def summary(self, yname=None, xname=None, title=0, alpha=.05,
return_fmt='text'):
"""
This is for testing the new summary setup
"""
from statsmodels.iolib.summary import (summary_top,
summary_params, summary_return)
## left = [(i, None) for i in (
## 'Dependent Variable:',
## 'Model type:',
## 'Method:',
## 'Date:',
## 'Time:',
## 'Number of Obs:',
## 'df resid',
## 'df model',
## )]
top_left = [('Dep. Variable:', None),
('Model:', None),
('Method:', ['IRLS']),
('Norm:', [self.fit_options['norm']]),
('Scale Est.:', [self.fit_options['scale_est']]),
('Cov Type:', [self.fit_options['cov']]),
('Date:', None),
('Time:', None),
('No. Iterations:', ["%d" % self.fit_history['iteration']])
]
top_right = [('No. Observations:', None),
('Df Residuals:', None),
('Df Model:', None)
]
if not title is None:
title = "Robust linear Model Regression Results"
#boiler plate
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right, #[],
yname=yname, xname=xname, title=title)
smry.add_table_params(self, yname=yname, xname=xname, alpha=.05,
use_t=False)
#diagnostic table is not used yet
# smry.add_table_2cols(self, gleft=diagn_left, gright=diagn_right,
# yname=yname, xname=xname,
# title="")
#add warnings/notes, added to text format only
etext =[]
wstr = \
'''If the model instance has been used for another fit with different fit
parameters, then the fit options might not be the correct ones anymore .'''
etext.append(wstr)
if etext:
smry.add_extra_txt(etext)
return smry
def summary(self,
yname=None,
xname=None,
title=0,
alpha=0.05,
return_fmt='text'):
from statsmodels.iolib.summary import (summary_top, summary_params,
summary_return)
top_left = [('Dep. Variable:', None), ('Model:', None),
('Method:', ['Interior Point']), ('Date:', None),
('Time:', None)]
top_right = [('No. Observations:', None), ('Df Residuals:', None),
('Df Model:', None),
('Tau:', ["%.3f" % self.fit_history['tau']]),
('Iterations:', ["%d" % self.fit_history['iterations']])]
if not title is None:
title = "Quantile Regression Results"
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right,
yname=yname,
xname=xname,
title=title)
smry.add_table_params(self,
yname=yname,
xname=xname,
alpha=alpha,
use_t=False)
return smry
def summary(self,
yname=None,
xname=None,
title=None,
alpha=.05,
yname_list=None):
top_left = [('Dep. Variable:', None),
('Model:', [self.model.__class__.__name__]),
('Method:', ['MLE']), ('Date:', None), ('Time:', None),
('Converged:', ["%s" % self.mle_retvals['converged']])]
top_right = [
('No. Observations:', None),
('Log-Likelihood:', None),
]
if title is None:
title = self.model.__class__.__name__ + ' ' + "Regression Results"
#boiler plate
from statsmodels.iolib.summary import Summary
smry = Summary()
# for top of table
smry.add_table_2cols(
self,
gleft=top_left,
gright=top_right, #[],
yname=yname,
xname=xname,
title=title)
# for parameters, etc
smry.add_table_params(self,
yname=yname_list,
xname=xname,
alpha=alpha,
use_t=True)
return smry
def summary(self, yname=None, xname=None, title=0, alpha=.05,
return_fmt='text'):
"""
This is for testing the new summary setup
"""
from statsmodels.iolib.summary import (summary_top,
summary_params, summary_return)
## left = [(i, None) for i in (
## 'Dependent Variable:',
## 'Model type:',
## 'Method:',
## 'Date:',
## 'Time:',
## 'Number of Obs:',
## 'df resid',
## 'df model',
## )]
top_left = [('Dep. Variable:', None),
('Model:', None),
('Method:', ['IRLS']),
('Norm:', [self.fit_options['norm']]),
('Scale Est.:', [self.fit_options['scale_est']]),
('Cov Type:', [self.fit_options['cov']]),
('Date:', None),
('Time:', None),
('No. Iterations:', ["%d" % self.fit_history['iteration']])
]
top_right = [('No. Observations:', None),
('Df Residuals:', None),
('Df Model:', None)
]
if not title is None:
title = "Robust linear Model Regression Results"
#boiler plate
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right, #[],
yname=yname, xname=xname, title=title)
smry.add_table_params(self, yname=yname, xname=xname, alpha=.05,
use_t=False)
#diagnostic table is not used yet
# smry.add_table_2cols(self, gleft=diagn_left, gright=diagn_right,
# yname=yname, xname=xname,
# title="")
#add warnings/notes, added to text format only
etext =[]
wstr = \
'''If the model instance has been used for another fit with different fit
parameters, then the fit options might not be the correct ones anymore .'''
etext.append(wstr)
if etext:
smry.add_extra_txt(etext)
return smry
def summary(self, yname=None, xname=None, title=0, alpha=0.05, return_fmt="text"):
"""
This is for testing the new summary setup
"""
from statsmodels.iolib.summary import summary_top, summary_params, summary_return
## left = [(i, None) for i in (
## 'Dependent Variable:',
## 'Model type:',
## 'Method:',
## 'Date:',
## 'Time:',
## 'Number of Obs:',
## 'df resid',
## 'df model',
## )]
top_left = [
("Dep. Variable:", None),
("Model:", None),
("Method:", ["IRLS"]),
("Norm:", [self.fit_options["norm"]]),
("Scale Est.:", [self.fit_options["scale_est"]]),
("Cov Type:", [self.fit_options["cov"]]),
("Date:", None),
("Time:", None),
("No. Iterations:", ["%d" % self.fit_history["iteration"]]),
]
top_right = [("No. Observations:", None), ("Df Residuals:", None), ("Df Model:", None)]
if not title is None:
title = "Robust linear Model Regression Results"
# boiler plate
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right, yname=yname, xname=xname, title=title) # [],
smry.add_table_params(self, yname=yname, xname=xname, alpha=alpha, use_t=self.use_t)
# diagnostic table is not used yet
# smry.add_table_2cols(self, gleft=diagn_left, gright=diagn_right,
# yname=yname, xname=xname,
# title="")
# add warnings/notes, added to text format only
etext = []
wstr = """If the model instance has been used for another fit with different fit
parameters, then the fit options might not be the correct ones anymore ."""
