def plot_ccpr_grid(results, exog_idx=None, grid=None, fig=None):
"""Generate CCPR plots against a set of regressors, plot in a grid.
Generates a grid of CCPR (component and component-plus-residual) plots.
Parameters
----------
results : result instance
uses exog and params of the result instance
exog_idx : None or list of int
(column) indices of the exog used in the plot
grid : None or tuple of int (nrows, ncols)
If grid is given, then it is used for the arrangement of the subplots.
If grid is None, then ncol is one, if there are only 2 subplots, and
the number of columns is two otherwise.
fig : Matplotlib figure instance, optional
If given, this figure is simply returned. Otherwise a new figure is
created.
Returns
-------
fig : Matplotlib figure instance
If `ax` is None, the created figure. Otherwise the figure to which
`ax` is connected.
Notes
-----
Partial residual plots are formed as::
Res + Betahat(i)*Xi versus Xi
and CCPR adds::
Betahat(i)*Xi versus Xi
See Also
--------
plot_ccpr : Creates CCPR plot for a single regressor.
References
----------
See http://www.itl.nist.gov/div898/software/dataplot/refman1/auxillar/ccpr.htm
"""
fig = utils.create_mpl_fig(fig)
exog_name, exog_idx = utils.maybe_name_or_idx(exog_idx, results.model)
if grid is not None:
nrows, ncols = grid
else:
if len(exog_idx) > 2:
nrows = int(np.ceil(len(exog_idx)/2.))
ncols = 2
else:
nrows = len(exog_idx)
ncols = 1
seen_constant = 0
for i, idx in enumerate(exog_idx):
if results.model.exog[:,idx].var() == 0:
seen_constant = 1
continue
ax = fig.add_subplot(nrows, ncols, i+1-seen_constant)
fig = plot_ccpr(results, exog_idx=idx, ax=ax)
ax.set_title("")
fig.suptitle("Component-Component Plus Residual Plot", fontsize="large")
fig = utils.maybe_tight_layout(fig)
fig.subplots_adjust(top=.95)
return fig
def plot_partregress_grid(results, exog_idx=None, grid=None, fig=None):
"""Plot partial regression for a set of regressors.
Parameters
----------
results : results instance
A regression model results instance
exog_idx : None, list of ints, list of strings
(column) indices of the exog used in the plot, default is all.
grid : None or tuple of int (nrows, ncols)
If grid is given, then it is used for the arrangement of the subplots.
If grid is None, then ncol is one, if there are only 2 subplots, and
the number of columns is two otherwise.
fig : Matplotlib figure instance, optional
If given, this figure is simply returned. Otherwise a new figure is
created.
Returns
-------
fig : Matplotlib figure instance
If `fig` is None, the created figure. Otherwise `fig` itself.
Notes
-----
A subplot is created for each explanatory variable given by exog_idx.
The partial regression plot shows the relationship between the response
and the given explanatory variable after removing the effect of all other
explanatory variables in exog.
See Also
--------
plot_partregress : Plot partial regression for a single regressor.
plot_ccpr
References
----------
See http://www.itl.nist.gov/div898/software/dataplot/refman1/auxillar/partregr.htm
"""
import pandas
fig = utils.create_mpl_fig(fig)
exog_name, exog_idx = utils.maybe_name_or_idx(exog_idx, results.model)
#maybe add option for using wendog, wexog instead
y = pandas.Series(results.model.endog, name=results.model.endog_names)
exog = results.model.exog
k_vars = exog.shape[1]
#this function doesn't make sense if k_vars=1
if not grid is None:
nrows, ncols = grid
else:
if len(exog_idx) > 2:
nrows = int(np.ceil(len(exog_idx)/2.))
ncols = 2
title_kwargs = {"fontdict" : {"fontsize" : 'small'}}
else:
nrows = len(exog_idx)
ncols = 1
title_kwargs = {}
# for indexing purposes
other_names = np.array(results.model.exog_names)
for i,idx in enumerate(exog_idx):
others = range(k_vars)
others.pop(idx)
exog_others = pandas.DataFrame(exog[:, others],
columns=other_names[others])
ax = fig.add_subplot(nrows, ncols, i+1)
plot_partregress(y, pandas.Series(exog[:, idx],
name=other_names[idx]),
exog_others, ax=ax, title_kwargs=title_kwargs,
obs_labels=False)
ax.set_title("")
fig.suptitle("Partial Regression Plot", fontsize="large")
fig = utils.maybe_tight_layout(fig)
fig.subplots_adjust(top=.95)
return fig
def plot_regress_exog(results, exog_idx, fig=None):
"""Plot regression results against one regressor.
This plots four graphs in a 2 by 2 figure: 'endog versus exog',
'residuals versus exog', 'fitted versus exog' and
'fitted plus residual versus exog'
Parameters
----------
results : result instance
result instance with resid, model.endog and model.exog as attributes
exog_idx : int
index of regressor in exog matrix
fig : Matplotlib figure instance, optional
If given, this figure is simply returned. Otherwise a new figure is
created.
