def init(cls):
nobs = cls.nobs
y_true, x, exog = cls.y_true, cls.x, cls.exog
if not hasattr(cls, 'scale'):
scale = 1
else:
scale = cls.scale
f = cls.family
cls.mu_true = mu_true = f.link.inverse(y_true)
np.random.seed(8765993)
#y_obs = np.asarray([stats.poisson.rvs(p) for p in mu], float)
if issubclass(get_class(cls.rvs), stats.rv_discrete):
# Discrete distributions don't take `scale`.
y_obs = cls.rvs(mu_true, size=nobs)
else:
y_obs = cls.rvs(mu_true, scale=scale, size=nobs)
m = GAM(y_obs, x, family=f) #TODO: y_obs is twice __init__ and fit
m.fit(y_obs, maxiter=100)
res_gam = m.results
cls.res_gam = res_gam #attached for debugging
cls.mod_gam = m #attached for debugging
res_glm = GLM(y_obs, exog, family=f).fit()
#Note: there still are some naming inconsistencies
cls.res1 = res1 = Dummy() #for gam model
#res2 = Dummy() #for benchmark
cls.res2 = res2 = res_glm #reuse existing glm results, will add additional
#eta in GLM terminology
res2.y_pred = res_glm.model.predict(res_glm.params, exog, linear=True)
res1.y_pred = res_gam.predict(x)
res1.y_predshort = res_gam.predict(x[:10]) #, linear=True)
#mu
res2.mu_pred = res_glm.model.predict(res_glm.params,
exog,
linear=False)
res1.mu_pred = res_gam.mu
#parameters
slopes = [i for ss in m.smoothers for i in ss.params[1:]]
const = res_gam.alpha + sum([ss.params[1] for ss in m.smoothers])
res1.params = np.array([const] + slopes)
def init(self):
nobs = self.nobs
y_true, x, exog = self.y_true, self.x, self.exog
if not hasattr(self, 'scale'):
scale = 1
else:
scale = self.scale
f = self.family
self.mu_true = mu_true = f.link.inverse(y_true)
np.random.seed(8765993)
#y_obs = np.asarray([stats.poisson.rvs(p) for p in mu], float)
if issubclass(self.rvs.__self__.__class__, stats.rv_discrete):
# Discrete distributions don't take `scale`.
y_obs = self.rvs(mu_true, size=nobs)
else:
y_obs = self.rvs(mu_true, scale=scale, size=nobs)
m = GAM(y_obs, x, family=f) #TODO: y_obs is twice __init__ and fit
m.fit(y_obs, maxiter=100)
res_gam = m.results
self.res_gam = res_gam #attached for debugging
self.mod_gam = m #attached for debugging
res_glm = GLM(y_obs, exog, family=f).fit()
#Note: there still are some naming inconsistencies
self.res1 = res1 = Dummy() #for gam model
#res2 = Dummy() #for benchmark
self.res2 = res2 = res_glm #reuse existing glm results, will add additional
#eta in GLM terminology
res2.y_pred = res_glm.model.predict(res_glm.params, exog, linear=True)
res1.y_pred = res_gam.predict(x)
res1.y_predshort = res_gam.predict(x[:10]) #, linear=True)
#mu
res2.mu_pred = res_glm.model.predict(res_glm.params, exog, linear=False)
res1.mu_pred = res_gam.mu
#parameters
slopes = [i for ss in m.smoothers for i in ss.params[1:]]
const = res_gam.alpha + sum([ss.params[1] for ss in m.smoothers])
res1.params = np.array([const] + slopes)
def init(self):
nobs = self.nobs
y_true, x, exog = self.y_true, self.x, self.exog
if not hasattr(self, 'scale'):
scale = 1
else:
scale = self.scale
f = self.family
self.mu_true = mu_true = f.link.inverse(y_true)
np.random.seed(8765993)
#y_obs = np.asarray([stats.poisson.rvs(p) for p in mu], float)
