def __init__(self, model, params, normalized_cov_params, scale):
super(RLMResults, self).__init__(model, params,
normalized_cov_params, scale)
self.model = model
self.df_model = model.df_model
self.df_resid = model.df_resid
self.nobs = model.nobs
self._cache = resettable_cache()
def __init__(self, model, params, normalized_cov_params, scale):
super(RLMResults, self).__init__(model, params, normalized_cov_params,
scale)
self.model = model
self.df_model = model.df_model
self.df_resid = model.df_resid
self.nobs = model.nobs
self._cache = resettable_cache()
def __init__(self, model, mlefit):
# super(DiscreteResults, self).__init__(model, params,
# np.linalg.inv(-hessian), scale=1.)
self.model = model
self.df_model = model.df_model
self.df_resid = model.df_resid
self._cache = resettable_cache()
self.nobs = model.exog.shape[0]
self.__dict__.update(mlefit.__dict__)
def __init__(self, model, mlefit):
# super(DiscreteResults, self).__init__(model, params,
# np.linalg.inv(-hessian), scale=1.)
self.model = model
self.df_model = model.df_model
self.df_resid = model.df_resid
self._cache = resettable_cache()
self.nobs = model.exog.shape[0]
self.__dict__.update(mlefit.__dict__)
def __init__(self, model, params, normalized_cov_params, scale):
super(GLMResults, self).__init__(model, params,
normalized_cov_params=normalized_cov_params, scale=scale)
self.family = model.family
self._endog = model.endog
self.nobs = model.endog.shape[0]
self.mu = model.mu
self._data_weights = model.data_weights
self.df_resid = model.df_resid
self.df_model = model.df_model
self.pinv_wexog = model.pinv_wexog
self._cache = resettable_cache()
def __init__(self, model, params, normalized_cov_params, scale):
super(GLMResults,
self).__init__(model,
params,
normalized_cov_params=normalized_cov_params,
scale=scale)
self.family = model.family
self._endog = model.endog
self.nobs = model.endog.shape[0]
self.mu = model.mu
self._data_weights = model.data_weights
self.df_resid = model.df_resid
self.df_model = model.df_model
self.pinv_wexog = model.pinv_wexog
self._cache = resettable_cache()
def __init__(self, model, params, normalized_cov_params, scale):
super(GLMResults, self).__init__(model, params,
normalized_cov_params=normalized_cov_params, scale=scale)
self.model._results = self.model.results = self # TODO: get rid of this
# since results isn't a
# property for GLM
# above is needed for model.predict
self.family = model.family
self._endog = model.endog
self.nobs = model.endog.shape[0]
self.mu = model.mu
self._data_weights = model.data_weights
self.df_resid = model.df_resid
self.df_model = model.df_model
self.pinv_wexog = model.pinv_wexog
self._cache = resettable_cache()
def __init__(self, model, params, normalized_cov_params, scale):
super(GLMResults, self).__init__(model, params,
normalized_cov_params=normalized_cov_params, scale=scale)
self.model._results = self.model.results = self # TODO: get rid of this
# since results isn't a
# property for GLM
# above is needed for model.predict
self.family = model.family
self._endog = model.endog
self.nobs = model.endog.shape[0]
self.mu = model.mu
self._data_weights = model.data_weights
self.df_resid = model.df_resid
self.df_model = model.df_model
self.pinv_wexog = model.pinv_wexog
self._cache = resettable_cache()
def __init__(self, model, params, normalized_cov_params=None, scale=1.):
super(ARResults, self).__init__(model, params, normalized_cov_params,
scale)
self._cache = resettable_cache()
self.nobs = model.nobs
n_totobs = len(model.endog)
self.n_totobs = n_totobs
self.X = model.X # copy?
self.Y = model.Y
k_ar = model.k_ar
self.k_ar = k_ar
k_trend = model.k_trend
self.k_trend = k_trend
trendorder = None
if k_trend > 0:
trendorder = k_trend - 1
self.trendorder = 1
self.df_resid = n_totobs - k_ar - k_trend #TODO: cmle vs mle?
