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) -> Summary:
"""Summary of test, containing statistic, p-value and critical values"""
table_data = [
("Test Statistic", f"{self.stat:0.3f}"),
("P-value", f"{self.pvalue:0.3f}"),
("ADF Lag length", f"{self.lags:d}"),
("Estimated Root ρ (γ+1)", f"{self.rho:0.3f}"),
]
title = self.name
table = SimpleTable(
table_data,
stubs=None,
title=title,
colwidths=18,
datatypes=[0, 1],
data_aligns=("l", "r"),
)
smry = Summary()
smry.tables.append(table)
cv_string = "Critical Values: "
for val in self.critical_values.keys():
p = str(int(val)) + "%"
cv_string += f"{self.critical_values[val]:0.2f}"
cv_string += " (" + p + ")"
cv_string += ", "
# Remove trailing ,<space>
cv_string = cv_string[:-2]
extra_text = [
"Trend: " + TREND_DESCRIPTION[self._trend],
cv_string,
"Null Hypothesis: " + self.null_hypothesis,
"Alternative Hypothesis: " + self.alternative_hypothesis,
"Distribution Order: " + str(self.distribution_order),
]
smry.add_extra_txt(extra_text)
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
"""
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"):
"""
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=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=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):
"""Summary of test, containing statistic, p-value and critical values
"""
table_data = [('Test Statistic', '{0:0.3f}'.format(self.stat)),
('P-value', '{0:0.3f}'.format(self.pvalue)),
('Lags', '{0:d}'.format(self.lags))]
title = self._title
if not title:
title = self._test_name + " Results"
table = SimpleTable(table_data, stubs=None, title=title, colwidths=18,
datatypes=[0, 1], data_aligns=("l", "r"))
smry = Summary()
smry.tables.append(table)
cv_string = 'Critical Values: '
cv = self._critical_values.keys()
g = lambda x: float(x.split('%')[0])
cv_numeric = array(lmap(g, cv))
cv_numeric = sort(cv_numeric)
for val in cv_numeric:
p = str(int(val)) + '%'
cv_string += '{0:0.2f}'.format(self._critical_values[p])
cv_string += ' (' + p + ')'
if val != cv_numeric[-1]:
cv_string += ', '
extra_text = ['Trend: ' + TREND_DESCRIPTION[self._trend],
cv_string,
'Null Hypothesis: ' + self.null_hypothesis,
'Alternative Hypothesis: ' + self.alternative_hypothesis]
smry.add_extra_txt(extra_text)
if self._summary_text:
smry.add_extra_txt(self._summary_text)
return smry
def summary(self) -> Summary:
"""
Summary of the model, containing estimated parameters and std. errors
Returns
-------
Summary
A summary instance with method that support export to text, csv
or latex.
"""
if self._bandwidth != int(self._bandwidth):
bw = str_format(self._bandwidth)
else:
bw = str(int(self._bandwidth))
top_left = [
("Trend:", SHORT_TREND_DESCRIPTION[self._trend]),
("Kernel:", str(self._kernel)),
("Bandwidth:", bw),
("", ""),
("", ""),
("", ""),
]
top_right = self._top_right()
smry = Summary()
title = self._estimator_type
table = self._top_table(top_left, top_right, title)
# Top Table
# Parameter table
smry.tables.append(table)
params = np.asarray(self.params)
stubs = list(self.params.index)
se = np.asarray(self.std_errors)
tstats = np.asarray(self.tvalues)
pvalues = np.asarray(self.pvalues)
title = "Cointegrating Vector"
table = self._param_table(params, se, tstats, pvalues, stubs, title)
smry.tables.append(table)
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):
"""Summary of test, containing statistic, p-value and critical values
"""
table_data = [('Test Statistic', '{0:0.3f}'.format(self.stat)),
('P-value', '{0:0.3f}'.format(self.pvalue)),
('Lags', '{0:d}'.format(self.lags))]
title = self._title
if not title:
title = self._test_name + " Results"
table = SimpleTable(table_data,
stubs=None,
title=title,
colwidths=18,
datatypes=[0, 1],
data_aligns=("l", "r"))
smry = Summary()
smry.tables.append(table)
cv_string = 'Critical Values: '
cv = self._critical_values.keys()
g = lambda x: float(x.split('%')[0])
cv_numeric = array(lmap(g, cv))
cv_numeric = sort(cv_numeric)
for val in cv_numeric:
p = str(int(val)) + '%'
cv_string += '{0:0.2f}'.format(self._critical_values[p])
cv_string += ' (' + p + ')'
if val != cv_numeric[-1]:
cv_string += ', '
extra_text = [
'Trend: ' + TREND_DESCRIPTION[self._trend], cv_string,
'Null Hypothesis: ' + self.null_hypothesis,
'Alternative Hypothesis: ' + self.alternative_hypothesis
]
smry.add_extra_txt(extra_text)
if self._summary_text:
smry.add_extra_txt(self._summary_text)
return smry
def summary(self):
"""
Constructs a summary of the results from a fit model.
Returns
-------
summary : Summary instance
Object that contains tables and facilitated export to text, html or
latex
"""
# Summary layout
# 1. Overall information
# 2. Mean parameters
# 3. Volatility parameters
# 4. Distribution parameters
# 5. Notes
model = self.model
model_name = model.name + ' - ' + model.volatility.name
# Summary Header
top_left = [('Dep. Variable:', self._dep_name),
('Mean Model:', model.name),
('Vol Model:', model.volatility.name),
('Distribution:', model.distribution.name),
('Method:', 'Maximum Likelihood'), ('', ''),
('Date:', self._datetime.strftime('%a, %b %d %Y')),
('Time:', self._datetime.strftime('%H:%M:%S'))]
top_right = [('R-squared:', '%#8.3f' % self.rsquared),
('Adj. R-squared:', '%#8.3f' % self.rsquared_adj),
('Log-Likelihood:', '%#10.6g' % self.loglikelihood),
('AIC:', '%#10.6g' % self.aic),
('BIC:', '%#10.6g' % self.bic),
('No. Observations:', self._nobs),
('Df Residuals:', self.nobs - self.num_params),
('Df Model:', self.num_params)]
title = model_name + ' Model Results'
stubs = []
vals = []
for stub, val in top_left:
stubs.append(stub)
vals.append([val])
table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)
# create summary table instance
smry = Summary()
# Top Table
# Parameter table
fmt = fmt_2cols
fmt['data_fmts'][1] = '%18s'
top_right = [('%-21s' % (' ' + k), v) for k, v in top_right]
stubs = []
vals = []
for stub, val in top_right:
stubs.append(stub)
vals.append([val])
table.extend_right(SimpleTable(vals, stubs=stubs))
smry.tables.append(table)
conf_int = np.asarray(self.conf_int())
conf_int_str = []
for c in conf_int:
conf_int_str.append('[' + format_float_fixed(c[0], 7, 3) + ',' +
format_float_fixed(c[1], 7, 3) + ']')
stubs = self._names
header = ['coef', 'std err', 't', 'P>|t|', '95.0% Conf. Int.']
