def main(script):
"""Tests the functions in this module.
script: string script name
"""
live, firsts, others = first.MakeFrames()
hist = thinkstats2.Hist(live.prglngth)
# test weight_comparison
weight_comparison(live, firsts, others)
preg_length_comparison(live, firsts, others)
# test Mode
mode = Mode(hist)
print('Mode of preg length', mode)
assert mode == 39, mode
# test AllModes
modes = AllModes(hist)
assert modes[0][1] == 4693, modes[0][1]
for value, freq in modes[:5]:
print(value, freq)
print('%s: All tests passed.' % script)
def main(script):
"""Tests the functions in this module.
script: string script name
"""
live, firsts, others = first.MakeFrames()
hist = thinkstats2.Hist(live.prglngth)
# test Mode
mode = Mode(hist)
print('Mode of preg length', mode)
assert mode == 39, mode
# test AllModes
modes = AllModes(hist)
assert modes[0][1] == 4693, modes[0][1]
for value, freq in modes[:5]:
print(value, freq)
firsts_wgt = firsts.totalwgt_lb.mean()
others_wgt = others.totalwgt_lb.mean()
print("firsts = {} pounds, others = {} pounds, dif = {} pounds ".format(
firsts_wgt, others_wgt, firsts_wgt - others_wgt))
d = thinkstats2.CohenEffectSize(firsts.totalwgt_lb, others.totalwgt_lb)
print(d)
print('%s: All tests passed.' % script)
def main(script):
"""Tests the functions in this module.
script: string script name
"""
live, firsts, others = first.MakeFrames()
hist = thinkstats2.Hist(live.prglngth)
# test Mode
mode = Mode(hist)
print('Mode of preg length', mode)
assert(mode == 39)
# test AllModes
modes = AllModes(hist)
assert(modes[0][1] == 4693)
for value, freq in modes[:5]:
print(value, freq)
d1 = WeightDifferences(firsts, others, live)
print("Cohens'd Effect of weight differences:", d1)
d2 = PregnancyLengthDifferences(firsts, others)
print("Cohens'd Effect of pregnancy length differences:", d2)
print('%s: All tests passed.' % script)
def main(script):
"""Tests the functions in this module.
script: string script name
"""
live, firsts, others = first.MakeFrames()
pmf = thinkstats2.Pmf(live.prglngth)
# test Mode
mean = PmfMean(pmf)
print('Mean of preg length', mean)
assert mean == pmf.Mean(), mean
variance = PmfVar(pmf)
print('Variance of preg length', variance)
assert variance == pmf.Var(), variance
# test AllModes
# modes = AllModes(hist)
# assert modes[0][1] == 4693, modes[0][1]
# for value, freq in modes[:5]:
# print(value, freq)
print('%s: All tests passed.' % script)
def main():
thinkstats2.RandomSeed(18)
live, firsts, others = first.MakeFrames()
n = len(live)
for _ in range(7):
sample = thinkstats2.SampleRows(live, n)
RunTests(sample)
n //= 2
def main():
live, firsts, others = first.MakeFrames()
diffs = PairwiseDiff(live)
mean = thinkstats2.Mean(diffs)
print('Mean: ', mean)
pmf = thinkstats2.Pmf(diffs)
thinkplot.Hist(pmf)
thinkplot.Show(xlabel='Diff in wks', ylabel='PMF')
def main(name, data_dir=''):
thinkstats2.RandomSeed(17)
MakeExample()
live, firsts, others = first.MakeFrames()
RandomFigure(live)
TestSample(live)
MakeCdf(live)
MakeFigures(live, firsts, others)
def main():
thinkstats2.RandomSeed(17)
live, firsts, others = first.MakeFrames()
PlotAdultWeights(live)
PlotPregLengths(live, firsts, others)
TestIntervention()
def main():
thinkstats2.RandomSeed(17)
live, _, _ = first.MakeFrames()
EstimateBirthWeight(live)
live = live.dropna(subset=['agepreg', 'totalwgt_lb'])
PlotSamplingDistributions(live)
PlotFit(live)
PlotResiduals(live)
def main():
#random seed saves the random samples
thinkstats2.RandomSeed(23)
live, firsts, others = first.MakeFrames()
RunResampleTest(firsts, others)
n = len(live)
for _ in range(7):
sample = thinkstats2.SampleRows(live, n)
RunTests(sample)
n //= 2
def main(name, data_dir='.'):
