def main():
resp = brfss.Respondents()
resp.ReadRecords(data_dir='res')
d = resp.SummarizeHeight()
man_d = d[1]
lady_d = d[2]
# 男性的mu, var, sigma, 变异系数CV
man_mu, man_var = thinkstats.TrimmedMeanVar(man_d)
man_sigma = math.sqrt(man_var)
man_cv = man_sigma/man_mu
print("man: mu = %.3f, var = %.3f, sigma = %.3f, cv = %.3f" % (man_mu, man_var, man_sigma, man_cv))
# 女性的mu, var, sigma, 变异系数CV
lady_mu, lady_var = thinkstats.TrimmedMeanVar(lady_d)
lady_sigma = math.sqrt(lady_var)
lady_cv = lady_sigma/lady_mu
print("lady: mu = %.3f, var = %.3f, sigma = %.3f, cv = %.3f" % (lady_mu, lady_var, lady_sigma, lady_cv))
# 男性, 女性Hist分布
man_hist = Pmf.MakeHistFromList(man_d, name='man hist')
myplot.Hist(man_hist)
myplot.Show()
myplot.Clf()
lady_hist = Pmf.MakeHistFromList(lady_d, name='lady hist')
myplot.Hist(lady_hist)
myplot.Show()
myplot.Clf()
# 男性, 女性Pmf分布
man_pmf = Pmf.MakePmfFromHist(man_hist, name='man pmf')
myplot.Pmf(man_pmf)
myplot.Show()
myplot.Clf()
lady_pmf = Pmf.MakePmfFromHist(lady_hist, name='lady pmf')
myplot.Pmf(lady_pmf)
myplot.Show()
myplot.Clf()
# 男性/女性Cdf累积分布
man_cdf = Cdf.MakeCdfFromPmf(man_pmf, name='man cdf')
lady_cdf = Cdf.MakeCdfFromPmf(lady_pmf, name='lady cdf')
myplot.Cdfs((man_cdf, lady_cdf), complement=False, transform=None)
myplot.Show()
def MakeNormalPlot(values):
"""Makes a normal probability plot.
Args:
values: sequence of values
lineoptions: dictionary of options for pyplot.plot
options: dictionary of options for myplot.Save
"""
# TODO: when n is small, generate a larger sample and desample
pyplot.clf()
# compute parameters
mu, var = thinkstats.TrimmedMeanVar(values, p=0.01)
sigma = math.sqrt(var)
n = len(values)
# plot resampled data
PlotSimulatedData(mu, sigma, n)
# plot real data
xs = GenerateNormalVariates(0, 1, n)
pyplot.plot(sorted(xs), sorted(values), 'r.', markersize=3)
myplot.Save(show=True,
xlabel='Standard normal values',
legend=False)
def MakeNormalModel(self, weights, root,
xmax=175,
xlabel='adult weight (kg)',
axis=None):
cdf = Cdf.MakeCdfFromList(weights)
pyplot.clf()
t = weights[:]
t.sort()
mu, var = thinkstats.TrimmedMeanVar(t)
print('n, Mean, Var', len(weights), mu, var)
sigma = math.sqrt(var)
print('Sigma', sigma)
xs, ps = continuous.RenderNormalCdf(mu, sigma, xmax)
pyplot.plot(xs, ps, label='model', linewidth=4, color='0.7')
xs, ps = cdf.Render()
pyplot.plot(xs, ps, label='data', linewidth=2, color='blue')
myplot.Save(root,
title = 'Adult weight',
xlabel = xlabel,
ylabel = 'CDF',
axis=axis or [0, xmax, 0, 1])
def SummarizeHeight(self):
"""Print summary statistics for male and female height."""
# make a dictionary that maps from gender code to list of heights
d = {1: [], 2: [], 'all': []}
[d[r.sex].append(r.htm3) for r in self.records if r.htm3 != 'NA']
[d['all'].append(r.htm3) for r in self.records if r.htm3 != 'NA']
for key, t in d.iteritems():
mu, var = thinkstats.TrimmedMeanVar(t)
sigma = math.sqrt(var)
cv = sigma / mu
print key, len(t), mu, var, sigma, cv
def SummarizeWeight(self):
"""Print summary statistics for male and female weight."""
# make a dictionary that maps from gender code to list of weights
d = {1: [], 2: [], 'all': []}
[d[r.sex].append(r.weight2) for r in self.records if r.weight2 != 'NA']
[d['all'].append(r.weight2) for r in self.records if r.weight2 != 'NA']
print('Weight (kg):')
print('key n mean var sigma cv')
for key, t in d.items():
mu, var = thinkstats.TrimmedMeanVar(t)
sigma = math.sqrt(var)
cv = sigma / mu
print(key, len(t), mu, var, sigma, cv)
def MakeNormalModel(values):
"""Plot the CDF of birthweights with a normal model."""
# estimate parameters: trimming outliers yields a better fit
mu, var = thinkstats.TrimmedMeanVar(values, p=0.01)
print 'Mean, Var', mu, var
# plot the model
sigma = math.sqrt(var)
print 'Sigma', sigma
xs, ps = RenderNormalCdf(mu, sigma, 200)
pyplot.clf()
pyplot.plot(xs, ps, label='model', linewidth=4, color='0.8')
# plot the data
cdf = Cdf.MakeCdfFromList(values)
xs, ps = cdf.Render()
pyplot.plot(xs, ps, label='data', linewidth=2, color='red')
myplot.Save(show=True,
ylabel = 'CDF')
def MakeNormalModel(weights):
"""Plot the CDF of birthweights with a normal model."""
# estimate parameters: trimming outliers yields a better fit
mu, var = thinkstats.TrimmedMeanVar(weights, p=0.01)
print('Mean, Var', mu, var)
# plot the model
sigma = math.sqrt(var)
print('Sigma', sigma)
xs, ps = RenderNormalCdf(mu, sigma, 200)
pyplot.clf()
pyplot.plot(xs, ps, label='model', linewidth=4, color='0.8')
# plot the data
cdf = Cdf.MakeCdfFromList(weights)
xs, ps = cdf.Render()
pyplot.plot(xs, ps, label='data', linewidth=2, color='blue')
myplot.Save('nsfg_birthwgt_model',
title='Birth weights',
xlabel='birth weight (oz)',
ylabel='CDF')
