def test_SimpleTable_2(self):
""" Test SimpleTable.extend_right()"""
desired = '''
=============================================================
header s1 header d1 header s2 header d2
-------------------------------------------------------------
stub R1 C1 10.30312 10.73999 stub R1 C2 50.95038 50.65765
stub R2 C1 90.30312 90.73999 stub R2 C2 40.95038 40.65765
-------------------------------------------------------------
'''
data1 = [[10.30312, 10.73999], [90.30312, 90.73999]]
data2 = [[50.95038, 50.65765], [40.95038, 40.65765]]
stubs1 = ['stub R1 C1', 'stub R2 C1']
stubs2 = ['stub R1 C2', 'stub R2 C2']
header1 = ['header s1', 'header d1']
header2 = ['header s2', 'header d2']
actual1 = SimpleTable(data1, header1, stubs1, txt_fmt=default_txt_fmt)
actual2 = SimpleTable(data2, header2, stubs2, txt_fmt=default_txt_fmt)
actual1.extend_right(actual2)
actual = '\n%s\n' % actual1.as_text()
self.assertEqual(desired, str(actual))
def test_SimpleTable_2(self):
""" Test SimpleTable.extend_right()"""
desired = '''
=============================================================
header s1 header d1 header s2 header d2
-------------------------------------------------------------
stub R1 C1 10.30312 10.73999 stub R1 C2 50.95038 50.65765
stub R2 C1 90.30312 90.73999 stub R2 C2 40.95038 40.65765
-------------------------------------------------------------
'''
data1 = [[10.30312, 10.73999], [90.30312, 90.73999]]
data2 = [[50.95038, 50.65765], [40.95038, 40.65765]]
stubs1 = ['stub R1 C1', 'stub R2 C1']
stubs2 = ['stub R1 C2', 'stub R2 C2']
header1 = ['header s1', 'header d1']
header2 = ['header s2', 'header d2']
actual1 = SimpleTable(data1, header1, stubs1, txt_fmt=default_txt_fmt)
actual2 = SimpleTable(data2, header2, stubs2, txt_fmt=default_txt_fmt)
actual1.extend_right(actual2)
actual = '\n%s\n' % actual1.as_text()
self.assertEqual(desired, str(actual))
def summary(self, yname=None, xname=None, returns='text'):
"""returns a string that summarizes the regression results
Parameters
-----------
yname : string, optional
Default is `Y`
xname : list of strings, optional
Default is `X.#` for # in p the number of regressors
Returns
-------
String summarizing the fit of a linear model.
Examples
--------
>>> 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
-----
All residual statistics are calculated on whitened residuals.
"""
import time
from scikits.statsmodels.iolib.table import SimpleTable
from scikits.statsmodels.stats.stattools import (jarque_bera,
omni_normtest, durbin_watson)
if yname is None:
yname = self.model.endog_names
if xname is None:
xname = self.model.exog_names
modeltype = self.model.__class__.__name__
llf, aic, bic = self.llf, self.aic, self.bic
JB, JBpv, skew, kurtosis = jarque_bera(self.wresid)
omni, omnipv = omni_normtest(self.wresid)
t = time.localtime()
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"],
data_fmts = ["%#10.4g","%#10.4g","%#6.4f","%#6.4f"],
#data_fmts = ["%#15.4F","%#15.4F","%#15.4F","%#14.4G"],
empty_cell = '',
colwidths = 14,
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'
)
part3_fmt = dict(
#data_fmts = ["%#12.6g","%#12.6g","%#10.4g","%#5.4g"],
data_fmts = ["%#10.4g","%#10.4g","%#10.4g","%#6.4g"],
empty_cell = '',
colwidths = 15,
colsep=' ',
row_pre = '| ',
row_post = ' |',
table_dec_above=None,
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'
)
# Print the first part of the summary table
part1data = [[yname],
[modeltype],
['Least Squares'],
[time.strftime("%a, %d %b %Y",t)],
[time.strftime("%H:%M:%S",t)],
[self.nobs],
[self.df_resid],
[self.df_model]]
part1header = None
part1title = 'Summary of Regression Results'
part1stubs = ('Dependent Variable:',
'Model:',
'Method:',
'Date:',
'Time:',
'# obs:',
'Df residuals:',
'Df model:')
part1 = SimpleTable(part1data,
part1header,
part1stubs,
title=part1title,
txt_fmt = part1_fmt)
######## summary Part 2 #######
part2data = zip([self.params[i] for i in range(len(xname))],
[self.bse[i] for i in range(len(xname))],
[self.tvalues[i] for i in range(len(xname))],
[self.pvalues[i] for i in range(len(xname))])
part2header = ('coefficient', 'std. error', 't-statistic', 'prob.')