thinkstats2.RandomSeed(17)
LogisticRegressionExample()
live, firsts, others = first.MakeFrames()
live['isfirst'] = (live.birthord == 1)
RunLogisticModels(live)
RunSimpleRegression(live)
RunModels(live)
PredictBirthWeight(live)
def main(script):
thinkstats2.RandomSeed(17)
live, firsts, others = first.MakeFrames()
live = live.dropna(subset=['agepreg', 'totalwgt_lb'])
BinnedPercentiles(live)
ages = live.agepreg
weights = live.totalwgt_lb
print('thinkstats2 Corr', thinkstats2.Corr(ages, weights))
print('thinkstats2 SpearmanCorr', thinkstats2.SpearmanCorr(ages, weights))
ScatterPlot(ages, weights, alpha=0.1)
thinkplot.Save(root='chap07scatter1', legend=False, formats=['jpg'])
def main(script):
random.seed(100)
np.random.seed(100)
# run the coin test
ct = CoinTest((140, 110))
pvalue = ct.PValue()
print("coin test p-value", pvalue)
# compare pregnancy lengths
print("\nprglngth")
live, firsts, others = first.MakeFrames()
data = firsts.prglngth.values, others.prglngth.values
RunTests(data)
# compare birth weights
print("\nbirth weight")
data = (firsts.totalwgt_lb.dropna().values,
others.totalwgt_lb.dropna().values)
ht = DiffMeansPermute(data)
p_value = ht.PValue(iters=1000)
print("means permute two-sided")
PrintTest(p_value, ht)
# test correlation
live2 = live.dropna(subset=["agepreg", "totalwgt_lb"])
data = live2.agepreg.values, live2.totalwgt_lb.values
ht = CorrelationPermute(data)
p_value = ht.PValue()
print("\nage weight correlation")
print("n=", len(live2))
PrintTest(p_value, ht)
# run the dice test
RunDiceTest()
# compare pregnancy lengths (chi-squared)
data = firsts.prglngth.values, others.prglngth.values
ht = PregLengthTest(data)
p_value = ht.PValue()
print("\npregnancy length chi-squared")
PrintTest(p_value, ht)
# compute the false negative rate for difference in pregnancy length
data = firsts.prglngth.values, others.prglngth.values
neg_rate = FalseNegRate(data)
print("false neg rate", neg_rate)
# run the tests with new nsfg data
ReplicateTests()
def main():
thinkstats2.RandomSeed(17)
# run the coin test
ct = CoinTest((140, 110))
pvalue = ct.PValue()
print('coin test p-value', pvalue)
# compare pregnancy lengths
print('\nprglngth')
live, firsts, others = first.MakeFrames()
data = firsts.prglngth.values, others.prglngth.values
RunTests(data)
# compare birth weights
print('\nbirth weight')
data = (firsts.totalwgt_lb.dropna().values,
others.totalwgt_lb.dropna().values)
ht = DiffMeansPermute(data)
p_value = ht.PValue(iters=1000)
print('means permute two-sided')
PrintTest(p_value, ht)
# test correlation
live2 = live.dropna(subset=['agepreg', 'totalwgt_lb'])
data = live2.agepreg.values, live2.totalwgt_lb.values
ht = CorrelationPermute(data)
p_value = ht.PValue()
print('\nage weight correlation')
print('n=', len(live2))
PrintTest(p_value, ht)
# run the dice test
RunDiceTest()
# compare pregnancy lengths (chi-squared)
data = firsts.prglngth.values, others.prglngth.values
ht = PregLengthTest(data)
p_value = ht.PValue()
print('\npregnancy length chi-squared')
PrintTest(p_value, ht)
# compute the false negative rate for difference in pregnancy length
data = firsts.prglngth.values, others.prglngth.values
neg_rate = FalseNegRate(data)
print('false neg rate', neg_rate)
# run the tests with new nsfg data
ReplicateTests()
def main():
thinkstats2.RandomSeed(17)
MakeCltPlots()
print('Gorilla example')
dist = Normal(90, 7.5**2)
print(dist)
dist_xbar = dist.Sum(9) / 9
print(dist_xbar.sigma)
print(dist_xbar.Percentile(5), dist_xbar.Percentile(95))
live, firsts, others = first.MakeFrames()
TestCorrelation(live)
PlotPregLengths(live, firsts, others)
TestChiSquared()
def main(script):
"""Tests the functions in this module.
