def main():
filename = 'mystery0.dat'
data = read_file(filename)
cdf = thinkstats2.MakeCdfFromList(data)
thinkplot.SubPlot(2, 3, 1)
thinkplot.Cdf(cdf)
thinkplot.Config(title='linear')
thinkplot.SubPlot(2, 3, 2)
scale = thinkplot.Cdf(cdf, xscale='log')
thinkplot.Config(title='logx', **scale)
thinkplot.SubPlot(2, 3, 3)
scale = thinkplot.Cdf(cdf, transform='exponential')
thinkplot.Config(title='expo', **scale)
thinkplot.SubPlot(2, 3, 4)
xs, ys = thinkstats2.NormalProbability(data)
thinkplot.Plot(xs, ys)
thinkplot.Config(title='normal')
thinkplot.SubPlot(2, 3, 5)
scale = thinkplot.Cdf(cdf, transform='pareto')
thinkplot.Config(title='pareto', **scale)
thinkplot.SubPlot(2, 3, 6)
scale = thinkplot.Cdf(cdf, transform='weibull')
thinkplot.Config(title='weibull', **scale)
thinkplot.Show()
def main(script, filename='mystery0.dat'):
data = ReadFile(filename)
cdf = thinkstats2.Cdf(data)
thinkplot.PrePlot(rows=2, cols=3)
thinkplot.SubPlot(1)
thinkplot.Cdf(cdf)
thinkplot.Config(title='linear')
thinkplot.SubPlot(2)
scale = thinkplot.Cdf(cdf, xscale='log')
thinkplot.Config(title='logx', **scale)
thinkplot.SubPlot(3)
scale = thinkplot.Cdf(cdf, transform='exponential')
thinkplot.Config(title='expo', **scale)
thinkplot.SubPlot(4)
xs, ys = thinkstats2.NormalProbability(data)
thinkplot.Plot(xs, ys)
thinkplot.Config(title='normal')
thinkplot.SubPlot(5)
scale = thinkplot.Cdf(cdf, transform='pareto')
thinkplot.Config(title='pareto', **scale)
thinkplot.SubPlot(6)
scale = thinkplot.Cdf(cdf, transform='weibull')
thinkplot.Config(title='weibull', **scale)
thinkplot.Show(legend=False)
def main(script, filename='mystery0.dat'):
data = ReadFile(filename)
cdf = thinkstats2.Cdf(data)
thinkplot.PrePlot(num=6, rows=2, cols=3)
thinkplot.SubPlot(1)
thinkplot.Cdf(cdf, color='C0', label=filename)
thinkplot.Config(title='CDF on linear scale', ylabel='CDF')
thinkplot.SubPlot(2)
scale = thinkplot.Cdf(cdf, xscale='log', color='C0')
thinkplot.Config(title='CDF on log-x scale', ylabel='CDF', **scale)
thinkplot.SubPlot(3)
scale = thinkplot.Cdf(cdf, transform='exponential', color='C0')
thinkplot.Config(title='CCDF on log-y scale', ylabel='log CCDF', **scale)
thinkplot.SubPlot(4)
xs, ys = thinkstats2.NormalProbability(data)
thinkplot.Plot(xs, ys, color='C0')
thinkplot.Config(title='Normal probability plot',
xlabel='random normal',
ylabel='data')
thinkplot.SubPlot(5)
scale = thinkplot.Cdf(cdf, transform='pareto', color='C0')
thinkplot.Config(title='CCDF on log-log scale', ylabel='log CCDF', **scale)
thinkplot.SubPlot(6)
scale = thinkplot.Cdf(cdf, transform='weibull', color='C0')
thinkplot.Config(title='CCDF on loglog-y log-x scale',
ylabel='log log CCDF',
**scale)
thinkplot.Show(legend=False)
def MakeNormalPlot(weights, term_weights):
"""Generates a normal probability plot of birth weights."""
