def penalized_wls(endog, exog, penalty_matrix, weights):
"""weighted least squares with quadratic penalty
Parameters
----------
endog : ndarray
response or endogenous variable
exog : ndarray
design matrix, matrix of exogenous or explanatory variables
penalty_matrix : ndarray, 2-Dim square
penality matrix for quadratic penalization. Note, the penalty_matrix
is multiplied by two to match non-pirls fitting methods.
weights : ndarray
weights for WLS
Returns
-------
results : Results instance of WLS
"""
y, x, s = endog, exog, penalty_matrix
# TODO: I don't understand why I need 2 * s
aug_y, aug_x, aug_weights = make_augmented_matrix(y, x, 2 * s, weights)
wls_results = lm.WLS(aug_y, aug_x, aug_weights).fit()
# TODO: use MinimalWLS during iterations, less overhead
# However, MinimalWLS does not return normalized_cov_params
# which we need at the end of the iterations
# call would be
# wls_results = reg_tools._MinimalWLS(aug_y, aug_x, aug_weights).fit()
wls_results.params = wls_results.params.ravel()
return wls_results
def null(self):
endog = self._endog
model = self.model
exog = np.ones((len(endog), 1))
if hasattr(model, 'offset'):
return GLM(endog, exog, offset=model.offset,
family=self.family).fit().mu
elif hasattr(model, 'exposure'):
return GLM(endog, exog, exposure=model.exposure,
family=self.family).fit().mu
else:
wls_model = lm.WLS(endog, exog, weights=self._data_weights)
return wls_model.fit().fittedvalues
def null(self):
endog = self._endog
model = self.model
exog = np.ones((len(endog), 1))
kwargs = {}
if hasattr(model, 'offset'):
kwargs['offset'] = model.offset
if hasattr(model, 'exposure'):
kwargs['exposure'] = model.exposure
if len(kwargs) > 0:
return GLM(endog, exog, family=self.family, **kwargs).fit().mu
else:
wls_model = lm.WLS(endog, exog, weights=self._data_weights)
return wls_model.fit().fittedvalues
def compute_QTL_gti_peaki(datapoint):
[peak_sample, gt_sample, weight_sample] = datapoint
valid_samples = np.where(gt_sample!= -1)[0]
y = np.array(peak_sample[valid_samples])
y = y.astype(float)
x = np.array(gt_sample[valid_samples])
x_weights = np.array(weight_sample[valid_samples])
x = sm.add_constant(x)
wls_model = sm.WLS(y, x, weights = x_weights)
results = wls_model.fit()
return results.pvalues[1]
def added_variable_resids(results,
focus_exog,
resid_type=None,
use_glm_weights=True,
fit_kwargs=None):
"""
Residualize the endog variable and a 'focus' exog variable in a
regression model with respect to the other exog variables.
Parameters
----------
results : regression results instance
A fitted model including the focus exog and all other
predictors of interest.
focus_exog : integer or string
The column of results.model.exog or a variable name that is
to be residualized against the other predictors.
resid_type : string
The type of residuals to use for the dependent variable. If
None, uses `resid_deviance` for GLM/GEE and `resid` otherwise.
use_glm_weights : bool
Only used if the model is a GLM or GEE. If True, the
residuals for the focus predictor are computed using WLS, with
the weights obtained from the IRLS calculations for fitting
the GLM. If False, unweighted regression is used.
fit_kwargs : dict, optional
Keyword arguments to be passed to fit when refitting the
model.
Returns
-------
endog_resid : array-like
The residuals for the original exog
focus_exog_resid : array-like
The residuals for the focus predictor
Notes
-----
The 'focus variable' residuals are always obtained using linear
regression.
Currently only GLM, GEE, and OLS models are supported.
