simulation.finalize_results(model)

    print model.results

    return model
Пример #14
0
def validate_covariate_model_fe(N=100, delta_true=3, pi_true=.01, beta_true=[.5, -.5, 0.], replicate=0):
    # set random seed for reproducibility
    mc.np.random.seed(1234567 + replicate)
    
    ## generate simulated data
    a = pl.arange(0, 100, 1)
    pi_age_true = pi_true * pl.ones_like(a)

    model = data.ModelData()
    model.parameters['p']['parameter_age_mesh'] = [0, 100]
    model.input_data = pandas.DataFrame(index=range(N))
    initialize_input_data(model.input_data)

    # add fixed effect to simulated data
    X = mc.rnormal(0., 1.**-2, size=(N,len(beta_true)))
    Y_true = pl.dot(X, beta_true)

    for i in range(len(beta_true)):
        model.input_data['x_%d'%i] = X[:,i]
    model.input_data['true'] = pi_true * pl.exp(Y_true)

    model.input_data['effective_sample_size'] = mc.runiform(100, 10000, N)

    n = model.input_data['effective_sample_size']
    p = model.input_data['true']
    model.input_data['value'] = mc.rnegative_binomial(n*p, delta_true) / n


    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p', 'all', 'total', 'all', None, None, None)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=10000, burn=5000, thin=5, tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)

    pl.show()

    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats()['standard deviation']
    add_quality_metrics(model.input_data)


    model.beta = pandas.DataFrame(index=model.vars['p']['X'].columns)
    model.beta['true'] = 0.
    for i in range(len(beta_true)):
        model.beta['true']['x_%d'%i] = beta_true[i]
    
    model.beta['mu_pred'] = [n.stats()['mean'] for n in model.vars['p']['beta']]
    model.beta['sigma_pred'] = [n.stats()['standard deviation'] for n in model.vars['p']['beta']]
    add_quality_metrics(model.beta)

    print '\nbeta'
    print model.beta
    
    model.results = dict(param=[], bias=[], mare=[], mae=[], pc=[])
    add_to_results(model, 'beta')

    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    add_quality_metrics(model.delta)

    print 'delta'
    print model.delta
    add_to_results(model, 'delta')

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.input_data['abs_err'].mean(),
                                                     pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
                                                                       model.input_data['covered?'].mean())
    print 'effect prediction MAE: %.3f, coverage: %.2f' % (pl.median(pl.absolute(model.beta['abs_err'].dropna())),
                                                           model.beta.dropna()['covered?'].mean())
    add_to_results(model, 'input_data')
    add_to_results(model, 'beta')

    model.results = pandas.DataFrame(model.results)
    return model
Пример #15
0
def validate_ai_re(N=500, delta_true=.15, sigma_true=[.1,.1,.1,.1,.1], pi_true=quadratic, smoothness='Moderately', heterogeneity='Slightly'):
    ## generate simulated data
    a = pl.arange(0, 101, 1)
    pi_age_true = pi_true(a)


    import dismod3
    import simplejson as json
    model = data.ModelData.from_gbd_jsons(json.loads(dismod3.disease_json.DiseaseJson().to_json()))
    gbd_hierarchy = model.hierarchy

    model = data_simulation.simple_model(N)
    model.hierarchy = gbd_hierarchy

    model.parameters['p']['parameter_age_mesh'] = range(0, 101, 10)
    model.parameters['p']['smoothness'] = dict(amount=smoothness)
    model.parameters['p']['heterogeneity'] = heterogeneity

    age_start = pl.array(mc.runiform(0, 100, size=N), dtype=int)
    age_end = pl.array(mc.runiform(age_start, 100, size=N), dtype=int)

    age_weights = pl.ones_like(a)
    sum_pi_wt = pl.cumsum(pi_age_true*age_weights)
    sum_wt = pl.cumsum(age_weights*1.)
    p = (sum_pi_wt[age_end] - sum_pi_wt[age_start]) / (sum_wt[age_end] - sum_wt[age_start])