etext.append(wstr)
if etext:
smry.add_extra_txt(etext)
return smry
def summary(self,
yname=None,
xname=None,
title=0,
alpha=.05,
return_fmt='text'):
"""
This is for testing the new summary setup
"""
top_left = [
('Dep. Variable:', None), ('Model:', None), ('Method:', ['IRLS']),
('Norm:', [self.fit_options['norm']]),
('Scale Est.:', [self.fit_options['scale_est']]),
('Cov Type:', [self.fit_options['cov']]), ('Date:', None),
('Time:', None),
('No. Iterations:', ["%d" % self.fit_history['iteration']])
]
top_right = [('No. Observations:', None), ('Df Residuals:', None),
('Df Model:', None)]
if title is not None:
title = "Robust linear Model Regression Results"
# boiler plate
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right,
yname=yname,
xname=xname,
title=title)
smry.add_table_params(self,
yname=yname,
xname=xname,
alpha=alpha,
use_t=self.use_t)
# add warnings/notes, added to text format only
etext = []
wstr = ("If the model instance has been used for another fit "
"with different fit\n"
"parameters, then the fit options might not be the correct "
"ones anymore .")
etext.append(wstr)
if etext:
smry.add_extra_txt(etext)
return smry
def summary(self, yname=None, xname=None, title=0, alpha=.05,
return_fmt='text'):
"""
This is for testing the new summary setup
"""
top_left = [('Dep. Variable:', None),
('Model:', None),
('Method:', ['IRLS']),
('Norm:', [self.fit_options['norm']]),
('Scale Est.:', [self.fit_options['scale_est']]),
('Cov Type:', [self.fit_options['cov']]),
('Date:', None),
('Time:', None),
('No. Iterations:', ["%d" % self.fit_history['iteration']])
]
top_right = [('No. Observations:', None),
('Df Residuals:', None),
('Df Model:', None)
]
if title is not None:
title = "Robust linear Model Regression Results"
# boiler plate
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right,
yname=yname, xname=xname, title=title)
smry.add_table_params(self, yname=yname, xname=xname, alpha=alpha,
use_t=self.use_t)
# add warnings/notes, added to text format only
etext = []
wstr = ("If the model instance has been used for another fit "
"with different fit\n"
"parameters, then the fit options might not be the correct "
"ones anymore .")
etext.append(wstr)
if etext:
smry.add_extra_txt(etext)
return smry
def summary(self, yname=None, xname=None, title=0, alpha=0.05, return_fmt='text'):
from statsmodels.iolib.summary import (summary_top, summary_params, summary_return)
top_left = [('Dep. Variable:', None),
('Model:', None),
('Method:', ['Interior Point']),
('Date:', None),
('Time:', None)]
top_right = [('No. Observations:', None),
('Df Residuals:', None),
('Df Model:', None),
('Outer Iterations:', ["%d" % self.fit_history['outer_iterations']]),
('Avg. Inner Iterations:', ["%d" % self.fit_history['avg_inner_iterations']]) ]
if not title is None:
title = "Nonlinear Quantile Regression Results"
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right, yname=yname, xname=xname, title=title)
smry.add_table_params(self, yname=yname, xname=xname, alpha=alpha, use_t=False)
return smry
def summary(self, yname=None, xname=None, title=None, alpha=.05,
yname_list=None):
top_left = [('Dep. Variable:', None),
('Model:', [self.model.__class__.__name__]),
('Method:', ['MLE']),
('Date:', None),
('Time:', None),
('Converged:', ["%s" % self.mle_retvals['converged']])]
top_right = [('No. Observations:', None),
('Log-Likelihood:', None),
]
if title is None:
title = self.model.__class__.__name__ + ' ' + "Regression Results"
#boiler plate
from statsmodels.iolib.summary import Summary
smry = Summary()
# for top of table
smry.add_table_2cols(self, gleft=top_left, gright=top_right, #[],
yname=yname, xname=xname, title=title)
# for parameters, etc
smry.add_table_params(self, yname=yname_list, xname=xname, alpha=alpha,
use_t=True)
return smry
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""
Summarize the Regression Results
Parameters
-----------
yname : string, optional
Default is `y`
xname : list of strings, optional
Default is `var_##` for ## in p the number of regressors
title : string, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary
results
"""
top_left = [('Dep. Variable:', None),
('Model:', None),
('Model Family:', [self.family.__class__.__name__]),
('Link Function:', [self.family.link.__class__.__name__]),
('Method:', ['IRLS']),
('Date:', None),
('Time:', None),
('No. Iterations:',
["%d" % self.fit_history['iteration']]),
]
top_right = [('No. Observations:', None),
('Df Residuals:', None),
('Df Model:', None),
('Scale:', [self.scale]),
('Log-Likelihood:', None),
('Deviance:', ["%#8.5g" % self.deviance]),
('Pearson chi2:', ["%#6.3g" % self.pearson_chi2])
]
if title is None:
title = "Generalized Linear Model Regression Results"
#create summary tables
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right, # [],
yname=yname, xname=xname, title=title)
smry.add_table_params(self, yname=yname, xname=xname, alpha=alpha,
use_t=True)
#diagnostic table is not used yet:
#smry.add_table_2cols(self, gleft=diagn_left, gright=diagn_right,
# yname=yname, xname=xname,
# title="")
return smry
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""Summarize the Regression Results
Parameters
-----------
yname : string, optional
Default is `y`
xname : list of strings, optional
Default is `var_##` for ## in p the number of regressors
title : string, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary
results
"""
# #TODO: import where we need it (for now), add as cached attributes
# from statsmodels.stats.stattools import (jarque_bera,
# omni_normtest, durbin_watson)
# jb, jbpv, skew, kurtosis = jarque_bera(self.wresid)
# omni, omnipv = omni_normtest(self.wresid)
#
eigvals = self.eigenvals
condno = self.condition_number
#
# self.diagn = dict(jb=jb, jbpv=jbpv, skew=skew, kurtosis=kurtosis,
# omni=omni, omnipv=omnipv, condno=condno,
# mineigval=eigvals[0])
top_left = [('Dep. Variable:', None), ('Model:', None),
('Method:', ['Least Squares']), ('Date:', None),
('Time:', None)]
top_right = [
('Pseudo R-squared:', ["%#8.4g" % self.prsquared]),
('Bandwidth:', ["%#8.4g" % self.bandwidth]),
('Sparsity:', ["%#8.4g" % self.sparsity]),
('No. Observations:', None),
('Df Residuals:', None), #[self.df_resid]), #TODO: spelling
('Df Model:', None) #[self.df_model])
]
# diagn_left = [('Omnibus:', ["%#6.3f" % omni]),
# ('Prob(Omnibus):', ["%#6.3f" % omnipv]),
# ('Skew:', ["%#6.3f" % skew]),
# ('Kurtosis:', ["%#6.3f" % kurtosis])
# ]
#
# diagn_right = [('Durbin-Watson:', ["%#8.3f" % durbin_watson(self.wresid)]),
# ('Jarque-Bera (JB):', ["%#8.3f" % jb]),
# ('Prob(JB):', ["%#8.3g" % jbpv]),
# ('Cond. No.', ["%#8.3g" % condno])
# ]
if title is None:
title = self.model.__class__.__name__ + ' ' + "Regression Results"
#create summary table instance
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right,
yname=yname,
xname=xname,
title=title)
smry.add_table_params(self,
yname=yname,
xname=xname,
alpha=.05,
use_t=True)
# smry.add_table_2cols(self, gleft=diagn_left, gright=diagn_right,
#yname=yname, xname=xname,
#title="")
#add warnings/notes, added to text format only
etext = []
if eigvals[-1] < 1e-10:
wstr = "The smallest eigenvalue is %6.3g. This might indicate "
wstr += "that there are\n"
wstr += "strong multicollinearity problems or that the design "
wstr += "matrix is singular."