part2stubs = xname
#dfmt={'data_fmt':["%#12.6g","%#12.6g","%#10.4g","%#5.4g"]}
part2 = SimpleTable(part2data,
part2header,
part2stubs,
title=None,
txt_fmt = part2_fmt)
self.summary2 = part2
######## summary Part 3 #######
part3Lheader = ['Models stats']
part3Rheader = ['Residual stats']
part3Lstubs = ('R-squared:',
'Adjusted R-squared:',
'F-statistic:',
'Prob (F-statistic):',
'Log likelihood:',
'AIC criterion:',
'BIC criterion:',)
part3Rstubs = ('Durbin-Watson:',
'Omnibus:',
'Prob(Omnibus):',
'JB:',
'Prob(JB):',
'Skew:',
'Kurtosis:')
part3Ldata = [[self.rsquared], [self.rsquared_adj],
[self.fvalue],
[self.f_pvalue],
[llf],
[aic],
[bic]]
part3Rdata = [[durbin_watson(self.wresid)],
[omni],
[omnipv],
[JB],
[JBpv],
[skew],
[kurtosis]]
part3L = SimpleTable(part3Ldata, part3Lheader, part3Lstubs,
txt_fmt = part3_fmt)
part3R = SimpleTable(part3Rdata, part3Rheader, part3Rstubs,
txt_fmt = part3_fmt)
part3L.extend_right(part3R)
######## Return Summary Tables ########
# join table parts then print
if returns == 'text':
return str(part1) + '\n' + str(part2) + '\n' + str(part3L)
elif returns == 'tables':
return [part1, part2 ,part3L]
elif returns == 'csv':
return part1.as_csv() + '\n' + part2.as_csv() + '\n' + \
part3L.as_csv()
elif returns == 'latex':
print('not available yet')
elif returns == 'html':
print('not available yet')
def summary_top(results, title=None, gleft=None, gright=None, yname=None, xname=None):
'''generate top table(s)
TODO: this still uses predefined model_methods
? allow gleft, gright to be 1 element tuples instead of filling with None?
'''
#change of names ?
