def _stats_table(self):
# TODO: do we want individual statistics or should users just
# use results if wanted?
# Handle overall fit statistics
model = self.model
part2Lstubs = ('No. of Equations:',
'Nobs:',
'Log likelihood:',
'AIC:')
part2Rstubs = ('BIC:',
'HQIC:',
'FPE:',
'Det(Omega_mle):')
part2Ldata = [[model.neqs], [model.nobs], [model.llf], [model.aic]]
part2Rdata = [[model.bic], [model.hqic], [model.fpe], [model.detomega]]
part2Lheader = None
part2L = SimpleTable(part2Ldata, part2Lheader, part2Lstubs,
txt_fmt = self.part2_fmt)
part2R = SimpleTable(part2Rdata, part2Lheader, part2Rstubs,
txt_fmt = self.part2_fmt)
part2L.extend_right(part2R)
return str(part2L)
def _stats_table(self):
# TODO: do we want individual statistics or should users just
# use results if wanted?
# Handle overall fit statistics
model = self.model
part2Lstubs = ('No. of Equations:', 'Nobs:', 'Log likelihood:', 'AIC:')
part2Rstubs = ('BIC:', 'HQIC:', 'FPE:', 'Det(Omega_mle):')
part2Ldata = [[model.neqs], [model.nobs], [model.llf], [model.aic]]
part2Rdata = [[model.bic], [model.hqic], [model.fpe], [model.detomega]]
part2Lheader = None
part2L = SimpleTable(part2Ldata,
part2Lheader,
part2Lstubs,
txt_fmt=self.part2_fmt)
part2R = SimpleTable(part2Rdata,
part2Lheader,
part2Rstubs,
txt_fmt=self.part2_fmt)
part2L.extend_right(part2R)
return str(part2L)
def summary_old(self,
yname=None,
xname=None,
title='Generalized linear model',
returns='text'):
"""
Print a table of results or returns SimpleTable() instance which
summarizes the Generalized linear model results.
Parameters
-----------
yname : string
optional, Default is `Y`
xname : list of strings
optional, Default is `X.#` for # in p the number of regressors
title : string
optional, Defualt is 'Generalized linear model'
returns : string
'text', 'table', 'csv', 'latex', 'html'
Returns
-------
Defualt :
returns='print'
Prints the summarirized results
Option :
returns='text'
Prints the summarirized results
Option :
returns='table'
SimpleTable instance : summarizing the fit of a linear model.
Option :
returns='csv'
returns a string of csv of the results, to import into a
spreadsheet
Option :
returns='latex'
Not implimented yet
Option :
returns='HTML'
Not implimented yet
Examples (needs updating)
--------
>>> import scikits.statsmodels.api as sm
>>> data = sm.datasets.longley.load()
>>> data.exog = sm.add_constant(data.exog)
>>> ols_results = sm.OLS(data.endog, data.exog).results
>>> print ols_results.summary()
...
Notes
-----
stand_errors are not implimented.
conf_int calculated from normal dist.
"""
import time as Time
from scikits.statsmodels.iolib import SimpleTable
yname = 'Y'
if xname is None:
xname = ['x%d' % i for i in range(self.model.exog.shape[1])]
#List of results used in summary
#yname = yname
#xname = xname
time = Time.localtime()
dist_family = self.model.family.__class__.__name__
df_model = self.df_model
df_resid = self.df_resid
llf = self.llf
nobs = self.nobs
params = self.params
scale = self.scale
#TODO #stand_errors = self.stand_errors
stand_errors = self.bse #[' ' for x in range(len(self.params))]
#Added note about conf_int
conf_int = self.conf_int()
#f_test() = self.f_test()
t = self.tvalues
#t_test = self.t_test()
table_1l_fmt = dict(data_fmts=["%s", "%s", "%s", "%s", "%s"],
empty_cell='',
colwidths=15,
colsep=' ',
row_pre=' ',
row_post=' ',
table_dec_above='=',
table_dec_below='',
header_dec_below=None,
header_fmt='%s',
stub_fmt='%s',
title_align='c',
header_align='r',
data_aligns="r",
stubs_align="l",
fmt='txt')
# Note table_1l_fmt over rides the below formating. in extend_right? JP
table_1r_fmt = dict(data_fmts=["%s", "%s", "%s", "%s", "%1s"],
empty_cell='',
colwidths=12,
colsep=' ',
row_pre='',