    # correct cases where age_start == age_end
    i = age_start == age_end
    if pl.any(i):
        p[i] = pi_age_true[age_start[i]]

    model.input_data['age_start'] = age_start
    model.input_data['age_end'] = age_end
    model.input_data['effective_sample_size'] = mc.runiform(100, 10000, size=N)


    from validate_covariates import alpha_true_sim
    area_list = pl.array(['all', 'super-region_3', 'north_africa_middle_east', 'EGY', 'KWT', 'IRN', 'IRQ', 'JOR', 'SYR'])
    alpha = alpha_true_sim(model, area_list, sigma_true)
    print alpha

    model.input_data['true'] = pl.nan

    model.input_data['area'] = area_list[mc.rcategorical(pl.ones(len(area_list)) / float(len(area_list)), N)]
    
    for i, a in model.input_data['area'].iteritems():
        model.input_data['true'][i] = p[i] * pl.exp(pl.sum([alpha[n] for n in nx.shortest_path(model.hierarchy, 'all', a) if n in alpha]))
    p = model.input_data['true']

    n = model.input_data['effective_sample_size']
    model.input_data['value'] = mc.rnegative_binomial(n*p, delta_true*n*p) / n

    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p', 'north_africa_middle_east', 'total', 'all', None, None, None)
    #model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=1005, burn=500, thin=5, tune_interval=100)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=10000, burn=5000, thin=25, tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)
    graphics.plot_one_type(model, model.vars['p'], {}, 'p')
    pl.plot(range(101), pi_age_true, 'r:', label='Truth')
    pl.legend(fancybox=True, shadow=True, loc='upper left')

    pl.show()

    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats()['standard deviation']
    data_simulation.add_quality_metrics(model.input_data)

    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    data_simulation.add_quality_metrics(model.delta)

    model.alpha = pandas.DataFrame(index=[n for n in nx.traversal.dfs_preorder_nodes(model.hierarchy)])
    model.alpha['true'] = pandas.Series(dict(alpha))
    model.alpha['mu_pred'] = pandas.Series([n.stats()['mean'] for n in model.vars['p']['alpha']], index=model.vars['p']['U'].columns)
    model.alpha['sigma_pred'] = pandas.Series([n.stats()['standard deviation'] for n in model.vars['p']['alpha']], index=model.vars['p']['U'].columns)
    model.alpha = model.alpha.dropna()
    data_simulation.add_quality_metrics(model.alpha)

    model.sigma = pandas.DataFrame(dict(true=sigma_true))
    model.sigma['mu_pred'] = [n.stats()['mean'] for n in model.vars['p']['sigma_alpha']]
    model.sigma['sigma_pred']=[n.stats()['standard deviation'] for n in model.vars['p']['sigma_alpha']]
    data_simulation.add_quality_metrics(model.sigma)

    print 'delta'
    print model.delta

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.input_data['abs_err'].mean(),
                                                     pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
                                                                       model.input_data['covered?'].mean())

    model.mu = pandas.DataFrame(dict(true=pi_age_true,
                                     mu_pred=model.vars['p']['mu_age'].stats()['mean'],
                                     sigma_pred=model.vars['p']['mu_age'].stats()['standard deviation']))
    data_simulation.add_quality_metrics(model.mu)

    data_simulation.initialize_results(model)
    data_simulation.add_to_results(model, 'delta')
    data_simulation.add_to_results(model, 'mu')
    data_simulation.add_to_results(model, 'input_data')
    data_simulation.add_to_results(model, 'alpha')
    data_simulation.add_to_results(model, 'sigma')
    data_simulation.finalize_results(model)

    print model.results

    return model
Пример #16
0
def validate_covariate_model_dispersion(N=1000,
                                        delta_true=.15,
                                        pi_true=.01,
                                        zeta_true=[.5, -.5, 0.]):
    ## generate simulated data
    a = pl.arange(0, 100, 1)
    pi_age_true = pi_true * pl.ones_like(a)

    model = data.ModelData()
    model.parameters['p']['parameter_age_mesh'] = [0, 100]
    model.input_data = pandas.DataFrame(index=range(N))
    initialize_input_data(model.input_data)

    Z = mc.rbernoulli(.5, size=(N, len(zeta_true))) * 1.0
    delta = delta_true * pl.exp(pl.dot(Z, zeta_true))
    for i in range(len(zeta_true)):
        model.input_data['z_%d' % i] = Z[:, i]

    model.input_data['true'] = pi_true

    model.input_data['effective_sample_size'] = mc.runiform(100, 10000, N)

    n = model.input_data['effective_sample_size']
    p = model.input_data['true']
    model.input_data['value'] = mc.rnegative_binomial(n * p, delta * n * p) / n