y_obs = self.rvs(mu_true, scale=scale, size=nobs) #this should work
m = GAM(y_obs, x, family=f) #TODO: y_obs is twice __init__ and fit
m.fit(y_obs, maxiter=100)
res_gam = m.results
self.res_gam = res_gam #attached for debugging
self.mod_gam = m #attached for debugging
res_glm = GLM(y_obs, exog, family=f).fit()
#Note: there still are some naming inconsistencies
self.res1 = res1 = Dummy() #for gam model
#res2 = Dummy() #for benchmark
self.res2 = res2 = res_glm #reuse existing glm results, will add additional
#eta in GLM terminology
res2.y_pred = res_glm.model.predict(res_glm.params, exog, linear=True)
res1.y_pred = res_gam.predict(x)
res1.y_predshort = res_gam.predict(x[:10]) #, linear=True)
#mu
res2.mu_pred = res_glm.model.predict(res_glm.params,
exog,
linear=False)
res1.mu_pred = res_gam.mu
#parameters
slopes = [i for ss in m.smoothers for i in ss.params[1:]]
const = res_gam.alpha + sum([ss.params[1] for ss in m.smoothers])
res1.params = np.array([const] + slopes)
x2 = R.standard_normal(nobs)
x2.sort()
y = R.standard_normal((nobs, ))
d = np.array([x1, x2]).T
import scipy.stats, time
print("binomial")
f = family.Binomial()
# b = np.asarray([scipy.stats.bernoulli.rvs(p) for p in f.link.inverse(y)])
# b.shape = y.shape
b = np.zeros(len(x1))
b[x1 > 0.5] = 1
m = GAM(b, d, family=f)
toc = time.time()
m.fit(b)
tic = time.time()
print(tic - toc)
plt.figure()
plt.plot(x1, standardize(m.smoothers[0](x1)), 'r')
#plt.plot(x1, standardize(f1(x1)), linewidth=2)
#plt.figure()
plt.plot(x2, standardize(m.smoothers[0](x2)), 'r')
#plt.plot(x2, standardize(f2(x2)), linewidth=2)
plt.show()
exog_reduced = exog[:, idx] #remove duplicate constant
y_true = exog.sum(1) #/ 4.
z = y_true #alias check
d = x
y = y_true + sigma_noise * np.random.randn(nobs)
example = 3
if example == 2:
print "binomial"
f = family.Binomial()
mu_true = f.link.inverse(z)
#b = np.asarray([scipy.stats.bernoulli.rvs(p) for p in f.link.inverse(y)])
b = np.asarray([stats.bernoulli.rvs(p) for p in f.link.inverse(z)])
b.shape = y.shape
m = GAM(b, d, family=f)
toc = time.time()
m.fit(b)
tic = time.time()
print tic - toc
#for plotting
yp = f.link.inverse(y)
p = b
if example == 3:
print "Poisson"
f = family.Poisson()
#y = y/y.max() * 3
yp = f.link.inverse(z)
#p = np.asarray([scipy.stats.poisson.rvs(p) for p in f.link.inverse(y)], float)
p = np.asarray([stats.poisson.rvs(p) for p in f.link.inverse(z)], float)
exog_reduced = exog[:,idx] #remove duplicate constant
y_true = exog.sum(1) #/ 4.
z = y_true #alias check
d = x
y = y_true + sigma_noise * np.random.randn(nobs)
example = 3
if example == 2:
print("binomial")
f = family.Binomial()
mu_true = f.link.inverse(z)
#b = np.asarray([scipy.stats.bernoulli.rvs(p) for p in f.link.inverse(y)])
b = np.asarray([stats.bernoulli.rvs(p) for p in f.link.inverse(z)])
b.shape = y.shape
m = GAM(b, d, family=f)
toc = time.time()
m.fit(b)
tic = time.time()
print(tic-toc)
#for plotting
yp = f.link.inverse(y)
p = b
if example == 3:
print("Poisson")
f = family.Poisson()
#y = y/y.max() * 3
yp = f.link.inverse(z)
#p = np.asarray([scipy.stats.poisson.rvs(p) for p in f.link.inverse(y)], float)