"""
model = results.model
if not isinstance(model, (GEE, GLM, OLS)):
raise ValueError(
"model type %s not supported for added variable residuals" %
model.__class__.__name__)
exog = model.exog
endog = model.endog
focus_exog, focus_col = utils.maybe_name_or_idx(focus_exog, model)
focus_exog_vals = exog[:, focus_col]
# Default residuals
if resid_type is None:
if isinstance(model, (GEE, GLM)):
resid_type = "resid_deviance"
else:
resid_type = "resid"
ii = range(exog.shape[1])
ii = list(ii)
ii.pop(focus_col)
reduced_exog = exog[:, ii]
start_params = results.params[ii]
klass = model.__class__
kwargs = model._get_init_kwds()
new_model = klass(endog, reduced_exog, **kwargs)
args = {"start_params": start_params}
if fit_kwargs is not None:
args.update(fit_kwargs)
new_result = new_model.fit(**args)
if not new_result.converged:
raise ValueError(
"fit did not converge when calculating added variable residuals")
try:
endog_resid = getattr(new_result, resid_type)
except AttributeError:
raise ValueError("'%s' residual type not available" % resid_type)
import statsmodels.regression.linear_model as lm
if isinstance(model, (GLM, GEE)) and use_glm_weights:
weights = model.family.weights(results.fittedvalues)
if hasattr(model, "data_weights"):
weights = weights * model.data_weights
lm_results = lm.WLS(focus_exog_vals, reduced_exog, weights).fit()
else:
lm_results = lm.OLS(focus_exog_vals, reduced_exog).fit()
focus_exog_resid = lm_results.resid
return endog_resid, focus_exog_resid
def fit(self,
maxiter=50,
tol=1e-8,
scale_est='mad',
init=None,
cov='H1',
update_scale=True,
conv='dev'):
"""
Fits the model using iteratively reweighted least squares.
The IRLS routine runs until the specified objective converges to `tol`
or `maxiter` has been reached.
Parameters
----------
conv : string
Indicates the convergence criteria.
Available options are "coefs" (the coefficients), "weights" (the
weights in the iteration), "sresid" (the standardized residuals),
and "dev" (the un-normalized log-likelihood for the M
estimator). The default is "dev".
cov : string, optional
'H1', 'H2', or 'H3'
Indicates how the covariance matrix is estimated. Default is 'H1'.
See rlm.RLMResults for more information.
init : string
Specifies method for the initial estimates of the parameters.
Default is None, which means that the least squares estimate
is used. Currently it is the only available choice.
maxiter : int
The maximum number of iterations to try. Default is 50.
scale_est : string or HuberScale()
'mad', 'stand_mad', or HuberScale()
Indicates the estimate to use for scaling the weights in the IRLS.
The default is 'mad' (median absolute deviation. Other options are
use 'stand_mad' for the median absolute deviation standardized
around the median and 'HuberScale' for Huber's proposal 2.
Huber's proposal 2 has optional keyword arguments d, tol, and
maxiter for specifying the tuning constant, the convergence
tolerance, and the maximum number of iterations.
See models.robust.scale for more information.
tol : float
The convergence tolerance of the estimate. Default is 1e-8.
update_scale : Bool
If `update_scale` is False then the scale estimate for the
weights is held constant over the iteration. Otherwise, it
is updated for each fit in the iteration. Default is True.