mean, var = thinkstats2.TrimmedMeanVar(weights, p=0.01)
std = math.sqrt(var)
xs = [-4, 4]
fxs, fys = thinkstats2.FitLine(xs, mean, std)
thinkplot.Plot(fxs, fys, linewidth=4, color='0.8')
thinkplot.PrePlot(2)
xs, ys = thinkstats2.NormalProbability(weights)
thinkplot.Plot(xs, ys, label='all live')
xs, ys = thinkstats2.NormalProbability(term_weights)
thinkplot.Plot(xs, ys, label='full term')
thinkplot.Save(root='analytic_birthwgt_normal',
title='Normal probability plot',
xlabel='Standard deviations from mean',
ylabel='Birth weight (lbs)')
def PlotNormalProbability(sample, title="", ylabel=""):
mu, var = thinkstats2.TrimmedMeanVar(sample, p=0.01)
sigma = np.sqrt(var)
xs = [-5, 5]
fxs, fys = thinkstats2.FitLine(xs, inter=mu, slope=sigma)
thinkplot.plot(fxs,
fys,
color='gray',
label=r'model $\mu$={:.2f} $\sigma$={:.2f}'.format(
mu, sigma))
xs, ys = thinkstats2.NormalProbability(sample)
thinkplot.Plot(xs, ys, label="actual")
thinkplot.Config(title=title, xlabel="z", ylabel=ylabel)
def MakeNormalPlot(weights):
"""Generates a normal probability plot of birth weights.
weights: sequence
"""
mean, var = thinkstats2.TrimmedMeanVar(weights, p=0.01)
std = math.sqrt(var)
xs = [-5, 5]
xs, ys = thinkstats2.FitLine(xs, mean, std)
thinkplot.Plot(xs, ys, color='0.8', label='model')
xs, ys = thinkstats2.NormalProbability(weights)
thinkplot.Plot(xs, ys, label='weights')
def MakeNormalPlot(x):
"""Generates a normal probability plot of birth weights."""
mean, var = thinkstats2.TrimmedMeanVar(df[x], p=0.01)
std = math.sqrt(var)
xs = [-4, 4]
fxs, fys = thinkstats2.FitLine(xs, mean, std)
thinkplot.Plot(fxs, fys, linewidth=4, color='0.8')
thinkplot.PrePlot(2)
xs, ys = thinkstats2.NormalProbability(df[x])
thinkplot.Plot(xs, ys, label='Number of Crimes')
thinkplot.Show(title='Normal Prob Plot: {}'.format(x),
xlabel='Standard deviations from mean',
ylabel='Number of Crimes')
def MakeExampleNormalPlot():
"""Generates a sample normal probability plot.
"""
n = 1000
thinkplot.PrePlot(3)
mus = [0, 1, 5]
sigmas = [1, 1, 2]
for mu, sigma in zip(mus, sigmas):
sample = np.random.normal(mu, sigma, n)
xs, ys = thinkstats2.NormalProbability(sample)
label = '$\mu=%d$, $\sigma=%d$' % (mu, sigma)
thinkplot.Plot(xs, ys, label=label)
thinkplot.Save(root='analytic_normal_prob_example',
title='Normal probability plot',
xlabel='standard normal sample',
ylabel='sample values')
def MakeNormalPlot(arrivalDelays):
"""Generate the normal probability plot for the arrival delays.
This is a modified copy from analytic.py
"""
mean = arrivalDelays.mean()
std = arrivalDelays.std()
xs = [-4, 4]
fxs, fys = thinkstats2.FitLine(xs, mean, std)
thinkplot.Plot(fxs, fys, linewidth=4, color='0.8')
thinkplot.PrePlot(2)
xs, ys = thinkstats2.NormalProbability(arrivalDelays)
thinkplot.Plot(xs, ys, label='arrival delays (min)')
thinkplot.Save(root='NormalModel_arrivaldelay_normalplot',
title='Normal probability plot',
xlabel='Standard deviations from mean',
ylabel='Arrival Delays (min)')
def plotDist(data):
""" function to plot normal probability plot
@param: data (series) - data to be ploted
"""
n = 30
thinkplot.PrePlot(3)
mus = [0, 1, 5]
sigmas = [1, 1, 2]
for mu, sigma in zip(mus, sigmas):
sample = data.sample(n=n)
xs, ys = thinkstats2.NormalProbability(sample)
label = '$\mu=%d$, $\sigma=%d$' % (mu, sigma)
thinkplot.Plot(xs, ys, label=label)
thinkplot.Config(title='Normal probability plot',
xlabel='standard normal sample',
ylabel='sample values')
thinkplot.Hist(male_pmf, width=width, align='left', color='blue') thinkplot.Hist(female_pmf, width=width, align='right', color='red') thinkplot.Config(ylabel='Probability') #plot CDF 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)
xlabel='Birth weight (pounds)',
ylabel='CDF')
#%% [markdown]
# A normal probability plot is a visual test for normality. The following example shows that if the data are actually from a normal distribution, the plot is approximately straight.