wstr = wstr % eigvals[-1]
etext.append(wstr)
elif condno > 1000: #TODO: what is recommended
wstr = "The condition number is large, %6.3g. This might "
wstr += "indicate that there are\n"
wstr += "strong multicollinearity or other numerical "
wstr += "problems."
wstr = wstr % condno
etext.append(wstr)
if etext:
smry.add_extra_txt(etext)
return smry
def summary(
self,
alpha=0.05,
start=None,
title=None,
model_name=None,
display_params=True,
):
"""
Summarize the Model
Parameters
----------
alpha : float, optional
Significance level for the confidence intervals. Default is 0.05.
start : int, optional
Integer of the start observation. Default is 0.
model_name : str
The name of the model used. Default is to use model class name.
Returns
-------
summary : Summary instance
This holds the summary table and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary
"""
from statsmodels.iolib.summary import Summary
# Model specification results
model = self.model
if title is None:
title = "Statespace Model Results"
if start is None:
start = 0
if self.model._index_dates:
ix = self.model._index
d = ix[start]
sample = ["%02d-%02d-%02d" % (d.month, d.day, d.year)]
d = ix[-1]
sample += ["- " + "%02d-%02d-%02d" % (d.month, d.day, d.year)]
else:
sample = [str(start), " - " + str(self.nobs)]
# Standardize the model name as a list of str
if model_name is None:
model_name = model.__class__.__name__
# Diagnostic tests results
try:
het = self.test_heteroskedasticity(method="breakvar")
except Exception: # FIXME: catch something specific
het = np.array([[np.nan] * 2])
try:
lb = self.test_serial_correlation(method="ljungbox")
except Exception: # FIXME: catch something specific
lb = np.array([[np.nan] * 2]).reshape(1, 2, 1)
try:
jb = self.test_normality(method="jarquebera")
except Exception: # FIXME: catch something specific
jb = np.array([[np.nan] * 4])
# Create the tables
if not isinstance(model_name, list):
model_name = [model_name]
top_left = [("Dep. Variable:", None)]
top_left.append(("Model:", [model_name[0]]))
for i in range(1, len(model_name)):
top_left.append(("", ["+ " + model_name[i]]))
top_left += [
("Date:", None),
("Time:", None),
("Sample:", [sample[0]]),
("", [sample[1]]),
]
top_right = [
("No. Observations:", [self.nobs]),
("Log Likelihood", ["%#5.3f" % self.llf]),
]
if hasattr(self, "rsquared"):
top_right.append(("R-squared:", ["%#8.3f" % self.rsquared]))
top_right += [
("AIC", ["%#5.3f" % self.aic]),
("BIC", ["%#5.3f" % self.bic]),
("HQIC", ["%#5.3f" % self.hqic]),
]
if hasattr(self, "filter_results"):
if (self.filter_results is not None
and self.filter_results.filter_concentrated):
top_right.append(("Scale", ["%#5.3f" % self.scale]))
else:
top_right.append(("Scale", ["%#5.3f" % self.scale]))
if hasattr(self, "cov_type"):
top_left.append(("Covariance Type:", [self.cov_type]))
format_str = lambda array: [ # noqa:E731
", ".join(["{0:.2f}".format(i) for i in array])
]
diagn_left = [
("Ljung-Box (Q):", format_str(lb[:, 0, -1])),
("Prob(Q):", format_str(lb[:, 1, -1])),
("Heteroskedasticity (H):", format_str(het[:, 0])),
("Prob(H) (two-sided):", format_str(het[:, 1])),
]
diagn_right = [
("Jarque-Bera (JB):", format_str(jb[:, 0])),
("Prob(JB):", format_str(jb[:, 1])),
("Skew:", format_str(jb[:, 2])),
("Kurtosis:", format_str(jb[:, 3])),
]
summary = Summary()
summary.add_table_2cols(self,
gleft=top_left,
gright=top_right,
title=title)
if len(self.params) > 0 and display_params:
summary.add_table_params(self,
alpha=alpha,
xname=self.param_names,
use_t=False)
summary.add_table_2cols(self,
gleft=diagn_left,
gright=diagn_right,
title="")
# Add warnings/notes, added to text format only
etext = []
if hasattr(self, "cov_type") and "description" in self.cov_kwds:
etext.append(self.cov_kwds["description"])
if self._rank < (len(self.params) - len(self.fixed_params)):
cov_params = self.cov_params()
if len(self.fixed_params) > 0:
mask = np.ix_(self._free_params_index, self._free_params_index)
cov_params = cov_params[mask]
etext.append("Covariance matrix is singular or near-singular,"
" with condition number %6.3g. Standard errors may be"
" unstable." % _safe_cond(cov_params))
if etext:
etext = [
"[{0}] {1}".format(i + 1, text) for i, text in enumerate(etext)
]
etext.insert(0, "Warnings:")
summary.add_extra_txt(etext)
return summary
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""
Summarize the Regression Results
Parameters
-----------
yname : string, optional
Default is `y`
xname : list of strings, optional
Default is `var_##` for ## in p the number of regressors
title : string, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary
results
"""
top_left = [('Dep. Variable:', None), ('Model:', [self.model]),
('Model Family:', [self.family_name]),
('Link Function:', [self.family_link]),
('Method:', [self.method]),
('Covariance Type:', [self.cov_type]),
('No. Observations:', [self.nobs])]
top_right = [('No. Iterations:', ["%d" % self.fit_history]),
('Df Residuals:', [self.df_resid]),
('Df Model:', [self.df_model]),
('Scale:', ["%#8.5g" % self.scale]),
('Log-Likelihood:', ["%#8.5g" % self.llf]),
('Deviance:', ["%#8.5g" % self.deviance]),
('Pearson chi2:', ["%#6.3g" % self.pearson_chi2])]
if title is None:
title = "Generalized Linear Model Regression Results"
# create summary tables
y = self.yname
x = self.xname
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(
self,
gleft=top_left,
gright=top_right, # [],
yname=y,
xname=x,
title=title)
smry.add_table_params(self, yname=y, xname=x, alpha=0.05, use_t=True)
if hasattr(self, 'constraints'):
smry.add_extra_txt([
'Model has been estimated subject to linear '
'equality constraints.'
