Skip to content

Commit

Permalink
Merge pull request statsmodels#1179 from phobson/ProbPlot-enhancement…
Browse files Browse the repository at this point in the history 
…s-and-tests

REF/TST: `ProbPlot` now uses `resettable_cache` and added some kwargs to plotting fxns
  • Loading branch information
@josef-pkt
josef-pkt committed Dec 24, 2013
2 parents d777064 + 394d29c commit 13f9d51
Show file tree
Hide file tree
Showing 2 changed files with 240 additions and 133 deletions.
128 changes: 79 additions & 49 deletions statsmodels/graphics/gofplots.py
View file
Expand Up @@ -2,6 +2,9 @@
from scipy import stats
from statsmodels.regression.linear_model import OLS
from statsmodels.tools.tools import add_constant
from statsmodels.tools.decorators import (resettable_cache,
cache_readonly,
cache_writable)

from . import utils

Expand Down Expand Up @@ -148,46 +151,56 @@ def __init__(self, data, dist=stats.norm, fit=False,
self.loc = loc
self.scale = scale

# propertes
self._cache = resettable_cache()

@cache_readonly
def theoretical_percentiles(self):
return plotting_pos(self.nobs, self.a)

@cache_readonly
def theoretical_quantiles(self):
try:
return self.dist.ppf(self.theoretical_percentiles())
return self.dist.ppf(self.theoretical_percentiles)
except TypeError:
print('%s requires more parameters to compute ppf' % \
(self.dist.name,))
msg = '%s requires more parameters to ' \
'compute ppf'.format(self.dist.name,)
raise TypeError(msg)
except:
print('failed to compute the ppf of %s' % \
(self.dist.name,))
msg = 'failed to compute the ppf of {0}'.format(self.dist.name,)
raise

@cache_readonly
def sorted_data(self):
sorted_data = np.array(self.data, copy=True)
sorted_data.sort()
return sorted_data

@cache_readonly
def sample_quantiles(self):
if self.fit and self.loc != 0 and self.scale != 1:
return (self.sorted_data() - self.loc)/self.scale
return (self.sorted_data-self.loc)/self.scale
else:
return self.sorted_data()
return self.sorted_data

@cache_readonly
def sample_percentiles(self):
qntls = (self.sorted_data() - self.fit_params[-2])/self.fit_params[-1]
quantiles = \
(self.sorted_data - self.fit_params[-2])/self.fit_params[-1]
return self.dist.cdf(qntls)

def ppplot(self, xlabel=None, ylabel=None, line=None, other=None, ax=None):
def ppplot(self, xlabel=None, ylabel=None, line=None, other=None,
ax=None, **plotkwargs):
"""
P-P plot of the percentiles (probabilities) of x versus the
probabilities (percetiles) of a distribution.
Parameters
----------
xlabel, ylabel : str or None
xlabel, ylabel : str or None, optional
User-provided lables for the x-axis and y-axis. If None (default),
other values are used depending on the status of the kwarg `other`.
line : str {'45', 's', 'r', q'} or None
line : str {'45', 's', 'r', q'} or None, optional
Options for the reference line to which the data is compared:
- '45' - 45-degree line
Expand All @@ -199,8 +212,7 @@ def ppplot(self, xlabel=None, ylabel=None, line=None, other=None, ax=None):
- None - by default no reference line is added to the plot.
- If True a reference line is drawn on the graph. The default is to
fit a line via OLS regression.
other : `ProbPlot` instance, array-like, or None
other : `ProbPlot` instance, array-like, or None, optional
If provided, the sample quantiles of this `ProbPlot` instance are
plotted against the sample quantiles of the `other` `ProbPlot`
instance. If an array-like object is provided, it will be turned
Expand All @@ -209,6 +221,8 @@ def ppplot(self, xlabel=None, ylabel=None, line=None, other=None, ax=None):
ax : Matplotlib AxesSubplot instance, optional
If given, this subplot is used to plot in instead of a new figure
being created.
**plotkwargs : additional matplotlib arguments to be passed to the
`plot` command.
Returns
-------
Expand All @@ -221,19 +235,21 @@ def ppplot(self, xlabel=None, ylabel=None, line=None, other=None, ax=None):
if not check_other:
other = ProbPlot(other)

fig, ax = _do_plot(other.sample_percentiles(),
self.sample_percentiles(),
self.dist, ax=ax, line=line)
fig, ax = _do_plot(other.sample_percentiles,
self.sample_percentiles,
self.dist, ax=ax, line=line,
**plotkwargs)

if xlabel is None:
xlabel = 'Probabilities of 2nd Sample'
if ylabel is None:
ylabel = 'Probabilities of 1st Sample'

else:
fig, ax = _do_plot(self.theoretical_percentiles(),
self.sample_percentiles(),
self.dist, ax=ax, line=line)
fig, ax = _do_plot(self.theoretical_percentiles,
self.sample_percentiles,
self.dist, ax=ax, line=line,
**plotkwargs)
if xlabel is None:
xlabel = "Theoretical Probabilities"
if ylabel is None:
Expand All @@ -247,21 +263,19 @@ def ppplot(self, xlabel=None, ylabel=None, line=None, other=None, ax=None):