Returns
-------
fig : matplotlib figure instance
"""
fig = utils.create_mpl_fig(fig)
exog_name, exog_idx = utils.maybe_name_or_idx(exog_idx, results.model)
results = maybe_unwrap_results(results)
#maybe add option for wendog, wexog
y_name = results.model.endog_names
x1 = results.model.exog[:,exog_idx]
prstd, iv_l, iv_u = wls_prediction_std(results)
ax = fig.add_subplot(2,2,1)
ax.plot(x1, results.model.endog, 'o', color='b', alpha=0.9, label=y_name)
ax.plot(x1, results.fittedvalues, 'D', color='r', label='fitted',
alpha=.5)
ax.vlines(x1, iv_l, iv_u, linewidth=1, color='k', alpha=.7)
ax.set_title('Y and Fitted vs. X', fontsize='large')
ax.set_xlabel(exog_name)
ax.set_ylabel(y_name)
ax.legend(loc='best')
ax = fig.add_subplot(2,2,2)
ax.plot(x1, results.resid, 'o')
ax.axhline(y=0, color='black')
ax.set_title('Residuals versus %s' % exog_name, fontsize='large')
ax.set_xlabel(exog_name)
ax.set_ylabel("resid")
ax = fig.add_subplot(2,2,3)
exog_noti = np.ones(results.model.exog.shape[1], bool)
exog_noti[exog_idx] = False
exog_others = results.model.exog[:, exog_noti]
from pandas import Series
fig = plot_partregress(results.model.data.orig_endog,
Series(x1, name=exog_name, index=results.model.data.row_labels),
exog_others, obs_labels=False, ax=ax)
ax.set_title('Partial regression plot', fontsize='large')
#ax.set_ylabel("Fitted values")
#ax.set_xlabel(exog_name)
ax = fig.add_subplot(2,2,4)
fig = plot_ccpr(results, exog_idx, ax=ax)
ax.set_title('CCPR Plot', fontsize='large')
#ax.set_xlabel(exog_name)
#ax.set_ylabel("Fitted values + resids")
fig.suptitle('Regression Plots for %s' % exog_name, fontsize="large")
fig = utils.maybe_tight_layout(fig)
fig.subplots_adjust(top=.90)
return fig
def plot_ccpr_grid(results, exog_idx=None, grid=None, fig=None):
"""Generate CCPR plots against a set of regressors, plot in a grid.
Generates a grid of CCPR (component and component-plus-residual) plots.
Parameters
----------
results : result instance
uses exog and params of the result instance
exog_idx : None or list of int
(column) indices of the exog used in the plot
grid : None or tuple of int (nrows, ncols)
If grid is given, then it is used for the arrangement of the subplots.
If grid is None, then ncol is one, if there are only 2 subplots, and
the number of columns is two otherwise.
fig : Matplotlib figure instance, optional
If given, this figure is simply returned. Otherwise a new figure is
created.
Returns
-------
fig : Matplotlib figure instance
If `ax` is None, the created figure. Otherwise the figure to which
`ax` is connected.
Notes
-----
Partial residual plots are formed as::
Res + Betahat(i)*Xi versus Xi
and CCPR adds::
Betahat(i)*Xi versus Xi
See Also
--------
plot_ccpr : Creates CCPR plot for a single regressor.
References
----------
See http://www.itl.nist.gov/div898/software/dataplot/refman1/auxillar/ccpr.htm
"""
fig = utils.create_mpl_fig(fig)
exog_name, exog_idx = utils.maybe_name_or_idx(exog_idx, results.model)
if grid is not None:
nrows, ncols = grid
else:
if len(exog_idx) > 2:
nrows = int(np.ceil(len(exog_idx) / 2.))
ncols = 2
else:
nrows = len(exog_idx)
ncols = 1
seen_constant = 0
for i, idx in enumerate(exog_idx):
if results.model.exog[:, idx].var() == 0:
seen_constant = 1
continue
ax = fig.add_subplot(nrows, ncols, i + 1 - seen_constant)
fig = plot_ccpr(results, exog_idx=idx, ax=ax)
ax.set_title("")
fig.suptitle("Component-Component Plus Residual Plot", fontsize="large")
fig = utils.maybe_tight_layout(fig)
fig.subplots_adjust(top=.95)
return fig
def plot_partregress_grid(results, exog_idx=None, grid=None, fig=None):
"""Plot partial regression for a set of regressors.
Parameters
----------
results : results instance
A regression model results instance
exog_idx : None, list of ints, list of strings
(column) indices of the exog used in the plot, default is all.
grid : None or tuple of int (nrows, ncols)
If grid is given, then it is used for the arrangement of the subplots.