Returns
-------
results : object
statsmodels.rlm.RLMresults
"""
if not cov.upper() in ["H1", "H2", "H3"]:
raise ValueError("Covariance matrix %s not understood" % cov)
else:
self.cov = cov.upper()
conv = conv.lower()
if not conv in ["weights", "coefs", "dev", "sresid"]:
raise ValueError("Convergence argument %s not understood" \
% conv)
self.scale_est = scale_est
wls_results = lm.WLS(self.endog, self.exog).fit()
if not init:
self.scale = self._estimate_scale(wls_results.resid)
history = dict(params=[np.inf], scale=[])
if conv == 'coefs':
criterion = history['params']
elif conv == 'dev':
history.update(dict(deviance=[np.inf]))
criterion = history['deviance']
elif conv == 'sresid':
history.update(dict(sresid=[np.inf]))
criterion = history['sresid']
elif conv == 'weights':
history.update(dict(weights=[np.inf]))
criterion = history['weights']
# done one iteration so update
history = self._update_history(wls_results, history, conv)
iteration = 1
converged = 0
while not converged:
self.weights = self.M.weights(wls_results.resid / self.scale)
wls_results = lm.WLS(self.endog, self.exog,
weights=self.weights).fit()
if update_scale is True:
self.scale = self._estimate_scale(wls_results.resid)
history = self._update_history(wls_results, history, conv)
iteration += 1
converged = _check_convergence(criterion, iteration, tol, maxiter)
results = RLMResults(self, wls_results.params,
self.normalized_cov_params, self.scale)
history['iteration'] = iteration
results.fit_history = history
results.fit_options = dict(cov=cov.upper(),
scale_est=scale_est,
norm=self.M.__class__.__name__,
conv=conv)
#norm is not changed in fit, no old state
#doing the next causes exception
#self.cov = self.scale_est = None #reset for additional fits
#iteration and history could contain wrong state with repeated fit
return RLMResultsWrapper(results)
# Use noise values copied from book (based on sds above).
eta = [
-0.0023, -0.0728, 0.1104, 0.6076, -0.3034, -0.2237, 0.7407, -1.0, -3.0,
-2.4653, -3.0
]
# Find observed values of x (with noise added).
x = m * s + c + eta
# Weighted Least Squares regression.
# Find weightings w (discount) for each data point.
vars0 = sds**2
w = 1 / vars0
# Un-comment next line for solution based on un-weighted regression.
#w=ones(size(w))
ss = sm.add_constant(s) # Add column of 1s for regression.
model = sm.WLS(x, ss, weights=w)
results = model.fit()
cest2, mest2 = results.params
print('Estimated slope = %.3f,' % mest2)
print(' estimated intercept = %.3f.' % cest2)
# Make line xest2 based on fitted slope and intercept.
s2 = arange(0, 13)
xest2 = mest2 * s2 + cest2
# Plot fitted line xest, data points, and error bars.
fig1 = plt.figure()
plt.errorbar(s, x, yerr=sds, fmt='o', color='k')
plt.plot(s, x, 'k*', s2, xest2, 'k--')
plt.xlabel('Salary, $s$ (groats)')
plt.ylabel('Height, $x$ (feet)')
def fit_model(data,
model,
sigma,
fit_method='chisq',
masking=None,
mask_only=False,
**kwargs):
def chisq(x):
return np.sum((data[mask] - x * model[mask])**2 /
sigma[mask]**2) / (sum(mask) - 1)
def difference(x):
return np.sum(np.abs(data[mask] - x * model[mask]))
mask = np.array([True for _ in data])
sigmalimit = None
if masking is not None:
for masktype in masking.split(';'):
masktype = masktype.strip().lower()
if masktype.startswith('middle'):
perinterval = float(masktype[6:])
# Estimate model strength (source rate) by fitting middle %
interval = PercentileInterval(perinterval)
lim = interval.get_limits(data)
mask = (mask & (data >= lim[0]) & (data <= lim[1]))
elif (masktype.startswith('minalt')) and ('altitude' in kwargs):
minalt = float(masktype[6:])
mask = mask & (kwargs['altitude'] >= minalt)
elif masktype.startswith('minalt'):
raise InputError('mathMB.fit_model', 'Altitude not supplied.')
elif masktype.startswith('minsnr'):
minSNR = float(masktype[6:])
snr = data / sigma
mask = mask & (snr > minSNR)
elif masktype.startswith('siglimit'):
sigmalimit = masktype
else:
raise InputError('MESSENGERdata.fit_model',
f'masking = {masktype} not defined.')
