def test_tc(modelfile, distfile):
with open(modelfile, "r") as modelfp:
model = DDPModel()
model.init_from(modelfp, ',')
with open(distfile, "r") as distfp:
dist = DistributionModel()
dist.init_from(distfp, ',')
output = StringIO.StringIO()
dist.apply_as_distribution(model).write(output, ',')
print output.getvalue()
output.close()
def apply_as_distribution(self, model):
if model.kind() == 'ddp_model':
if len(model.xx) != len(self.yy):
raise ValueError("Wrong number of values.")
for ii in range(len(model.xx)):
if model.get_xx()[ii] != self.get_yy()[ii]:
raise ValueError("Wrong values in distribution.")
vv = self.lin_p().dot(model.lin_p())
return DDPModel('ddp1',
'distribution',
self.xx_is_categorical,
self.get_xx(),
model.yy_is_categorical,
model.get_yy(),
vv,
scaled=self.scaled)
elif model.kind() == 'spline_model':
if len(model.xx) != len(self.yy):
raise ValueError("Wrong number of values.")
for ii in range(len(model.xx)):
if model.get_xx()[ii] not in self.get_yy():
raise ValueError("Wrong values in distribution.")
pp = self.lin_p()
conditionals = []
for ii in range(len(self.xx)):
conds = []
for jj in range(len(model.xx)):
original = model.get_conditional(model.get_xx()[jj])
conditional = SplineModelConditional(
original.y0s, original.y1s, original.coeffs)
conditional.scale(
pp[ii, self.get_yy().index(model.get_xx()[jj])])
conds.append(conditional)
conditionals.append(
SplineModelConditional.approximate_sum(conds))
return SplineModel(self.xx_is_categorical,
self.get_xx(),
conditionals,
scaled=self.scaled)
else:
raise ValueError("Unknown model type in apply_as_distribution")
import sys, StringIO
sys.path.append("../lib/models")
from model import Model
from ddp_model import DDPModel
from spline_model import SplineModel
mod1 = DDPModel.create_lin([0, 1], dict(control=[.5, .5], treatment=[0, 1]))
mod2 = DDPModel.create_lin([0, 1], dict(control=[.5, .5], treatment=[1, 0]))
def printmod(mod):
output = StringIO.StringIO()
mod.write(output, ',')
print output.getvalue()
printmod(Model.combine([mod1, mod2], [.5, .5]))
printmod(Model.combine([mod1, mod2], [.25, 2]))
mod1 = SplineModel.create_gaussian(dict(control=(0, 1), treatment=(1, 1e-3)))
mod2 = SplineModel.create_gaussian(dict(control=(0, 1), treatment=(0, 1e-3)))
def printmod2(mod):
output = StringIO.StringIO()
mod.write_gaussian_plus(output, ',')
print output.getvalue()
printmod2(Model.combine([mod1, mod2], [.5, .5]))
printmod2(Model.combine([mod1, mod2], [.25, 2]))
model = BinModel(newmodels[0].get_xx(), allmodel)
return model
# Both models are BinModels
@staticmethod
def combine(one, two):
if not one.scaled or not two.scaled:
raise ValueError("Cannot combine unscaled models")
(one, two, xx) = UnivariateModel.intersect_x(one, two)
allxx = set(one.xx) | set(two.xx)
allxx = np.array(allxx)
midpts = (allxx[1:] + allxx[:-1]) / 2
onemodel = one.model.recategorize_x(map(model.get_bin_at, midpts), range(1, len(allxx)))
twomodel = two.model.recategorize_x(map(model.get_bin_at, midpts), range(1, len(allxx)))
model = Model.combine([onemodel, twomodel], [1, 1])
return BinModel(allxx, model, True)
from ddp_model import DDPModel
Model.mergers["bin_model"] = BinModel.merge
Model.mergers["bin_model+ddp_model"] = lambda models: DDPModel.merge(map(lambda m: m.to_ddp(), models))
Model.mergers["bin_model+spline_model"] = lambda models: DDPModel.merge(map(lambda m: m.to_ddp(), models))
Model.combiners['bin_model+bin_model'] = BinModel.combine
Model.combiners["bin_model+ddp_model"] = lambda one, two: DDPModel.combine(one.to_ddp(), two)
Model.combiners["bin_model+spline_model"] = lambda one, two: DDPModel.combine(one.to_ddp(), two)
if not one.scaled or not two.scaled:
raise ValueError("Cannot combine unscaled models")
(one, two, xx) = UnivariateModel.intersect_x(one, two)
allxx = set(one.xx) | set(two.xx)
allxx = np.array(allxx)
midpts = (allxx[1:] + allxx[:-1]) / 2
onemodel = one.model.recategorize_x(map(model.get_bin_at, midpts),
range(1, len(allxx)))
twomodel = two.model.recategorize_x(map(model.get_bin_at, midpts),
range(1, len(allxx)))
model = Model.combine([onemodel, twomodel], [1, 1])
return BinModel(allxx, model, True)
from ddp_model import DDPModel
Model.mergers["bin_model"] = BinModel.merge
Model.mergers["bin_model+ddp_model"] = lambda models: DDPModel.merge(
map(lambda m: m.to_ddp(), models))
Model.mergers["bin_model+spline_model"] = lambda models: DDPModel.merge(
map(lambda m: m.to_ddp(), models))
Model.combiners['bin_model+bin_model'] = BinModel.combine
Model.combiners["bin_model+ddp_model"] = lambda one, two: DDPModel.combine(
one.to_ddp(), two)
Model.combiners["bin_model+spline_model"] = lambda one, two: DDPModel.combine(
one.to_ddp(), two)
import sys, StringIO
sys.path.append("../lib/models")
from model import Model
from ddp_model import DDPModel
from spline_model import SplineModel
mod1 = DDPModel.create_lin([0, 1], dict(control=[.5, .5], treatment=[0, 1]))
mod2 = DDPModel.create_lin([0, 1], dict(control=[.5, .5], treatment=[1, 0]))
def printmod(mod):
output = StringIO.StringIO()
mod.write(output, ',')
print output.getvalue()
printmod(Model.combine([mod1, mod2], [.5, .5]))
printmod(Model.combine([mod1, mod2], [.25, 2]))
mod1 = SplineModel.create_gaussian(dict(control=(0, 1), treatment=(1, 1e-3)))
mod2 = SplineModel.create_gaussian(dict(control=(0, 1), treatment=(0, 1e-3)))
def printmod2(mod):
output = StringIO.StringIO()
mod.write_gaussian_plus(output, ',')
print output.getvalue()
printmod2(Model.combine([mod1, mod2], [.5, .5]))