gen_left, gen_right = gleft, gright
#time and names are always included
import time
time_now = time.localtime()
time_of_day = [time.strftime("%H:%M:%S", time_now)]
date = time.strftime("%a, %d %b %Y", time_now)
yname, xname = _getnames(results, yname=yname, xname=xname)
#create dictionary with default
#use lambdas because some values raise exception if they are not available
#alternate spellings are commented out to force unique labels
default_items = dict([
('Dependent Variable:', lambda: [yname]),
('Dep. Variable:', lambda: [yname]),
('Model:', lambda: [results.model.__class__.__name__]),
#('Model type:', lambda: [results.model.__class__.__name__]),
('Date:', lambda: [date]),
('Time:', lambda: time_of_day),
('Number of Obs:', lambda: [results.nobs]),
#('No. of Observations:', lambda: ["%#6d" % results.nobs]),
('No. Observations:', lambda: ["%#6d" % results.nobs]),
#('Df model:', lambda: [results.df_model]),
('Df Model:', lambda: ["%#6d" % results.df_model]),
#TODO: check when we have non-integer df
('Df Residuals:', lambda: ["%#6d" % results.df_resid]),
#('Df resid:', lambda: [results.df_resid]),
#('df resid:', lambda: [results.df_resid]), #check capitalization
('Log-Likelihood:', lambda: ["%#8.5g" % results.llf]) #doesn't exist for RLM - exception
#('Method:', lambda: [???]), #no default for this
])
if title is None:
title = results.model.__class__.__name__ + 'Regression Results'
if gen_left is None:
#default: General part of the summary table, Applicable to all? models
gen_left = [('Dep. Variable:', None),
('Model type:', None),
('Date:', None),
('No. Observations:', None)
('Df model:', None),
('Df resid:', None)]
try:
llf = results.llf
gen_left.append(('Log-Likelihood', None))
except: #AttributeError, NotImplementedError
pass
gen_right = []
gen_title = title
gen_header = None
#needed_values = [k for k,v in gleft + gright if v is None] #not used anymore
#replace missing (None) values with default values
gen_left_ = []
for item, value in gen_left:
if value is None:
value = default_items[item]() #let KeyErrors raise exception
gen_left_.append((item, value))
gen_left = gen_left_
if gen_right:
gen_right_ = []
for item, value in gen_right:
if value is None:
value = default_items[item]() #let KeyErrors raise exception
gen_right_.append((item, value))
gen_right = gen_right_
#check
missing_values = [k for k,v in gen_left + gen_right if v is None]
assert missing_values == [], missing_values
#pad both tables to equal number of rows
if gen_right:
if len(gen_right) < len(gen_left):
#fill up with blank lines to same length
gen_right += [(' ', ' ')] * (len(gen_left) - len(gen_right))
elif len(gen_right) > len(gen_left):
#fill up with blank lines to same length, just to keep it symmetric
gen_left += [(' ', ' ')] * (len(gen_right) - len(gen_left))
#padding in SimpleTable doesn't work like I want
#force extra spacing and exact string length in right table
gen_right = [('%-21s' % (' '+k), v) for k,v in gen_right]
gen_stubs_right, gen_data_right = map(None, *gen_right) #transpose row col
gen_table_right = SimpleTable(gen_data_right,
gen_header,
gen_stubs_right,
title = gen_title,
txt_fmt = fmt_2cols #gen_fmt
)
else:
gen_table_right = [] #because .extend_right seems works with []
#moved below so that we can pad if needed to match length of gen_right
#transpose rows and columns, `unzip`
gen_stubs_left, gen_data_left = map(None, *gen_left)
gen_table_left = SimpleTable(gen_data_left,
gen_header,
gen_stubs_left,
title = gen_title,
txt_fmt = fmt_2cols
)
gen_table_left.extend_right(gen_table_right)
general_table = gen_table_left
return general_table #, gen_table_left, gen_table_right
def summary(self, yname=None, xname=None, title=0, alpha=.05,
returns='text', model_info=None):
"""
Parameters
-----------
yname : string
optional, Default is `Y`
xname : list of strings
optional, Default is `X.#` for # in p the number of regressors
Confidance interval : (0,1) not implimented
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 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
-----
conf_int calculated from normal dist.
"""
import time as time
#TODO Make sure all self.model.__class__.__name__ are listed
model_types = {'OLS' : 'Ordinary least squares',
'GLS' : 'Generalized least squares',
'GLSAR' : 'Generalized least squares with AR(p)',
'WLS' : 'Weigthed least squares',
'RLM' : 'Robust linear model',
'GLM' : 'Generalized linear model'
}
model_methods = {'OLS' : 'Least Squares',
'GLS' : 'Least Squares',
'GLSAR' : 'Least Squares',
'WLS' : 'Least Squares',
'RLM' : '?',
'GLM' : '?'