vals = (self.params, self.std_err, self.tvalues, self.pvalues,
conf_int_str)
formats = [(10, 4), (9, 3), (9, 3), (9, 3), None]
pos = 0
param_table_data = []
for _ in range(len(vals[0])):
row = []
for i, val in enumerate(vals):
if isinstance(val[pos], np.float64):
converted = format_float_fixed(val[pos], *formats[i])
else:
converted = val[pos]
row.append(converted)
pos += 1
param_table_data.append(row)
mc = self.model.num_params
vc = self.model.volatility.num_params
dc = self.model.distribution.num_params
counts = (mc, vc, dc)
titles = ('Mean Model', 'Volatility Model', 'Distribution')
total = 0
for title, count in zip(titles, counts):
if count == 0:
continue
table_data = param_table_data[total:total + count]
table_stubs = stubs[total:total + count]
total += count
table = SimpleTable(table_data,
stubs=table_stubs,
txt_fmt=fmt_params,
headers=header,
title=title)
smry.tables.append(table)
extra_text = ['Covariance estimator: ' + self.cov_type]
if self.convergence_flag:
extra_text.append("""
WARNING: The optimizer did not indicate sucessful convergence. The message was
{string_message}. See convergence_flag.""".format(
string_message=self._optim_output[-1]))
smry.add_extra_txt(extra_text)
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
def summary(self, alpha=.05):
"""
Returns a summary table for marginal effects
Parameters
----------
alpha : float
Number between 0 and 1. The confidence intervals have the
probability 1-alpha.
Returns
-------
Summary : SummaryTable
A SummaryTable instance
"""
_check_at_is_all(self.margeff_options)
results = self.results
model = results.model
title = model.__class__.__name__ + " Marginal Effects"
method = self.margeff_options['method']
top_left = [('Dep. Variable:', [model.endog_names]),
('Method:', [method]),
('At:', [self.margeff_options['at']]),]
from statsmodels.iolib.summary import (Summary, summary_params,
table_extend)
exog_names = model.exog_names[:] # copy
smry = Summary()
# sigh, we really need to hold on to this in _data...
_, const_idx = _get_const_index(model.exog)
if const_idx is not None:
exog_names.pop(const_idx)
J = int(getattr(model, "J", 1))
if J > 1:
yname, yname_list = results._get_endog_name(model.endog_names,
None, all=True)
else:
yname = model.endog_names
yname_list = [yname]
smry.add_table_2cols(self, gleft=top_left, gright=[],
yname=yname, xname=exog_names, title=title)
#NOTE: add_table_params is not general enough yet for margeff
# could use a refactor with getattr instead of hard-coded params
# tvalues etc.
table = []
conf_int = self.conf_int(alpha)
margeff = self.margeff
margeff_se = self.margeff_se
tvalues = self.tvalues
pvalues = self.pvalues
if J > 1:
for eq in range(J):
restup = (results, margeff[:,eq], margeff_se[:,eq],
tvalues[:,eq], pvalues[:,eq], conf_int[:,:,eq])
tble = summary_params(restup, yname=yname_list[eq],
xname=exog_names, alpha=alpha, use_t=False,
skip_header=True)
tble.title = yname_list[eq]
# overwrite coef with method name
header = ['', _transform_names[method], 'std err', 'z',
'P>|z|', '[%3.1f%% Conf. Int.]' % (100-alpha*100)]
tble.insert_header_row(0, header)
#from IPython.core.debugger import Pdb; Pdb().set_trace()
table.append(tble)
table = table_extend(table, keep_headers=True)
else:
restup = (results, margeff, margeff_se, tvalues, pvalues, conf_int)
table = summary_params(restup, yname=yname, xname=exog_names,
alpha=alpha, use_t=False, skip_header=True)
header = ['', _transform_names[method], 'std err', 'z',
'P>|z|', '[%3.1f%% Conf. Int.]' % (100-alpha*100)]
table.insert_header_row(0, header)
smry.tables.append(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 summary(self) -> Summary:
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
"""
# #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, impact_date=None, impacted_variable=None,
update_date=None, updated_variable=None,
impacts_groupby='impact date', details_groupby='update date',
show_revisions_columns=None, sparsify=True,
include_details_tables=None, include_revisions_tables=False,
float_format='%.2f'):
"""
Create summary tables describing news and impacts
Parameters
----------
impact_date : int, str, datetime, list, array, or slice, optional
Observation index label or slice of labels specifying particular
impact periods to display. The impact date(s) describe the periods
in which impacted variables were *affected* by the news. If this
argument is given, the impact and details tables will only show
this impact date or dates. Note that this argument is passed to the
Pandas `loc` accessor, and so it should correspond to the labels of
the model's index. If the model was created with data in a list or
numpy array, then these labels will be zero-indexes observation
integers.
impacted_variable : str, list, array, or slice, optional
Observation variable label or slice of labels specifying particular
impacted variables to display. The impacted variable(s) describe
the variables that were *affected* by the news. If you do not know
the labels for the variables, check the `endog_names` attribute of
the model instance.
update_date : int, str, datetime, list, array, or slice, optional
Observation index label or slice of labels specifying particular
updated periods to display. The updated date(s) describe the
periods in which the new data points were available that generated
the news). See the note on `impact_date` for details about what
these labels are.
updated_variable : str, list, array, or slice, optional
Observation variable label or slice of labels specifying particular
updated variables to display. The updated variable(s) describe the
variables that were *affected* by the news. If you do not know the
labels for the variables, check the `endog_names` attribute of the
model instance.
impacts_groupby : {impact date, impacted date}
The primary variable for grouping results in the impacts table. The
default is to group by update date.
details_groupby : str
One of "update date", "updated date", "impact date", or
"impacted date". The primary variable for grouping results in the
details table. Only used if the details tables are included. The
default is to group by update date.
show_revisions_columns : bool, optional
If set to False, the impacts table will not show the impacts from
data revisions or the total impacts. Default is to show the
revisions and totals columns if any revisions were made and
otherwise to hide them.
sparsify : bool, optional, default True
Set to False for the table to include every one of the multiindex
keys at each row.
include_details_tables : bool, optional
If set to True, the summary will show tables describing the details
of how news from specific updates translate into specific impacts.