])
# diagnostic table is not used yet:
# smry.add_table_2cols(self, gleft=diagn_left, gright=diagn_right,
# yname=yname, xname=xname,
# title="")
return smry
def get_statsmodels_summary(self,
title=None,
alpha=.05):
"""
title: OPTIONAL. string or None. Will be
the title of the returned summary.
If None, the default title is used.
alpha: OPTIONAL. float. Between 0.0 and
1.0. Determines the width of the
displayed, (1 - alpha)% confidence
interval.
====================
Returns: statsmodels.summary object.
"""
try:
# Get the statsmodels Summary class
from statsmodels.iolib.summary import Summary
# Get an instantiation of the Summary class.
smry = Summary()
# Get the yname and yname_list.
# Note I'm not really sure what the yname_list is.
new_yname, new_yname_list = self.choice_col, None
# Get the model name
model_name = self.model_type
##########
# Note the following commands are basically directly from
# statsmodels.discrete.discrete_model
##########
top_left = [('Dep. Variable:', None),
('Model:', [model_name]),
('Method:', ['MLE']),
('Date:', None),
('Time:', None),
#('No. iterations:', ["%d" % self.mle_retvals['iterations']]),
('converged:', [str(self.estimation_success)])
]
top_right = [('No. Observations:', ["{:,}".format(self.nobs)]),
('Df Residuals:', ["{:,}".format(self.df_resid)]),
('Df Model:', ["{:,}".format(self.df_model)]),
('Pseudo R-squ.:',
["{:.3f}".format(self.rho_squared)]),
('Pseudo R-bar-squ.:',
["{:.3f}".format(self.rho_bar_squared)]),
('Log-Likelihood:', ["{:,.3f}".format(self.llf)]),
('LL-Null:',
["{:,.3f}".format(self.null_log_likelihood)]),
]
if title is None:
title = model_name + ' ' + "Regression Results"
xnames = self.params.index.tolist()
# for top of table
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right, #[],
yname=new_yname,
xname=xnames,
title=title)
# for parameters, etc
smry.add_table_params(self,
yname=[new_yname_list],
xname=xnames,
alpha=alpha,
use_t=False)
return smry
except:
print("statsmodels not installed. Resorting to standard summary")
return self.print_summaries()
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""Summarize the Regression Results
Parameters
----------
yname : str, optional
Default is `y`
xname : list[str], optional
Names for the exogenous variables. Default is `var_##` for ## in
the number of regressors. Must match the number of parameters
in the model
title : str, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary results
"""
eigvals = self.eigenvals
condno = self.condition_number
top_left = [('Dep. Variable:', None),
('Model:', None),
('Method:', ['Least Squares']),
('Date:', None),
('Time:', None)
]
top_right = [('Pseudo R-squared:', ["%#8.4g" % self.prsquared]),
('Bandwidth:', ["%#8.4g" % self.bandwidth]),
('Sparsity:', ["%#8.4g" % self.sparsity]),
('No. Observations:', None),
('Df Residuals:', None),
('Df Model:', None)
]
if title is None:
title = self.model.__class__.__name__ + ' ' + "Regression Results"
# create summary table instance
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right,
yname=yname, xname=xname, title=title)
smry.add_table_params(self, yname=yname, xname=xname, alpha=alpha,
use_t=self.use_t)
# add warnings/notes, added to text format only
etext = []
if eigvals[-1] < 1e-10:
wstr = "The smallest eigenvalue is %6.3g. This might indicate "
wstr += "that there are\n"
wstr += "strong multicollinearity problems or that the design "
wstr += "matrix is singular."
wstr = wstr % eigvals[-1]
etext.append(wstr)
elif condno > 1000: # TODO: what is recommended
wstr = "The condition number is large, %6.3g. This might "
wstr += "indicate that there are\n"
wstr += "strong multicollinearity or other numerical "
wstr += "problems."
wstr = wstr % condno
etext.append(wstr)
if etext:
smry.add_extra_txt(etext)
return smry
def summary(self, alpha=.05):
"""Summarize the Model
Parameters
----------
alpha : float, optional
Significance level for the confidence intervals.
Returns
-------
smry : Summary instance
This holds the summary table and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary
"""
model = self.model
title = model.__class__.__name__ + ' Model Results'
method = model.method
# get sample
start = 0 if 'mle' in method else self.k_ar
if self.data.dates is not None:
dates = self.data.dates
sample = [dates[start].strftime('%m-%d-%Y')]
sample += ['- ' + dates[-1].strftime('%m-%d-%Y')]
else:
sample = str(start) + ' - ' + str(len(self.data.orig_endog))
k_ar = self.k_ar
order = '({0})'.format(k_ar)
dep_name = str(self.model.endog_names)
top_left = [('Dep. Variable:', dep_name),
('Model:', [model.__class__.__name__ + order]),
('Method:', [method]),
('Date:', None),
('Time:', None),
('Sample:', [sample[0]]),
('', [sample[1]])
]
top_right = [
('No. Observations:', [str(len(self.model.endog))]),
('Log Likelihood', ["%#5.3f" % self.llf]),
('S.D. of innovations', ["%#5.3f" % self.sigma2 ** .5]),
('AIC', ["%#5.3f" % self.aic]),
('BIC', ["%#5.3f" % self.bic]),
('HQIC', ["%#5.3f" % self.hqic])]
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right,
title=title)
smry.add_table_params(self, alpha=alpha, use_t=False)
# Make the roots table
from statsmodels.iolib.table import SimpleTable
if k_ar:
arstubs = ["AR.%d" % i for i in range(1, k_ar + 1)]
stubs = arstubs
roots = self.roots
freq = self.arfreq
else: # AR(0) model
stubs = []
if len(stubs): # not AR(0)
modulus = np.abs(roots)
data = np.column_stack((roots.real, roots.imag, modulus, freq))
roots_table = SimpleTable([('%17.4f' % row[0],
'%+17.4fj' % row[1],
'%17.4f' % row[2],
'%17.4f' % row[3]) for row in data],
headers=[' Real',
' Imaginary',
' Modulus',
' Frequency'],
title="Roots",
stubs=stubs)
smry.tables.append(roots_table)
return smry
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""Summarize the Regression Results
Parameters
-----------
yname : string, optional
Default is `y`
xname : list of strings, optional
Default is `var_##` for ## in p the number of regressors
title : string, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary
results
"""
top_left = [('Dep. Variable:', None),
('Model:', None),
('Model Family:', [self.family.__class__.__name__]),
('Link Function:', [self.family.link.__class__.__name__]),
('Method:', ['IRLS']),
('Date:', None),
('Time:', None),
('No. Iterations:', ["%d" % self.fit_history['iteration']]),
]
top_right = [('No. Observations:', None),
('Df Residuals:', None),
('Df Model:', None),
('Scale:', [self.scale]),
('Log-Likelihood:', None),
('Deviance:', ["%#8.5g" % self.deviance]),
('Pearson chi2:', ["%#6.3g" % self.pearson_chi2])
]
if title is None:
title = "Generalized Linear Model Regression Results"
#create summary tables
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right, #[],
yname=yname, xname=xname, title=title)
smry.add_table_params(self, yname=yname, xname=xname, alpha=alpha,
use_t=True)
#diagnostic table is not used yet:
#smry.add_table_2cols(self, gleft=diagn_left, gright=diagn_right,
# yname=yname, xname=xname,
# title="")
return smry
def get_statsmodels_summary(self, title=None, alpha=.05):
"""
title: OPTIONAL. string or None. Will be
the title of the returned summary.
