def generate_table(left_col, right_col, table_title):
# Do not use column headers
col_headers = None
# Generate the right table
if right_col:
# Add padding
if len(right_col) < len(left_col):
right_col += [(' ', ' ')] * (len(left_col) - len(right_col))
elif len(right_col) > len(left_col):
left_col += [(' ', ' ')] * (len(right_col) - len(left_col))
right_col = [('%-21s' % (' '+k), v) for k,v in right_col]
# Generate the right table
gen_stubs_right, gen_data_right = zip_longest(*right_col)
gen_table_right = SimpleTable(gen_data_right,
col_headers,
gen_stubs_right,
title = table_title,
txt_fmt = fmt_2cols)
else:
# If there is no right table set the right table to empty
gen_table_right = []
# Generate the left table
gen_stubs_left, gen_data_left = zip_longest(*left_col)
gen_table_left = SimpleTable(gen_data_left,
col_headers,
gen_stubs_left,
title = table_title,
txt_fmt = fmt_2cols)
# Merge the left and right tables to make a single table
gen_table_left.extend_right(gen_table_right)
general_table = gen_table_left
return general_table
def insert_header_row(self, rownum, headers, dec_below='header_dec_below'):
"""Return None. Insert a row of headers,
where ``headers`` is a sequence of strings.
(The strings may contain newlines, to indicated multiline headers.)
"""
header_rows = [header.split('\n') for header in headers]
# rows in reverse order
rows = list(zip_longest(*header_rows, **dict(fillvalue='')))
rows.reverse()
for i, row in enumerate(rows):
self.insert(rownum, row, datatype='header')
if i == 0:
self[rownum].dec_below = dec_below
else:
self[rownum].dec_below = None
def insert_header_row(self, rownum, headers, dec_below='header_dec_below'):
"""Return None. Insert a row of headers,
where ``headers`` is a sequence of strings.
(The strings may contain newlines, to indicated multiline headers.)
"""
header_rows = [header.split('\n') for header in headers]
# rows in reverse order
rows = list(zip_longest(*header_rows, **dict(fillvalue='')))
rows.reverse()
for i, row in enumerate(rows):
self.insert(rownum, row, datatype='header')
if i == 0:
self[rownum].dec_below = dec_below
else:
self[rownum].dec_below = None
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
-------
Default :
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 statsmodels as sm
>>> data = sm.datasets.longley.load(as_pandas=False)
>>> 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.
"""
if title == 0:
title = _model_types[self.model.__class__.__name__]
if xname is not None and len(xname) != len(self.params):
# GH 2298
raise ValueError('User supplied xnames must have the same number of '
'entries as the number of model parameters '
'({0})'.format(len(self.params)))
yname, xname = _getnames(self, yname, xname)
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__
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), # TODO: What happens with multiple names?
('df model', [df_model])
]
gen_stubs_left, gen_data_left = zip_longest(*gen_left) #transpose row col
gen_title = title
gen_header = None
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 = lrange(len(xname))
tstat = tstats[modeltype]
prob_stat = prob_stats[modeltype]
# Simpletable should be able to handle the formating
params_data = lzip(["%#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)
#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 glm_printer():
table = str(general_table) + '\n' + str(parameter_table)
return table
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
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
default_items = dict([
('Dependent Variable:', lambda: [yname]),
('Dep. Variable:', lambda: [yname]),
('Model:', lambda: [results.model.__class__.__name__]),
('Date:', lambda: [date]),
('Time:', lambda: time_of_day),
('Number of Obs:', lambda: [results.nobs]),
('No. Observations:', lambda: [d_or_f(results.nobs)]),
('Df Model:', lambda: [d_or_f(results.df_model)]),
('Df Residuals:', lambda: [d_or_f(results.df_resid)]),
('Log-Likelihood:', lambda: ["%#8.5g" % results.llf]
) # doesn't exist for RLM - exception
])
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 # noqa: F841
gen_left.append(('Log-Likelihood', None))
except: # AttributeError, NotImplementedError
pass
gen_right = []
gen_title = title
gen_header = None
# 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 nothing was missed
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 = zip_longest(
*gen_right) #transpose row col
gen_table_right = SimpleTable(gen_data_right,
gen_header,
gen_stubs_right,
title=gen_title,
txt_fmt=fmt_2cols)
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 = zip_longest(*gen_left) #transpose row col
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
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
-------
Default :
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 statsmodels as sm
>>> data = sm.datasets.longley.load(as_pandas=False)
>>> 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.
"""
if title == 0:
title = _model_types[self.model.__class__.__name__]
yname, xname = _getnames(self, yname, xname)
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__
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), # TODO: What happens with multiple names?
('df model', [df_model])
]
gen_stubs_left, gen_data_left = zip_longest(*gen_left) #transpose row col
gen_title = title
gen_header = None
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 = lrange(len(xname))
tstat = tstats[modeltype]
prob_stat = prob_stats[modeltype]
# Simpletable should be able to handle the formating
params_data = lzip(["%#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
)
#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 glm_printer():
table = str(general_table)+'\n'+str(parameter_table)
return table
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
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
default_items = dict([
('Dependent Variable:', lambda: [yname]),
('Dep. Variable:', lambda: [yname]),
('Model:', lambda: [results.model.__class__.__name__]),
('Date:', lambda: [date]),
('Time:', lambda: time_of_day),
('Number of Obs:', lambda: [results.nobs]),
('No. Observations:', lambda: [d_or_f(results.nobs)]),
('Df Model:', lambda: [d_or_f(results.df_model)]),
('Df Residuals:', lambda: [d_or_f(results.df_resid)]),
('Log-Likelihood:', lambda: ["%#8.5g" % results.llf]) # doesn't exist for RLM - exception
])
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 # noqa: F841
gen_left.append(('Log-Likelihood', None))
except: # AttributeError, NotImplementedError
pass
gen_right = []
gen_title = title
gen_header = None
# 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 nothing was missed
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 = zip_longest(*gen_right) #transpose row col
gen_table_right = SimpleTable(gen_data_right,
gen_header,
gen_stubs_right,
title=gen_title,
txt_fmt=fmt_2cols
)
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 = zip_longest(*gen_left) #transpose row col
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