These tables can be very long, particularly in cases where there
were many updates and in multivariate models. The default is to
show detailed tables only for univariate models.
include_revisions_tables : bool, optional
If set to True, the summary will show tables describing the
revisions and updates that lead to impacts on variables of
interest.
float_format : str, optional
Formatter format string syntax for converting numbers to strings.
Default is '%.2f'.
Returns
-------
summary_tables : Summary
Summary tables describing news and impacts. Basic tables include:
- A table with general information about the sample.
- A table describing the impacts of revisions and news.
- Tables describing revisions in the dataset since the previous
results set (unless `include_revisions_tables=False`).
In univariate models or if `include_details_tables=True`, one or
more tables will additionally be included describing the details
of how news from specific updates translate into specific impacts.
See Also
--------
summary_impacts
summary_details
summary_revisions
summary_updates
"""
# Default for include_details_tables
if include_details_tables is None:
include_details_tables = self.updated.model.k_endog == 1
# Model specification results
model = self.model.model
title = 'News'
def get_sample(model):
if model._index_dates:
ix = model._index
d = ix[0]
sample = ['%s' % d]
d = ix[-1]
sample += ['- ' + '%s' % d]
else:
sample = [str(0), ' - ' + str(model.nobs)]
return sample
previous_sample = get_sample(self.previous.model)
revised_sample = get_sample(self.updated.model)
# Standardize the model name as a list of str
model_name = model.__class__.__name__
# Top summary table
top_left = [('Model:', [model_name]),
('Date:', None),
('Time:', None)]
top_right = [
('Original sample:', [previous_sample[0]]),
('', [previous_sample[1]]),
('Update through:', [revised_sample[1][2:]]),
('No. Revisions:', [len(self.revisions_ix)]),
('No. New datapoints:', [len(self.updates_ix)])]
summary = Summary()
self.model.endog_names = self.model.model.endog_names
summary.add_table_2cols(self, gleft=top_left, gright=top_right,
title=title)
table_ix = 1
# Impact table
summary.tables.insert(table_ix, self.summary_impacts(
impact_date=impact_date, impacted_variable=impacted_variable,
groupby=impacts_groupby,
show_revisions_columns=show_revisions_columns, sparsify=sparsify,
float_format=float_format))
table_ix += 1
# News table
if len(self.updates_iloc) > 0:
summary.tables.insert(
table_ix, self.summary_news(sparsify=sparsify))
table_ix += 1
# Detail tables
multiple_tables = self.updated.model.k_endog > 1
details_tables = self.summary_details(
impact_date=impact_date, impacted_variable=impacted_variable,
groupby=details_groupby, sparsify=sparsify,
float_format=float_format, multiple_tables=multiple_tables)
if not multiple_tables:
details_tables = [details_tables]
if include_details_tables:
for table in details_tables:
summary.tables.insert(table_ix, table)
table_ix += 1
# Revisions
if include_revisions_tables and len(self.revisions_iloc) > 0:
summary.tables.insert(
table_ix, self.summary_revisions(sparsify=sparsify))
table_ix += 1
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, 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):
"""Summary table of model estimation results"""
title = self._method + ' Estimation Summary'
mod = self.model
top_left = [('Dep. Variable:', mod.dependent.cols[0]),
('Estimator:', self._method),
('No. Observations:', self.nobs),
('Date:', self._datetime.strftime('%a, %b %d %Y')),
('Time:', self._datetime.strftime('%H:%M:%S')),
('Cov. Estimator:', self._cov_type), ('', '')]
top_right = [('R-squared:', _str(self.rsquared)),
('Adj. R-squared:', _str(self.rsquared_adj)),
('F-statistic:', _str(self.f_statistic.stat)),
('P-value (F-stat)', pval_format(self.f_statistic.pval)),
('Distribution:', str(self.f_statistic.dist_name)),
('', ''), ('', '')]
stubs = []
vals = []
for stub, val in top_left:
stubs.append(stub)
vals.append([val])
table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)
# create summary table instance
smry = Summary()
# Top Table
# Parameter table
fmt = fmt_2cols
fmt['data_fmts'][1] = '%18s'
top_right = [('%-21s' % (' ' + k), v) for k, v in top_right]
stubs = []
vals = []
for stub, val in top_right:
stubs.append(stub)
vals.append([val])
table.extend_right(SimpleTable(vals, stubs=stubs))
smry.tables.append(table)
param_data = c_[self.params.values[:, None],
self.std_errors.values[:, None],
self.tstats.values[:, None], self.pvalues.values[:,
None],
self.conf_int()]
data = []
for row in param_data:
txt_row = []
for i, v in enumerate(row):
f = _str
if i == 3:
f = pval_format
txt_row.append(f(v))
data.append(txt_row)
title = 'Parameter Estimates'
table_stubs = list(self.params.index)
header = [
'Parameters', 'Std. Err.', 'T-stat', 'P-value', 'Lower CI',
'Upper CI'
]
table = SimpleTable(data,
stubs=table_stubs,
txt_fmt=fmt_params,
headers=header,
title=title)
smry.tables.append(table)
instruments = self.model.instruments
if instruments.shape[1] > 0:
extra_text = []
endog = self.model.endog
extra_text.append('Endogenous: ' + ', '.join(endog.cols))
extra_text.append('Instruments: ' + ', '.join(instruments.cols))
cov_descr = str(self._cov_estimator)
for line in cov_descr.split('\n'):
extra_text.append(line)
smry.add_extra_txt(extra_text)
return smry
def summary(self):
"""
Summarize the fitted Model
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
"""
from statsmodels.iolib.summary import Summary
from statsmodels.iolib.table import SimpleTable
model = self.model
title = model.__class__.__name__ + ' Model Results'
dep_variable = 'endog'
if isinstance(self.model.endog, pd.DataFrame):
dep_variable = self.model.endog.columns[0]
elif isinstance(self.model.endog, pd.Series):
dep_variable = self.model.endog.name
seasonal_periods = None if self.model.seasonal is None else self.model.seasonal_periods
lookup = {
'add': 'Additive',