If None, the default title is used.
alpha: OPTIONAL. float. Between 0.0 and
1.0. Determines the width of the
displayed, (1 - alpha)% confidence
interval.
====================
Returns: statsmodels.summary object.
"""
try:
# Get the statsmodels Summary class
from statsmodels.iolib.summary import Summary
# Get an instantiation of the Summary class.
smry = Summary()
# Get the yname and yname_list.
# Note I'm not really sure what the yname_list is.
new_yname, new_yname_list = self.choice_col, None
# Get the model name
model_name = self.model_type
##########
# Note the following commands are basically directly from
# statsmodels.discrete.discrete_model
##########
top_left = [
('Dep. Variable:', None),
('Model:', [model_name]),
('Method:', ['MLE']),
('Date:', None),
('Time:', None),
#('No. iterations:', ["%d" % self.mle_retvals['iterations']]),
('converged:', [str(self.estimation_success)])
]
top_right = [
('No. Observations:', ["{:,}".format(self.nobs)]),
('Df Residuals:', ["{:,}".format(self.df_resid)]),
('Df Model:', ["{:,}".format(self.df_model)]),
('Pseudo R-squ.:', ["{:.3f}".format(self.rho_squared)]),
('Pseudo R-bar-squ.:', ["{:.3f}".format(self.rho_bar_squared)
]),
('Log-Likelihood:', ["{:,.3f}".format(self.llf)]),
('LL-Null:', ["{:,.3f}".format(self.null_log_likelihood)]),
]
if title is None:
title = model_name + ' ' + "Regression Results"
xnames = self.params.index.tolist()
# for top of table
smry.add_table_2cols(
self,
gleft=top_left,
gright=top_right, #[],
yname=new_yname,
xname=xnames,
title=title)
# for parameters, etc
smry.add_table_params(self,
yname=[new_yname_list],
xname=xnames,
alpha=alpha,
use_t=False)
return smry
except:
print("statsmodels not installed. Resorting to standard summary")
return self.print_summaries()
def summary(self, alpha=.05, start=None, model_name=None):
"""
Summarize the Model
Parameters
----------
alpha : float, optional
Significance level for the confidence intervals. Default is 0.05.
start : int, optional
Integer of the start observation. Default is 0.
model_name : string
The name of the model used. Default is to use model class name.
Returns
-------
summary : Summary instance
This holds the summary table and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary
"""
from statsmodels.iolib.summary import Summary
model = self.model
title = 'Statespace Model Results'
if start is None:
start = 0
if self.data.dates is not None:
dates = self.data.dates
d = dates[start]
sample = ['%02d-%02d-%02d' % (d.month, d.day, d.year)]
d = dates[-1]
sample += ['- ' + '%02d-%02d-%02d' % (d.month, d.day, d.year)]
else:
sample = [str(start), ' - ' + str(self.model.nobs)]
if model_name is None:
model_name = model.__class__.__name__
top_left = [('Dep. Variable:', None), ('Model:', [model_name]),
('Date:', None), ('Time:', None), ('Sample:', [sample[0]]),
('', [sample[1]])]
top_right = [('No. Observations:', [self.model.nobs]),
('Log Likelihood', ["%#5.3f" % self.llf]),
('AIC', ["%#5.3f" % self.aic]),
('BIC', ["%#5.3f" % self.bic]),
('HQIC', ["%#5.3f" % self.hqic])]
if hasattr(self, 'cov_type'):
top_left.append(('Covariance Type:', [self.cov_type]))
summary = Summary()
summary.add_table_2cols(self,
gleft=top_left,
gright=top_right,
title=title)
summary.add_table_params(self,
alpha=alpha,
xname=self._param_names,
use_t=False)
# Add warnings/notes, added to text format only
etext = []
if hasattr(self, 'cov_type'):
etext.append(self.cov_kwds['description'])
if etext:
etext = [
"[{0}] {1}".format(i + 1, text) for i, text in enumerate(etext)
]
etext.insert(0, "Warnings:")
summary.add_extra_txt(etext)
return summary
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""Summarize the Regression Results
Parameters
----------
yname : string, optional
Default is `y`
xname : list of strings, optional
Default is `var_##` for ## in p the number of regressors
title : string, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary results
"""
top_left = [
('Dep. Variable:', None),
# ('Model:', None),
('Method:', ['Maximum Likelihood']),
# ('Date:', None),
# ('Time:', None),
('No. Observations:', None),
('No. Uncensored Obs:', ["{:.0f}".format(self.obs[1])]),
('No. Left-censored Obs:', ["{:.0f}".format(self.obs[2])]),
('No. Right-censored Obs:', ["{:.0f}".format(self.obs[3])]),
('Df Residuals:', None),
('Df Model:', None),
]
top_right = [
('Pseudo R-squ:', ["{:.3f}".format(self.prsquared)]),
('Log-Likelihood:', ["{:.1f}".format(self.llf)]),
('LL-Null:', ["{:.1f}".format(self.llnull)]),
('LL-Ratio:', ["{:.1f}".format(self.llr)]),
('LLR p-value:', ["{:.3f}".format(self.llr_pvalue)]),
('AIC:', ["{:.1f}".format(self.aic)]),
('BIC:', ["{:.1f}".format(self.bic)]),
('Covariance Type:', [self.cov_type]),
]
if title is None:
title = self.model.__class__.__name__ + ' ' + "Regression Results"
# create summary table instance
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right,
yname=yname,
xname=xname,
title=title)
smry.add_table_params(self,
yname=yname,
xname=xname,
alpha=alpha,
use_t=self.use_t)
return smry
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""
Summarize the fitted model.