}
if title==0:
title = model_types[self.model.__class__.__name__]
if yname is None:
try:
yname = self.model.endog_names
except AttributeError:
yname = 'y'
if xname is None:
try:
xname = self.model.exog_names
except AttributeError:
xname = ['var_%d' % i for i in range(len(self.params))]
time_now = time.localtime()
time_of_day = [time.strftime("%H:%M:%S", time_now)]
date = time.strftime("%a, %d %b %Y", time_now)
modeltype = self.model.__class__.__name__
#dist_family = self.model.family.__class__.__name__
nobs = self.nobs
df_model = self.df_model
df_resid = self.df_resid
#General part of the summary table, Applicable to all? models
#------------------------------------------------------------
#TODO: define this generically, overwrite in model classes
#replace definition of stubs data by single list
#e.g.
gen_left = [('Model type:', [modeltype]),
('Date:', [date]),
('Dependent Variable:', yname), #What happens with multiple names?
('df model', [df_model])
]
gen_stubs_left, gen_data_left = map(None, *gen_left) #transpose row col
gen_title = title
gen_header = None
## gen_stubs_left = ('Model type:',
## 'Date:',
## 'Dependent Variable:',
## 'df model'
## )
## gen_data_left = [[modeltype],
## [date],
## yname, #What happens with multiple names?
## [df_model]
## ]
gen_table_left = SimpleTable(gen_data_left,
gen_header,
gen_stubs_left,
title = gen_title,
txt_fmt = gen_fmt
)
gen_stubs_right = ('Method:',
'Time:',
'Number of Obs:',
'df resid'
)
gen_data_right = ([modeltype], #was dist family need to look at more
time_of_day,
[nobs],
[df_resid]
)
gen_table_right = SimpleTable(gen_data_right,
gen_header,
gen_stubs_right,
title = gen_title,
txt_fmt = gen_fmt
)
gen_table_left.extend_right(gen_table_right)
general_table = gen_table_left
#Parameters part of the summary table
#------------------------------------
#Note: this is not necessary since we standardized names, only t versus normal
tstats = {'OLS' : self.t(),
'GLS' : self.t(),
'GLSAR' : self.t(),
'WLS' : self.t(),
'RLM' : self.t(),
'GLM' : self.t()
}
prob_stats = {'OLS' : self.pvalues,
'GLS' : self.pvalues,
'GLSAR' : self.pvalues,
'WLS' : self.pvalues,
'RLM' : self.pvalues,
'GLM' : self.pvalues
}
#Dictionary to store the header names for the parameter part of the
#summary table. look up by modeltype
alp = str((1-alpha)*100)+'%'
param_header = {
'OLS' : ['coef', 'std err', 't', 'P>|t|', alp + ' Conf. Interval'],
'GLS' : ['coef', 'std err', 't', 'P>|t|', alp + ' Conf. Interval'],
'GLSAR' : ['coef', 'std err', 't', 'P>|t|', alp + ' Conf. Interval'],
'WLS' : ['coef', 'std err', 't', 'P>|t|', alp + ' Conf. Interval'],
'GLM' : ['coef', 'std err', 't', 'P>|t|', alp + ' Conf. Interval'], #glm uses t-distribution
'RLM' : ['coef', 'std err', 'z', 'P>|z|', alp + ' Conf. Interval'] #checke z
}
params_stubs = xname
params = self.params
conf_int = self.conf_int(alpha)
std_err = self.bse
exog_len = xrange(len(xname))
tstat = tstats[modeltype]
prob_stat = prob_stats[modeltype]
# Simpletable should be able to handle the formating
params_data = zip(["%#6.4g" % (params[i]) for i in exog_len],
["%#6.4f" % (std_err[i]) for i in exog_len],
["%#6.4f" % (tstat[i]) for i in exog_len],
["%#6.4f" % (prob_stat[i]) for i in exog_len],
["(%#5g, %#5g)" % tuple(conf_int[i]) for i in \
exog_len]
)
parameter_table = SimpleTable(params_data,
param_header[modeltype],
params_stubs,
title = None,
txt_fmt = fmt_2, #gen_fmt,
)
#special table
#-------------
#TODO: exists in linear_model, what about other models
#residual diagnostics
#output options
#--------------
#TODO: JP the rest needs to be fixed, similar to summary in linear_model
def ols_printer():
"""
print summary table for ols models
"""
table = str(general_table)+'\n'+str(parameter_table)
return table
def ols_to_csv():
"""
exports ols summary data to csv
"""
pass
def glm_printer():
table = str(general_table)+'\n'+str(parameter_table)
return table
pass
printers = {'OLS': ols_printer,
'GLM' : glm_printer
}
if returns=='print':
try:
return printers[modeltype]()
except KeyError:
return printers['OLS']()
def summary_top(results,
title=None,
gleft=None,
gright=None,
yname=None,
xname=None):
'''generate top table(s)
TODO: this still uses predefined model_methods
? allow gleft, gright to be 1 element tuples instead of filling with None?
