def main():
df = hinc.ReadData()
log_sample = InterpolateSample(df, log_upper=6.0)
log_cdf = thinkstats2.Cdf(log_sample)
print("median", thinkstats2.Median(log_sample))
print("pearson's median skewness",
thinkstats2.PearsonMedianSkewness(log_sample))
print("skewness", thinkstats2.Skewness(log_sample))
print("mean", log_cdf.Mean())
print(
"the higher our log_upper, the more right-skewed (according to g_1) or at least less left-skewed (according to g_p) things get"
)
print("the mean moves to the right a bit, too.")
print("proportion of the population with income < mean",
log_cdf.Prob(log_cdf.Mean()))
print(
"the higher the upper bound, the greater the proprtion below the mean."
)
thinkplot.Cdf(log_cdf)
thinkplot.Show(xlabel='household income', ylabel='CDF')
def Summarize(data):
mean = data.mean()
std = data.std()
median = thinkstats2.Median(data)
print('mean', mean)
print('std', std)
print('median', median)
print('skewness', thinkstats2.Skewness(data))
print('pearson skewness', thinkstats2.PearsonMedianSkewness(data))
return mean, median
def Summarize(data):
"""Prints summary statistics.
data: pandas Series
"""
mean = data.mean()
std = data.std()
median = thinkstats2.Median(data)
print('mean', mean)
print('std', std)
print('median', median)
print('skewness', thinkstats2.Skewness(data))
print('pearson skewness', thinkstats2.PearsonMedianSkewness(data))
return mean, median
def describe_inc_dist(log_upper):
log_sample = hinc2.InterpolateSample(df, log_upper=j)
incomes = np.power(10, log_sample)
inc_mean = thinkstats2.Mean(incomes)
inc_med = thinkstats2.Median(incomes)
inc_skew = thinkstats2.Skewness(incomes)
inc_pearskew = thinkstats2.PearsonMedianSkewness(incomes)
print('log_upper = ', j)
print('Mean Income: ', inc_mean)
print('Median Income: ', inc_med)
print('Skewness: ', inc_skew)
print('Pearson Median Skewness: ', inc_pearskew)
cdf = thinkstats2.Cdf(incomes)
inc_below_mean = cdf.Prob(inc_mean)
print('Pct. below mean: ', inc_below_mean)
print('\n')
def main():
df = hinc.ReadData()
log_sample = InterpolateSample(df, log_upper=6.0)
log_cdf = thinkstats2.Cdf(log_sample)
thinkplot.Cdf(log_cdf)
thinkplot.Show(xlabel='household income', ylabel='CDF')
sample = np.power(10, log_sample)
mean = np.mean(sample)
cdf = thinkstats2.Cdf(sample)
print "Median:", np.median(sample)
print "Mean:", mean
print "Skewness:", thinkstats2.Skewness(sample)
print "Pearson's Skewness:", thinkstats2.PearsonMedianSkewness(sample)
print "Percent of people with incomes <= mean:", cdf[mean]
pdf = thinkstats2.EstimatedPdf(sample)
thinkplot.Pdf(pdf)
SampleDistrPLot(lams, n, lam)
thinkplot.Config(xlabel='L estimate',
ylabel='CDF',
title='Sampling distribution',
xlim=[0, 4],
legend=True)
#--- Chapter6 Ex1
df = hinc.ReadData()
log_sample = hinc2.InterpolateSample(df, log_upper=6.0)
sample = np.power(10, log_sample)
print('Mean = ', sample.mean())
print('Median =', thinkstats2.Median(sample))
print('Skewness =', thinkstats2.Skewness(sample))
print('Pearson Median Skweness =', thinkstats2.PearsonMedianSkewness(sample))
income_cdf = thinkstats2.Cdf(sample)
print(income_cdf.Prob(sample.mean()) * 100)
#--- Chapter8 Ex3
def SimulateGame(lam):
t = 0
goals = 0
while True:
time_int = random.expovariate(lam)
t += time_int
if t > 1:
break
goals += 1
return goals