More notebooks for Think Stats

import scipy.stats

mu = 178
sigma = 7.7
dist = scipy.stats.norm(loc=mu, scale=sigma)
type(dist)

dist.mean(), dist.std()

dist.cdf(mu-sigma)

# Solution

low = dist.cdf(177.8)    # 5'10"
high = dist.cdf(185.4)   # 6'1"
low, high, high-low

alpha = 1.7
xmin = 1       # meter
dist = scipy.stats.pareto(b=alpha, scale=xmin)
dist.median()

# Solution

dist.mean()

# Solution

dist.cdf(dist.mean())

# Solution

(1 - dist.cdf(1000)) * 7e9, dist.sf(1000) * 7e9

# Solution

# One way to solve this is to search for a height that we
# expect one person out of 7 billion to exceed.

# It comes in at roughly 600 kilometers.

dist.sf(600000) * 7e9            

# Solution

# Another way is to use `ppf`, which evaluates the "percent point function", which
# is the inverse CDF.  So we can compute the height in meters that corresponds to
# the probability (1 - 1/7e9).

dist.ppf(1 - 1/7e9)

sample = [random.weibullvariate(2, 1) for _ in range(1000)]
cdf = thinkstats2.Cdf(sample)
thinkplot.Cdf(cdf, transform='weibull')
thinkplot.Config(xlabel='Weibull variate', ylabel='CCDF')

import analytic
df = analytic.ReadBabyBoom()

diffs = df.minutes.diff()

cdf = thinkstats2.Cdf(diffs, label='actual')
n = len(diffs)

lam = 44.0 / 24 / 60

sample = [rand