def test_zip_longest():
lili = [['a0', 'b0', 'c0', 'd0'], ['a1', 'b1', 'c1'],
['a2', 'b2', 'c2', 'd2'], ['a3', 'b3', 'c3', 'd3'], ['a4', 'b4']]
transposed = [
('a0', 'a1', 'a2', 'a3', 'a4'), ('b0', 'b1', 'b2', 'b3', 'b4'),
('c0', 'c1', 'c2', 'c3', None), ('d0', None, 'd2', 'd3', None)
]
assert_(
list(zip_longest(*lili)) == transposed,
'%r not equal %r' % (zip_longest(*lili), transposed))
def test_zip_longest():
lili = [['a0', 'b0', 'c0', 'd0'],
['a1', 'b1', 'c1'],
['a2', 'b2', 'c2', 'd2'],
['a3', 'b3', 'c3', 'd3'],
['a4', 'b4']]
transposed = [('a0', 'a1', 'a2', 'a3', 'a4'),
('b0', 'b1', 'b2', 'b3', 'b4'),
('c0', 'c1', 'c2', 'c3', None),
('d0', None, 'd2', 'd3', None)]
assert_(list(zip_longest(*lili)) == transposed, '%r not equal %r' % (
zip_longest(*lili), transposed))
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 = 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 #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 = 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 #, 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 gwstatsmodels 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 = zip_longest(*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']()