else:
pass
if mask_only:
return None, None, mask
else:
available_fitfunctions = ['chisq', 'difference', 'wls']
if np.any(mask) == False:
# No data points are included - just do a simple fit for show
mask_ = mask.copy()
mask[:] = True
model_strength = minimize_scalar(difference)
mask = mask_
return model_strength.x, model_strength.fun, mask
elif fit_method.lower() in available_fitfunctions:
if fit_method == 'wls':
# Weighted least squares fit
wls_model = lm.WLS(model[mask], data[mask],
1. / sigma[mask]**2)
result = wls_model.fit()
if sigmalimit is not None:
siglimit = float(sigmalimit[8:])
diff = (data - model / result.params[0]) / sigma
mask = mask & (diff < siglimit * sigma)
wls_model = lm.WLS(model[mask], data[mask],
1. / sigma[mask]**2)
result = wls_model.fit()
else:
pass
return 1. / result.params[0], result.rsquared, mask
else:
model_strength = minimize_scalar(eval(fit_method.lower()))
if sigmalimit is not None:
siglimit = float(sigmalimit[8:])
diff = (data - model_strength.x * model) / sigma
mask = mask & (diff < siglimit * sigma)
model_strength = minimize_scalar(eval(fit_method.lower()))
else:
pass
return model_strength.x, model_strength.fun, mask
else:
raise InputError('mathMB.fit_model',
f'fit_method = {fit_method} not defined.')
def fit(self,
maxiter=50,
tol=1e-8,
scale_est='mad',
init=None,
cov='H1',
update_scale=True,
conv='dev',
start_params=None):
"""
Fits the model using iteratively reweighted least squares.
The IRLS routine runs until the specified objective converges to `tol`
or `maxiter` has been reached.
Parameters
----------
conv : str
Indicates the convergence criteria.
Available options are "coefs" (the coefficients), "weights" (the
weights in the iteration), "sresid" (the standardized residuals),
and "dev" (the un-normalized log-likelihood for the M
estimator). The default is "dev".
cov : str, optional
'H1', 'H2', or 'H3'
Indicates how the covariance matrix is estimated. Default is 'H1'.
See rlm.RLMResults for more information.
init : str
Specifies method for the initial estimates of the parameters.
Default is None, which means that the least squares estimate
is used. Currently it is the only available choice.
maxiter : int
The maximum number of iterations to try. Default is 50.
scale_est : str or HuberScale()
'mad' or HuberScale()
Indicates the estimate to use for scaling the weights in the IRLS.
The default is 'mad' (median absolute deviation. Other options are
'HuberScale' for Huber's proposal 2. Huber's proposal 2 has
optional keyword arguments d, tol, and maxiter for specifying the
tuning constant, the convergence tolerance, and the maximum number
of iterations. See statsmodels.robust.scale for more information.
tol : float
The convergence tolerance of the estimate. Default is 1e-8.
update_scale : Bool
If `update_scale` is False then the scale estimate for the
weights is held constant over the iteration. Otherwise, it
is updated for each fit in the iteration. Default is True.
start_params : array-like, optional
Initial guess of the solution of the optimizer. If not provided,
the initial parameters are computed using OLS.