'additive': 'Additive',
'mul': 'Multiplicative',
'multiplicative': 'Multiplicative',
None: 'None'
}
transform = self.params['use_boxcox']
box_cox_transform = True if transform else False
box_cox_coeff = transform if isinstance(transform,
str) else self.params['lamda']
if isinstance(box_cox_coeff, float):
box_cox_coeff = '{:>10.5f}'.format(box_cox_coeff)
top_left = [('Dep. Variable:', [dep_variable]),
('Model:', [model.__class__.__name__]),
('Optimized:', [str(np.any(self.optimized))]),
('Trend:', [lookup[self.model.trend]]),
('Seasonal:', [lookup[self.model.seasonal]]),
('Seasonal Periods:', [str(seasonal_periods)]),
('Box-Cox:', [str(box_cox_transform)]),
('Box-Cox Coeff.:', [str(box_cox_coeff)])]
top_right = [('No. Observations:', [str(len(self.model.endog))]),
('SSE', ['{:5.3f}'.format(self.sse)]),
('AIC', ['{:5.3f}'.format(self.aic)]),
('BIC', ['{:5.3f}'.format(self.bic)]),
('AICC', ['{:5.3f}'.format(self.aicc)]), ('Date:', None),
('Time:', None)]
smry = Summary()
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right,
title=title)
formatted = self.params_formatted # type: pd.DataFrame
def _fmt(x):
abs_x = np.abs(x)
scale = 1
if abs_x != 0:
scale = int(np.log10(abs_x))
if scale > 4 or scale < -3:
return '{:>20.5g}'.format(x)
dec = min(7 - scale, 7)
fmt = '{{:>20.{0}f}}'.format(dec)
return fmt.format(x)
tab = []
for _, vals in formatted.iterrows():
tab.append([
_fmt(vals.iloc[1]), '{0:>20}'.format(vals.iloc[0]),
'{0:>20}'.format(str(bool(vals.iloc[2])))
])
params_table = SimpleTable(tab,
headers=['coeff', 'code', 'optimized'],
title="",
stubs=list(formatted.index))
smry.tables.append(params_table)
return smry
def summary(self):
"""Summary table of model comparison"""
smry = Summary()
models = list(self._results.keys())
title = 'Model Comparison'
stubs = [
'Dep. Variable', 'Estimator', 'No. Observations', 'Cov. Est.',
'R-squared', 'Adj. R-squared', 'F-statistic', 'P-value (F-stat)'
]
dep_name = {}
for key in self._results:
dep_name[key] = self._results[key].model.dependent.cols[0]
dep_name = Series(dep_name)
vals = concat([
dep_name, self.estimator_method, self.nobs, self.cov_estimator,
self.rsquared, self.rsquared_adj, self.f_statistic
], 1)
vals = [[i for i in v] for v in vals.T.values]
vals[2] = [str(v) for v in vals[2]]
for i in range(4, len(vals)):
vals[i] = [_str(v) for v in vals[i]]
params = self.params
tstats = self.tstats
params_fmt = []
params_stub = []
for i in range(len(params)):
params_fmt.append([_str(v) for v in params.values[i]])
tstats_fmt = []
for v in tstats.values[i]:
v_str = _str(v)
v_str = '({0})'.format(v_str) if v_str.strip() else v_str
tstats_fmt.append(v_str)
params_fmt.append(tstats_fmt)
params_stub.append(params.index[i])
params_stub.append(' ')
vals = table_concat((vals, params_fmt))
stubs = stub_concat((stubs, params_stub))
all_instr = []
for key in self._results:
res = self._results[key]
all_instr.append(res.model.instruments.cols)
ninstr = max(map(lambda l: len(l), all_instr))
instruments = []
instrument_stub = ['Instruments']
for i in range(ninstr):
if i > 0:
instrument_stub.append('')
row = []
for j in range(len(self._results)):
instr = all_instr[j]
if len(instr) > i:
row.append(instr[i])
else:
row.append('')
instruments.append(row)
if instruments:
vals = table_concat((vals, instruments))
stubs = stub_concat((stubs, instrument_stub))
txt_fmt = default_txt_fmt.copy()
txt_fmt['data_aligns'] = 'r'
txt_fmt['header_align'] = 'r'
table = SimpleTable(vals,
headers=models,
title=title,
stubs=stubs,
txt_fmt=txt_fmt)
smry.tables.append(table)
smry.add_extra_txt(['T-stats reported in parentheses'])
return smry
def summary(self):
"""
Summarize the fitted Model
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
"""
from statsmodels.iolib.summary import Summary
from statsmodels.iolib.table import SimpleTable
model = self.model
title = model.__class__.__name__ + ' Model Results'
dep_variable = 'endog'
if isinstance(self.model.endog, pd.DataFrame):
dep_variable = self.model.endog.columns[0]
elif isinstance(self.model.endog, pd.Series):
dep_variable = self.model.endog.name
seasonal_periods = None if self.model.seasonal is None else self.model.seasonal_periods
lookup = {'add': 'Additive', 'additive': 'Additive',
'mul': 'Multiplicative', 'multiplicative': 'Multiplicative', None: 'None'}
transform = self.params['use_boxcox']
box_cox_transform = True if transform else False
box_cox_coeff = transform if isinstance(transform, string_types) else self.params['lamda']
if isinstance(box_cox_coeff, float):
box_cox_coeff = '{:>10.5f}'.format(box_cox_coeff)
top_left = [('Dep. Variable:', [dep_variable]),
('Model:', [model.__class__.__name__]),
('Optimized:', [str(np.any(self.optimized))]),
('Trend:', [lookup[self.model.trend]]),
('Seasonal:', [lookup[self.model.seasonal]]),
('Seasonal Periods:', [str(seasonal_periods)]),
('Box-Cox:', [str(box_cox_transform)]),
('Box-Cox Coeff.:', [str(box_cox_coeff)])]
top_right = [
('No. Observations:', [str(len(self.model.endog))]),
('SSE', ['{:5.3f}'.format(self.sse)]),
('AIC', ['{:5.3f}'.format(self.aic)]),
('BIC', ['{:5.3f}'.format(self.bic)]),
('AICC', ['{:5.3f}'.format(self.aicc)]),
('Date:', None),
('Time:', None)]
smry = Summary()
smry.add_table_2cols(self, gleft=top_left, gright=top_right,
title=title)
formatted = self.params_formatted # type: pd.DataFrame
def _fmt(x):
abs_x = np.abs(x)
scale = 1
if abs_x != 0:
scale = int(np.log10(abs_x))
if scale > 4 or scale < -3:
return '{:>20.5g}'.format(x)
dec = min(7 - scale, 7)
fmt = '{{:>20.{0}f}}'.format(dec)
return fmt.format(x)
tab = []
for _, vals in formatted.iterrows():
tab.append([_fmt(vals.iloc[1]),
'{0:>20}'.format(vals.iloc[0]),
'{0:>20}'.format(str(bool(vals.iloc[2])))])
params_table = SimpleTable(tab, headers=['coeff', 'code', 'optimized'],
title="",
stubs=list(formatted.index))
smry.tables.append(params_table)
return smry
def summary(self):
"""Summary table of model estimation results"""