Parameters
----------
yname : str, optional
Default is `y`
xname : list[str], optional
Names for the exogenous variables, default is "var_xx".
Must match the number of parameters in the model
title : str, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
Significance level for the confidence intervals
Returns
-------
smry : Summary instance
This holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary
results
"""
top_left = [
('Dep. Variable:', None),
('Model:', None),
('Log-Likelihood:', None),
('Method:', [self.method]),
('Date:', None),
('Time:', None),
]
top_right = [
('No. Observations:', None),
('No. groups:', [self.n_groups]),
('Min group size:', [self._group_stats[0]]),
('Max group size:', [self._group_stats[1]]),
('Mean group size:', [self._group_stats[2]]),
]
if title is None:
title = "Conditional Logit Model Regression Results"
# create summary tables
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(
self,
gleft=top_left,
gright=top_right, # [],
yname=yname,
xname=xname,
title=title)
smry.add_table_params(
self, yname=yname, xname=xname, alpha=alpha, use_t=self.use_t)
return smry
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""
Summarize the QIF regression results
Parameters
----------
yname : string, optional
Default is `y`
xname : list of strings, optional
Default is `var_##` for ## in p the number of regressors
title : string, optional
Title for the top table. If not None, then this replaces
the default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be
printed or converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary results
"""
top_left = [
('Dep. Variable:', None),
('Method:', ['QIF']),
('Family:', [self.model.family.__class__.__name__]),
('Covariance structure:',
[self.model.cov_struct.__class__.__name__]),
('Date:', None),
('Time:', None),
]
NY = [len(y) for y in self.model.groups_ix]
top_right = [
('No. Observations:', [sum(NY)]),
('No. clusters:', [len(NY)]),
('Min. cluster size:', [min(NY)]),
('Max. cluster size:', [max(NY)]),
('Mean cluster size:', ["%.1f" % np.mean(NY)]),
('Scale:', ["%.3f" % self.scale]),
]
if title is None:
title = self.model.__class__.__name__ + ' ' +\
"Regression Results"
# Override the exog variable names if xname is provided as an
# argument.
if xname is None:
xname = self.model.exog_names
if yname is None:
yname = self.model.endog_names
# Create summary table instance
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right,
yname=yname,
xname=xname,
title=title)
smry.add_table_params(self,
yname=yname,
xname=xname,
alpha=alpha,
use_t=False)
return smry
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""
Summarize the fitted model.
Parameters
----------
yname : string, optional
Default is `y`
xname : list of strings, optional
Default is `var_##` for ## in p the number of regressors
title : string, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary
results
"""
top_left = [
('Dep. Variable:', None),
('Model:', None),
('Log-Likelihood:', None),
('Method:', [self.method]),
('Date:', None),
('Time:', None),
]
top_right = [
('No. Observations:', None),
('No. groups:', [self.n_groups]),
('Min group size:', [self._group_stats[0]]),
('Max group size:', [self._group_stats[1]]),
('Mean group size:', [self._group_stats[2]]),
]
if title is None:
title = "Conditional Logit Model Regression Results"
# create summary tables
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(
self,
gleft=top_left,
gright=top_right, # [],
yname=yname,
xname=xname,
title=title)
smry.add_table_params(
self, yname=yname, xname=xname, alpha=alpha, use_t=self.use_t)
return smry
def summary(self, title = None, alpha = .05):
"""Summarize the Clogit Results
Parameters
-----------
title : string, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary
results
"""
top_left = [('Dep. Variable:', None),
('Model:', [self.model.__class__.__name__]),
('Method:', [self.mle_settings['optimizer']]),
('Date:', None),
('Time:', None),
('Converged:', ["%s" % self.mle_retvals['converged']]),
('Iterations:', ["%s" % self.mle_retvals['iterations']]),
('Elapsed time (seg.):',
["%10.4f" % self.model.elapsed_time]),
('Num. alternatives:', [self.model.J])
]
top_right = [
('No. Cases:', [self.nobs]),
('No. Observations:', [self.nobs_bychoice]),
('Df Residuals:', [self.model.df_resid]),
('Df Model:', [self.model.df_model]),
('Log-Likelihood:', None),
('LL-Null:', ["%#8.5g" % self.llnull]),
('Pseudo R-squ.:', ["%#6.4g" % self.prsquared]),
('LLR p-value:', ["%#6.4g" % self.llr_pvalue]),
('Likelihood ratio test:', ["%#8.5g" %self.llrt]),
('AIC:', ["%#8.5g" %self.aic])
]
if title is None:
title = self.model.__class__.__name__ + ' ' + \
"results"
#boiler plate
from statsmodels.iolib.summary import Summary, SimpleTable
smry = Summary()
# for top of table
smry.add_table_2cols(self, gleft=top_left, gright=top_right,
title=title)
# Frequencies of alternatives
mydata = [self.freq_alt, self.perc_alt]
myheaders = self.alt
mytitle = ("")
mystubs = ["Frequencies of alternatives: ", "Percentage:"]
tbl = SimpleTable(mydata, myheaders, mystubs, title = mytitle,
data_fmts = ["%5.2f"])
smry.tables.append(tbl)
# for parameters
smry.add_table_params(self, alpha=alpha, use_t=False)
return smry
def summary(self, alpha=.05, start=None, model_name=None):
"""
Summarize the Model
Parameters
----------
alpha : float, optional
Significance level for the confidence intervals. Default is 0.05.
start : int, optional
Integer of the start observation. Default is 0.
model_name : string
The name of the model used. Default is to use model class name.
Returns
-------
summary : Summary instance
This holds the summary table and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary
"""
from statsmodels.iolib.summary import Summary
model = self.model
title = 'Statespace Model Results'
if start is None:
start = 0
if self.data.dates is not None:
dates = self.data.dates
d = dates[start]
sample = ['%02d-%02d-%02d' % (d.month, d.day, d.year)]
d = dates[-1]
sample += ['- ' + '%02d-%02d-%02d' % (d.month, d.day, d.year)]
else:
sample = [str(start), ' - ' + str(self.model.nobs)]
if model_name is None:
model_name = model.__class__.__name__
top_left = [
('Dep. Variable:', None),
('Model:', [model_name]),
('Date:', None),
('Time:', None),
('Sample:', [sample[0]]),
('', [sample[1]])
]
top_right = [
('No. Observations:', [self.model.nobs]),
('Log Likelihood', ["%#5.3f" % self.llf]),
('AIC', ["%#5.3f" % self.aic]),
('BIC', ["%#5.3f" % self.bic]),
('HQIC', ["%#5.3f" % self.hqic])
]
if hasattr(self, 'cov_type'):
top_left.append(('Covariance Type:', [self.cov_type]))
summary = Summary()
summary.add_table_2cols(self, gleft=top_left, gright=top_right,
title=title)
summary.add_table_params(self, alpha=alpha,
xname=self.data.param_names, use_t=False)
# Add warnings/notes, added to text format only
etext = []
if hasattr(self, 'cov_type'):
etext.append(self.cov_kwds['description'])
if etext:
etext = ["[{0}] {1}".format(i + 1, text)
for i, text in enumerate(etext)]
etext.insert(0, "Warnings:")
summary.add_extra_txt(etext)
return summary
def summary(self, regpyhdfe, yname=None, xname=None, title=None, alpha=.05):
"""
Summarize the Regression Results.