script: string script name
"""
live, firsts, others = first.MakeFrames()
# test PmfMean and PmfVar function we created
prglngth = live.prglngth
pmf = thinkstats2.Pmf(prglngth)
mean = PmfMean(pmf)
var = PmfVar(pmf, mean)
assert (mean == pmf.Mean())
assert (var == pmf.Var())
print('mean/var preg length', mean, var)
print('%s: All tests passed.' % script)
def main():
thinkstats2.RandomSeed(17)
# get the data
live, firsts, others = first.MakeFrames()
mean_var = thinkstats2.MeanVar(live.prglngth)
print('(Mean, Var) of prglength for live births', mean_var)
data = firsts.prglngth.values, others.prglngth.values
# test the difference in means
ht = DiffMeansPermute(data)
p_value = ht.PValue(iters=1000)
print('p-value =', p_value)
ht.PlotCdf()
thinkplot.Save(root='hypothesis1',
title='Permutation test',
xlabel='difference in means (weeks)',
ylabel='CDF',
legend=False)
# test the difference in std
ht = DiffStdPermute(data)
p_value = ht.PValue(iters=1000)
print('p-value =', p_value)
ht.PlotCdf()
thinkplot.Save(root='hypothesis2',
title='Permutation test',
xlabel='difference in std (weeks)',
ylabel='CDF',
legend=False)
# test the difference in means by resampling
ht = DiffStdPermute(data)
p_value = ht.PValue(iters=1000)
print('p-value =', p_value)
ht.PlotCdf()
thinkplot.Save(root='hypothesis3',
title='Resampling test',
xlabel='difference in means (weeks)',
ylabel='CDF',
legend=False)
def ComputeSkewnesses():
"""Plots KDE of birthweight and adult weight.
"""
def VertLine(x, y):
thinkplot.Plot([x, x], [0, y], color='0.6', linewidth=1)
live, firsts, others = first.MakeFrames()
data = live.totalwgt_lb.dropna()
print('Birth weight')
mean, median = Summarize(data)
y = 0.35
VertLine(mean, y)
thinkplot.Text(mean - 0.15, 0.1 * y, 'mean', horizontalalignment='right')
VertLine(median, y)
thinkplot.Text(median + 0.1, 0.1 * y, 'median', horizontalalignment='left')
pdf = thinkstats2.EstimatedPdf(data)
thinkplot.Pdf(pdf, label='birth weight')
thinkplot.Save(root='density_totalwgt_kde', xlabel='lbs', ylabel='PDF')
df = brfss.ReadBrfss(nrows=None)
data = df.wtkg2.dropna()
print('Adult weight')
mean, median = Summarize(data)
y = 0.02499
VertLine(mean, y)
thinkplot.Text(mean + 1, 0.1 * y, 'mean', horizontalalignment='left')
VertLine(median, y)
thinkplot.Text(median - 1.5,
0.1 * y,
'median',
horizontalalignment='right')
pdf = thinkstats2.EstimatedPdf(data)
thinkplot.Pdf(pdf, label='adult weight')
thinkplot.Save(root='density_wtkg2_kde',
xlabel='kg',
ylabel='PDF',
xlim=[0, 200])
def main(script):
"""Tests the functions in this module.