If grid is None, then ncol is one, if there are only 2 subplots, and
the number of columns is two otherwise.
fig : Matplotlib figure instance, optional
If given, this figure is simply returned. Otherwise a new figure is
created.
Returns
-------
fig : Matplotlib figure instance
If `fig` is None, the created figure. Otherwise `fig` itself.
Notes
-----
A subplot is created for each explanatory variable given by exog_idx.
The partial regression plot shows the relationship between the response
and the given explanatory variable after removing the effect of all other
explanatory variables in exog.
See Also
--------
plot_partregress : Plot partial regression for a single regressor.
plot_ccpr
References
----------
See http://www.itl.nist.gov/div898/software/dataplot/refman1/auxillar/partregr.htm
"""
import pandas
fig = utils.create_mpl_fig(fig)
exog_name, exog_idx = utils.maybe_name_or_idx(exog_idx, results.model)
#maybe add option for using wendog, wexog instead
y = pandas.Series(results.model.endog, name=results.model.endog_names)
exog = results.model.exog
k_vars = exog.shape[1]
#this function doesn't make sense if k_vars=1
if not grid is None:
nrows, ncols = grid
else:
if len(exog_idx) > 2:
nrows = int(np.ceil(len(exog_idx) / 2.))
ncols = 2
title_kwargs = {"fontdict": {"fontsize": 'small'}}
else:
nrows = len(exog_idx)
ncols = 1
title_kwargs = {}
# for indexing purposes
other_names = np.array(results.model.exog_names)
for i, idx in enumerate(exog_idx):
others = range(k_vars)
others.pop(idx)
exog_others = pandas.DataFrame(exog[:, others],
columns=other_names[others])
ax = fig.add_subplot(nrows, ncols, i + 1)
plot_partregress(y,
pandas.Series(exog[:, idx], name=other_names[idx]),
exog_others,
ax=ax,
title_kwargs=title_kwargs,
obs_labels=False)
ax.set_title("")
fig.suptitle("Partial Regression Plot", fontsize="large")
fig = utils.maybe_tight_layout(fig)
fig.subplots_adjust(top=.95)
return fig
def plot_regress_exog(results, exog_idx, fig=None):
"""Plot regression results against one regressor.
This plots four graphs in a 2 by 2 figure: 'endog versus exog',
'residuals versus exog', 'fitted versus exog' and
'fitted plus residual versus exog'
Parameters
----------
results : result instance
result instance with resid, model.endog and model.exog as attributes
exog_idx : int
index of regressor in exog matrix
fig : Matplotlib figure instance, optional
If given, this figure is simply returned. Otherwise a new figure is
created.
Returns
-------
fig : matplotlib figure instance
"""
fig = utils.create_mpl_fig(fig)
exog_name, exog_idx = utils.maybe_name_or_idx(exog_idx, results.model)
results = maybe_unwrap_results(results)
#maybe add option for wendog, wexog
y_name = results.model.endog_names
x1 = results.model.exog[:, exog_idx]
prstd, iv_l, iv_u = wls_prediction_std(results)
ax = fig.add_subplot(2, 2, 1)
ax.plot(x1, results.model.endog, 'o', color='b', alpha=0.9, label=y_name)
ax.plot(x1, results.fittedvalues, 'D', color='r', label='fitted', alpha=.5)
ax.vlines(x1, iv_l, iv_u, linewidth=1, color='k', alpha=.7)
ax.set_title('Y and Fitted vs. X', fontsize='large')
ax.set_xlabel(exog_name)
ax.set_ylabel(y_name)
ax.legend(loc='best')
ax = fig.add_subplot(2, 2, 2)
ax.plot(x1, results.resid, 'o')
ax.axhline(y=0, color='black')
ax.set_title('Residuals versus %s' % exog_name, fontsize='large')
ax.set_xlabel(exog_name)
ax.set_ylabel("resid")
ax = fig.add_subplot(2, 2, 3)
exog_noti = np.ones(results.model.exog.shape[1], bool)
exog_noti[exog_idx] = False
exog_others = results.model.exog[:, exog_noti]
from pandas import Series
fig = plot_partregress(results.model.data.orig_endog,
Series(x1,
name=exog_name,
index=results.model.data.row_labels),
exog_others,
obs_labels=False,
ax=ax)
ax.set_title('Partial regression plot', fontsize='large')
#ax.set_ylabel("Fitted values")
#ax.set_xlabel(exog_name)
ax = fig.add_subplot(2, 2, 4)
fig = plot_ccpr(results, exog_idx, ax=ax)
ax.set_title('CCPR Plot', fontsize='large')
#ax.set_xlabel(exog_name)
#ax.set_ylabel("Fitted values + resids")
fig.suptitle('Regression Plots for %s' % exog_name, fontsize="large")
fig = utils.maybe_tight_layout(fig)
fig.subplots_adjust(top=.90)
return fig
