コード例 #1
0
ファイル: variability.py プロジェクト: qrsforever/workspace
def RunEstimate(update_func, num_points=31, median_flag=False):
    """Runs the whole analysis.

    update_func: which of the update functions to use
    num_points: number of points in the Suite (in each dimension)
    """
    d = ReadHeights(nrows=None)
    labels = {1: 'male', 2: 'female'}

    # PlotCdfs(d, labels)

    suites = {}
    for key, xs in d.items():
        label = labels[key]
        print(label, len(xs))
        Summarize(xs)

        xs = thinkbayes2.Jitter(xs, 1.3)

        mus, sigmas = FindPriorRanges(xs, num_points, median_flag=median_flag)
        suite = Height(mus, sigmas, label)
        suites[label] = suite
        update_func(suite, xs)
        print('MLE', suite.MaximumLikelihood())

        PlotPosterior(suite)

        pmf_m = suite.Marginal(0)
        pmf_s = suite.Marginal(1)
        print('marginal mu', pmf_m.Mean(), pmf_m.Var())
        print('marginal sigma', pmf_s.Mean(), pmf_s.Var())

        # PlotMarginals(suite)

    PlotCoefVariation(suites)
コード例 #2
0
def RunEstimate(update_func, num_points=31, median_flag=False):
    """Runs the whole analysis.

    update_func: which of the update functions to use
    num_points: number of points in the Suite (in each dimension)
    """
    d = ReadHeights(nrows=None)
    labels = {1: 'male', 2: 'female'}

    suites = {}
    for key, xs in d.items():
        label = labels[key]
        print(label, len(xs))
        Summarize(xs)

        xs = thinkbayes2.Jitter(xs, 1.3)

        mus, sigmas = FindPriorRanges(xs, num_points, median_flag=median_flag)
        suite = Height(mus, sigmas, label)
        suites[label] = suite
        update_func(suite, xs)
        print('MAP', suite.MaximumLikelihood())

    # joint distributions of mu and sigma for men and women
    suite1 = suites['male']
    suite2 = suites['female']
コード例 #3
0
ファイル: variability.py プロジェクト: qrsforever/workspace
def PlotCdfs(d, labels):
    """Plot CDFs for each sequence in a dictionary.

    Jitters the data and subtracts away the mean.

    d: map from key to sequence of values
    labels: map from key to string label
    """
    thinkplot.Clf()
    for key, xs in d.items():
        mu = thinkbayes2.Mean(xs)
        xs = thinkbayes2.Jitter(xs, 1.3)
        xs = [x - mu for x in xs]
        cdf = thinkbayes2.MakeCdfFromList(xs)
        thinkplot.Cdf(cdf, label=labels[key])
    thinkplot.Show()
コード例 #4
0
def RunEstimate(update_func, num_points=31, median_flag=False):
    """Runs the whole analysis.

    update_func: which of the update functions to use
    num_points: number of points in the Suite (in each dimension)
    """
    d = ReadHeights(nrows=None)
    labels = {1: 'male', 2: 'female'}

    suites = {}
    for key, xs in d.items():
        label = labels[key]
        print(label, len(xs))
        Summarize(xs)

        xs = thinkbayes2.Jitter(xs, 1.3)

        mus, sigmas = FindPriorRanges(xs, num_points, median_flag=median_flag)
        suite = Height(mus, sigmas, label)
        suites[label] = suite
        update_func(suite, xs)
        print('MAP', suite.MaximumLikelihood())

    suite1 = suites['male']
    suite2 = suites['female']

    mu1 = suite1.Marginal(0)
    sigma1 = suite1.Marginal(1)

    mu2 = suite2.Marginal(0)
    sigma2 = suite2.Marginal(1)

    diff = mu1 - mu2
    sigma = (sigma1 + sigma2) / 2

    pmf_d = diff / sigma

    thinkplot.Cdf(pmf_d.MakeCdf())
    thinkplot.Show(xlabel='# stddev between means', ylabel='PMF')