'''
#change of names ?
gen_left, gen_right = gleft, gright
#time and names are always included
import time
time_now = time.localtime()
time_of_day = [time.strftime("%H:%M:%S", time_now)]
date = time.strftime("%a, %d %b %Y", time_now)
yname, xname = _getnames(results, yname=yname, xname=xname)
#create dictionary with default
#use lambdas because some values raise exception if they are not available
#alternate spellings are commented out to force unique labels
default_items = dict([
('Dependent Variable:', lambda: [yname]),
('Dep. Variable:', lambda: [yname]),
('Model:', lambda: [results.model.__class__.__name__]),
#('Model type:', lambda: [results.model.__class__.__name__]),
('Date:', lambda: [date]),
('Time:', lambda: time_of_day),
('Number of Obs:', lambda: [results.nobs]),
#('No. of Observations:', lambda: ["%#6d" % results.nobs]),
('No. Observations:', lambda: ["%#6d" % results.nobs]),
#('Df model:', lambda: [results.df_model]),
('Df Model:', lambda: ["%#6d" % results.df_model]),
#TODO: check when we have non-integer df
('Df Residuals:', lambda: ["%#6d" % results.df_resid]),
#('Df resid:', lambda: [results.df_resid]),
#('df resid:', lambda: [results.df_resid]), #check capitalization
('Log-Likelihood:', lambda: ["%#8.5g" % results.llf]
) #doesn't exist for RLM - exception
#('Method:', lambda: [???]), #no default for this
])
if title is None:
title = results.model.__class__.__name__ + 'Regression Results'
if gen_left is None:
#default: General part of the summary table, Applicable to all? models
gen_left = [('Dep. Variable:', None), ('Model type:', None),
('Date:', None), ('No. Observations:', None)('Df model:',
None),
('Df resid:', None)]
try:
llf = results.llf
gen_left.append(('Log-Likelihood', None))
except: #AttributeError, NotImplementedError
pass
gen_right = []
gen_title = title
gen_header = None
#needed_values = [k for k,v in gleft + gright if v is None] #not used anymore
#replace missing (None) values with default values
gen_left_ = []
for item, value in gen_left:
if value is None:
value = default_items[item]() #let KeyErrors raise exception
gen_left_.append((item, value))
gen_left = gen_left_
if gen_right:
gen_right_ = []
for item, value in gen_right:
if value is None:
value = default_items[item]() #let KeyErrors raise exception
gen_right_.append((item, value))
gen_right = gen_right_
#check
missing_values = [k for k, v in gen_left + gen_right if v is None]
assert missing_values == [], missing_values
#pad both tables to equal number of rows
if gen_right:
if len(gen_right) < len(gen_left):
#fill up with blank lines to same length
gen_right += [(' ', ' ')] * (len(gen_left) - len(gen_right))
elif len(gen_right) > len(gen_left):
#fill up with blank lines to same length, just to keep it symmetric
