def Summarize(data_dir):
"""Prints summary statistics for first babies and others.
Returns:
tuple of Tables
"""
table, firsts, others = MakeTables(data_dir)
ProcessTables(firsts, others)
print("Number of first babies", firsts.n)
print("Number of others", others.n)
mu1, mu2 = firsts.mu, others.mu
print("Mean gestation in weeks:")
print("First babies", mu1)
print("Others", mu2)
print("Difference in days", (mu1 - mu2) * 7.0)
var = thinkstats.Var(firsts.lengths)
sd = numpy.sqrt(var)
print("Firsts sd = ", sd)
var = thinkstats.Var(others.lengths)
sd = numpy.sqrt(var)
print("Others sd = ", sd)
histfirst = Pmf.MakeHistFromList(firsts.lengths)
histother = Pmf.MakeHistFromList(others.lengths)
myplot.Hists([histfirst, histother])
myplot.Show()
def testVar(self):
t = [1, 1, 1, 3, 3, 591]
mu = thinkstats.Mean(t)
var1 = thinkstats.Var(t)
var2 = thinkstats.Var(t, mu)
print
print 'Pumpkins'
print 'mean', mu
print 'var', var1
print 'var', var2
self.assertAlmostEquals(mu, 100.0)
self.assertAlmostEquals(var1, 48217.0)
self.assertAlmostEquals(var2, 48217.0)
def testCov(self):
xs = [1, 2, 3]
ys = [3, 4, 5]
cov = correlation.Cov(xs, ys)
self.assertAlmostEquals(cov, 0.666666666)
var = thinkstats.Var(xs)
cov = correlation.Cov(xs, xs)
self.assertAlmostEquals(var, cov)
def pumpkin(weights):
"""
Given an iterable of pumpkin weights, compute the sequence's mean,
variance, and standard deviation.
"""
mean = thinkstats.Mean(weights)
variance = thinkstats.Var(weights, mean)
stddev = std_dev(weights, mean, variance)
return mean, variance, stddev
def Process(table, name):
''' 对数据表进行各种分析处理 '''
practice001.Process(table)
table.name = name
# 计算方差：根据序列、均值
table.var = thinkstats.Var(table.lengths, table.mu)
# 计算切尾均值：根据序列
table.trim = thinkstats.TrimmedMean(table.lengths)
table.hist = Pmf.MakeHistFromList(table.lengths, name=name)
table.pmf = Pmf.MakePmfFromList(table.lengths, name=name)
def testMeanAndVar(self):
t = [1, 2, 2, 3, 5]
mu = thinkstats.Mean(t)
var = thinkstats.Var(t, mu)
pmf = Pmf.MakePmfFromList(t)
mu2 = pmf.Mean()
var2 = pmf.Var()
var3 = pmf.Var(mu2)
self.assertAlmostEquals(mu, mu2)
self.assertAlmostEquals(var, var2)
self.assertAlmostEquals(var, var3)
import thinkstats
import math
pumpkin_weights = [1, 1, 1, 3, 3, 591]
print('Mean of the pumpkin is:', thinkstats.Mean(pumpkin_weights))
print('Variance of the pumpkin is:', thinkstats.Var(pumpkin_weights))
print('Standard Deviation of the pumpkin is:',
math.sqrt(thinkstats.Var(pumpkin_weights)))
def variance(data):
prglengths = map(lambda x: x.prglength, data)
return thinkstats.Var(prglengths)
def Pumpkin():
pumpkins = [1, 1, 1, 3, 3, 591]
pumpkins = [1, 1, 1, 3, 3, 2]
print "Mean:", thinkstats.Mean(pumpkins), "lbs"
print "Variance:", thinkstats.Var(pumpkins)
print "SD:", math.sqrt(thinkstats.Var(pumpkins)), "lbs"
def size_variance(self):
return thinkstats.Var(self.sizes())
def Pumpkin():
weights = [p.weight for p in pumpkins]
mu, var = thinkstats.MeanVar(weights)
s = math.sqrt(var)
return (mu, var, s)
print 'mean, variance, standard deviation', Pumpkin()
# ex 2.2
all, firsts, others = first.MakeTables()
first.ProcessTables(firsts, others)
firsts.s = math.sqrt(thinkstats.Var(firsts.lengths, firsts.mu))
others.s = math.sqrt(thinkstats.Var(others.lengths, others.mu))
print 'first babies mean:', firsts.mu, 'standard deviation:', firsts.s
print 'others mean:', others.mu, 'standard deviation:', others.s
print 'mean difference (hours)', (firsts.mu - others.mu) * 7 * 24
print 'spread difference (hours)', (firsts.s - others.s) * 7 * 24
# Distributions
firstsPrgLengthFreqDict = {}
for length in firsts.lengths:
firstsPrgLengthFreqDict[length] = firstsPrgLengthFreqDict.get(length,
0) + 1
print firstsPrgLengthFreqDict
def std_dev(seq, mean=None, var=None):
if not var:
var = thinkstats.Var(seq, mean)
return math.sqrt(var)
import thinkstats
import math
import survey
def pumpkin():
pumpkins = [1, 1, 1, 3, 3, 591] # pumpkin weights
mean, variance = thinkstats.MeanVar(pumpkins)
standardDeviation = math.sqrt(variance)
return mean, variance, standardDeviation
for p in pumpkin():
print(p) # prints mean, variance, and standardDeviation for pumpkin wights
table = survey.Pregnancies()
table.ReadRecords()
firstPregLength = [p.prglength for p in table.records if p.birthord == 1 and p.outcome == 1]
firstPregDeviation = math.sqrt(thinkstats.Var(firstPregLength))
followingPregLength = [p.prglength for p in table.records if p.birthord != 1 and p.outcome == 1]
followingPregDeviation = math.sqrt(thinkstats.Var(followingPregLength))
print (firstPregDeviation, followingPregDeviation)
__author__ = 'Maxiee' # -*- coding: UTF-8 -*- import thinkstats import math import Pmf import matplotlib.pyplot as pyplot pumpkin_weight = [1, 1, 1, 3, 3, 8] print "均值：", thinkstats.Mean(pumpkin_weight) print "方差：", thinkstats.Var(pumpkin_weight) print "标准差：", math.sqrt(thinkstats.Var(pumpkin_weight)) hist = Pmf.MakeHistFromList(pumpkin_weight) # 返回众数 mode = sorted(hist.Values())[0] print "众数为：%d 频数为：%d" % (mode, hist.Freq(mode)) # 绘制直方图 vals, freqs = hist.Render() rectangles = pyplot.bar(vals, freqs) pyplot.show()
