def single_plot(dfs):
"""Make the plot.
"""
for i, age_group in enumerate(age_groups):
print(i, age_group)
series = [df.loc[age_group] for df in dfs]
models = [fit_row(s).fittedvalues for s in series]
xs = series[0].index + 2
rows = thinkstats2.PercentileRows(models, [5, 95])
thinkplot.fill_between(xs,
rows[0],
rows[1],
color=colors[i],
alpha=0.3)
rows = thinkstats2.PercentileRows(series, [50])
thinkplot.plot(xs,
rows[0],
label=labels[i],
color=colors[i],
alpha=0.6)
thinkplot.config(xlabel=xlabel, ylabel=ylabel, loc='upper left', axis=axis)
plt.gca().get_legend().set(title='Age group')
thinkplot.save(root='age_religion2')
def ResampleSurvival(resp, iters=101):
"""Resamples respondents and estimates the survival function.
resp: DataFrame of respondents
iters: number of resamples
"""
_, sf = EstimateMarriageSurvival(resp)
thinkplot.Plot(sf)
low, high = resp.min(), resp.max()
ts = np.arange(low, high, 1/12.0)
ss_seq = []
for _ in range(iters):
sample = thinkstats2.ResampleRowsWeighted(resp)
_, sf = EstimateMarriageSurvival(sample)
ss_seq.append(sf.Probs(ts))
low, high = thinkstats2.PercentileRows(ss_seq, [5, 95])
thinkplot.FillBetween(ts, low, high, color='gray', label='90% CI')
thinkplot.Save(root='survival3',
xlabel='age (years)',
ylabel='prob unmarried',
xlim=[12, 46],
ylim=[0, 1],
formats=FORMATS)
def PlotConfidenceIntervals(xs,
inters,
slopes,
res=None,
percent=90,
**options):
"""Plots the 90% confidence intervals for weights based on ages.
xs: sequence
inters: estimated intercepts
slopes: estimated slopes
res: residuals
percent: what percentile range to show
"""
fys_seq = []
for inter, slope in zip(inters, slopes):
fxs, fys = thinkstats2.FitLine(xs, inter, slope)
if res is not None:
fys += np.random.permutation(res)
fys_seq.append(fys)
p = (100 - percent) / 2
percents = p, 100 - p
low, high = thinkstats2.PercentileRows(fys_seq, percents)
thinkplot.FillBetween(fxs, low, high, **options)
def PlotConfidenceIntervals(xs, inters, slopes, percent=90, **options):
fys_seq = []
for inter, slope in zip(inters, slopes):
fxs, fys = thinkstats2.FitLine(xs, inter, slope)
fys_seq.append(fys)
p = (100 - percent) / 2
percents = p, 100 - p
low, high = thinkstats2.PercentileRows(fys_seq, percents)
thinkplot.FillBetween(fxs, low, high, **options)
def PlotPredictions(daily, years, iters=101, percent=90, func=RunLinearModel):
"""Plots predictions.
daily: DataFrame of daily prices
years: sequence of times (in years) to make predictions for
iters: number of simulations
percent: what percentile range to show
func: function that fits a model to the data
"""
result_seq = SimulateResults(daily, iters=iters, func=func)
p = (100 - percent) / 2
percents = p, 100 - p
predict_seq = GeneratePredictions(result_seq, years, add_resid=True)
low, high = thinkstats2.PercentileRows(predict_seq, percents)
thinkplot.FillBetween(years, low, high, alpha=0.3, color='gray')
predict_seq = GeneratePredictions(result_seq, years, add_resid=False)
low, high = thinkstats2.PercentileRows(predict_seq, percents)
thinkplot.FillBetween(years, low, high, alpha=0.5, color='gray')
def main():
gss = utils.ReadGss('gss_college_religion')
diffs = [run(gss) for _ in range(101)]
years = diffs[0].index
rows = thinkstats2.PercentileRows(diffs, [5, 50, 95])
thinkplot.fill_between(years, rows[0], rows[2], alpha=0.2)
thinkplot.plot(years, rows[1])
thinkplot.config(xlabel='Year',
ylabel='Difference in fraction with no affiliation',
xlim=[1970, 2018])
thinkplot.save(root='college_religion')
def SimulateAutocorrelation(daily, iters=1001, nlags=40):
"""Resample residuals, compute autocorrelation, and plot percentiles
daily: DataFrame
iters: number of simulations to run
nlags: maximum lags to compute autocorrelation
"""
t = []
for _ in range(iters):
filled = FillMissing(daily, span=30)
resid = thinkstats2.Resample(filled.resid)
acf = smtsa.acf(resid, nlags=nlags, unbiased=True)[1:]
t.append(np.abs(acf))
high = thinkstats2.PercentileRows(t, [97.5])[0]
low = -high
lags = range(1, nlags + 1)
thinkplot.FillBetween(lags, low, high, alpha=0.2, color='gray')
def ResampleSurvival(dados, limiar, iters=101):
"""Resamples respondents and estimates the survival function.
resp: DataFrame of respondents
iters: number of resamples
"""
_, sf = EstimateMarriageSurvival(dados, limiar)
thinkplot.Plot(sf)
low, high = dados.min(), dados.max()
ts = np.arange(low, high, 1)
ss_seq = []
for _ in range(iters):
sample = thinkstats2.ResampleRowsWeighted(pd.DataFrame(dados), column='MANSO')
_, sf = EstimateMarriageSurvival(sample['MANSO'], limiar)
ss_seq.append(sf.Probs(ts))
low, high = thinkstats2.PercentileRows(ss_seq, [5, 95])
thinkplot.FillBetween(ts, low, high, color='gray', label='90% CI')
def MakeSurvivalCI(sf_seq, percents):
"""Makes confidence intervals from a list of survival functions.
sf_seq: list of SurvivalFunction
percents: list of percentiles to select, like [5, 95]
returns: (ts, rows) where ts is a sequence of times and
rows contains one row of values for each percent
"""
# find the union of all ts where the sfs are evaluated
ts = set()
for sf in sf_seq:
ts |= set(sf.ts)
ts = list(ts)
ts.sort()
# evaluate each sf at all times
ss_seq = [sf.Probs(ts) for sf in sf_seq if len(sf) > 0]
# return the requested percentiles from each column
rows = thinkstats2.PercentileRows(ss_seq, percents)
return ts, rows