Returns
-------
results : statsmodels.rlm.RLMresults
Results instance
"""
if cov.upper() not in ["H1", "H2", "H3"]:
raise ValueError("Covariance matrix %s not understood" % cov)
else:
self.cov = cov.upper()
conv = conv.lower()
if conv not in ["weights", "coefs", "dev", "sresid"]:
raise ValueError("Convergence argument %s not understood" % conv)
self.scale_est = scale_est
if start_params is None:
wls_results = lm.WLS(self.endog, self.exog).fit()
else:
start_params = np.asarray(start_params, dtype=np.double).squeeze()
if (start_params.shape[0] != self.exog.shape[1]
or start_params.ndim != 1):
raise ValueError('start_params must by a 1-d array with {0} '
'values'.format(self.exog.shape[1]))
fake_wls = reg_tools._MinimalWLS(self.endog,
self.exog,
weights=np.ones_like(self.endog),
check_weights=False)
wls_results = fake_wls.results(start_params)
if not init:
self.scale = self._estimate_scale(wls_results.resid)
history = dict(params=[np.inf], scale=[])
if conv == 'coefs':
criterion = history['params']
elif conv == 'dev':
history.update(dict(deviance=[np.inf]))
criterion = history['deviance']
elif conv == 'sresid':
history.update(dict(sresid=[np.inf]))
criterion = history['sresid']
elif conv == 'weights':
history.update(dict(weights=[np.inf]))
criterion = history['weights']
# done one iteration so update
history = self._update_history(wls_results, history, conv)
iteration = 1
converged = 0
while not converged:
if self.scale == 0.0:
import warnings
warnings.warn(
'Estimated scale is 0.0 indicating that the most'
' last iteration produced a perfect fit of the '
'weighted data.', ConvergenceWarning)
break
self.weights = self.M.weights(wls_results.resid / self.scale)
wls_results = reg_tools._MinimalWLS(self.endog,
self.exog,
weights=self.weights,
check_weights=True).fit()
if update_scale is True:
self.scale = self._estimate_scale(wls_results.resid)
history = self._update_history(wls_results, history, conv)
iteration += 1
converged = _check_convergence(criterion, iteration, tol, maxiter)
results = RLMResults(self, wls_results.params,
self.normalized_cov_params, self.scale)
history['iteration'] = iteration
results.fit_history = history
results.fit_options = dict(cov=cov.upper(),
scale_est=scale_est,
norm=self.M.__class__.__name__,
conv=conv)
# norm is not changed in fit, no old state
# doing the next causes exception
# self.cov = self.scale_est = None #reset for additional fits
# iteration and history could contain wrong state with repeated fit
return RLMResultsWrapper(results)
def fit(self, start_params=None, maxiter=100, method='IRLS', tol=1e-8,
scale=None):
"""
Fits a generalized linear model for a given family.
parameters
----------
maxiter : int, optional
Default is 100.
method : string
Default is 'IRLS' for iteratively reweighted least squares. This
is currently the only method available for GLM fit.
scale : string or float, optional
`scale` can be 'X2', 'dev', or a float
The default value is None, which uses `X2` for Gamma, Gaussian,
and Inverse Gaussian.
`X2` is Pearson's chi-square divided by `df_resid`.
The default is 1 for the Binomial and Poisson families.
`dev` is the deviance divided by df_resid
tol : float
Convergence tolerance. Default is 1e-8.
start_params : array-like, optional
Initial guess of the solution for the loglikelihood maximization.
The default is family-specific and is given by the
``family.starting_mu(endog)``. If start_params is given then the
initial mean will be calculated as ``np.dot(exog, start_params)``.
"""
endog = self.endog
if endog.ndim > 1 and endog.shape[1] == 2:
data_weights = endog.sum(1) # weights are total trials
else:
data_weights = np.ones((endog.shape[0]))
self.data_weights = data_weights
if np.shape(self.data_weights) == () and self.data_weights > 1:
self.data_weights = self.data_weights * np.ones((endog.shape[0]))
self.scaletype = scale
if isinstance(self.family, families.Binomial):
# this checks what kind of data is given for Binomial.
# family will need a reference to endog if this is to be removed from
# preprocessing
self.endog = self.family.initialize(self.endog)
if hasattr(self, 'offset'):
offset = self.offset
elif hasattr(self, 'exposure'):
offset = self.exposure
else:
offset = 0
#TODO: would there ever be both and exposure and an offset?
wlsexog = self.exog
if start_params is None:
mu = self.family.starting_mu(self.endog)
else:
mu = self.family.fitted(np.dot(wlsexog, start_params))
eta = self.family.predict(mu)
dev = self.family.deviance(self.endog, mu)
if np.isnan(dev):
raise ValueError("The first guess on the deviance function "
"returned a nan. This could be a boundary "
" problem and should be reported.")