title = self.name + ' Estimation Summary'
mod = self.model
top_left = [('Dep. Variable:', mod.dependent.vars[0]),
('Estimator:', self.name),
('No. Observations:', self.nobs),
('Date:', self._datetime.strftime('%a, %b %d %Y')),
('Time:', self._datetime.strftime('%H:%M:%S')),
('Cov. Estimator:', self._cov_type), ('', ''),
('Entities:', str(int(self.entity_info['total']))),
('Avg Obs:', _str(self.entity_info['mean'])),
('Min Obs:', _str(self.entity_info['min'])),
('Max Obs:', _str(self.entity_info['max'])), ('', ''),
('Time periods:', str(int(self.time_info['total']))),
('Avg Obs:', _str(self.time_info['mean'])),
('Min Obs:', _str(self.time_info['min'])),
('Max Obs:', _str(self.time_info['max'])), ('', '')]
is_invalid = np.isfinite(self.f_statistic.stat)
f_stat = _str(self.f_statistic.stat) if is_invalid else '--'
f_pval = pval_format(self.f_statistic.pval) if is_invalid else '--'
f_dist = self.f_statistic.dist_name if is_invalid else '--'
f_robust = _str(self.f_statistic_robust.stat) if is_invalid else '--'
f_robust_pval = pval_format(
self.f_statistic_robust.pval) if is_invalid else '--'
f_robust_name = self.f_statistic_robust.dist_name if is_invalid else '--'
top_right = [
('R-squared:', _str(self.rsquared)),
('R-squared (Between):', _str(self.rsquared_between)),
('R-squared (Within):', _str(self.rsquared_within)),
('R-squared (Overall):', _str(self.rsquared_overall)),
('Log-likelihood', _str(self._loglik)),
('', ''),
('F-statistic:', f_stat),
('P-value', f_pval),
('Distribution:', f_dist),
('', ''),
('F-statistic (robust):', f_robust),
('P-value', f_robust_pval),
('Distribution:', f_robust_name),
('', ''),
('', ''),
('', ''),
('', ''),
]
stubs = []
vals = []
for stub, val in top_left:
stubs.append(stub)
vals.append([val])
table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)
# create summary table instance
smry = Summary()
# Top Table
# Parameter table
fmt = fmt_2cols
fmt['data_fmts'][1] = '%18s'
top_right = [('%-21s' % (' ' + k), v) for k, v in top_right]
stubs = []
vals = []
for stub, val in top_right:
stubs.append(stub)
vals.append([val])
table.extend_right(SimpleTable(vals, stubs=stubs))
smry.tables.append(table)
param_data = np.c_[self.params.values[:, None],
self.std_errors.values[:, None],
self.tstats.values[:,
None], self.pvalues.values[:,
None],
self.conf_int()]
data = []
for row in param_data:
txt_row = []
for i, v in enumerate(row):
f = _str
if i == 3:
f = pval_format
txt_row.append(f(v))
data.append(txt_row)
title = 'Parameter Estimates'
table_stubs = list(self.params.index)
header = [
'Parameters', 'Std. Err.', 'T-stat', 'P-value', 'Lower CI',
'Upper CI'
]
table = SimpleTable(data,
stubs=table_stubs,
txt_fmt=fmt_params,
headers=header,
title=title)
smry.tables.append(table)
return smry
def summary(self):
"""
Constructs a summary of the results from a fit model.
Returns
-------
summary : Summary instance
Object that contains tables and facilitated export to text, html or
latex
"""
# Summary layout
# 1. Overall information
# 2. Mean parameters
# 3. Volatility parameters
# 4. Distribution parameters
# 5. Notes
model = self.model
model_name = model.name + ' - ' + model.volatility.name
# Summary Header
top_left = [('Dep. Variable:', self._dep_name),
('Mean Model:', model.name),
('Vol Model:', model.volatility.name),
('Distribution:', model.distribution.name),
('Method:', 'Maximum Likelihood'),
('', ''),
('Date:', self._datetime.strftime('%a, %b %d %Y')),
('Time:', self._datetime.strftime('%H:%M:%S'))]
top_right = [('R-squared:', '%#8.3f' % self.rsquared),
('Adj. R-squared:', '%#8.3f' % self.rsquared_adj),
('Log-Likelihood:', '%#10.6g' % self.loglikelihood),
('AIC:', '%#10.6g' % self.aic),
('BIC:', '%#10.6g' % self.bic),
('No. Observations:', self._nobs),
('Df Residuals:', self.nobs - self.num_params),
('Df Model:', self.num_params)]
title = model_name + ' Model Results'
stubs = []
vals = []
for stub, val in top_left:
stubs.append(stub)
vals.append([val])
table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)
# create summary table instance
smry = Summary()
# Top Table
# Parameter table
fmt = fmt_2cols
fmt['data_fmts'][1] = '%18s'
top_right = [('%-21s' % (' ' + k), v) for k, v in top_right]
stubs = []
vals = []
for stub, val in top_right:
stubs.append(stub)
vals.append([val])
table.extend_right(SimpleTable(vals, stubs=stubs))
smry.tables.append(table)
conf_int = np.asarray(self.conf_int())
conf_int_str = []
for c in conf_int:
conf_int_str.append('[' + format_float_fixed(c[0], 7, 3)
+ ',' + format_float_fixed(c[1], 7, 3) + ']')
stubs = self._names
header = ['coef', 'std err', 't', 'P>|t|', '95.0% Conf. Int.']
vals = (self.params,
self.std_err,
self.tvalues,
self.pvalues,
conf_int_str)
formats = [(10, 4), (9, 3), (9, 3), (9, 3), None]
pos = 0
param_table_data = []
for _ in range(len(vals[0])):
row = []
for i, val in enumerate(vals):
if isinstance(val[pos], np.float64):
converted = format_float_fixed(val[pos], *formats[i])
else:
converted = val[pos]
row.append(converted)
pos += 1
param_table_data.append(row)
mc = self.model.num_params
vc = self.model.volatility.num_params
dc = self.model.distribution.num_params
counts = (mc, vc, dc)
titles = ('Mean Model', 'Volatility Model', 'Distribution')
total = 0
for title, count in zip(titles, counts):
if count == 0:
continue
table_data = param_table_data[total:total + count]
table_stubs = stubs[total:total + count]
total += count
table = SimpleTable(table_data,
stubs=table_stubs,
txt_fmt=fmt_params,
headers=header, title=title)
smry.tables.append(table)
extra_text = ['Covariance estimator: ' + self.cov_type]
if self.convergence_flag:
extra_text.append("""
WARNING: The optimizer did not indicate sucessful convergence. The message was
{string_message}. See convergence_flag.""".format(
string_message=self._optim_output[-1]))
smry.add_extra_txt(extra_text)
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):
"""
Constructs a summary of the results from a fit model.