Parameters
----------
yname : str, optional
Name of endogenous (response) variable. The Default is `y`.
xname : list[str], optional
Names for the exogenous variables. Default is `var_##` for ## in
the number of regressors. Must match the number of parameters
in the model.
title : str, optional
Title for the top table. If not None, then this replaces the
default title.
alpha : float
The significance level for the confidence intervals.
Returns
-------
Summary
Instance holding the summary tables and text, which can be printed
or converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : A class that holds summary results.
"""
##########################################################################################################
##########################################################################################################
# https://apithymaxim.wordpress.com/2020/03/16/clustering-standard-errors-by-hand-using-python/
# http://cameron.econ.ucdavis.edu/research/Cameron_Miller_JHR_2015_February.pdf
#N,k,Nclusts = len(df.index),3,50 # Number of observations, right hand side columns counting constant, number of clusters
#X = np.hstack( (np.random.random((N,k-1)), np.ones((N,1)) ) )
#X = get_np_columns(df, ['wks_ue', 'tenure'], intercept=True)
X = regpyhdfe.data[:, 1:]
#y = get_np_columns(df, ['ttl_exp'])
y = np.expand_dims(regpyhdfe.data[:, 0], 1)
# Calculate (X'X)^-1 and the vector of coefficients, beta
XX_inv = np.linalg.inv(X.T.dot(X))
beta = (XX_inv).dot(X.T.dot(y))
resid = y - X.dot(beta)
#ID = np.random.choice([x for x in range(Nclusts)],N) # Vector of cluster IDs
#ID = np.squeeze(get_np_columns(df, ['delete_me']))
ID = np.squeeze(regpyhdfe.groups_np)
c_list = np.unique(ID) # Get unique list of clusters
N, k, Nclusts = X.shape[0], X.shape[1], int(c_list.shape[0])
sum_XuuTX = 0
for c in range(0, Nclusts):
in_cluster = (ID == c_list[c]) # Indicator for given cluster value
resid_c = resid[in_cluster]
uuT = resid_c.dot(resid_c.T)
Xc = X[in_cluster]
XuuTX = Xc.T.dot(uuT).dot(Xc)
sum_XuuTX += XuuTX
adj = (Nclusts / (Nclusts - 1)) * (
(N - 1) / (N - k)
) # Degrees of freedom correction from https://www.stata.com/manuals13/u20.pdf p. 54
# TODO: actually check if the fixed effects are nested
df_a_nested = 1
adj = ((N - 1) / (N - df_a_nested - k)) * (Nclusts / (Nclusts - 1))
V_beta = adj * (XX_inv.dot(sum_XuuTX).dot(XX_inv))
se_beta = np.sqrt(np.diag(V_beta))
# Output data for Stata
for_stata = pd.DataFrame(X)
for_stata.columns = ["X" + str(i) for i in range(k)]
for_stata['ID'] = ID
for_stata['y'] = y
##for_stata.to_stata("resid_test.dta")
print('B', beta, '\n SE: \n', se_beta)
beta = np.squeeze(beta)
t_values = beta / se_beta
print('T values', t_values)
from scipy.stats import t
p_values = 2 * t.cdf(-np.abs(t_values), regpyhdfe.model.df_resid)
# confidence interval size
t_interval = np.asarray(
t.interval(alpha=(1 - alpha), df=regpyhdfe.model.df_resid))
print("t_interval", t_interval)
intervals = np.empty(shape=(beta.shape[0], 2))
# for each variables
for i in range(0, intervals.shape[0]):
intervals[i] = t_interval * se_beta[i] + beta[i]
print('intervals', intervals)
tmp1 = np.linalg.solve(V_beta, np.mat(beta).T)
tmp2 = np.dot(np.mat(beta), tmp1)
fvalue = tmp2[0, 0] / k
import pdb
pdb.set_trace()
print('fvalue', fvalue)
# from statsmodels.stats.stattools import (
# jarque_bera, omni_normtest, durbin_watson)
# jb, jbpv, skew, kurtosis = jarque_bera(self.wresid)
# omni, omnipv = omni_normtest(self.wresid)
# eigvals = self.eigenvals
# condno = self.condition_number
# TODO: Avoid adding attributes in non-__init__
# self.diagn = dict(jb=jb, jbpv=jbpv, skew=skew, kurtosis=kurtosis,
# omni=omni, omnipv=omnipv, condno=condno,
# mineigval=eigvals[-1])
# TODO not used yet
# diagn_left_header = ['Models stats']
# diagn_right_header = ['Residual stats']
# TODO: requiring list/iterable is a bit annoying
# need more control over formatting
# TODO: default do not work if it's not identically spelled
top_left = [
('Dep. Variable:', None),
('Model:', None),
('Method:', ['Least Squares']),
('Date:', None),
('Time:', None),
('No. Observations:', None),
('Df Residuals:', None),
('Df Model:', None),
]
if hasattr(self, 'cov_type'):
top_left.append(('Covariance Type:', [self.cov_type]))
rsquared_type = '' if self.k_constant else ' (uncentered)'
top_right = [
('R-squared' + rsquared_type + ':', ["%#8.3f" % self.rsquared]),
('Adj. R-squared' + rsquared_type + ':',
["%#8.3f" % self.rsquared_adj]),
('F-statistic:', ["%#8.4g" % self.fvalue]),
('Prob (F-statistic):', ["%#6.3g" % self.f_pvalue]),
]
# diagn_left = [('Omnibus:', ["%#6.3f" % omni]),
# ('Prob(Omnibus):', ["%#6.3f" % omnipv]),
# ('Skew:', ["%#6.3f" % skew]),
# ('Kurtosis:', ["%#6.3f" % kurtosis])
# ]
#
# diagn_right = [('Durbin-Watson:',
# ["%#8.3f" % durbin_watson(self.wresid)]
# ),
# ('Jarque-Bera (JB):', ["%#8.3f" % jb]),
# ('Prob(JB):', ["%#8.3g" % jbpv]),
# ]
if title is None:
title = self.model.__class__.__name__ + ' ' + "Regression Results"
# create summary table instance
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right,
yname=yname,
xname=xname,
title=title)
smry.add_table_params(self,
yname=yname,
xname=xname,
alpha=alpha,
use_t=self.use_t)
# smry.add_table_2cols(self, gleft=diagn_left, gright=diagn_right,
# yname=yname, xname=xname,
# title="")
# add warnings/notes, added to text format only
etext = []
if not self.k_constant:
etext.append("R² is computed without centering (uncentered) since the "
"model does not contain a constant.")
