def MakeHists(live):
"""Plot Hists for live births
live: DataFrame
others: DataFrame
"""
hist = mystats.Hist(live.birthwgt_lb, label="birthwgt_lb")
myplots.Hist(hist)
myplots.Save(root="first_wgt_lb_hist",
xlabel="pounds",
ylabel="frequency",
axis=[-1, 14, 0, 3200])
hist = mystats.Hist(live.birthwgt_oz, label="birthwgt_oz")
myplots.Hist(hist)
myplots.Save(root="first_wgt_oz_hist",
xlabel="ounces",
ylabel="frequency",
axis=[-1, 16, 0, 1200])
hist = mystats.Hist(np.floor(live.agepreg), label="agepreg")
myplots.Hist(hist)
myplots.Save(root="first_agepreg_hist", xlabel="years", ylabel="frequency")
hist = mystats.Hist(live.prglngth, label="prglngth")
myplots.Hist(hist)
myplots.Save(root="first_prglngth_hist",
xlabel="weeks",
ylabel="frequency",
axis=[-1, 53, 0, 5000])
def RunTests(data, iters=1000):
# test the difference in means
ht = DiffMeansPermute(data)
p_value = ht.PValue(iters=iters)
print("\nmeans permute two-sided")
PrintTest(p_value, ht)
ht.PlotCdf()
myplots.Save(
root="hypothesis1",
title="Permutation test",
xlabel="difference in means (weeks)",
ylabel="CDF",
legend=False,
)
# test the difference in means one-sided
ht = DiffMeansOneSided(data)
p_value = ht.PValue(iters=iters)
print("\nmeans permute one-sided")
PrintTest(p_value, ht)
# test the difference in std
ht = DiffStdPermute(data)
p_value = ht.PValue(iters=iters)
print("\nstd permute one-sided")
PrintTest(p_value, ht)
def MakePdfExample(n=500):
# mean and var of women's heights in cm, from the BRFSS
mean, var = 163, 52.8
std = math.sqrt(var)
print(PDF(mean + std, mean, std))
plotPDF(mean, std, n=n, label="normal")
myplots.Save(root="pdf_example", xlabel="Height (cm)", ylabel="Density")
def MakeFigures(df):
sample = mystats.SampleRows(df, 5000)
# simple scatter plot
myplots.PrePlot(cols=2)
heights, weights = GetHeightWeight(sample)
ScatterPlot(heights, weights)
# scatter plot with jitter
myplots.SubPlot(2)
heights, weights = GetHeightWeight(sample, hjitter=1.3, wjitter=0.5)
ScatterPlot(heights, weights)
myplots.Save(root="scatter1")
# with jitter and transparency
myplots.PrePlot(cols=2)
ScatterPlot(heights, weights, alpha=0.1)
# hexbin plot
myplots.SubPlot(2)
heights, weights = GetHeightWeight(df, hjitter=1.3, wjitter=0.5)
HexBin(heights, weights)
myplots.Save(root="scatter2")
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])
def BinnedPercentiles(df):
cdf = mystats.Cdf(df.htm3)
print("Fraction between 140 and 200 cm", cdf[200] - cdf[140])
bins = np.arange(135, 210, 5)
indices = np.digitize(df.htm3, bins)
groups = df.groupby(indices)
heights = [group.htm3.mean() for i, group in groups][1:-1]
cdfs = [mystats.Cdf(group.wtkg2) for i, group in groups][1:-1]
myplots.PrePlot(3)
for percent in [75, 50, 25]:
weights = [cdf.Percentile(percent) for cdf in cdfs]
label = "%dth" % percent
myplots.Plot(heights, weights, label=label)
myplots.Save(root="scatter3", xlabel="height (cm)", ylabel="weight (kg)")
def PrintExtremes(live):
"""Plots the histogram of pregnancy lengths and prints the extremes.
live: DataFrame of live births
"""
hist = mystats.Hist(live.prglngth)
myplots.Hist(hist, label="live births")
myplots.Save(root="first_nsfg_hist_live",
title="Histogram",
xlabel="weeks",
ylabel="frequency")
print("Shortest lengths:")
for weeks, freq in hist.Smallest(10):
print(weeks, freq)
print("Longest lengths:")
for weeks, freq in hist.Largest(10):
print(weeks, freq)
def MakeComparison(firsts, others):
"""Plots histograms of pregnancy length for first babies and others.
firsts: DataFrame
others: DataFrame
"""
first_hist = mystats.Hist(firsts.prglngth, label="first")
other_hist = mystats.Hist(others.prglngth, label="other")
width = 0.45
myplots.PrePlot(2)
myplots.Hist(first_hist, align="right", width=width)
myplots.Hist(other_hist, align="left", width=width)
myplots.Save(
root="first_nsfg_hist",
title="Histogram",
xlabel="weeks",
ylabel="frequency",
axis=[27, 46, 0, 2700],
)
def SimulateSample(mu=90, sigma=7.5, n=9, m=1000):
def VertLine(x, y=1):
myplots.Plot([x, x], [0, y], color="0.8", linewidth=3)
means = []
for _ in range(m):
xs = np.random.normal(mu, sigma, n)
xbar = np.mean(xs)
means.append(xbar)
stderr = RMSE(means, mu)
print("standard error", stderr)
cdf = mystats.Cdf(means)
ci = cdf.Percentile(5), cdf.Percentile(95)
print("confidence interval", ci)
VertLine(ci[0])
VertLine(ci[1])
# plot the CDF
myplots.Cdf(cdf)
myplots.Save(root="estimation1",
xlabel="sample mean",
ylabel="CDF",
title="Sampling distribution")