    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p', 'all', 'total',
                                            'all', None, None, None)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'],
                                                     iter=10000,
                                                     burn=5000,
                                                     thin=5,
                                                     tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)

    pl.show()

    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats(
    )['standard deviation']
    add_quality_metrics(model.input_data)

    model.zeta = pandas.DataFrame(index=model.vars['p']['Z'].columns)
    model.zeta['true'] = zeta_true

    model.zeta['mu_pred'] = model.vars['p']['zeta'].stats()['mean']
    model.zeta['sigma_pred'] = model.vars['p']['zeta'].stats(
    )['standard deviation']
    add_quality_metrics(model.zeta)

    print '\nzeta'
    print model.zeta

    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    add_quality_metrics(model.delta)

    print 'delta'
    print model.delta

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
        model.input_data['abs_err'].mean(),
        pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
        model.input_data['covered?'].mean())
    print 'effect prediction MAE: %.3f, coverage: %.2f' % (
        pl.median(pl.absolute(model.zeta['abs_err'].dropna())),
        model.zeta.dropna()['covered?'].mean())

    model.results = dict(param=[], bias=[], mare=[], mae=[], pc=[])
    add_to_results(model, 'delta')
    add_to_results(model, 'input_data')
    add_to_results(model, 'zeta')
    model.results = pandas.DataFrame(model.results,
                                     columns='param bias mae mare pc'.split())

    return model
Пример #17
0
def validate_age_integrating_model_sim(N=500,
                                       delta_true=.15,
                                       pi_true=quadratic):
    ## generate simulated data
    a = pl.arange(0, 101, 1)
    pi_age_true = pi_true(a)

    model = data_simulation.simple_model(N)
    #model.parameters['p']['parameter_age_mesh'] = range(0, 101, 10)
    #model.parameters['p']['smoothness'] = dict(amount='Very')

    age_start = pl.array(mc.runiform(0, 100, size=N), dtype=int)
    age_end = pl.array(mc.runiform(age_start, 100, size=N), dtype=int)

    age_weights = pl.ones_like(a)
    sum_pi_wt = pl.cumsum(pi_age_true * age_weights)
    sum_wt = pl.cumsum(age_weights)
    p = (sum_pi_wt[age_end] - sum_pi_wt[age_start]) / (sum_wt[age_end] -
                                                       sum_wt[age_start])

    # correct cases where age_start == age_end
    i = age_start == age_end
    if pl.any(i):
        p[i] = pi_age_true[age_start[i]]

    n = mc.runiform(100, 10000, size=N)

    model.input_data['age_start'] = age_start
    model.input_data['age_end'] = age_end
    model.input_data['effective_sample_size'] = n
    model.input_data['true'] = p
    model.input_data['value'] = mc.rnegative_binomial(n * p,
                                                      delta_true * n * p) / n

    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p', 'all', 'total',
                                            'all', None, None, None)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'],
                                                     iter=10000,
                                                     burn=5000,
                                                     thin=25,
                                                     tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)
    graphics.plot_one_type(model, model.vars['p'], {}, 'p')
    pl.plot(a, pi_age_true, 'r:', label='Truth')
    pl.legend(fancybox=True, shadow=True, loc='upper left')

    pl.show()

    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats(
    )['standard deviation']
    data_simulation.add_quality_metrics(model.input_data)

    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    data_simulation.add_quality_metrics(model.delta)

    print 'delta'
    print model.delta

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (
        model.input_data['abs_err'].mean(),
        pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
        model.input_data['covered?'].mean())

    model.mu = pandas.DataFrame(
        dict(true=pi_age_true,
             mu_pred=model.vars['p']['mu_age'].stats()['mean'],
             sigma_pred=model.vars['p']['mu_age'].stats()
             ['standard deviation']))
    data_simulation.add_quality_metrics(model.mu)

    model.results = dict(param=[], bias=[], mare=[], mae=[], pc=[])
    data_simulation.add_to_results(model, 'delta')
    data_simulation.add_to_results(model, 'mu')
    data_simulation.add_to_results(model, 'input_data')
    model.results = pandas.DataFrame(model.results,
                                     columns='param bias mae mare pc'.split())

    print model.results

    return model
Пример #18
0
def validate_covariate_model_re(N=500, delta_true=.15, pi_true=.01, sigma_true = [.1,.1,.1,.1,.1], ess=1000):
    ## set simulation parameters
    import dismod3
    import simplejson as json
    model = data.ModelData.from_gbd_jsons(json.loads(dismod3.disease_json.DiseaseJson().to_json()))
    model.parameters['p']['parameter_age_mesh'] = [0, 100]
    model.parameters['p']['heterogeneity'] = 'Slightly'  # ensure heterogeneity is slightly

    area_list = []
    for sr in sorted(model.hierarchy.successors('all')):
        area_list.append(sr)
        for r in sorted(model.hierarchy.successors(sr)):
            area_list.append(r)
            area_list += sorted(model.hierarchy.successors(r))[:5]
    area_list = pl.array(area_list)


