def PartitionRecords(table):
"""Divides records into two lists: first babies and others.
Only live births are included
Args:
table: pregnancy Table
"""
firsts = survey.Pregnancies()
others = survey.Pregnancies()
for p in table.records:
# skip non-live births
if p.outcome != 1:
continue
if p.birthord == 1:
firsts.AddRecord(p)
else:
others.AddRecord(p)
return firsts, others
def PoolRecords(*tables):
"""Construct a table with records from all tables.
Args:
constructor: init method used to make the new table
tables: any number of tables
Returns:
new table object
"""
pool = survey.Pregnancies()
for table in tables:
pool.ExtendRecords(table.records)
return pool
def main():
# Exercise 3.11
table = survey.Pregnancies()
table.ReadRecords()
unfilteredLiveBirthWeights = [(p.birthwgt_lb, p.birthwgt_oz)
for p in table.records if p.outcome == 1]
liveBirthWeights = [
lbs * 16 + oz for lbs, oz in unfilteredLiveBirthWeights
if type(lbs) == int and type(oz) == int and lbs * 16 + oz <= 200
]
liveBirthWeightsCdf = Cdf.MakeCdfFromList(liveBirthWeights,
name="live birth weights")
print('25th: %d 50th: %d 75th: %d interquartile range: %d' %
(liveBirthWeightsCdf.Value(.25), median(liveBirthWeightsCdf),
liveBirthWeightsCdf.Value(.75), interquartile(liveBirthWeightsCdf)))
def Summarize(data_dir):
"""Prints summary statistics for first babies and others.
Returns:
tuple of Tables
"""
table = survey.Pregnancies()
table.ReadRecords(data_dir)
# make a map from caseid to list of pairs
d = {}
for record in table.records:
# skip non-live births
if record.outcome != 1:
continue
# skip multiple births
if record.nbrnaliv > 1:
continue
pair = record.birthord, record.prglength
d.setdefault(record.caseid, []).append(pair)
print len(d)
# find all caseids with more than one live birth
pmf = Pmf()
for caseid, t in d.iteritems():
if len(t) <= 1:
continue
t.sort()
_, prglength1 = t[0]
_, prglength2 = t[1]
if prglength1 < 15 or prglength2 < 15:
continue
diff = prglength2 - prglength1
if abs(diff) > 15:
print caseid, prglength1, prglength2
pmf.Incr(diff)
pmf.Normalize()
return pmf
def PartitionBabies():
firsts, others, babies = [],[],[]
table = survey.Pregnancies()
table.ReadRecords('res')
for baby in table.records:
if baby.outcome != 1:
continue
data = (baby.prglength, baby.totalwgt_oz)
babies.append(data)
if baby.birthord == 1:
firsts.append(data)
else:
others.append(data)
return firsts, others, babies
def main(name, data_dir='.'):
table = survey.Pregnancies()
table.ReadRecords(data_dir)
print "Number of Pregnancies: ", len(table.records)
live_births = 0
tot_births = 0
first_babies = []
other_bablies = []
for record in table.records:
tot_births += 1
if record.outcome == 1:
live_births += 1
if record.birthord == 1:
first_babies.append(record)
else:
other_bablies.append(record)
print "live_births: ", live_births, " out of: ", tot_births, " records."
print "first_babies: ", len(first_babies)
print "other_bablies: ", len(other_bablies)
print thinkstats.Mean([1, 1, 1, 3, 3, 591])
def GetDurations(data_dir, keep_codes):
"""Reads pregnancy durations from NSFG data.
