def PlotResampledByDecade(resps,
iters=11,
predict_flag=False,
omit=None,
weighted=True):
"""Plots survival curves for resampled data.
resps: list of DataFrames
iters: number of resamples to plot
predict_flag: whether to also plot predictions
"""
for i in range(iters):
if weighted:
samples = [
thinkstats2.ResampleRowsWeighted(resp) for resp in resps
]
else:
samples = [thinkstats2.ResampleRows(resp) for resp in resps]
sample = pandas.concat(samples, ignore_index=True)
groups = sample.groupby('decade')
if omit:
groups = [(name, group) for name, group in groups
if name not in omit]
# TODO: refactor this to collect resampled estimates and
# plot shaded areas
if i == 0:
AddLabelsByDecade(groups, alpha=0.7)
if predict_flag:
PlotPredictionsByDecade(groups, alpha=0.1)
EstimateSurvivalByDecade(groups, alpha=0.1)
else:
EstimateSurvivalByDecade(groups, alpha=0.2)
def SamplingDistributions(dados_chuva, dados_vazao, iters=101):
dados = pd.DataFrame([dados_chuva, dados_vazao])
dados = dados.T
t = []
for _ in range(iters):
sample = thinkstats2.ResampleRows(dados)
chuva = sample["COIMBRA_P"]
vazao = sample["COIMBRA_F"]
estimates = thinkstats2.LeastSquares(chuva, vazao)
t.append(estimates)
inters, slopes = zip(*t)
return inters, slopes
def SamplingDistributions(live, iters=101):
"""Estimates sampling distributions by resampling rows.
live: DataFrame
iters: number of times to run simulations
returns: pair of sequences (inters, slopes)
"""
t = []
for _ in range(iters):
sample = thinkstats2.ResampleRows(live)
ages = sample.agepreg
weights = sample.totalwgt_lb
estimates = thinkstats2.LeastSquares(ages, weights)
t.append(estimates)
inters, slopes = zip(*t)
return inters, slopes
def EstimateBirthWeight(live, iters=1001):
"""Estimate mean birth weight by resampling, with and without weights.
live: DataFrame
iters: number of experiments to run
"""
mean = live.totalwgt_lb.mean()
print('mean', mean)
estimates = [
thinkstats2.ResampleRows(live).totalwgt_lb.mean() for _ in range(iters)
]
Summarize(estimates)
estimates = [
ResampleRowsWeighted(live).totalwgt_lb.mean() for _ in range(iters)
]
Summarize(estimates)
print("Standard deviation w/o height: {:.3f}".format(std_ys))
#%%
# calc standard deviation (RMSE) of prediction w/ height
std_res = thinkstats2.Std(res)
print("Standard deviation w/ height: {:.3f}".format(std_res))
#%%
# How does RMSE get impacted by height info
print("Impact: {:.3f}".format(1 - (std_res / std_ys)))
#%%
# Resampling to compute inter and slope
t = []
for _ in range(100):
sample = thinkstats2.ResampleRows(data)
estimates = thinkstats2.LeastSquares(sample.htm3, np.log10(sample.wtkg2))
t.append(estimates)
inters, slopes = zip(*t)
#%%
# Plot the sampling distribution of slope.
cdf = thinkstats2.Cdf(slopes)
thinkplot.Cdf(cdf)
#%%
# Compute the p-value of the slope.
pvalue = cdf[0]
pvalue