script: string script name
"""
live, firsts, others = first.MakeFrames()
hist = thinkstats2.Hist(live.prglngth)
mean1 = firsts.totalwgt_lb.mean()
mean2 = others.totalwgt_lb.mean()
var1 = firsts.totalwgt_lb.var()
var2 = others.totalwgt_lb.var()
print('Mean Weight')
print('First babies', mean1)
print('Others babies', mean2)
print('Variance in Weight')
print('First babies', var1)
print('Others babies', var2)
print('Difference in lbs', mean1 - mean2)
cohen_d = thinkstats2.CohenEffectSize(firsts.totalwgt_lb,
others.totalwgt_lb)
print('Cohen d', cohen_d)
# test Mode
mode = Mode(hist)
print('Mode of preg length', mode)
assert mode == 39, mode
# test AllModes
modes = AllModes(hist)
assert modes[0][1] == 4693, modes[0][1]
for value, freq in modes[:5]:
print(value, freq)
print('%s: All tests passed.' % script)
def main(script):
"""Tests the functions in this module.
script: string script name
"""
live, firsts, others = first.MakeFrames()
# test PmfMean and PmfVar
prglngth = live.prglngth
pmf = thinkstats2.Pmf(prglngth)
mean = PmfMean(pmf)
var = PmfVar(pmf)
assert (mean == pmf.Mean())
assert (var == pmf.Var())
print('# capture the mean value')
print('Mean Value length', mean)
print('# capture the var value')
print('Var Value length', var)
print('# capture the mean/ preg length value')
print('mean/var preg length', mean, var)
print('%s: All tests passed.' % script)
def main(script):
"""Tests the functions in this module.
script: string script name
"""
live, firsts, others = first.MakeFrames()
hist = thinkstats2.Hist(live.prglngth)
# explore the weight difference between first babies and others
WeightDifference(live, firsts, others)
# test Mode
mode = Mode(hist)
print('Mode of preg length', mode)
assert(mode == 39)
# test AllModes
modes = AllModes(hist)
assert(modes[0][1] == 4693)
for value, freq in modes[:5]:ies
print(value, freq)
def main(script):
"""Tests the functions in this module.
script: string script name
"""
live, firsts, others = first.MakeFrames()
hist = thinkstats2.Hist(live.prglngth)
# test Mode
mode = Mode(hist)
print('Mode of preg length', mode)
assert (mode == 39)
# test AllModes
modes = AllModes(hist)
print(modes)
assert (modes[0][1] == 4693)
for value, freq in modes[:5]:
print(value, freq)
print('%s: All tests passed.' % script)
print("Cohen's d:", cohen_d(firsts.totalwgt_lb, others.totalwgt_lb))
def ComputeSkewnesses():
def VertLine(x, y):
myplots.Plot([x, x], [0, y], color="0.6", linewidth=1)
live, firsts, others = first.MakeFrames()
data = live.totalwgt_lb.dropna()
print("Birth weight")
mean, median = Summarize(data)
y = 0.35
VertLine(mean, y)
myplots.Text(mean - 0.15, 0.1 * y, "mean", horizontalalignment="right")
VertLine(median, y)
myplots.Text(median + 0.1, 0.1 * y, "median", horizontalalignment="left")
pdf = mystats.EstimatedPdf(data)
myplots.Pdf(pdf, label="birth weight")
myplots.Save(root="density_totalwgt_kde", xlabel="lbs", ylabel="PDF")
df = brfss.ReadBrfss(nrows=None)
data = df.wtkg2.dropna()
print("Adult weight")
mean, median = Summarize(data)
y = 0.02499
VertLine(mean, y)
myplots.Text(mean + 1, 0.1 * y, "mean", horizontalalignment="left")