def __init__(self, model, params, normalized_cov_params=None, scale=1.0):
super(ARMAResults, self).__init__(model, params, normalized_cov_params, scale)
self.sigma2 = model.sigma2
nobs = model.nobs
self.nobs = nobs
k_exog = model.k_exog
self.k_exog = k_exog
k_trend = model.k_trend
self.k_trend = k_trend
k_ar = model.k_ar
self.k_ar = k_ar
self.n_totobs = len(model.endog)
k_ma = model.k_ma
self.k_ma = k_ma
df_model = k_exog + k_trend + k_ar + k_ma
self.df_model = df_model
self.df_resid = self.nobs - df_model
self._cache = resettable_cache()
def __init__(self, model, params, normalized_cov_params=None, scale=1.):
super(ARResults, self).__init__(model, params, normalized_cov_params,
scale)
self._cache = resettable_cache()
self.nobs = model.nobs
n_totobs = len(model.endog)
self.n_totobs = n_totobs
self.X = model.X # copy?
self.Y = model.Y
k_ar = model.k_ar
self.k_ar = k_ar
k_trend = model.k_trend
self.k_trend = k_trend
trendorder = None
if k_trend > 0:
trendorder = k_trend - 1
self.trendorder = 1
self.df_resid = n_totobs - k_ar - k_trend #TODO: cmle vs mle?
def __init__(self, model, params, normalized_cov_params=None, scale=1.):
super(ARMAResults, self).__init__(model, params, normalized_cov_params,
scale)
self.sigma2 = model.sigma2
nobs = model.nobs
self.nobs = nobs
k_exog = model.k_exog
self.k_exog = k_exog
k_trend = model.k_trend
self.k_trend = k_trend
k_ar = model.k_ar
self.k_ar = k_ar
self.n_totobs = len(model.endog)
k_ma = model.k_ma
self.k_ma = k_ma
df_model = k_exog + k_trend + k_ar + k_ma
self.df_model = df_model
self.df_resid = self.nobs - df_model
self._cache = resettable_cache()
def __init__(self, model, params, normalized_cov_params=None, scale=1.):
super(RegressionResults, self).__init__(model, params,
normalized_cov_params,
scale)
self._cache = resettable_cache()
def __init__(self, model, params, normalized_cov_params=None, scale=1.):
super(RegressionResults, self).__init__(model, params,
normalized_cov_params,
scale)
self._cache = resettable_cache()
def __init__(self, endog, exog=None, **kwds):
self._orig_endog = endog
self._orig_exog = exog
self.endog, self.exog = self._convert_endog_exog(endog, exog)
self._check_integrity()
self._cache = resettable_cache()
def __init__(self, endog, exog=None, **kwds):
self._orig_endog = endog
self._orig_exog = exog
self.endog, self.exog = self._convert_endog_exog(endog, exog)
self._check_integrity()
self._cache = resettable_cache()
class KDE(object):
"""
Kernel Density Estimator
Parameters
----------
endog : array-like
The variable for which the density estimate is desired.
Notes
-----
If cdf, sf, cumhazard, or entropy are computed, they are computed based on
the definition of the kernel rather than the FFT approximation, even if
the density is fit with FFT = True.
"""
_cache = resettable_cache()
def __init__(self, endog):
self.endog = np.asarray(endog)
def fit(self,
kernel="gau",
bw="scott",
fft=True,
weights=None,
gridsize=None,
adjust=1,
cut=3,
clip=(-np.inf, np.inf)):
"""
Attach the density estimate to the KDE class.
Parameters
----------
kernel : str
The Kernel to be used. Choices are
- "biw" for biweight
- "cos" for cosine
- "epa" for Epanechnikov
- "gauss" for Gaussian.