Returns
-------
summary : Summary instance
Object that contains tables and facilitated export to text, html or
latex
"""
# Summary layout
# 1. Overall information
# 2. Mean parameters
# 3. Volatility parameters
# 4. Distribution parameters
# 5. Notes
model = self.model
model_name = model.name + ' - ' + model.volatility.name
# Summary Header
top_left = [('Dep. Variable:', self._dep_name),
('Mean Model:', model.name),
('Vol Model:', model.volatility.name),
('Distribution:', model.distribution.name),
('Method:', 'User-specified Parameters'),
('', ''),
('Date:', self._datetime.strftime('%a, %b %d %Y')),
('Time:', self._datetime.strftime('%H:%M:%S'))]
top_right = [('R-squared:', '--'),
('Adj. R-squared:', '--'),
('Log-Likelihood:', '%#10.6g' % self.loglikelihood),
('AIC:', '%#10.6g' % self.aic),
('BIC:', '%#10.6g' % self.bic),
('No. Observations:', self._nobs),
('', ''),
('', ''),]
title = model_name + ' Model Results'
stubs = []
vals = []
for stub, val in top_left:
stubs.append(stub)
vals.append([val])
table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)
# create summary table instance
smry = Summary()
# Top Table
# Parameter table
fmt = fmt_2cols
fmt['data_fmts'][1] = '%18s'
top_right = [('%-21s' % (' ' + k), v) for k, v in top_right]
stubs = []
vals = []
for stub, val in top_right:
stubs.append(stub)
vals.append([val])
table.extend_right(SimpleTable(vals, stubs=stubs))
smry.tables.append(table)
stubs = self._names
header = ['coef']
vals = (self.params,)
formats = [(10, 4)]
pos = 0
param_table_data = []
for _ in range(len(vals[0])):
row = []
for i, val in enumerate(vals):
if isinstance(val[pos], np.float64):
converted = format_float_fixed(val[pos], *formats[i])
else:
converted = val[pos]
row.append(converted)
pos += 1
param_table_data.append(row)
mc = self.model.num_params
vc = self.model.volatility.num_params
dc = self.model.distribution.num_params
counts = (mc, vc, dc)
titles = ('Mean Model', 'Volatility Model', 'Distribution')
total = 0
for title, count in zip(titles, counts):
if count == 0:
continue
table_data = param_table_data[total:total + count]
table_stubs = stubs[total:total + count]
total += count
table = SimpleTable(table_data,
stubs=table_stubs,
txt_fmt=fmt_params,
headers=header, title=title)
smry.tables.append(table)
extra_text = ('Results generated with user-specified parameters.',
'Since the model was not estimated, there are no std. '
'errors.')
smry.add_extra_txt(extra_text)
return smry
def summary(self):
"""
Summarize the fitted Model
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
"""
from statsmodels.iolib.summary import Summary
from statsmodels.iolib.table import SimpleTable
model = self.model
title = model.__class__.__name__ + " Model Results"
dep_variable = "endog"
orig_endog = self.model.data.orig_endog
if isinstance(orig_endog, pd.DataFrame):
dep_variable = orig_endog.columns[0]
elif isinstance(orig_endog, pd.Series):
dep_variable = orig_endog.name
seasonal_periods = (None if self.model.seasonal is None else
self.model.seasonal_periods)
lookup = {
"add": "Additive",
"additive": "Additive",
"mul": "Multiplicative",
"multiplicative": "Multiplicative",
None: "None",
}
transform = self.params["use_boxcox"]
box_cox_transform = True if transform else False
box_cox_coeff = (transform if isinstance(transform, str) else
self.params["lamda"])
if isinstance(box_cox_coeff, float):
box_cox_coeff = "{:>10.5f}".format(box_cox_coeff)
top_left = [
("Dep. Variable:", [dep_variable]),
("Model:", [model.__class__.__name__]),
("Optimized:", [str(np.any(self.optimized))]),
("Trend:", [lookup[self.model.trend]]),
("Seasonal:", [lookup[self.model.seasonal]]),
("Seasonal Periods:", [str(seasonal_periods)]),
("Box-Cox:", [str(box_cox_transform)]),
("Box-Cox Coeff.:", [str(box_cox_coeff)]),
]
top_right = [
("No. Observations:", [str(len(self.model.endog))]),
("SSE", ["{:5.3f}".format(self.sse)]),
("AIC", ["{:5.3f}".format(self.aic)]),
("BIC", ["{:5.3f}".format(self.bic)]),
("AICC", ["{:5.3f}".format(self.aicc)]),
("Date:", None),
("Time:", None),
]
smry = Summary()
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right,
title=title)
formatted = self.params_formatted # type: pd.DataFrame
def _fmt(x):
abs_x = np.abs(x)
scale = 1
if abs_x != 0:
scale = int(np.log10(abs_x))
if scale > 4 or scale < -3:
return "{:>20.5g}".format(x)
dec = min(7 - scale, 7)
fmt = "{{:>20.{0}f}}".format(dec)
return fmt.format(x)
tab = []
for _, vals in formatted.iterrows():
tab.append([
_fmt(vals.iloc[1]),
"{0:>20}".format(vals.iloc[0]),
"{0:>20}".format(str(bool(vals.iloc[2]))),
])
params_table = SimpleTable(
tab,
headers=["coeff", "code", "optimized"],
title="",
stubs=list(formatted.index),
)
smry.tables.append(params_table)
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=alpha,
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=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, 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, 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
"""
# #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):
"""
Constructs a summary of the results from a fit model.