VertLine(median, y)
myplots.Text(median - 1.5, 0.1 * y, "median", horizontalalignment="right")
pdf = mystats.EstimatedPdf(data)
myplots.Pdf(pdf, label="adult weight")
myplots.Save(root="density_wtkg2_kde",
xlabel="kg",
ylabel="PDF",
xlim=[0, 200])
[Think Stats Chapter 7 Exercise 1](http://greenteapress.com/thinkstats2/html/thinkstats2008.html#toc70) (weight vs. age)
# imports
from __future__ import print_function, division
%matplotlib inline
import numpy as np
import thinkstats2
import thinkplot
# get data
import first
live, firsts, others = first.MakeFrames()
live = live.dropna(subset=['agepreg', 'totalwgt_lb'])
ages = live.agepreg
weights = live.totalwgt_lb
# make a scatter plot of birth weight versus mother’s age
thinkplot.Scatter(ages, weights, alpha=1, s=10)
thinkplot.Config(xlabel='Age (years)',
ylabel='Weight (lbs)',
xlim=[10, 45],
ylim=[0, 15],
legend=False)
# RESULTS: messy plot
# Plot percentiles of birth weight versus mother’s age
bins = np.arange(10, 45, 5)
indices = np.digitize(live.agepreg, bins)
groups = live.groupby(indices)
# binned mother's age
def COHEN(Frame1, Frame2):
CD = (Frame1.mean() - Frame2.mean())
SD = ((Frame1.std()**2 + Frame2.std()**2) / 2)**.5
CD = CD / SD
return CD
import thinkstats2, first
live, firsts, others = first.MakeFrames(
) #Gets data from dataframe python. taken from solutions obvs
TotalW = live.totalwgt_lb
FirstW = firsts.totalwgt_lb
OtherW = others.totalwgt_lb
MyCohen = COHEN(FirstW, OtherW)
NotMyCohen = thinkstats2.CohenEffectSize(FirstW, OtherW)
FirstPMean = firsts.prglngth.mean()
OtherPMean = others.prglngth.mean()
print("the mean weight of first babies is " + str(FirstW.mean()) + " lbs")
print("the mean weight of other babies is " + str(OtherW.mean()) + " lbs")
print("the Cohen's d between the two sets is " + str(MyCohen))
print("the mean pregnancy length of first babies was " + str(FirstPMean) +
" weeks")
print("the mean pregnancy length of other babies was " + str(OtherPMean) +
" weeks")
print("the difference between the pregnancy lengths was " +
str(FirstPMean - OtherPMean))
def main(script):
live, firsts, others = first.MakeFrames()
make_figures(firsts, others)
make_hists(live)
class_sizes()
import thinkplot
def Diffs(t):
first = t[0]
rest = t[1:]
diffs = [first - x for x in rest]
return diffs
def PairWiseDifference(live):
live = live[live.prglngth >= 37]
preg_map = nsfg.MakePregMap(live)
diffs = []
for caseid, indicies in preg_map.items():
lengths = live.loc[indicies].prglngth.values
if len(lengths) >= 2:
diffs.extend(Diffs(lengths))
return diffs
if __name__ == '__main__':
live, first, other = first.MakeFrames()
diffs = PairWiseDifference(live)
mean = thinkstats2.Mean(diffs)
print('Mean difference between pairs', mean)
pmf = thinkstats2.Pmf(diffs)
thinkplot.Hist(pmf, align="center")
thinkplot.Show(xlabel='Difference in weeks', ylabel='PMF')
def main(script):
live, firsts, others = first.MakeFrames()
MakeFigures(firsts, others)
MakeHists(live)
ClassSizes()
def main(script):
live, firsts, others = first.MakeFrames()
Summarize(live, firsts, others)
MakeFigures(firsts, others)