return fig

return fig

def qqplot(self, xlabel=None, ylabel=None, line=None, other=None, ax=None):
def qqplot(self, xlabel=None, ylabel=None, line=None, other=None,
ax=None, **plotkwargs):
"""
Q-Q plot of the quantiles of x versus the quantiles/ppf of a
distribution or the quantiles of another `ProbPlot` instance.
Parameters
----------
xlabel, ylabel : str or None
xlabel, ylabel : str or None, optional
User-provided lables for the x-axis and y-axis. If None (default),
other values are used depending on the status of the kwarg `other`.
line : str {'45', 's', 'r', q'} or None
line : str {'45', 's', 'r', q'} or None, optional
Options for the reference line to which the data is compared:
- '45' - 45-degree line
- 's' - standardized line, the expected order statistics are scaled
by the standard deviation of the given sample and have the mean
Expand All @@ -271,16 +285,17 @@ def qqplot(self, xlabel=None, ylabel=None, line=None, other=None, ax=None):
- None - by default no reference line is added to the plot.
- If True a reference line is drawn on the graph. The default is to
fit a line via OLS regression.
other : `ProbPlot` instance, array-like, or None
other : `ProbPlot` instance, array-like, or None, optional
If provided, the sample quantiles of this `ProbPlot` instance are
plotted against the sample quantiles of the `other` `ProbPlot`
instance. If an array-like object is provided, it will be turned
into a `ProbPlot` instance using default parameters. If not provided
(defualt), the theoretical quantiles are used.
(default), the theoretical quantiles are used.
ax : Matplotlib AxesSubplot instance, optional
If given, this subplot is used to plot in instead of a new figure
being created.
**plotkwargs : additional matplotlib arguments to be passed to the
`plot` command.
Returns
-------
Expand All @@ -293,19 +308,21 @@ def qqplot(self, xlabel=None, ylabel=None, line=None, other=None, ax=None):
if not check_other:
other = ProbPlot(other)

fig, ax = _do_plot(other.sample_quantiles(),
self.sample_quantiles(),
self.dist, ax=ax, line=line)
fig, ax = _do_plot(other.sample_quantiles,
self.sample_quantiles,
self.dist, ax=ax, line=line,
**plotkwargs)

if xlabel is None:
xlabel = 'Quantiles of 2nd Sample'
if ylabel is None:
ylabel = 'Quantiles of 1st Sample'

else:
fig, ax = _do_plot(self.theoretical_quantiles(),
self.sample_quantiles(),
self.dist, ax=ax, line=line)
fig, ax = _do_plot(self.theoretical_quantiles,
self.sample_quantiles,
self.dist, ax=ax, line=line,
**plotkwargs)
if xlabel is None:
xlabel = "Theoretical Quantiles"
if ylabel is None:
Expand All @@ -316,7 +333,8 @@ def qqplot(self, xlabel=None, ylabel=None, line=None, other=None, ax=None):

return fig

def probplot(self, line=None, ax=None, exceed=False):
def probplot(self, xlabel=None, ylabel=None, line=None,
exceed=False, ax=None, **plotkwargs):
"""
Probability plot of the unscaled quantiles of x versus the
probabilities of a distibution (not to be confused with a P-P plot).
Expand All @@ -326,7 +344,10 @@ def probplot(self, line=None, ax=None, exceed=False):
Parameters
----------
line : str {'45', 's', 'r', q'} or None
xlabel, ylabel : str or None, optional
User-provided lables for the x-axis and y-axis. If None (default),
other values are used depending on the status of the kwarg `other`.
line : str {'45', 's', 'r', q'} or None, optional
Options for the reference line to which the data is compared:
- '45' - 45-degree line
Expand All @@ -338,17 +359,19 @@ def probplot(self, line=None, ax=None, exceed=False):
- None - by default no reference line is added to the plot.
- If True a reference line is drawn on the graph. The default is to
fit a line via OLS regression.
exceed : boolean, optional
ax : Matplotlib AxesSubplot instance, optional
If given, this subplot is used to plot in instead of a new figure
being created.
excced : boolean
- If False (default) the raw sample quantiles are plotted against
the theoretical quantiles, show the probability that a sample
will not exceed a given value
- If True, the theoretical quantiles are flipped such that the
figure displays the probability that a sample will exceed a
given value.
ax : Matplotlib AxesSubplot instance, optional
If given, this subplot is used to plot in instead of a new figure
being created.
**plotkwargs : additional matplotlib arguments to be passed to the
`plot` command.
Returns
-------
Expand All @@ -357,19 +380,26 @@ def probplot(self, line=None, ax=None, exceed=False):
`ax` is connected.
"""
if exceed:
fig, ax = _do_plot(self.theoretical_quantiles()[::-1],
self.sorted_data(),
self.dist, ax=ax, line=line)
xlabel = 'Probability of Exceedance (%)'
fig, ax = _do_plot(self.theoretical_quantiles[::-1],
self.sorted_data,
self.dist, ax=ax, line=line,
**plotkwargs)
if xlabel is None:
xlabel = 'Probability of Exceedance (%)'

else:
fig, ax = _do_plot(self.theoretical_quantiles(),
self.sorted_data(),
self.dist, ax=ax, line=line)
xlabel = 'Non-exceedance Probability (%)'
fig, ax = _do_plot(self.theoretical_quantiles,
self.sorted_data,
self.dist, ax=ax, line=line,
**plotkwargs)
if xlabel is None:
xlabel = 'Non-exceedance Probability (%)'

if ylabel is None:
ylabel = "Sample Quantiles"

ax.set_xlabel(xlabel)
ax.set_ylabel("Sample Quantiles")
ax.set_ylabel(ylabel)
_fmt_probplot_axis(ax, self.dist, self.nobs)

return fig
Expand Down

0 comments on commit 13f9d51

Please sign in to comment.