Returns
-------
summary : Summary instance
Object that contains tables and facilitated export to text, html or
latex
"""
# Summary layout
# 1. Overall information
# 2. Mean parameters
# 3. Volatility parameters
# 4. Distribution parameters
# 5. Notes
model = self.model
model_name = model.name + " - " + model.volatility.name
# Summary Header
top_left = [
("Dep. Variable:", self._dep_name),
("Mean Model:", model.name),
("Vol Model:", model.volatility.name),
("Distribution:", model.distribution.name),
("Method:", "User-specified Parameters"),
("", ""),
("Date:", self._datetime.strftime("%a, %b %d %Y")),
("Time:", self._datetime.strftime("%H:%M:%S")),
]
top_right = [
("R-squared:", "--"),
("Adj. R-squared:", "--"),
("Log-Likelihood:", "%#10.6g" % self.loglikelihood),
("AIC:", "%#10.6g" % self.aic),
("BIC:", "%#10.6g" % self.bic),
("No. Observations:", self._nobs),
("", ""),
("", ""),
]
title = model_name + " Model Results"
stubs = []
vals = []
for stub, val in top_left:
stubs.append(stub)
vals.append([val])
table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)
# create summary table instance
smry = Summary()
# Top Table
# Parameter table
fmt = fmt_2cols
fmt["data_fmts"][1] = "%18s"
top_right = [("%-21s" % (" " + k), v) for k, v in top_right]
stubs = []
vals = []
for stub, val in top_right:
stubs.append(stub)
vals.append([val])
table.extend_right(SimpleTable(vals, stubs=stubs))
smry.tables.append(table)
stubs = self._names
header = ["coef"]
vals = (self.params,)
formats = [(10, 4)]
pos = 0
param_table_data = []
for _ in range(len(vals[0])):
row = []
for i, val in enumerate(vals):
if isinstance(val[pos], np.float64):
converted = format_float_fixed(val[pos], *formats[i])
else:
converted = val[pos]
row.append(converted)
pos += 1
param_table_data.append(row)
mc = self.model.num_params
vc = self.model.volatility.num_params
dc = self.model.distribution.num_params
counts = (mc, vc, dc)
titles = ("Mean Model", "Volatility Model", "Distribution")
total = 0
for title, count in zip(titles, counts):
if count == 0:
continue
table_data = param_table_data[total : total + count]
table_stubs = stubs[total : total + count]
total += count
table = SimpleTable(table_data, stubs=table_stubs, txt_fmt=fmt_params, headers=header, title=title)
smry.tables.append(table)
extra_text = (
"Results generated with user-specified parameters.",
"Since the model was not estimated, there are no std. " "errors.",
)
smry.add_extra_txt(extra_text)
return smry
def summary(self) -> Summary:
"""
Summarize the model
Returns
-------
Summary
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
smry = Summary()
model_name = type(model).__name__
title = model_name + " Results"
method = "MLE" if self._use_mle else "OLS/SES"
is_series = isinstance(model.endog_orig, pd.Series)
index = getattr(model.endog_orig, "index", None)
if is_series and isinstance(index, (pd.DatetimeIndex, pd.PeriodIndex)):
sample = [index[0].strftime("%m-%d-%Y")]
sample += ["- " + index[-1].strftime("%m-%d-%Y")]
else:
sample = [str(0), str(model.endog_orig.shape[0])]
dep_name = getattr(model.endog_orig, "name", "endog") or "endog"
top_left = [
("Dep. Variable:", [dep_name]),
("Method:", [method]),
("Date:", None),
("Time:", None),
("Sample:", [sample[0]]),
("", [sample[1]]),
]
method = ("Multiplicative"
if model.method.startswith("mul") else "Additive")
top_right = [
("No. Observations:", [str(self._nobs)]),
("Deseasonalized:", [str(model.deseasonalize)]),
]
if model.deseasonalize:
top_right.extend([
("Deseas. Method:", [method]),
("Period:", [str(model.period)]),
("", [""]),
("", [""]),
])
else:
top_right.extend([("", [""])] * 4)
smry.add_table_2cols(self,
gleft=top_left,
gright=top_right,
title=title)
table_fmt = {"data_fmts": ["%s", "%#0.4g"], "data_aligns": "r"}
data = np.asarray(self.params)[:, None]
st = SimpleTable(
data,
["Parameters", "Estimate"],
list(self.params.index),
title="Parameter Estimates",
txt_fmt=table_fmt,
)
smry.tables.append(st)
return smry
def summary(self):
"""
Constructs a summary of the results from a fit model.
Returns
-------
summary : Summary instance
Object that contains tables and facilitated export to text, html or
latex
"""
# Summary layout
# 1. Overall information
# 2. Mean parameters
# 3. Volatility parameters
# 4. Distribution parameters
# 5. Notes
model = self.model
model_name = model.name + ' - ' + model.volatility.name
# Summary Header
top_left = [('Dep. Variable:', self._dep_name),
('Mean Model:', model.name),
('Vol Model:', model.volatility.name),
('Distribution:', model.distribution.name),
('Method:', 'User-specified Parameters'), ('', ''),
('Date:', self._datetime.strftime('%a, %b %d %Y')),
('Time:', self._datetime.strftime('%H:%M:%S'))]
top_right = [
('R-squared:', '--'),
('Adj. R-squared:', '--'),
('Log-Likelihood:', '%#10.6g' % self.loglikelihood),
('AIC:', '%#10.6g' % self.aic),
('BIC:', '%#10.6g' % self.bic),
('No. Observations:', self._nobs),
('', ''),
('', ''),
]
title = model_name + ' Model Results'
stubs = []
vals = []
for stub, val in top_left:
stubs.append(stub)
vals.append([val])
table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)
# create summary table instance
smry = Summary()
# Top Table
# Parameter table
fmt = fmt_2cols
fmt['data_fmts'][1] = '%18s'
top_right = [('%-21s' % (' ' + k), v) for k, v in top_right]
stubs = []
vals = []
for stub, val in top_right:
stubs.append(stub)
vals.append([val])
table.extend_right(SimpleTable(vals, stubs=stubs))
smry.tables.append(table)
stubs = self._names
header = ['coef']
vals = (self.params, )
formats = [(10, 4)]
pos = 0
param_table_data = []
for _ in range(len(vals[0])):
row = []
for i, val in enumerate(vals):
if isinstance(val[pos], np.float64):
converted = format_float_fixed(val[pos], *formats[i])
else:
converted = val[pos]
row.append(converted)
pos += 1
param_table_data.append(row)
mc = self.model.num_params
vc = self.model.volatility.num_params
dc = self.model.distribution.num_params
counts = (mc, vc, dc)
titles = ('Mean Model', 'Volatility Model', 'Distribution')
total = 0
for title, count in zip(titles, counts):
if count == 0:
continue
table_data = param_table_data[total:total + count]
table_stubs = stubs[total:total + count]
total += count
table = SimpleTable(table_data,
stubs=table_stubs,
txt_fmt=fmt_params,
headers=header,
title=title)
smry.tables.append(table)
extra_text = ('Results generated with user-specified parameters.',
'Since the model was not estimated, there are no std. '
'errors.')
smry.add_extra_txt(extra_text)
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 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 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, 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, 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, alpha=.05):
"""
Returns a summary table for marginal effects
Parameters
----------
alpha : float
Number between 0 and 1. The confidence intervals have the
probability 1-alpha.