data_dir: location of the data file
"""
preg = survey.Pregnancies()
preg.ReadRecords(data_dir)
print 'Number of pregnancies', len(preg.records)
pmf = thinkstats2.Pmf()
for record in preg.records:
pmf.Incr(record.outcome)
pmf.Print()
durations = [
record.prglength for record in preg.records
if record.outcome in keep_codes
]
print 'Number of relevant pregnancies', len(durations)
return durations
def main():
# Exercise 3.9
table = survey.Pregnancies()
table.ReadRecords()
unfilteredLiveBirthWeights = [(p.birthwgt_lb, p.birthwgt_oz)
for p in table.records if p.outcome == 1]
liveBirthWeights = [
lbs * 16 + oz for lbs, oz in unfilteredLiveBirthWeights
if type(lbs) == int and type(oz) == int and lbs * 16 + oz <= 200
]
liveBirthWeightsCdf = Cdf.MakeCdfFromList(liveBirthWeights,
name="live birth weights")
samepleListLiveBirthWeights = sample(liveBirthWeightsCdf, 1000)
myplot.Cdf(Cdf.MakeCdfFromList(samepleListLiveBirthWeights))
myplot.show(title="CDF of live births resampled")
# Exercise 3.10
randomList = [random.random() for x in range(1000)]
myplot.Pmf(Pmf.MakePmfFromList(randomList))
myplot.show(title="random pmf")
myplot.Cdf(Cdf.MakeCdfFromList(randomList))
myplot.Show(title="random cdf")
def main():
table = survey.Pregnancies()
table.read_records()
# Calculate the first babies and other babies averages.
firsts, others = first.collect_live_births(table)
firsts_average, others_average = first.averages(firsts, others)
# Get the pregnancy lengths for first babies and others.
firsts_lengths = [r.prglength for r in firsts]
others_lengths = [r.prglength for r in others]
# Compute the variance for first babies.
firsts_var = thinkstats.variance(firsts_lengths, firsts_average)
# Compute the variance for other babies.
others_var = thinkstats.variance(others_lengths, others_average)
# Show standard deviations.
print 'Standard deviation for first gestations: {0}'.format(
math.sqrt(firsts_var))
print 'Standard deviation for other gestations: {0}'.format(
math.sqrt(others_var))
def testPregnancies(self):
preg = survey.Pregnancies()
preg.ReadRecords()
self.assertEquals(len(preg.records), 13593)
hist = MakeHist(preg, 'nbrnaliv')
self.assertEquals(hist.Freq(1), 8981)
hist = MakeHist(preg, 'babysex')
self.assertEquals(hist.Freq(1), 4641)
self.assertEquals(hist.Freq(2), 4500)
hist = MakeHist(preg, 'outcome')
self.assertEquals(hist.Freq(1), 9148)
hist = MakeHist(preg, 'birthord')
self.assertEquals(hist.Freq(1), 4413)
hist = MakeHist(preg, 'birthwgt_lb')
self.assertEquals(hist.Freq(6), 2223)
hist = MakeHist(preg, 'birthwgt_oz')
self.assertEquals(hist.Freq(6), 709)
hist = MakeHist(preg, 'agepreg')
self.assertEquals(hist.Freq('NA'), 352)
self.assertEquals(hist.Freq(25.0), 58)
hist = MakeHist(preg, 'totalwgt_oz')
self.assertEquals(hist.Freq('NA'), 4509)
hist = MakeHist(preg, 'finalwgt')
t = hist.Values()
low, high = min(t), max(t)
self.assertAlmostEquals(low, 118.656789706)
self.assertAlmostEquals(high, 261879.9538641)
def main():
table = survey.Pregnancies()
table.read_records()
print 'Number of pregnancies: {0}'.format(len(table.records))
# 2nd exercise
live = live_births(table)
print 'Live birhs: {0}'.format(live)
# 3rd exercise
firsts, others = collect_live_births(table)
print 'First babies: {0}'.format(len(firsts))
print 'Other babies: {0}'.format(len(others))
# 4th exercise
firsts_average, others_average = averages(firsts, others)
difference_days = (firsts_average - others_average) * 7.0
print 'Difference in days: {0}'.format(difference_days)
print 'Difference in hours: {0}'.format(difference_days * 24.0)
import survey table = survey.Pregnancies() table.ReadRecords() print 'Num of pregnancies', len(table)
def main(): table = survey.Pregnancies() table.ReadRecords() unfilteredLiveBirthWeights = [(p.birthwgt_lb, p.birthwgt_oz) for p in table.records if p.outcome == 1] liveBirthWeights = [lbs * 16 + oz for lbs, oz in unfilteredLiveBirthWeights if type(lbs) == int and type(oz) == int and lbs * 16 + oz <= 200] print(liveBirthWeights[0])
def MakeTables(data_dir='.'):
"""Reads survey data and returns tables for first babies and others."""
