def residuals_plot(self, x, y=None, **kwargs):
"""Plot the distribution of residuals of the model's predictions.
TODO: docs...
Parameters
----------
x : |ndarray| or |DataFrame| or |Series| or |DataGenerator|
Independent variable values of the dataset to evaluate (aka the
"features"). Or a |DataGenerator| for both x and y.
y : |ndarray| or |DataFrame| or |Series|
Dependent variable values of the dataset to evaluate (aka the
"target").
**kwargs
Additional keyword arguments are passed to :func:`.plot_dist`
Example
-------
TODO
"""
res = self.residuals(x, y)
plot_dist(res, **kwargs)
plt.xlabel("Residual (True - Predicted)")
def r_squared_plot(self, x, y=None, n=1000, style="hist", **kwargs):
"""Plot the Bayesian R-squared distribution.
See :meth:`~r_squared` for more info on the Bayesian R-squared metric.
Parameters
----------
x : |ndarray| or |DataFrame| or |Series| or |DataGenerator|
Independent variable values of the dataset to evaluate (aka the
"features"). Or a |DataGenerator| for both x and y.
y : |ndarray| or |DataFrame| or |Series|
Dependent variable values of the dataset to evaluate (aka the
"target").
n : int
Number of posterior draws to use for computing the r-squared
distribution. Default = `1000`.
**kwargs
Additional keyword arguments are passed to :func:`.plot_dist`
Example
-------
TODO
"""
r2 = self.r_squared(x, y, n=n)
plot_dist(r2, style=style, **kwargs)
plt.xlabel("Bayesian R squared")
def residuals_plot(self, x, y=None, batch_size=None, **kwargs):
r"""Plot the distribution of residuals of the model's predictions.
TODO: docs...
Parameters
----------
x : |ndarray| or |DataFrame| or |Series| or |DataGenerator|
Independent variable values of the dataset to evaluate (aka the
"features"). Or a |DataGenerator| for both x and y.
y : |ndarray| or |DataFrame| or |Series|
Dependent variable values of the dataset to evaluate (aka the
"target").
batch_size : None or int
Compute using batches of this many datapoints. Default is `None`
(i.e., do not use batching).
**kwargs
Additional keyword arguments are passed to :func:`.plot_dist`
Example
-------
TODO
"""
res = self.residuals(x, y, batch_size=batch_size)
plot_dist(res, **kwargs)
plt.xlabel("Residual (True - Predicted)")
def posterior_plot(self,
n: int = 10000,
style: str = 'fill',
bins: Union[int, list, np.ndarray] = 20,
ci: float = 0.0,
bw: float = 0.075,
alpha: float = 0.4,
color=None,
**kwargs):
"""Plot distribution of samples from the posterior distribution.
Parameters
----------
n : int
Number of samples to take from each posterior distribution for
estimating the density. Default = 10000
style : str
Which style of plot to show. Available types are:
* ``'fill'`` - filled density plot (the default)
* ``'line'`` - line density plot
* ``'hist'`` - histogram
bins : int or list or |ndarray|
Number of bins to use for the posterior density histogram (if
``style='hist'``), or a list or vector of bin edges.
ci : float between 0 and 1
Confidence interval to plot. Default = 0.0 (i.e., not plotted)
bw : float
Bandwidth of the kernel density estimate (if using ``style='line'``
or ``style='fill'``). Default is 0.075
alpha : float between 0 and 1
Transparency of fill/histogram
color : matplotlib color code or list of them
Color(s) to use to plot the distribution.
See https://matplotlib.org/tutorials/colors/colors.html
Default = use the default matplotlib color cycle
kwargs
Additional keyword arguments are passed to
:meth:`.utils.plotting.plot_dist`
"""
# Sample from the posterior
samples = self.posterior_sample(n=n)
# Plot the posterior densities
plot_dist(samples,
xlabel=self.name,
style=style,
bins=bins,
ci=ci,
bw=bw,
alpha=alpha,
color=color,
**kwargs)
# Label with parameter name
plt.xlabel(self.name)
def pred_dist_plot(self, x, n=10000, cols=1, individually=False, **kwargs):
"""Plot posterior predictive distribution from the model given ``x``.
TODO: Docs...
Parameters
----------
x : |ndarray| or |DataFrame| or |Series| or |DataGenerator|
Independent variable values of the dataset to evaluate (aka the
"features").
n : int
Number of samples to draw from the model given ``x``.
Default = 10000
cols : int
Divide the subplots into a grid with this many columns (if
``individually=True``.
individually : bool
If ``True``, plot one subplot per datapoint in ``x``, otherwise
plot all the predictive distributions on the same plot.
**kwargs
Additional keyword arguments are passed to :func:`.plot_dist`
Example
-------
TODO
"""
# Sample from the predictive distribution
samples = self.predictive_sample(x, n=n)
# Independent variable must be scalar
Ns = samples.shape[0]
N = samples.shape[1]
if samples.ndim > 2 and any(e > 1 for e in samples.shape[2:]):
raise NotImplementedError("only scalar dependent variables are "
"supported")
else:
samples = samples.reshape([Ns, N])
# Plot the predictive distributions
if individually:
rows = np.ceil(N / cols)
for i in range(N):
plt.subplot(rows, cols, i + 1)
plot_dist(samples[:, i], **kwargs)
plt.xlabel("Predicted dependent variable value for " + str(i))
plt.tight_layout()
else:
plot_dist(samples, **kwargs)
plt.xlabel("Predicted dependent variable value")