gen_left += [(' ', ' ')] * (len(gen_right) - len(gen_left))
#padding in SimpleTable doesn't work like I want
#force extra spacing and exact string length in right table
gen_right = [('%-21s' % (' ' + k), v) for k, v in gen_right]
gen_stubs_right, gen_data_right = map(None,
*gen_right) #transpose row col
gen_table_right = SimpleTable(
gen_data_right,
gen_header,
gen_stubs_right,
title=gen_title,
txt_fmt=fmt_2cols #gen_fmt
)
else:
gen_table_right = [] #because .extend_right seems works with []
#moved below so that we can pad if needed to match length of gen_right
#transpose rows and columns, `unzip`
gen_stubs_left, gen_data_left = map(None, *gen_left)
gen_table_left = SimpleTable(gen_data_left,
gen_header,
gen_stubs_left,
title=gen_title,
txt_fmt=fmt_2cols)
gen_table_left.extend_right(gen_table_right)
general_table = gen_table_left
return general_table #, gen_table_left, gen_table_right
def summary(self,
yname=None,
xname=None,
title=0,
alpha=.05,
returns='text',
model_info=None):
"""
Parameters
-----------
yname : string
optional, Default is `Y`
xname : list of strings
optional, Default is `X.#` for # in p the number of regressors
Confidance interval : (0,1) not implimented
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 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
-----
conf_int calculated from normal dist.
"""
import time as time
#TODO Make sure all self.model.__class__.__name__ are listed
model_types = {
'OLS': 'Ordinary least squares',
'GLS': 'Generalized least squares',
'GLSAR': 'Generalized least squares with AR(p)',
'WLS': 'Weigthed least squares',
'RLM': 'Robust linear model',
'GLM': 'Generalized linear model'
}
model_methods = {
'OLS': 'Least Squares',
'GLS': 'Least Squares',
'GLSAR': 'Least Squares',
'WLS': 'Least Squares',
'RLM': '?',
'GLM': '?'
}
if title == 0:
title = model_types[self.model.__class__.__name__]
if yname is None:
try:
yname = self.model.endog_names
except AttributeError:
yname = 'y'
if xname is None:
try:
xname = self.model.exog_names
except AttributeError:
xname = ['var_%d' % i for i in range(len(self.params))]
time_now = time.localtime()
time_of_day = [time.strftime("%H:%M:%S", time_now)]
date = time.strftime("%a, %d %b %Y", time_now)
modeltype = self.model.__class__.__name__
#dist_family = self.model.family.__class__.__name__
nobs = self.nobs
df_model = self.df_model
df_resid = self.df_resid
#General part of the summary table, Applicable to all? models
#------------------------------------------------------------
#TODO: define this generically, overwrite in model classes
#replace definition of stubs data by single list
#e.g.
gen_left = [
('Model type:', [modeltype]),
('Date:', [date]),
('Dependent Variable:', yname), #What happens with multiple names?
('df model', [df_model])
]