# first guess on the deviance is assumed to be scaled by 1.
# params are none to start, so they line up with the deviance
history = dict(params=[None, start_params], deviance=[np.inf, dev])
iteration = 0
converged = 0
criterion = history['deviance']
while not converged:
self.weights = data_weights*self.family.weights(mu)
wlsendog = (eta + self.family.link.deriv(mu) * (self.endog-mu)
- offset)
wls_results = lm.WLS(wlsendog, wlsexog, self.weights).fit()
eta = np.dot(self.exog, wls_results.params) + offset
mu = self.family.fitted(eta)
history = self._update_history(wls_results, mu, history)
self.scale = self.estimate_scale(mu)
iteration += 1
if endog.squeeze().ndim == 1 and np.allclose(mu - endog, 0):
msg = "Perfect separation detected, results not available"
raise PerfectSeparationError(msg)
converged = _check_convergence(criterion, iteration, tol, maxiter)
self.mu = mu
glm_results = GLMResults(self, wls_results.params,
wls_results.normalized_cov_params,
self.scale)
history['iteration'] = iteration
glm_results.fit_history = history
return GLMResultsWrapper(glm_results)
def fit(self,
start_params=None,
maxiter=100,
method='IRLS',
tol=1e-8,
scale=None,
cov_type='nonrobust',
cov_kwds=None,
use_t=None,
**kwargs):
"""
Fits a generalized linear model for a given family.
parameters
----------
maxiter : int, optional
Default is 100.
method : string
Default is 'IRLS' for iteratively reweighted least squares. This
is currently the only method available for GLM fit.
scale : string or float, optional
`scale` can be 'X2', 'dev', or a float
The default value is None, which uses `X2` for Gamma, Gaussian,
and Inverse Gaussian.
`X2` is Pearson's chi-square divided by `df_resid`.
The default is 1 for the Binomial and Poisson families.
`dev` is the deviance divided by df_resid
tol : float
Convergence tolerance. Default is 1e-8.
start_params : array-like, optional
Initial guess of the solution for the loglikelihood maximization.
The default is family-specific and is given by the
``family.starting_mu(endog)``. If start_params is given then the
initial mean will be calculated as ``np.dot(exog, start_params)``.
Notes
-----
This method does not take any extra undocumented ``kwargs``.
"""
endog = self.endog
if endog.ndim > 1 and endog.shape[1] == 2:
data_weights = endog.sum(1) # weights are total trials
else:
data_weights = np.ones((endog.shape[0]))
self.data_weights = data_weights
if np.shape(self.data_weights) == () and self.data_weights > 1:
self.data_weights = self.data_weights * np.ones((endog.shape[0]))
self.scaletype = scale
if isinstance(self.family, families.Binomial):
# this checks what kind of data is given for Binomial.
# family will need a reference to endog if this is to be removed from
# preprocessing
self.endog = self.family.initialize(self.endog)
# Construct a combined offset/exposure term. Note that
# exposure has already been logged if present.
offset_exposure = 0.
if hasattr(self, 'offset'):
offset_exposure = self.offset
if hasattr(self, 'exposure'):
offset_exposure = offset_exposure + self.exposure
self._offset_exposure = offset_exposure
wlsexog = self.exog
if start_params is None:
mu = self.family.starting_mu(self.endog)
lin_pred = self.family.predict(mu)
else:
lin_pred = np.dot(wlsexog, start_params) + offset_exposure
mu = self.family.fitted(lin_pred)
dev = self.family.deviance(self.endog, mu)
if np.isnan(dev):
raise ValueError("The first guess on the deviance function "
"returned a nan. This could be a boundary "
" problem and should be reported.")
