def _summarize_weight_change(self):
"""Print the mean reported change in weight in kg."""
data = [(r.weight2, r.wtyrago) for r in self.records if r.weight2 != 'NA' and r.wtyrago != 'NA']
changes = [(curr - prev) for curr, prev in data]
print('Mean change', _03_thinkstats._mean(changes))
def _difference_in_means(firsts, others, attr):
"""
Compute the difference in means between tables for a given attr.
Prints summary statistics.
"""
firsts_mean = _03_thinkstats._mean(getattr(firsts, attr))
print('First babies, %s, trimmed mean:' % attr, firsts_mean)
others_mean = _03_thinkstats._mean(getattr(others, attr))
print('Other babies, %s, trimmed mean:' % attr, others_mean)
diff = others_mean - firsts_mean
print('Difference in means:', diff)
print
return diff
def testVar(self):
t = [1, 1, 1, 3, 3, 591]
mu = _03_thinkstats._mean(t)
var1 = _03_thinkstats._var(t)
var2 = _03_thinkstats._var(t, mu)
self.assertAlmostEquals(mu, 100.0)
self.assertAlmostEquals(var1, 48217.0)
self.assertAlmostEquals(var2, 48217.0)
def _make_line_plot(age_bins):
xs = []
ys = []
for bin, weights in sorted(age_bins.iteritems()):
xs.append(bin)
ys.append(_03_thinkstats._mean(weights))
_05_myplot._plot(xs, ys, 'bs-')
_05_myplot._save(root='agemodel_line',
xlabel="Mother's age (years)",
ylabel='Mean birthweight (oz)',
legend=False)
def testMeanAndVar(self):
t = [1, 2, 2, 3, 5]
mu = _03_thinkstats._mean(t)
var = _03_thinkstats._var(t, mu)
pmf = _04_Pmf._make_pmf_from_list(t)
mu2 = pmf._mean()
var2 = pmf._var()
var3 = pmf._var(mu2)
self.assertAlmostEquals(mu, mu2)
self.assertAlmostEquals(var, var2)
self.assertAlmostEquals(var, var3)
def _cov(xs, ys, mux=None, muy=None):
"""
Computes Cov(X, Y).
Args:
xs: sequence of values
ys: sequence of values
mux: optional float mean of xs
muy: optional float mean of ys
Returns:
Cov(X, Y)
"""
if mux is None:
mux = _03_thinkstats._mean(xs)
if muy is None:
muy = _03_thinkstats._mean(ys)
total = 0.0
for x, y in zip(xs, ys):
total += (x - mux) * (y - muy)
return total / len(xs)
def _estimate_rankits(n=6, m=1000):
"""
Estimates the expected values of sorted random samples.
Args:
n: sample size
m: number of iterations
Returns: list of n rankits
"""
t = _samples(n, m)
t = zip(*t)
means = [_03_thinkstats._mean(x) for x in t]
return means
def _partition(ages, weights, bin_size=2):
"""
Break ages into bins.
Returns a map from age to list of weights.
"""
weight_dict = {}
for age, weight in zip(ages, weights):
bin = bin_size * math.floor(age / bin_size) + bin_size / 2.0
weight_dict.setdefault(bin, []).append(weight)
for bin, bin_weights in weight_dict.iteritems():
try:
mean = _03_thinkstats._mean(bin_weights)
except ZeroDivisionError:
continue
return weight_dict
def testMean(self):
t = [1, 1, 1, 3, 3, 591]
mu = _03_thinkstats._mean(t)
self.assertEquals(mu, 100)
