def GetArrivalDepartureDelay(flights, hjitter=0.0, wjitter=0.0):
"""Get sequences of airports and arrival delays.
df:
hjitter: float magnitude of random noise added to heights
wjitter: float magnitude of random noise added to weights
returns: tuple of sequences (airport, arrivaldelays)
"""
arrivalDelays = flights.ARRIVAL_DELAY
if hjitter:
arrivalDelays = thinkstats2.Jitter(arrivalDelays, hjitter)
departureDelays = flights.DEPARTURE_DELAY
if wjitter:
departureDelays = thinkstats2.Jitter(departureDelays, wjitter)
return arrivalDelays, departureDelays
def GetHeightWeight(df, hjitter=0.0, wjitter=0.0):
"""Get sequences of height and weight.
df: DataFrame with htm3 and wtkg2
hjitter: float magnitude of random noise added to heights
wjitter: float magnitude of random noise added to weights
returns: tuple of sequences (heights, weights)
"""
heights = df.htm3
if hjitter:
heights = thinkstats2.Jitter(heights, hjitter)
weights = df.wtkg2
if wjitter:
weights = thinkstats2.Jitter(weights, wjitter)
return heights, weights
cdf = thinkstats2.Cdf(df.Age) thinkplot.Cdf(cdf) thinkplot.Config(xlabel='Age', ylabel='CDF') #plot normal distribution mean = df.Age.mean() std = df.Age.std() xs = [-4, 4] fxs, fys = thinkstats2.FitLine(xs, inter=mean, slope=std) thinkplot.Plot(fxs, fys, color='gray', label='model') xs, ys = thinkstats2.NormalProbability(df.Age) thinkplot.Plot(xs, ys, label='Age') #scatter plots and correlation #year vs. age year = thinkstats2.Jitter(df.Year, .25) thinkplot.Scatter(year, df.Age) thinkplot.Show(xlabel='Year', ylabel='Age') thinkstats2.Corr(df.Year, df.Age) #drug vs. age thinkplot.Scatter(df.Age, df.Drug) thinkplot.Show(xlabel='Age', ylabel='Drug') #testing a difference in gender data = male.Age.values, female.Age.values ht = DiffMeansPermute(data) pvalue = ht.PValue() print(pvalue) ht.PlotCdf() thinkplot.Config(xlabel='test statistic', ylabel='CDF')
def CorrelationPlots(df,
xlabel,
ylabel,
xjitter=0,
yjitter=0,
axis=None,
nbins=5,
**options):
cleaned = df.dropna(subset=[xlabel, ylabel])
xs = cleaned[xlabel]
ys = cleaned[ylabel]
xs = thinkstats2.Jitter(xs, xjitter)
ys = thinkstats2.Jitter(ys, yjitter)
xmin, xmax = min(xs), max(xs)
ymin, ymax = min(ys), max(ys)
if axis is None:
axis = [xmin, xmax, ymin, ymax]
PrePlot(num=4, rows=2, cols=2)
# make scatter plot
SubPlot(1)
Scatter(xs, ys, alpha=0.1, s=10)
Config(xlabel=xlabel, ylabel=ylabel, axis=axis, legend=False)
# make HexBin plot
SubPlot(2)
HexBin(xs, ys)
Config(xlabel=xlabel, ylabel=ylabel, axis=axis, legend=False)
# plot percentiles
SubPlot(3)
xs_cdf = thinkstats2.Cdf(xs)
lower = xs_cdf.Percentile(1)
upper = xs_cdf.Percentile(99)
bins = np.arange(lower, upper, nbins)
indices = np.digitize(xs, bins)
groups = cleaned.groupby(indices)
mean_xs = [group[xlabel].mean() for i, group in groups]
cdfs = [thinkstats2.Cdf(group[ylabel]) for i, group in groups]
for percent in [75, 50, 25]:
y_percentiles = [cdf.Percentile(percent) for cdf in cdfs]
label = '%dth' % percent
Plot(mean_xs, y_percentiles, label=label)
Config(xlabel=xlabel, ylabel=ylabel, axis=axis, legend=True)
# plot CDFs
n = (upper - lower) // (nbins - 2)
bins = np.arange(lower, upper, n)
indices = np.digitize(cleaned[xlabel], bins)
groups = cleaned.groupby(indices)
mean_xs = [group[xlabel].mean() for i, group in groups]
cdfs = [thinkstats2.Cdf(group[ylabel]) for i, group in groups]
## plot the cdfs
SubPlot(4)
PrePlot(len(cdfs))
for i, cdf in enumerate(cdfs):
if i == 0:
label = '<%d ' % bins[0] + xlabel
elif i == len(cdfs) - 1:
label = '>%d ' % bins[-1] + xlabel
else:
label = '%d - %d ' % (bins[i - 1], bins[i]) + xlabel
Cdf(cdf, label=label)
Config(xlabel=ylabel, ylabel='CDF', legend=True)
#print statistics
print('Correlation:\n', thinkstats2.Corr(xs, ys))
print('Spearman Correlation Coefficient:\n',
thinkstats2.SpearmanCorr(xs, ys))