row_post='',
table_dec_above='=',
table_dec_below='',
header_dec_below=None,
header_fmt='%s',
stub_fmt='%s',
title_align='c',
header_align='r',
data_aligns="r",
stubs_align="l",
fmt='txt')
table_2_fmt = dict(
data_fmts=["%s", "%s", "%s", "%s"],
#data_fmts = ["%#12.6g","%#12.6g","%#10.4g","%#5.4g"],
#data_fmts = ["%#10.4g","%#6.4f", "%#6.4f"],
#data_fmts = ["%#15.4F","%#15.4F","%#15.4F","%#14.4G"],
empty_cell='',
colwidths=13,
colsep=' ',
row_pre=' ',
row_post=' ',
table_dec_above='=',
table_dec_below='=',
header_dec_below='-',
header_fmt='%s',
stub_fmt='%s',
title_align='c',
header_align='r',
data_aligns='r',
stubs_align='l',
fmt='txt')
######## summary table 1 #######
table_1l_title = title
table_1l_header = None
table_1l_stubs = (
'Model Family:',
'Method:',
'Dependent Variable:',
'Date:',
'Time:',
)
table_1l_data = [
[dist_family],
['IRLS'],
[yname],
[Time.strftime("%a, %d %b %Y", time)],
[Time.strftime("%H:%M:%S", time)],
]
table_1l = SimpleTable(table_1l_data,
table_1l_header,
table_1l_stubs,
title=table_1l_title,
txt_fmt=table_1l_fmt)
table_1r_title = None
table_1r_header = None
table_1r_stubs = ('# of obs:', 'Df residuals:', 'Df model:', 'Scale:',
'Log likelihood:')
table_1r_data = [[nobs], [df_resid], [df_model],
["%#6.4f" % (scale, )], ["%#6.4f" % (llf, )]]
table_1r = SimpleTable(table_1r_data,
table_1r_header,
table_1r_stubs,
title=table_1r_title,
txt_fmt=table_1r_fmt)
######## summary table 2 #######
#TODO add % range to confidance interval column header
table_2header = ('coefficient', 'stand errors', 't-statistic',
'Conf. Interval')
table_2stubs = xname
table_2data = zip(
["%#6.4f" % (params[i]) for i in range(len(xname))],
["%#6.4f" % stand_errors[i] for i in range(len(xname))],
["%#6.4f" % (t[i]) for i in range(len(xname))], [
""" [%#6.3f, %#6.3f]""" % tuple(conf_int[i])
for i in range(len(xname))
])
#dfmt={'data_fmt':["%#12.6g","%#12.6g","%#10.4g","%#5.4g"]}
table_2 = SimpleTable(table_2data,
table_2header,
table_2stubs,
title=None,
txt_fmt=table_2_fmt)
######## Return Summary Tables ########
# join table table_s then print
if returns == 'text':
table_1l.extend_right(table_1r)
return str(table_1l) + '\n' + str(table_2)
elif returns == 'print':
table_1l.extend_right(table_1r)
print(str(table_1l) + '\n' + str(table_2))
elif returns == 'tables':
return [table_1l, table_1r, table_2]
#return [table_1, table_2 ,table_3L, notes]
elif returns == 'csv':
return table_1.as_csv() + '\n' + table_2.as_csv() + '\n' + \
table_3L.as_csv()
elif returns == 'latex':
print('not avalible yet')
elif returns == html:
print('not avalible yet')
def summary(self, endog_names=None, exog_names=None):
"""
Summary of VAR model
"""
import time
from scikits.statsmodels.iolib import SimpleTable
model = self.model
if endog_names is None:
endog_names = self.model.endog_names
# take care of exogenous names
if model.exog is not None and exog_names is None:
exog_names = model.exog_names
elif exog_names is not None:
if len(exog_names) != model.exog.shape[1]:
raise ValueError("The number of exog_names does not match the \
size of model.exog")
else:
exog_names = []
lag_names = []
# take care of lagged endogenous names
laglen = self.laglen
for i in range(1,laglen+1):
for ename in endog_names:
lag_names.append('L'+str(i)+'.'+ename)
# put them together
Xnames = exog_names + lag_names
# handle the constant name
trendorder = self.trendorder
if trendorder != 0:
Xnames.insert(0, 'const')
if trendorder > 1:
Xnames.insert(0, 'trend')
if trendorder > 2:
Xnames.insert(0, 'trend**2')
Xnames *= self.neqs
modeltype = model.__class__.__name__
t = time.localtime()
ncoefs = self.ncoefs #TODO: change when we allow coef restrictions
part1_fmt = dict(
data_fmts = ["%s"],
empty_cell = '',
