def MakeFigures(df):
"""Make scatterplots.
"""
sample = thinkstats2.SampleRows(df, 5000)
# simple scatter plot
thinkplot.PrePlot(cols=2)
heights, weights = GetHeightWeight(sample)
ScatterPlot(heights, weights)
# scatter plot with jitter
thinkplot.SubPlot(2)
heights, weights = GetHeightWeight(sample, hjitter=1.3, wjitter=0.5)
ScatterPlot(heights, weights)
thinkplot.Save(root='scatter1')
# with jitter and transparency
thinkplot.PrePlot(cols=2)
ScatterPlot(heights, weights, alpha=0.1)
# hexbin plot
thinkplot.SubPlot(2)
heights, weights = GetHeightWeight(df, hjitter=1.3, wjitter=0.5)
HexBin(heights, weights)
thinkplot.Save(root='scatter2')
def PlotArrivalDepartureDelayFit(flights):
"""Plots a scatter plot and fitted curve.
live: DataFrame
"""
sample = thinkstats2.SampleRows(flights, 1000)
arrivalDelays = sample.ARRIVAL_DELAY
departureDelays = sample.DEPARTURE_DELAY
inter, slope = thinkstats2.LeastSquares(arrivalDelays, departureDelays)
fit_xs, fit_ys = thinkstats2.FitLine(arrivalDelays, inter, slope)
thinkplot.Scatter(arrivalDelays, departureDelays, color='gray', alpha=0.1)
thinkplot.Plot(fit_xs, fit_ys, color='white', linewidth=3)
thinkplot.Plot(fit_xs, fit_ys, color='blue', linewidth=2)
thinkplot.Save(
root='ArrivalDepartureDelayFit_linear1',
xlabel='arrival delay (min)',
ylabel='departure delay (min)',
# axis=[10, 45, 0, 15],
legend=False)
formula = 'DEPARTURE_DELAY ~ ARRIVAL_DELAY'
model = smf.ols(formula, data=sample)
results = model.fit()
regression.SummarizeResults(results)
def MakeArrivalDepartureDelayScatterPlots(flights):
"""Make scatterplots.
"""
sample = thinkstats2.SampleRows(flights, 10000)
# simple scatter plot
thinkplot.PrePlot(cols=2)
# departureDelays, arrivalDelays = GetArrivalDepartureDelay(sample)
# airports = sample.AIRLINE
# arrivalDelays = sample.ARRIVAL_DELAY
# ScatterPlot(airports, arrivalDelays)
# scatter plot with jitter
# thinkplot.SubPlot(2)
departureDelays, arrivalDelays = GetArrivalDepartureDelay(sample,
hjitter=1.3,
wjitter=0.5)
thinkplot.Scatter(arrivalDelays, departureDelays, alpha=1)
thinkplot.Config(
xlabel='arrival delay (min)',
ylabel='departure delay (min)',
# axis=[-20, 20, 20, 200],
legend=False)
thinkplot.Save(root='ArrivalDepartureDelayScatterplot')
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 ResampleRows(df):
"""Resamples rows from a DataFrame.
df: DataFrame
returns: DataFrame
"""
return thinkstats2.SampleRows(df, len(df), replace=True)
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
# compare total time spent between males and females (chi-squared)
data = male_ds.Daily_Time_Spent.values, female_ds.Daily_Time_Spent.values
ht = Totaltimespent(data)
p4 = ht.PValue(iters=iters)
print('\nn\tp1\tp2\tp3\tp4' )
print('%d\t%0.2f\t%0.2f\t%0.2f\t%0.2f' % (n, p1, p2, p3, p4))
RunResampleTest(male_ds, female_ds)
print('\nn-number of sample records\np1-p-value for total time spent on site\np2-p value for daily internet usage\np3-correlation pvalue \np4-Chi-squared p-value')
n = len(advertisement_data)
for _ in range(8):
sample = thinkstats2.SampleRows(advertisement_data, n)
RunTests(sample)
n //= 2
#########################################################################################################
############################# Section 6 -Multiple Regression Model #####################################
#########################################################################################################
# Build and run a regression model with one dependent variable and multiple explanatory variables
ht = hypothesis.DiffMeansOneSided(data)
p2 = ht.PValue(iters=iters)
data = firsts_n.totalwgt_lb.values, others_n.totalwgt_lb.values
ht = hypothesis.DiffMeansPermute(data)
p3 = ht.PValue(iters=iters)
data = df.agepreg.values, df.totalwgt_lb.values
ht = hypothesis.CorrelationPermute(data)
p4 = ht.PValue(iters=iters)
data = firsts_n.prglngth.values, others_n.prglngth.values
ht = hypothesis.PregLengthTest(data)
p5 = ht.PValue(iters=iters)
data = firsts_n.totalwgt_lb.values, others_n.totalwgt_lb.values
ht = hypothesis.PregLengthTest(data)
p6 = ht.PValue(iters=iters)
print('%d\t%.2f\t%.2f\t%.2f\t%.2f\t%.2f\t%.2f\n' %
(n, p1, p2, p3, p4, p5, p6))
live, firsts, others = first.MakeFrames()
n = len(live)
for _ in range(8):
live_n = thinkstats2.SampleRows(live, n)
RunTests(live_n, 5000)
n //= 2
live, firsts, others = nsfg2.MakeFrames()
## test difference in pregnancy lengths
data_length = firsts.prglngth.values, others.prglngth.values
ht = DiffMeansPermute(data_length)
pvalue = ht.PValue()
print('pvalue:\n', pvalue)
ht.PlotCdf()
thinkplot.Show(xlabel='test statistic', ylabel='CDF')
## evaluate p value vs. sample size
ns = np.logspace(2, 12, num=50, base=2, dtype=int)
pvalues = []
for n in ns:
firsts_sub = thinkstats2.SampleRows(firsts, n)
others_sub = thinkstats2.SampleRows(others, n)
data = firsts_sub.prglngth.values, others_sub.prglngth.values
ht = DiffMeansPermute(data)
pvalue = ht.PValue()
pvalues.append(pvalue)
print('sample size: %d \npvalue: %f\n' % (n, pvalue))
thinkplot.Plot(ns, pvalues, '.')
thinkplot.axhline(0.05)
thinkplot.Show(xlabel='sample size', ylabel='p values')
## test difference in pregnancy lengths with resampling
data_length = firsts.prglngth.values, others.prglngth.values
ht = DiffMeansResample(data_length)
# Clara Garcia-Sanchez # 12/08/2020 ################################# DO NOT CHANGE ##################################### # some_file.py import sys # insert at 1, 0 is the script path (or '' in REPL) sys.path.insert(1, '../common_functions/') import numpy as np # import matplotlib.pyplot as plt # import pandas as pd # import thinkstats2 import brfss from scipy import stats ##################################################################################### df = brfss.ReadBrfss(nrows=None) sample = thinkstats2.SampleRows(df, 5000) heights, weights = sample.htm3, sample.wtkg2 print(heights)