gen_stubs_left, gen_data_left = map(None, *gen_left) #transpose row col
gen_title = title
gen_header = None
## gen_stubs_left = ('Model type:',
## 'Date:',
## 'Dependent Variable:',
## 'df model'
## )
## gen_data_left = [[modeltype],
## [date],
## yname, #What happens with multiple names?
## [df_model]
## ]
gen_table_left = SimpleTable(gen_data_left,
gen_header,
gen_stubs_left,
title=gen_title,
txt_fmt=gen_fmt)
gen_stubs_right = ('Method:', 'Time:', 'Number of Obs:', 'df resid')
gen_data_right = (
[modeltype], #was dist family need to look at more
time_of_day,
[nobs],
[df_resid])
gen_table_right = SimpleTable(gen_data_right,
gen_header,
gen_stubs_right,
title=gen_title,
txt_fmt=gen_fmt)
gen_table_left.extend_right(gen_table_right)
general_table = gen_table_left
#Parameters part of the summary table
#------------------------------------
#Note: this is not necessary since we standardized names, only t versus normal
tstats = {
'OLS': self.t(),
'GLS': self.t(),
'GLSAR': self.t(),
'WLS': self.t(),
'RLM': self.t(),
'GLM': self.t()
}
prob_stats = {
'OLS': self.pvalues,
'GLS': self.pvalues,
'GLSAR': self.pvalues,
'WLS': self.pvalues,
'RLM': self.pvalues,
'GLM': self.pvalues
}
#Dictionary to store the header names for the parameter part of the
#summary table. look up by modeltype
alp = str((1 - alpha) * 100) + '%'
param_header = {
'OLS': ['coef', 'std err', 't', 'P>|t|', alp + ' Conf. Interval'],
'GLS': ['coef', 'std err', 't', 'P>|t|', alp + ' Conf. Interval'],
'GLSAR': ['coef', 'std err', 't', 'P>|t|', alp + ' Conf. Interval'],
'WLS': ['coef', 'std err', 't', 'P>|t|', alp + ' Conf. Interval'],
'GLM': ['coef', 'std err', 't', 'P>|t|',
alp + ' Conf. Interval'], #glm uses t-distribution
'RLM': ['coef', 'std err', 'z', 'P>|z|',
alp + ' Conf. Interval'] #checke z
}
params_stubs = xname
params = self.params
conf_int = self.conf_int(alpha)
std_err = self.bse
exog_len = xrange(len(xname))
tstat = tstats[modeltype]
prob_stat = prob_stats[modeltype]
# Simpletable should be able to handle the formating
params_data = zip(["%#6.4g" % (params[i]) for i in exog_len],
["%#6.4f" % (std_err[i]) for i in exog_len],
["%#6.4f" % (tstat[i]) for i in exog_len],
["%#6.4f" % (prob_stat[i]) for i in exog_len],
["(%#5g, %#5g)" % tuple(conf_int[i]) for i in \
exog_len]
)
parameter_table = SimpleTable(
params_data,
param_header[modeltype],
params_stubs,
title=None,
txt_fmt=fmt_2, #gen_fmt,
)
#special table
#-------------
#TODO: exists in linear_model, what about other models
#residual diagnostics
#output options
#--------------
#TODO: JP the rest needs to be fixed, similar to summary in linear_model
def ols_printer():
"""
print summary table for ols models
"""
table = str(general_table) + '\n' + str(parameter_table)
return table
def ols_to_csv():
"""
exports ols summary data to csv
"""
pass
def glm_printer():
table = str(general_table) + '\n' + str(parameter_table)
return table
pass
printers = {'OLS': ols_printer, 'GLM': glm_printer}
if returns == 'print':
try:
return printers[modeltype]()
except KeyError:
return printers['OLS']()
def summary(self, yname=None, xname=None, returns='text'):
"""returns a string that summarizes the regression results
Parameters
-----------
yname : string, optional
Default is `Y`
xname : list of strings, optional
Default is `X.#` for # in p the number of regressors
Returns
-------
String summarizing the fit of a linear model.
Examples
--------
>>> 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
-----
All residual statistics are calculated on whitened residuals.