    ## generate simulation data
    model.input_data = pandas.DataFrame(index=range(N))
    initialize_input_data(model.input_data)

    alpha = alpha_true_sim(model, area_list, sigma_true)

    # choose observed prevalence values
    model.input_data['effective_sample_size'] = ess

    model.input_data['area'] = area_list[mc.rcategorical(pl.ones(len(area_list)) / float(len(area_list)), N)]

    model.input_data['true'] = pl.nan
    for i, a in model.input_data['area'].iteritems():
        model.input_data['true'][i] = pi_true * pl.exp(pl.sum([alpha[n] for n in nx.shortest_path(model.hierarchy, 'all', a) if n in alpha]))

    n = model.input_data['effective_sample_size']
    p = model.input_data['true']
    model.input_data['value'] = mc.rnegative_binomial(n*p, delta_true*n*p) / n



    ## Then fit the model and compare the estimates to the truth
    model.vars = {}
    model.vars['p'] = data_model.data_model('p', model, 'p', 'all', 'total', 'all', None, None, None)
    model.map, model.mcmc = fit_model.fit_data_model(model.vars['p'], iter=20000, burn=10000, thin=10, tune_interval=100)

    graphics.plot_one_ppc(model.vars['p'], 'p')
    graphics.plot_convergence_diag(model.vars)

    pl.show()

    model.input_data['mu_pred'] = model.vars['p']['p_pred'].stats()['mean']
    model.input_data['sigma_pred'] = model.vars['p']['p_pred'].stats()['standard deviation']
    add_quality_metrics(model.input_data)


    model.alpha = pandas.DataFrame(index=[n for n in nx.traversal.dfs_preorder_nodes(model.hierarchy)])
    model.alpha['true'] = pandas.Series(dict(alpha))
    model.alpha['mu_pred'] = pandas.Series([n.stats()['mean'] for n in model.vars['p']['alpha']], index=model.vars['p']['U'].columns)
    model.alpha['sigma_pred'] = pandas.Series([n.stats()['standard deviation'] for n in model.vars['p']['alpha']], index=model.vars['p']['U'].columns)
    add_quality_metrics(model.alpha)

    print '\nalpha'
    print model.alpha.dropna()


    model.sigma = pandas.DataFrame(dict(true=sigma_true))
    model.sigma['mu_pred'] = [n.stats()['mean'] for n in model.vars['p']['sigma_alpha']]
    model.sigma['sigma_pred']=[n.stats()['standard deviation'] for n in model.vars['p']['sigma_alpha']]
    add_quality_metrics(model.sigma)

    print 'sigma_alpha'
    print model.sigma

    
    model.results = dict(param=[], bias=[], mare=[], mae=[], pc=[])
    add_to_results(model, 'sigma')

    model.delta = pandas.DataFrame(dict(true=[delta_true]))
    model.delta['mu_pred'] = pl.exp(model.vars['p']['eta'].trace()).mean()
    model.delta['sigma_pred'] = pl.exp(model.vars['p']['eta'].trace()).std()
    add_quality_metrics(model.delta)

    print 'delta'
    print model.delta
    add_to_results(model, 'delta')

    print '\ndata prediction bias: %.5f, MARE: %.3f, coverage: %.2f' % (model.input_data['abs_err'].mean(),
                                                     pl.median(pl.absolute(model.input_data['rel_err'].dropna())),
                                                                       model.input_data['covered?'].mean())
    print 'effect prediction MAE: %.3f, coverage: %.2f' % (pl.median(pl.absolute(model.alpha['abs_err'].dropna())),
                                                          model.alpha.dropna()['covered?'].mean())
    add_to_results(model, 'input_data')
    add_to_results(model, 'alpha')

    model.results = pandas.DataFrame(model.results)
    return model