- "tri" for triangular
- "triw" for triweight
- "uni" for uniform
bw : str, float
"scott" - 1.059 * A * nobs ** (-1/5.), where A is
min(std(X),IQR/1.34)
"silverman" - .9 * A * nobs ** (-1/5.), where A is
min(std(X),IQR/1.34)
If a float is given, it is the bandwidth.
fft : bool
Whether or not to use FFT. FFT implementation is more
computationally efficient. However, only the Gaussian kernel
is implemented. If FFT is False, then a 'nobs' x 'gridsize'
intermediate array is created.
gridsize : int
If gridsize is None, max(len(X), 50) is used.
cut : float
Defines the length of the grid past the lowest and highest values
of X so that the kernel goes to zero. The end points are
-/+ cut*bw*{min(X) or max(X)}
adjust : float
An adjustment factor for the bw. Bandwidth becomes bw * adjust.
"""
try:
bw = float(bw)
self.bw_method = "user-given"
except:
self.bw_method = bw
endog = self.endog
if fft:
if kernel != "gau":
msg = "Only gaussian kernel is available for fft"
raise NotImplementedError(msg)
if weights is not None:
msg = "Weights are not implemented for fft"
raise NotImplementedError(msg)
density, grid, bw = kdensityfft(endog,
kernel=kernel,
bw=bw,
adjust=adjust,
weights=weights,
gridsize=gridsize,
clip=clip,
cut=cut)
else:
density, grid, bw = kdensity(endog,
kernel=kernel,
bw=bw,
adjust=adjust,
weights=weights,
gridsize=gridsize,
clip=clip,
cut=cut)
self.density = density
self.support = grid
self.bw = bw
self.kernel = kernel_switch[kernel](h=bw) # we instantiate twice,
# should this passed to funcs?
@cache_readonly
def cdf(self):
"""
Returns the cumulative distribution function evaluated at the support.
Notes
-----
Will not work if fit has not been called.
"""
_checkisfit(self)
density = self.density
kern = self.kernel
if kern.domain is None: # TODO: test for grid point at domain bound
a, b = -np.inf, np.inf
else:
a, b = kern.domain
func = lambda x, s: kern.density(s, x)
support = self.support
support = np.r_[a, support]
gridsize = len(support)
endog = self.endog
probs = [
integrate.quad(func, support[i - 1], support[i], args=endog)[0]
for i in xrange(1, gridsize)
]
return np.cumsum(probs)
@cache_readonly
def cumhazard(self):
"""
Returns the hazard function evaluated at the support.
Notes
-----
Will not work if fit has not been called.
"""
_checkisfit(self)
return -np.log(self.sf)
@cache_readonly
def sf(self):
"""
Returns the survival function evaluated at the support.
Notes
-----
Will not work if fit has not been called.
"""
_checkisfit(self)
return 1 - self.cdf
@cache_readonly
def entropy(self):
"""
Returns the differential entropy evaluated at the support
Notes
-----
Will not work if fit has not been called. 1e-12 is added to each
probability to ensure that log(0) is not called.
"""
_checkisfit(self)
def entr(x, s):
pdf = kern.density(s, x)
return pdf * np.log(pdf + 1e-12)
pdf = self.density
kern = self.kernel
if kern.domain is not None:
a, b = self.domain
else:
a, b = -np.inf, np.inf
endog = self.endog
#TODO: below could run into integr problems, cf. stats.dist._entropy
return -integrate.quad(entr, a, b, args=(endog, ))[0]
@cache_readonly
def icdf(self):
"""
Inverse Cumulative Distribution (Quantile) Function
Notes
-----
Will not work if fit has not been called. Uses
`scipy.stats.mstats.mquantiles`.
"""
_checkisfit(self)
gridsize = len(self.density)
return stats.mstats.mquantiles(self.endog, np.linspace(0, 1, gridsize))
def evaluate(self, point):
"""
Evaluate density at a single point.
Paramters
---------
point : float
Point at which to evaluate the density.
"""
_checkisfit(self)
return self.kernel.density(self.endog, point)
