def main():
df = hinc.ReadData()
log_sample = InterpolateSample(df, log_upper=6.0)
log_cdf = thinkstats2.Cdf(log_sample)
print("median", thinkstats2.Median(log_sample))
print("pearson's median skewness",
thinkstats2.PearsonMedianSkewness(log_sample))
print("skewness", thinkstats2.Skewness(log_sample))
print("mean", log_cdf.Mean())
print(
"the higher our log_upper, the more right-skewed (according to g_1) or at least less left-skewed (according to g_p) things get"
)
print("the mean moves to the right a bit, too.")
print("proportion of the population with income < mean",
log_cdf.Prob(log_cdf.Mean()))
print(
"the higher the upper bound, the greater the proprtion below the mean."
)
thinkplot.Cdf(log_cdf)
thinkplot.Show(xlabel='household income', ylabel='CDF')
def main():
df = hinc.ReadData()
log_sample = InterpolateSample(df, log_upper=6.0)
log_cdf = thinkstats2.Cdf(log_sample)
thinkplot.Cdf(log_cdf)
thinkplot.Show(xlabel='household income', ylabel='CDF')
def main():
df = hinc.ReadData()
log_sample = InterpolateSample(df, log_upper=6.0)
log_cdf = thinkstats2.Cdf(log_sample)
thinkplot.Cdf(log_cdf)
thinkplot.Show(xlabel='household income', ylabel='CDF')
sample = np.power(10, log_sample)
mean, median = density.Summarize(sample)
cdf = thinkstats2.Cdf(sample)
print('cdf[mean]', cdf[mean])
pdf = thinkstats2.EstimatedPdf(sample)
thinkplot.Pdf(pdf)
thinkplot.Show(xlabel='household income', ylabel='PDF')
def main():
df = hinc.ReadData()
log_sample = InterpolateSample(df, log_upper=6.0)
log_cdf = thinkstats2.Cdf(log_sample)
thinkplot.Cdf(log_cdf)
thinkplot.Show(xlabel='household income', ylabel='CDF')
sample = np.power(10, log_sample)
mean = np.mean(sample)
cdf = thinkstats2.Cdf(sample)
print "Median:", np.median(sample)
print "Mean:", mean
print "Skewness:", thinkstats2.Skewness(sample)
print "Pearson's Skewness:", thinkstats2.PearsonMedianSkewness(sample)
print "Percent of people with incomes <= mean:", cdf[mean]
pdf = thinkstats2.EstimatedPdf(sample)
thinkplot.Pdf(pdf)
import hinc
import hinc2
import thinkstats2
import thinkplot
import numpy as np
df = hinc.ReadData()
def describe_inc_dist(log_upper):
log_sample = hinc2.InterpolateSample(df, log_upper=j)
incomes = np.power(10, log_sample)
inc_mean = thinkstats2.Mean(incomes)
inc_med = thinkstats2.Median(incomes)
inc_skew = thinkstats2.Skewness(incomes)
inc_pearskew = thinkstats2.PearsonMedianSkewness(incomes)
print('log_upper = ', j)
print('Mean Income: ', inc_mean)
print('Median Income: ', inc_med)
print('Skewness: ', inc_skew)
print('Pearson Median Skewness: ', inc_pearskew)
cdf = thinkstats2.Cdf(incomes)
inc_below_mean = cdf.Prob(inc_mean)
print('Pct. below mean: ', inc_below_mean)
print('\n')
for j in [6.0, 7.0, 8.0]:
describe_inc_dist(log_upper=j)
def main():
df = hinc.ReadData()
MakeFigures(df)
df.loc[41, 'log_upper'] = log_upper
# use the freq column to generate the right number of values in
# each range
arrays = []
for _, row in df.iterrows():
vals = np.linspace(row.log_lower, row.log_upper, row.freq)
arrays.append(vals)
# collect the arrays into a single sample
log_sample = np.concatenate(arrays)
return log_sample
# get data
import hinc
income_df = hinc.ReadData()
log_sample = InterpolateSample(income_df, log_upper=6.0)
log_cdf = thinkstats2.Cdf(log_sample)
thinkplot.Cdf(log_cdf)
thinkplot.Config(xlabel='Household income (log $)',
ylabel='CDF')
# RESULTS: plot
sample = np.power(10, log_sample)
cdf = thinkstats2.Cdf(sample)
thinkplot.Cdf(cdf)
thinkplot.Config(xlabel='Household income ($)',
ylabel='CDF')
def RunModel(self):
"""
Goal: Use resampling to simulate test data
Output: Simulated data
"""
group1 = np.random.choice(self.pool, self.n, replace=True)
group2 = np.random.choice(self.pool, self.m, replace=True)
data = group1, group2
return data
preg = nsfg.ReadFemPreg()
live = preg[preg["outcome"] == 1]
resp = nsfg.ReadFemResp()
bs = brfss.ReadBrfss()
income = hinc.ReadData()
log_intp_income = hinc2.InterpolateSample(income, log_upper=6.0)
# Q1. Think Stats Chapter 2 Exercise 4 (effect size of Cohen's d)
first_wt = live.loc[preg["birthord"] == 1, "totalwgt_lb"]
other_wt = live.loc[preg["birthord"] != 1, "totalwgt_lb"]
ts.CohenEffectSize(first_wt, other_wt)
# Q2. Think Stats Chapter 3 Exercise 1 (actual vs. biased)
d = np.diff(np.unique(resp["numkdhh"])).min()
left_of_first_bin = resp["numkdhh"].min() - float(d) / 2
right_of_last_bin = resp["numkdhh"].max() + float(d) / 2
plt.clf()
plt.hist(resp["numkdhh"],
bins=np.arange(left_of_first_bin, right_of_last_bin + d, d),
histtype="step",