table = survey.Pregnancies()
table.ReadRecords(data_dir)
firsts, others = PartitionRecords(table)
return table, firsts, others
import survey
import Pmf
import matplotlib.pyplot as plt
import numpy as np
table = survey.Pregnancies()
table.readRecords(data_dir='data')
firsts_babies = survey.Pregnancies()
others_babies = survey.Pregnancies()
for r in table.records:
if r.outcome != 1:
continue
if r.birthord == 1:
firsts_babies.addRecord(r)
else:
others_babies.addRecord(r)
firsts_prglengths = [r.prglength for r in firsts_babies.records]
others_prglengths = [r.prglength for r in others_babies.records]
firts_hist = Pmf.Hist(firsts_prglengths)
others_hist = Pmf.Hist(others_prglengths)
times1, values1 = firts_hist.render()
times2, values2 = others_hist.render()
times2 = np.array(times2)
plt.bar(times1, values1, width=0.45)
plt.bar(times2 + 0.45, values2, width=0.45)
import survey
table = survey.Pregnancies()
table.ReadRecords()
firsts = survey.Pregnancies()
others = survey.Pregnancies()
for p in table.records:
if p.outcome != 1: continue
else:
if p.birthord == 1:
firsts.AddRecord(p)
else:
others.AddRecord(p)
print 'Number of first babies', len(firsts.records)
print 'Number of other babies', len(others.records)
def PoolRecords(*tables):
''' 合并数据表 '''
pool = survey.Pregnancies()
for table in tables:
pool.ExtendRecords(table.records)
return pool
def ReadPregnancyRecords():
"""Reads survey data and returns a table of records."""
table = survey.Pregnancies()
table.ReadRecords()
return table
#!/usr/bin/env python
import survey
import thinkstats
TABLE = survey.Pregnancies()
TABLE.ReadRecords()
def ex1_3_2():
"""Number of live births
"""
d = {'live': 0, 'death': 0}
for r in TABLE.records:
if r.outcome == 1:
d['live'] += 1
elif r.outcome == 2:
d['death'] += 1
return d
def ex1_3_3():
"""Number of live, first births vs. non-first
"""
d = {'first': 0, 'other': 0}
for r in TABLE.records:
if r.outcome == 1:
if r.birthord == 1:
d['first'] += 1
def makeTables(data_dir):
table = survey.Pregnancies()
table.readRecords(data_dir)
firsts, others = partitionRecords(table)
return table, firsts, others
import survey
import thinkstats
import math
pregnancies = survey.Pregnancies()
pregnancies.ReadRecords()
print 'Number of pregnancies', len(pregnancies.records)
print
preg_lengths_first = []
preg_lengths_others = []
for preg in pregnancies.records:
if preg.outcome != 1:
continue
if preg.birthord == 1:
preg_lengths_first.append(preg.prglength)
else:
preg_lengths_others.append(preg.prglength)
pregs_first = len(preg_lengths_first)
mean_length_first, var_length_first = thinkstats.MeanVar(preg_lengths_first)
std_length_first = math.sqrt(var_length_first)
pregs_others = len(preg_lengths_others)
mean_length_others, var_length_others = thinkstats.MeanVar(preg_lengths_others)
std_length_others = math.sqrt(var_length_others)
print 'Number of live births, first child', pregs_first
print 'Mean pregnancy length (weeks), first child', mean_length_first
print 'Variance of gestation time, first child', var_length_first