if hasattr(self, 'cov_type'):
etext.append(self.cov_kwds['description'])
if self.model.exog.shape[0] < self.model.exog.shape[1]:
wstr = "The input rank is higher than the number of observations."
etext.append(wstr)
# if eigvals[-1] < 1e-10:
# wstr = "The smallest eigenvalue is %6.3g. This might indicate "
# wstr += "that there are\n"
# wstr += "strong multicollinearity problems or that the design "
# wstr += "matrix is singular."
# wstr = wstr % eigvals[-1]
# etext.append(wstr)
# elif condno > 1000: # TODO: what is recommended?
# wstr = "The condition number is large, %6.3g. This might "
# wstr += "indicate that there are\n"
# wstr += "strong multicollinearity or other numerical "
# wstr += "problems."
# wstr = wstr % condno
# etext.append(wstr)
if etext:
etext = [
"[{0}] {1}".format(i + 1, text) for i, text in enumerate(etext)
]
etext.insert(0, "Notes:")
smry.add_extra_txt(etext)
return smry
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""Summarize the Regression Results
Parameters
-----------
yname : string, optional
Default is `y`
xname : list of strings, optional
Default is `var_##` for ## in p the number of regressors
title : string, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary
results
"""
# #TODO: import where we need it (for now), add as cached attributes
# from statsmodels.stats.stattools import (jarque_bera,
# omni_normtest, durbin_watson)
# jb, jbpv, skew, kurtosis = jarque_bera(self.wresid)
# omni, omnipv = omni_normtest(self.wresid)
#
eigvals = self.eigenvals
condno = self.condition_number
#
# self.diagn = dict(jb=jb, jbpv=jbpv, skew=skew, kurtosis=kurtosis,
# omni=omni, omnipv=omnipv, condno=condno,
# mineigval=eigvals[0])
top_left = [('Dep. Variable:', None),
('Model:', None),
('Method:', ['Least Squares']),
('Date:', None),
('Time:', None)
]
top_right = [('Pseudo R-squared:', ["%#8.4g" % self.prsquared]),
('Bandwidth:', ["%#8.4g" % self.bandwidth]),
('Sparsity:', ["%#8.4g" % self.sparsity]),
('No. Observations:', None),
('Df Residuals:', None), #[self.df_resid]), #TODO: spelling
('Df Model:', None) #[self.df_model])
]
# diagn_left = [('Omnibus:', ["%#6.3f" % omni]),
# ('Prob(Omnibus):', ["%#6.3f" % omnipv]),
# ('Skew:', ["%#6.3f" % skew]),
# ('Kurtosis:', ["%#6.3f" % kurtosis])
# ]
#
# diagn_right = [('Durbin-Watson:', ["%#8.3f" % durbin_watson(self.wresid)]),
# ('Jarque-Bera (JB):', ["%#8.3f" % jb]),
# ('Prob(JB):', ["%#8.3g" % jbpv]),
# ('Cond. No.', ["%#8.3g" % condno])
# ]
if title is None:
title = self.model.__class__.__name__ + ' ' + "Regression Results"
#create summary table instance
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right,
yname=yname, xname=xname, title=title)
smry.add_table_params(self, yname=yname, xname=xname, alpha=.05,
use_t=True)
# smry.add_table_2cols(self, gleft=diagn_left, gright=diagn_right,
#yname=yname, xname=xname,
#title="")
#add warnings/notes, added to text format only
etext = []
if eigvals[-1] < 1e-10:
wstr = "The smallest eigenvalue is %6.3g. This might indicate "
wstr += "that there are\n"
wstr += "strong multicollinearity problems or that the design "
wstr += "matrix is singular."
wstr = wstr % eigvals[-1]
etext.append(wstr)
elif condno > 1000: #TODO: what is recommended
wstr = "The condition number is large, %6.3g. This might "
wstr += "indicate that there are\n"
wstr += "strong multicollinearity or other numerical "
wstr += "problems."
wstr = wstr % condno
etext.append(wstr)
if etext:
smry.add_extra_txt(etext)
return smry
def summary(self, yname=None, xname=None, title=None, alpha=.05):
"""Summarize the Regression Results
Parameters
----------
yname : string, optional
Default is `y`
xname : list of strings, optional
Default is `var_##` for ## in p the number of regressors
title : string, optional
Title for the top table. If not None, then this replaces the
default title
alpha : float
significance level for the confidence intervals
Returns
-------
smry : Summary instance
this holds the summary tables and text, which can be printed or
converted to various output formats.
See Also
--------
statsmodels.iolib.summary.Summary : class to hold summary results
"""
eigvals = self.eigenvals
condno = self.condition_number
top_left = [('Dep. Variable:', None),
('Model:', None),
('Method:', ['Least Squares']),
('Date:', None),
('Time:', None)
]
top_right = [('Pseudo R-squared:', ["%#8.4g" % self.prsquared]),
('Bandwidth:', ["%#8.4g" % self.bandwidth]),
('Sparsity:', ["%#8.4g" % self.sparsity]),
('No. Observations:', None),
('Df Residuals:', None),
('Df Model:', None)
]
if title is None:
title = self.model.__class__.__name__ + ' ' + "Regression Results"
# create summary table instance
from statsmodels.iolib.summary import Summary
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right,
yname=yname, xname=xname, title=title)
smry.add_table_params(self, yname=yname, xname=xname, alpha=alpha,
use_t=self.use_t)
# add warnings/notes, added to text format only
etext = []
if eigvals[-1] < 1e-10:
wstr = "The smallest eigenvalue is %6.3g. This might indicate "
wstr += "that there are\n"
wstr += "strong multicollinearity problems or that the design "
wstr += "matrix is singular."
wstr = wstr % eigvals[-1]
etext.append(wstr)
elif condno > 1000: # TODO: what is recommended
wstr = "The condition number is large, %6.3g. This might "
wstr += "indicate that there are\n"
wstr += "strong multicollinearity or other numerical "
wstr += "problems."
wstr = wstr % condno
etext.append(wstr)
if etext:
smry.add_extra_txt(etext)
return smry