# first guess on the deviance is assumed to be scaled by 1.
# params are none to start, so they line up with the deviance
history = dict(params=[None, start_params], deviance=[np.inf, dev])
converged = False
criterion = history['deviance']
# This special case is used to get the likelihood for a specific
# params vector.
if maxiter == 0:
mu = self.family.fitted(lin_pred)
self.scale = self.estimate_scale(mu)
wls_results = lm.RegressionResults(self, start_params, None)
iteration = 0
for iteration in range(maxiter):
self.weights = data_weights * self.family.weights(mu)
wlsendog = (lin_pred + self.family.link.deriv(mu) *
(self.endog - mu) - offset_exposure)
wls_results = lm.WLS(wlsendog, wlsexog, self.weights).fit()
lin_pred = np.dot(self.exog, wls_results.params) + offset_exposure
mu = self.family.fitted(lin_pred)
history = self._update_history(wls_results, mu, history)
self.scale = self.estimate_scale(mu)
if endog.squeeze().ndim == 1 and np.allclose(mu - endog, 0):
msg = "Perfect separation detected, results not available"
raise PerfectSeparationError(msg)
converged = _check_convergence(criterion, iteration, tol)
if converged:
break
self.mu = mu
glm_results = GLMResults(self,
wls_results.params,
wls_results.normalized_cov_params,
self.scale,
cov_type=cov_type,
cov_kwds=cov_kwds,
use_t=use_t)
history['iteration'] = iteration + 1
glm_results.fit_history = history
return GLMResultsWrapper(glm_results)
def fit(self, X, Y, sample_weight = None):
"""
fit the weighted model
Parameters
----------
X : design matrix
Y : response matrix
sample_weight: sample weight vector
"""
# family is the glm family with link, the family is the same as in the statsmodel
if sample_weight is None:
sample_weight = np.ones((X.shape[0],))
assert X.shape[0] == sample_weight.shape[0]
assert X.shape[0] == Y.shape[0]
assert Y.ndim == 1 or Y.shape[1] == 1
Y = Y.reshape(-1,)
sum_w = np.sum(sample_weight)
assert sum_w > 0
if X.ndim == 1:
X = X.reshape(-1,1)
if self.fit_intercept:
X = addIntercept(X)
self.n_samples = X.shape[0]
self.n_features = X.shape[1]
self.n_targets = 1
# start fitting using irls
mu = self.fam.starting_mu(Y)
lin_pred = self.fam.predict(mu)
dev = self.fam.deviance_weighted(Y, mu, sample_weight)
if np.isnan(dev):
raise ValueError("The first guess on the deviance function "
"returned a nan. This could be a boundary "
" problem and should be reported.")
# This special case is used to get the likelihood for a specific
# params vector.
for iteration in range(self.max_iter):
weights = sample_weight * self.fam.weights(mu)
wlsendog = lin_pred + self.fam.link.deriv(mu) * (Y-mu)
if self.penalty is None:
wls_results = lim.WLS(wlsendog, X, weights).fit(method = self.solver)
if self.penalty == 'elasticnet':
wls_results = lim.WLS(wlsendog, X, weights).fit_regularized(alpha = self.reg, L1_wt = self.l1_ratio)
lin_pred = np.dot(X, wls_results.params)
mu = self.fam.fitted(lin_pred)
if Y.squeeze().ndim == 1 and np.allclose(mu - Y, 0):
msg = "Perfect separation detected, results not available"
raise Error(msg)
dev_new = self.fam.deviance_weighted(Y, mu, sample_weight)
converged = np.fabs(dev - dev_new) <= self.tol
dev = dev_new
if converged:
break
self.converged = converged
self.coef = wls_results.params
self.dispersion = self.estimate_dispersion(X, Y, mu, sample_weight)
if self.est_sd:
self.sd = self.estimate_sd(X, Y, mu, sample_weight, weights)
self.ll = self.estimate_loglikelihood(Y, mu, sample_weight)