colwidths = 15,
colsep=' ',
row_pre = '',
row_post = '',
table_dec_above='=',
table_dec_below='',
header_dec_below=None,
header_fmt = '%s',
stub_fmt = '%s',
title_align='c',
header_align = 'r',
data_aligns = "r",
stubs_align = "l",
fmt = 'txt'
)
part2_fmt = dict(
data_fmts = ["%#12.6g","%#12.6g","%#10.4g","%#5.4g"],
empty_cell = '',
colwidths = None,
colsep=' ',
row_pre = '',
row_post = '',
table_dec_above='-',
table_dec_below='-',
header_dec_below=None,
header_fmt = '%s',
stub_fmt = '%s',
title_align='c',
header_align = 'r',
data_aligns = 'r',
stubs_align = 'l',
fmt = 'txt'
)
part3_fmt = dict(
#data_fmts = ["%#12.6g","%#12.6g","%#10.4g","%#5.4g"],
#data_fmts = ["%#10.4g","%#10.4g","%#10.4g","%#6.4g"],
data_fmts = ["%#15.6F","%#15.6F","%#15.3F","%#14.3F"],
empty_cell = '',
#colwidths = 10,
colsep=' ',
row_pre = '',
row_post = '',
table_dec_above='=',
table_dec_below='=',
header_dec_below='-',
header_fmt = '%s',
stub_fmt = '%s',
title_align='c',
header_align = 'r',
data_aligns = 'r',
stubs_align = 'l',
fmt = 'txt'
)
# Header information
part1title = "Summary of Regression Results"
part1data = [[modeltype],
["OLS"], #TODO: change when fit methods change
[time.strftime("%a, %d, %b, %Y", t)],
[time.strftime("%H:%M:%S", t)]]
part1header = None
part1stubs = ('Model:',
'Method:',
'Date:',
'Time:')
part1 = SimpleTable(part1data, part1header, part1stubs, title=
part1title, txt_fmt=part1_fmt)
#TODO: do we want individual statistics or should users just
# use results if wanted?
# Handle overall fit statistics
part2Lstubs = ('No. of Equations:',
'Nobs:',
'Log likelihood:',
'AIC:')
part2Rstubs = ('BIC:',
'HQIC:',
'FPE:',
'Det(Omega_mle):')
part2Ldata = [[self.neqs],[self.nobs],[self.llf],[self.aic]]
part2Rdata = [[self.bic],[self.hqic],[self.fpe],[self.detomega]]
part2Lheader = None
part2L = SimpleTable(part2Ldata, part2Lheader, part2Lstubs,
txt_fmt = part2_fmt)
part2R = SimpleTable(part2Rdata, part2Lheader, part2Rstubs,
txt_fmt = part2_fmt)
part2L.extend_right(part2R)
# Handle coefficients
part3data = []
part3data = zip([self.params.ravel()[i] for i in range(len(Xnames))],
[self.bse.ravel()[i] for i in range(len(Xnames))],
[self.z.ravel()[i] for i in range(len(Xnames))],
[self.pvalues.ravel()[i] for i in range(len(Xnames))])
part3header = ('coefficient','std. error','z-stat','prob')
part3stubs = Xnames
part3 = SimpleTable(part3data, part3header, part3stubs, title=None,
txt_fmt = part3_fmt)
table = str(part1) +'\n'+str(part2L) + '\n' + str(part3)
return table
def summary_old(self, yname=None, xname=None,
title='Generalized linear model', returns='text'):
"""
Print a table of results or returns SimpleTable() instance which
summarizes the Generalized linear model results.
Parameters
-----------
yname : string
optional, Default is `Y`
xname : list of strings
optional, Default is `X.#` for # in p the number of regressors
title : string
optional, Defualt is 'Generalized linear model'
returns : string
'text', 'table', 'csv', 'latex', 'html'
Returns
-------
Defualt :
returns='print'
Prints the summarirized results
Option :
returns='text'
Prints the summarirized results
Option :
returns='table'
SimpleTable instance : summarizing the fit of a linear model.
Option :
returns='csv'
returns a string of csv of the results, to import into a
spreadsheet
Option :
returns='latex'
Not implimented yet
Option :
returns='HTML'
Not implimented yet
Examples (needs updating)
--------
>>> import scikits.statsmodels.api as sm
>>> data = sm.datasets.longley.load()
>>> data.exog = sm.add_constant(data.exog)
>>> ols_results = sm.OLS(data.endog, data.exog).results
>>> print ols_results.summary()
...
Notes
-----
stand_errors are not implimented.
conf_int calculated from normal dist.