"""
import time
from scikits.statsmodels.iolib.table import SimpleTable
from scikits.statsmodels.stats.stattools import (jarque_bera,
omni_normtest, durbin_watson)
if yname is None:
yname = self.model.endog_names
if xname is None:
xname = self.model.exog_names
modeltype = self.model.__class__.__name__
llf, aic, bic = self.llf, self.aic, self.bic
JB, JBpv, skew, kurtosis = jarque_bera(self.wresid)
omni, omnipv = omni_normtest(self.wresid)
t = time.localtime()
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"],
data_fmts = ["%#10.4g","%#10.4g","%#6.4f","%#6.4f"],
#data_fmts = ["%#15.4F","%#15.4F","%#15.4F","%#14.4G"],
empty_cell = '',
colwidths = 14,
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'
)
part3_fmt = dict(
#data_fmts = ["%#12.6g","%#12.6g","%#10.4g","%#5.4g"],
data_fmts = ["%#10.4g","%#10.4g","%#10.4g","%#6.4g"],
empty_cell = '',
colwidths = 15,
colsep=' ',
row_pre = '| ',
row_post = ' |',
table_dec_above=None,
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'
)
# Print the first part of the summary table
part1data = [[yname],
[modeltype],
['Least Squares'],
[time.strftime("%a, %d %b %Y",t)],
[time.strftime("%H:%M:%S",t)],
[self.nobs],
[self.df_resid],
[self.df_model]]
part1header = None
part1title = 'Summary of Regression Results'
part1stubs = ('Dependent Variable:',
'Model:',
'Method:',
'Date:',
'Time:',
'# obs:',
'Df residuals:',
'Df model:')
part1 = SimpleTable(part1data,
part1header,
part1stubs,
title=part1title,
txt_fmt = part1_fmt)
######## summary Part 2 #######
part2data = zip([self.params[i] for i in range(len(xname))],
[self.bse[i] for i in range(len(xname))],
[self.tvalues[i] for i in range(len(xname))],
[self.pvalues[i] for i in range(len(xname))])
part2header = ('coefficient', 'std. error', 't-statistic', 'prob.')
part2stubs = xname
#dfmt={'data_fmt':["%#12.6g","%#12.6g","%#10.4g","%#5.4g"]}
part2 = SimpleTable(part2data,
part2header,
part2stubs,
title=None,
txt_fmt = part2_fmt)
self.summary2 = part2
######## summary Part 3 #######
part3Lheader = ['Models stats']
part3Rheader = ['Residual stats']
part3Lstubs = ('R-squared:',
'Adjusted R-squared:',
'F-statistic:',
'Prob (F-statistic):',
'Log likelihood:',
'AIC criterion:',
'BIC criterion:',)
part3Rstubs = ('Durbin-Watson:',
'Omnibus:',
'Prob(Omnibus):',
'JB:',
'Prob(JB):',
'Skew:',
'Kurtosis:')
part3Ldata = [[self.rsquared], [self.rsquared_adj],
[self.fvalue],
[self.f_pvalue],
[llf],
[aic],
[bic]]
part3Rdata = [[durbin_watson(self.wresid)],
[omni],
[omnipv],
[JB],
[JBpv],
[skew],
[kurtosis]]
part3L = SimpleTable(part3Ldata, part3Lheader, part3Lstubs,
txt_fmt = part3_fmt)
part3R = SimpleTable(part3Rdata, part3Rheader, part3Rstubs,
txt_fmt = part3_fmt)
part3L.extend_right(part3R)
######## Return Summary Tables ########
# join table parts then print
if returns == 'text':
return str(part1) + '\n' + str(part2) + '\n' + str(part3L)
elif returns == 'tables':
return [part1, part2 ,part3L]
elif returns == 'csv':
return part1.as_csv() + '\n' + part2.as_csv() + '\n' + \
part3L.as_csv()
elif returns == 'latex':
print('not available yet')
elif returns == 'html':
print('not available yet')
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.table import SimpleTable
from scikits.statsmodels.stats.stattools import (jarque_bera,
omni_normtest, durbin_watson)
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__
aic = self.aic
bic = self.bic
deviance = self.deviance
df_model = self.df_model
df_resid = self.df_resid
fittedvalues = self.fittedvalues
llf = self.llf
mu = self.mu
nobs = self.nobs
normalized_cov_params = self.normalized_cov_params
null_deviance = self.null_deviance
params = self.params
pearson_chi2 = self.pearson_chi2
pinv_wexog = self.pinv_wexog
resid_anscombe = self.resid_anscombe
resid_deviance = self.resid_deviance
resid_pearson = self.resid_pearson
resid_response = self.resid_response
resid_working = self.resid_working
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
pvalues = self.pvalues
conf_int = self.conf_int()
cov_params = self.cov_params()
#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')