Returns
-------
Summary : SummaryTable
A SummaryTable instance
"""
_check_at_is_all(self.margeff_options)
results = self.results
model = results.model
title = model.__class__.__name__ + " Marginal Effects"
method = self.margeff_options['method']
top_left = [
('Dep. Variable:', [model.endog_names]),
('Method:', [method]),
('At:', [self.margeff_options['at']]),
]
from statsmodels.iolib.summary import (Summary, summary_params,
table_extend)
exog_names = model.exog_names[:] # copy
smry = Summary()
# sigh, we really need to hold on to this in _data...
_, const_idx = _get_const_index(model.exog)
if const_idx is not None:
exog_names.pop(const_idx[0])
J = int(getattr(model, "J", 1))
if J > 1:
yname, yname_list = results._get_endog_name(model.endog_names,
None,
all=True)
else:
yname = model.endog_names
yname_list = [yname]
smry.add_table_2cols(self,
gleft=top_left,
gright=[],
yname=yname,
xname=exog_names,
title=title)
#NOTE: add_table_params is not general enough yet for margeff
# could use a refactor with getattr instead of hard-coded params
# tvalues etc.
table = []
conf_int = self.conf_int(alpha)
margeff = self.margeff
margeff_se = self.margeff_se
tvalues = self.tvalues
pvalues = self.pvalues
if J > 1:
for eq in range(J):
restup = (results, margeff[:, eq], margeff_se[:, eq],
tvalues[:, eq], pvalues[:, eq], conf_int[:, :, eq])
tble = summary_params(restup,
yname=yname_list[eq],
xname=exog_names,
alpha=alpha,
use_t=False,
skip_header=True)
tble.title = yname_list[eq]
# overwrite coef with method name
header = [
'', _transform_names[method], 'std err', 'z', 'P>|z|',
'[' + str(alpha / 2),
str(1 - alpha / 2) + ']'
]
tble.insert_header_row(0, header)
#from IPython.core.debugger import Pdb; Pdb().set_trace()
table.append(tble)
table = table_extend(table, keep_headers=True)
else:
restup = (results, margeff, margeff_se, tvalues, pvalues, conf_int)
table = summary_params(restup,
yname=yname,
xname=exog_names,
alpha=alpha,
use_t=False,
skip_header=True)
header = [
'', _transform_names[method], 'std err', 'z', 'P>|z|',
'[' + str(alpha / 2),
str(1 - alpha / 2) + ']'
]
table.insert_header_row(0, header)
smry.tables.append(table)
return smry
def summary(self):
"""
Constructs a summary of the results from a fit model.
Returns
-------
summary : Summary instance
Object that contains tables and facilitated export to text, html or
latex
"""
# Summary layout
# 1. Overall information
# 2. Mean parameters
# 3. Volatility parameters
# 4. Distribution parameters
# 5. Notes
model = self.model
model_name = model.name + " - " + model.volatility.name
# Summary Header
top_left = [
("Dep. Variable:", self._dep_name),
("Mean Model:", model.name),
("Vol Model:", model.volatility.name),
("Distribution:", model.distribution.name),
("Method:", "Maximum Likelihood"),
("", ""),
("Date:", self._datetime.strftime("%a, %b %d %Y")),
("Time:", self._datetime.strftime("%H:%M:%S")),
]
top_right = [
("R-squared:", "%#8.3f" % self.rsquared),
("Adj. R-squared:", "%#8.3f" % self.rsquared_adj),
("Log-Likelihood:", "%#10.6g" % self.loglikelihood),
("AIC:", "%#10.6g" % self.aic),
("BIC:", "%#10.6g" % self.bic),
("No. Observations:", self._nobs),
("Df Residuals:", self.nobs - self.num_params),
("Df Model:", self.num_params),
]
title = model_name + " Model Results"
stubs = []
vals = []
for stub, val in top_left:
stubs.append(stub)
vals.append([val])
table = SimpleTable(vals, txt_fmt=fmt_2cols, title=title, stubs=stubs)
# create summary table instance
smry = Summary()
# Top Table
# Parameter table
fmt = fmt_2cols
fmt["data_fmts"][1] = "%18s"
top_right = [("%-21s" % (" " + k), v) for k, v in top_right]
stubs = []
vals = []
for stub, val in top_right:
stubs.append(stub)
vals.append([val])
table.extend_right(SimpleTable(vals, stubs=stubs))
smry.tables.append(table)
conf_int = np.asarray(self.conf_int())
conf_int_str = []
for c in conf_int:
conf_int_str.append("[" + format_float_fixed(c[0], 7, 3) + "," + format_float_fixed(c[1], 7, 3) + "]")
stubs = self._names
header = ["coef", "std err", "t", "P>|t|", "95.0% Conf. Int."]
vals = (self.params, self.std_err, self.tvalues, self.pvalues, conf_int_str)
formats = [(10, 4), (9, 3), (9, 3), (9, 3), None]
pos = 0
param_table_data = []
for _ in range(len(vals[0])):
row = []
for i, val in enumerate(vals):
if isinstance(val[pos], np.float64):
converted = format_float_fixed(val[pos], *formats[i])
else:
converted = val[pos]
row.append(converted)
pos += 1
param_table_data.append(row)
mc = self.model.num_params
vc = self.model.volatility.num_params
dc = self.model.distribution.num_params
counts = (mc, vc, dc)
titles = ("Mean Model", "Volatility Model", "Distribution")
total = 0
for title, count in zip(titles, counts):
if count == 0:
continue
table_data = param_table_data[total : total + count]
table_stubs = stubs[total : total + count]
total += count
table = SimpleTable(table_data, stubs=table_stubs, txt_fmt=fmt_params, headers=header, title=title)
smry.tables.append(table)
extra_text = ("Covariance estimator: " + self.cov_type,)
smry.add_extra_txt(extra_text)
return smry
