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)
"""
# DumpHeights(n=10000000)
### injection ### injection ### injection ### injection ###
#d = LoadHeights()
labels = {1: 'male', 2: 'female'}
import pandas as pd
df = pd.read_csv(r"../data/BRFSS.csv", sep=',', index_col=0)
d = {1: df.M.dropna().values, 2: df.F.dropna().values}
### injection ### injection ### injection ### injection ###
# PlotCdfs(d, labels)
suites = {}
for key, xs in d.items():
name = labels[key]
print(name, len(xs))
Summarize(xs)
xs = thinkstats.Jitter(xs, 1.3)
mus, sigmas = FindPriorRanges(xs, num_points, median_flag=median_flag)
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.iteritems():
mu = thinkstats.Mean(xs)
xs = thinkstats.Jitter(xs, 1.3)
xs = [x - mu for x in xs]
cdf = thinkbayes.MakeCdfFromList(xs)
thinkplot.Cdf(cdf, label=labels[key])
thinkplot.Show()
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)
"""
DumpHeights(n=10000000)
d = LoadHeights()
labels = {1: 'male', 2: 'female'}
# PlotCdfs(d, labels)
suites = {}
for key, xs in d.iteritems():
name = labels[key]
print(name, len(xs))
Summarize(xs)
xs = thinkstats.Jitter(xs, 1.3)
mus, sigmas = FindPriorRanges(xs, num_points, median_flag=median_flag)
suite = Height(mus, sigmas, name)
suites[name] = 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)