def test_attribute_writable_resettable():
"""
Regression test for mutables and class constructors.
"""
data = sm.datasets.longley.load()
endog, exog = data.endog, data.exog
glm_model = sm.GLM(endog, exog)
assert_equal(glm_model.family.link.power, 1.0)
glm_model.family.link.power = 2.
assert_equal(glm_model.family.link.power, 2.0)
glm_model2 = sm.GLM(endog, exog)
assert_equal(glm_model2.family.link.power, 1.0)
def __init__(self):
# generate artificial data
np.random.seed(98765678)
nobs = 200
rvs = np.random.randn(nobs, 6)
data_exog = rvs
data_exog = sm.add_constant(data_exog)
xbeta = 1 + 0.1 * rvs.sum(1)
data_endog = np.random.poisson(np.exp(xbeta))
#estimate discretemod.Poisson as benchmark
self.res_discrete = Poisson(data_endog, data_exog).fit(disp=0)
mod_glm = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())
self.res_glm = mod_glm.fit()
#estimate generic MLE
#self.mod = PoissonGMLE(data_endog, data_exog)
#res = self.mod.fit()
offset = self.res_discrete.params[0] * data_exog[:, 0] #1d ???
#self.res = PoissonOffsetGMLE(data_endog, data_exog[:,1:], offset=offset).fit(start_params = np.ones(6)/2., method='nm')
modo = PoissonOffsetGMLE(data_endog, data_exog[:, 1:], offset=offset)
self.res = modo.fit(start_params=0.9 * self.res_discrete.params[1:],
method='nm',
disp=0)
def __init__(self):
# generate artificial data
np.random.seed(98765678)
nobs = 200
rvs = np.random.randn(nobs, 6)
data_exog = rvs
data_exog = sm.add_constant(data_exog)
xbeta = 0.1 + 0.1 * rvs.sum(1)
data_endog = np.random.poisson(np.exp(xbeta))
#estimate discretemod.Poisson as benchmark
self.res_discrete = Poisson(data_endog, data_exog).fit(disp=0)
mod_glm = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())
self.res_glm = mod_glm.fit()
#estimate generic MLE
self.mod = PoissonGMLE(data_endog, data_exog)
self.res = self.mod.fit(start_params=0.9 * self.res_discrete.params,
method='nm',
disp=0)
from scipy import stats
data = numpy.loadtxt("../doc/gelman/arm2/police/frisk_with_noise.dat", skiprows=7)
X = numpy.zeros((3,len(data[:,0])))
print X.shape
arrests = data[:,2]
arrests[arrests == 0] = 1
arrests = numpy.log(arrests)
stops = data[:,0]
stops[stops==0.0] = .0001
X[0,:] = arrests # arrests
X[1,:] = data[:,4] # eth
X[2,:] = numpy.ones(len(data[:,0])) # eth
glm = sm.GLM(stops, X.T, family=sm.families.Poisson())
res = glm.fit()
print "res.deviance=" + str(res.deviance)
print "res.scale=" + str(res.scale)
print "res.params=" + str(res.params)
print "res.pearson_chi2=" + str(res.pearson_chi2)
print "res.df_model=" + str(res.df_model)
print "res.null_deviance=" + str(res.null_deviance)
print "res.t()=" + str(res.t())
#print data_endog
modp = MyPoisson(data_endog, data_exog)
resp = modp.fit()
print resp.params
print resp.bse
from scikits.statsmodels.discretemod import Poisson
resdp = Poisson(data_endog, data_exog).fit()
print '\ncompare with discretemod'
print 'compare params'
print resdp.params - resp.params
print 'compare bse'
print resdp.bse - resp.bse
gmlp = sm.GLM(data_endog, data_exog, family=sm.families.Poisson())
resgp = gmlp.fit()
''' this creates a warning, bug bse is double defined ???
c:\josef\eclipsegworkspace\statsmodels-josef-experimental-gsoc\scikits\statsmodels\decorators.py:105: CacheWriteWarning: The attribute 'bse' cannot be overwritten
warnings.warn(errmsg, CacheWriteWarning)
'''
print '\ncompare with GLM'
print 'compare params'
print resgp.params - resp.params
print 'compare bse'
print resgp.bse - resp.bse
lam = np.exp(np.dot(data_exog, resp.params))
'''mean of Poisson distribution'''
predmean = stats.poisson.stats(lam, moments='m')
print np.max(np.abs(predmean - lam))
from pandas import DataFrame
data = sm.datasets.longley.load()
df = DataFrame(data.exog, columns=data.exog_name)
y = data.endog
# data.exog = sm.add_constant(data.exog)
df['intercept'] = 1.
olsresult = sm.OLS(y, df).fit()
rlmresult = sm.RLM(y, df).fit()
# olswrap = RegressionResultsWrapper(olsresult)
# rlmwrap = RLMResultsWrapper(rlmresult)
data = sm.datasets.wfs.load()
# get offset
offset = np.log(data.exog[:, -1])
exog = data.exog[:, :-1]
# convert dur to dummy
exog = sm.tools.categorical(exog, col=0, drop=True)
# drop reference category
# convert res to dummy
exog = sm.tools.categorical(exog, col=0, drop=True)
# convert edu to dummy
exog = sm.tools.categorical(exog, col=0, drop=True)
# drop reference categories and add intercept
exog = sm.add_constant(exog[:, [1, 2, 3, 4, 5, 7, 8, 10, 11, 12]])
endog = np.round(data.endog)
mod = sm.GLM(endog, exog, family=sm.families.Poisson()).fit()
# glmwrap = GLMResultsWrapper(mod)
# The percent of students taking college credit courses "PCTAF", # The percentage of charter schools in the districut "PCTCHRT" # The percent of schools in the district operating year round "PCTYRRND" # The following are interaction terms "PERMINTE_AVYRSEXP","PERMINTE_AVSAL", # "AVYRSEXP_AVSAL","PERSPEN_PTRATIO","PERSPEN_PCTAF","PTRATIO_PCTAF", # "PERMINTE_AVYRSEXP_AVSAL","PERSPEN_PTRATIO_PCTAF" data = sm.datasets.star98.load() data.exog = sm.add_constant(data.exog) print """The response variable is (success, failure). Eg., the first observation is """, data.endog[0] print"""Giving a total number of trials for this observation of """, data.endog[0].sum() glm_binom = sm.GLM(data.endog, data.exog, family=sm.families.Binomial()) binom_results = glm_binom.fit() print """The fitted values are """, binom_results.params print """The corresponding t-values are """, binom_results.tvalues # It is common in GLMs with interactions to compare first differences. # We are interested in the difference of the impact of the explanatory variable # on the response variable. This example uses interquartile differences for # the percentage of low income households while holding the other values # constant at their mean. means = data.exog.mean(axis=0)