"""
import time as Time
from scikits.statsmodels.iolib import SimpleTable
yname = 'Y'
if xname is None:
xname = ['x%d' % i for i in range(self.model.exog.shape[1])]
#List of results used in summary
#yname = yname
#xname = xname
time = Time.localtime()
dist_family = self.model.family.__class__.__name__
df_model = self.df_model
df_resid = self.df_resid
llf = self.llf
nobs = self.nobs
params = self.params
scale = self.scale
#TODO #stand_errors = self.stand_errors
stand_errors = self.bse #[' ' for x in range(len(self.params))]
#Added note about conf_int
conf_int = self.conf_int()
#f_test() = self.f_test()
t = self.tvalues
#t_test = self.t_test()
table_1l_fmt = dict(
data_fmts = ["%s", "%s", "%s", "%s", "%s"],
empty_cell = '',
colwidths = 15,
colsep=' ',
row_pre = ' ',
row_post = ' ',
table_dec_above='=',
table_dec_below='',
header_dec_below=None,
header_fmt = '%s',
stub_fmt = '%s',
title_align='c',
header_align = 'r',
data_aligns = "r",
stubs_align = "l",
fmt = 'txt'
)
# Note table_1l_fmt over rides the below formating. in extend_right? JP
table_1r_fmt = dict(
data_fmts = ["%s", "%s", "%s", "%s", "%1s"],
empty_cell = '',
colwidths = 12,
colsep=' ',
row_pre = '',
row_post = '',
table_dec_above='=',
table_dec_below='',
header_dec_below=None,
header_fmt = '%s',
stub_fmt = '%s',
title_align='c',
header_align = 'r',
data_aligns = "r",
stubs_align = "l",
fmt = 'txt'
)
table_2_fmt = dict(
data_fmts = ["%s", "%s", "%s", "%s"],
#data_fmts = ["%#12.6g","%#12.6g","%#10.4g","%#5.4g"],
#data_fmts = ["%#10.4g","%#6.4f", "%#6.4f"],
#data_fmts = ["%#15.4F","%#15.4F","%#15.4F","%#14.4G"],
empty_cell = '',
colwidths = 13,
colsep=' ',
row_pre = ' ',
row_post = ' ',
table_dec_above='=',
table_dec_below='=',
header_dec_below='-',
header_fmt = '%s',
stub_fmt = '%s',
title_align='c',
header_align = 'r',
data_aligns = 'r',
stubs_align = 'l',
fmt = 'txt'
)
######## summary table 1 #######
table_1l_title = title
table_1l_header = None
table_1l_stubs = ('Model Family:',
'Method:',
'Dependent Variable:',
'Date:',
'Time:',
)
table_1l_data = [
[dist_family],
['IRLS'],
[yname],
[Time.strftime("%a, %d %b %Y",time)],
[Time.strftime("%H:%M:%S",time)],
]
table_1l = SimpleTable(table_1l_data,
table_1l_header,
table_1l_stubs,
title=table_1l_title,
txt_fmt = table_1l_fmt)
table_1r_title = None
table_1r_header = None
table_1r_stubs = ('# of obs:',
'Df residuals:',
'Df model:',
'Scale:',
'Log likelihood:'
)
table_1r_data = [
[nobs],
[df_resid],
[df_model],
["%#6.4f" % (scale,)],
["%#6.4f" % (llf,)]
]
table_1r = SimpleTable(table_1r_data,
table_1r_header,
table_1r_stubs,
title=table_1r_title,
txt_fmt = table_1r_fmt)
######## summary table 2 #######
#TODO add % range to confidance interval column header
table_2header = ('coefficient', 'stand errors', 't-statistic',
'Conf. Interval')
table_2stubs = xname
table_2data = zip(["%#6.4f" % (params[i]) for i in range(len(xname))],
["%#6.4f" % stand_errors[i] for i in range(len(xname))],
["%#6.4f" % (t[i]) for i in range(len(xname))],
[""" [%#6.3f, %#6.3f]""" % tuple(conf_int[i]) for i in
range(len(xname))])
#dfmt={'data_fmt':["%#12.6g","%#12.6g","%#10.4g","%#5.4g"]}
table_2 = SimpleTable(table_2data,
table_2header,
table_2stubs,
title=None,
txt_fmt = table_2_fmt)
######## Return Summary Tables ########
# join table table_s then print
if returns == 'text':
table_1l.extend_right(table_1r)
return str(table_1l) + '\n' + str(table_2)
elif returns == 'print':
table_1l.extend_right(table_1r)
print(str(table_1l) + '\n' + str(table_2))
elif returns == 'tables':
return [table_1l, table_1r, table_2]
#return [table_1, table_2 ,table_3L, notes]
elif returns == 'csv':
return table_1.as_csv() + '\n' + table_2.as_csv() + '\n' + \
table_3L.as_csv()
elif returns == 'latex':
print('not avalible yet')
elif returns == html:
print('not avalible yet')