#%%
n = 1000
thinkplot.PrePlot(3)
mus = [0, 1, 5]
sigmas = [1, 1, 2]
for mu, sigma in zip(mus, sigmas):
sample = np.random.normal(mu, sigma, n)
xs, ys = thinkstats2.NormalProbability(sample)
label = '$\mu=%d$, $\sigma=%d$' % (mu, sigma)
thinkplot.Plot(xs, ys, label=label)
thinkplot.Config(title='Normal probability plot',
xlabel='standard normal sample',
ylabel='sample values')
#%% [markdown]
# Here's the normal probability plot for birth weights, showing that the lightest babies are lighter than we expect from the normal mode, and the heaviest babies are heavier.
#%%
mean, var = thinkstats2.TrimmedMeanVar(weights, p=0.01)
std = np.sqrt(var)
xs = [-4, 4]
y = thinkstats2.EvalNormalCdf(x, mu=mu, sigma=sigma)
thinkplot.plot(x, cdf.Probs(x), label='Data')
thinkplot.plot(x,
y,
label=r'Model $\mu$={:.2f} $\sigma$={:.2f}'.format(mu, sigma))
thinkplot.Config(xlabel="weight (pounds)", ylabel="CDF")
#%% [markdown]
# ## 5.3 Normal probability plt
#%%
n = 1000
thinkplot.PrePlot(3)
for mu, sigma in zip([0, 1, 5], [1, 1, 2]):
sample = np.random.normal(mu, sigma, n)
xs, ys = thinkstats2.NormalProbability(sample)
thinkplot.plot(xs, ys, label=r"$\mu$={} $\sigma$={}".format(mu, sigma))
thinkplot.Config(title="Normal probability plot",
xlabel="standard normal sample",
ylabel="sample value")
#%%
mu, var = thinkstats2.TrimmedMeanVar(totalwgt_lb, p=0.01)
maturity = live[live.prglngth >= 37].totalwgt_lb.dropna()
sigma = np.sqrt(var)
xs = [-4, 4]
fxs, fys = thinkstats2.FitLine(xs, inter=mu, slope=sigma)
thinkplot.plot(fxs,
fys,
color='gray',
label=r'model $\mu$={:.2f} $\sigma$={:.2f}'.format(mu, sigma))
# Model fits data except for in th left tail up to 15 minutes
# If data is from a normal distribution then the plot will be straight
# In[72]:
n = 1000
thinkplot.PrePlot(3)
mus = [0, 1, 5]
sigmas = [1, 1, 2]
for mu, sigma in zip(mus, sigmas):
sample = np.random.normal(mu, sigma, n)
xs, ys = thinkstats2.NormalProbability(sample)
label = '$\mu=%d$, $\sigma=%d$' % (mu, sigma)
thinkplot.Plot(xs, ys, label=label)
thinkplot.Config(title='Normal probability plot',
xlabel='standard normal sample',
ylabel='sample values')
# Normal Probability Plot for trip duration
# In[73]:
mean, var = thinkstats2.TrimmedMeanVar(df.tripduration, p=0.01)
std = np.sqrt(var)
cdf = thinkstats2.MakeCdfFromPmf(pmf, label=label)
thinkplot.Cdf(cdf, label=label)
thinkplot.Show(xlabel='x', ylabel='CDF', axis=[-1, 4, 0, 1])
## make data frames
live, firsts, others = first.MakeFrames()
## make normal probability plot of totalwgt_lb
full_term_wgt = live.loc[live.prglngth >= 36, 'totalwgt_lb']
weights = live.totalwgt_lb
thinkplot.PrePlot(2)
fxs, fys = MakeNormalPlot(weights)
thinkplot.Plot(fxs, fys, color='gray', label='model')
xs, ys = thinkstats2.NormalProbability(weights)
thinkplot.Plot(xs, ys, label='all live')
xs, ys = thinkstats2.NormalProbability(full_term_wgt)
thinkplot.Plot(xs, ys, label='full term')
thinkplot.Show(xlabel='standard deviations from mean',
ylabel='Birth weight (lbs)',
title='Normal probability plot')
## make Pareto CDF from random variates
t = [ParetoVariate(alpha=2, xm=1) for _ in range(1000)]
cdf = thinkstats2.Cdf(t)
thinkplot.Cdf(cdf, complement=True)
thinkplot.Show(xlabel='x', ylabel='CCDF', xscale='log', yscale='log')
