def __init__(self, simulator, quick_scale, noise_model, sparse, init_mode):
if noise_model is None:
raise ValueError("noise_model is None")
else:
if noise_model == "nb":
from batchglm.api.models.tf1.glm_nb import Estimator, InputDataGLM
elif noise_model == "norm":
from batchglm.api.models import Estimator, InputDataGLM
elif noise_model == "beta":
from batchglm.api.models.tf1.glm_beta import Estimator, InputDataGLM
else:
raise ValueError("noise_model not recognized")
batch_size = 2000
provide_optimizers = {
"gd": True,
"adam": True,
"adagrad": True,
"rmsprop": True,
"nr": True,
"nr_tr": True,
"irls": noise_model in ["nb", "norm"],
"irls_gd": noise_model in ["nb", "norm"],
"irls_tr": noise_model in ["nb", "norm"],
"irls_gd_tr": noise_model in ["nb", "norm"]
}
if sparse:
input_data = InputDataGLM(
data=scipy.sparse.csr_matrix(simulator.input_data.x),
design_loc=simulator.input_data.design_loc,
design_scale=simulator.input_data.design_scale,
design_loc_names=simulator.input_data.design_loc_names,
design_scale_names=simulator.input_data.design_scale_names,
constraints_loc=simulator.input_data.constraints_loc,
constraints_scale=simulator.input_data.constraints_scale,
size_factors=simulator.input_data.size_factors,
as_dask=False)
else:
input_data = InputDataGLM(
data=simulator.input_data.x,
design_loc=simulator.input_data.design_loc,
design_scale=simulator.input_data.design_scale,
design_loc_names=simulator.input_data.design_loc_names,
design_scale_names=simulator.input_data.design_scale_names,
constraints_loc=simulator.input_data.constraints_loc,
constraints_scale=simulator.input_data.constraints_scale,
size_factors=simulator.input_data.size_factors,
as_dask=False)
self.estimator = Estimator(input_data=input_data,
batch_size=batch_size,
quick_scale=quick_scale,
provide_optimizers=provide_optimizers,
provide_batched=True,
provide_fim=noise_model in ["nb", "norm"],
provide_hessian=True,
init_a=init_mode,
init_b=init_mode)
self.sim = simulator
def get_hessians(self, input_data: InputDataGLM):
if self.noise_model is None:
raise ValueError("noise_model is None")
else:
if self.noise_model == "nb":
from batchglm.api.models.tf1.glm_nb import Estimator
elif self.noise_model == "norm":
from batchglm.api.models import Estimator
elif self.noise_model == "beta":
from batchglm.api.models.tf1.glm_beta import Estimator
else:
raise ValueError("noise_model not recognized")
provide_optimizers = {
"gd": True,
"adam": True,
"adagrad": True,
"rmsprop": True,
"nr": False,
"nr_tr": False,
"irls": False,
"irls_gd": False,
"irls_tr": False,
"irls_gd_tr": False
}
estimator = Estimator(input_data=input_data,
quick_scale=False,
provide_optimizers=provide_optimizers,
provide_fim=False,
provide_hessian=False,
init_a="standard",
init_b="standard")
estimator.initialize()
estimator_store = estimator.finalize()
return -estimator_store.fisher_inv
def __init__(self, simulator, quick_scale, algo, batched, noise_model,
sparse):
if noise_model is None:
raise ValueError("noise_model is None")
else:
if noise_model == "nb":
from batchglm.api.models.tf1.glm_nb import Estimator, InputDataGLM
elif noise_model == "norm":
from batchglm.api.models import Estimator, InputDataGLM
elif noise_model == "beta":
from batchglm.api.models.tf1.glm_beta import Estimator, InputDataGLM
else:
raise ValueError("noise_model not recognized")
batch_size = 200
provide_optimizers = {
"gd": False,
"adam": False,
"adagrad": False,
"rmsprop": False,
"nr": False,
"nr_tr": False,
"irls": False,
"irls_gd": False,
"irls_tr": False,
"irls_gd_tr": False
}
provide_optimizers[algo.lower()] = True
if sparse:
input_data = InputDataGLM(
data=scipy.sparse.csr_matrix(simulator.input_data.x),
design_loc=simulator.input_data.design_loc,
design_scale=simulator.input_data.design_scale)
else:
input_data = InputDataGLM(
data=simulator.input_data.x,
design_loc=simulator.input_data.design_loc,
design_scale=simulator.input_data.design_scale)
estimator = Estimator(input_data=input_data,
batch_size=batch_size,
quick_scale=quick_scale,
provide_optimizers=provide_optimizers,
provide_batched=batched,
optim_algos=[algo.lower()])
self.estimator = estimator
self.sim = simulator
self.algo = algo.lower()
def get_jacs(
self,
input_data: InputDataGLM
):
if self.noise_model is None:
raise ValueError("noise_model is None")
else:
if self.noise_model == "nb":
from batchglm.api.models.tf1.glm_nb import Estimator
elif self.noise_model == "norm":
from batchglm.api.models import Estimator
elif self.noise_model == "beta":
from batchglm.api.models.tf1.glm_beta import Estimator
else:
raise ValueError("noise_model not recognized")
provide_optimizers = {"gd": True, "adam": True, "adagrad": True, "rmsprop": True,
"nr": False, "nr_tr": False,
"irls": False, "irls_gd": False, "irls_tr": False, "irls_gd_tr": False}
estimator = Estimator(
input_data=input_data,
quick_scale=False,
provide_optimizers=provide_optimizers,
provide_fim=False,
provide_hessian=False,
init_a="standard",
init_b="standard"
)
estimator.initialize()
# Do not train, evaluate at initialization!
estimator.train_sequence(training_strategy=[
{
"convergence_criteria": "step",
"stopping_criteria": 0,
"use_batching": False,
"optim_algo": "gd",
"train_mu": False,
"train_r": False
},
])
estimator_store = estimator.finalize()
return estimator_store.gradients.values
class _TestAccuracyGlmAllEstim:
def __init__(self, simulator, quick_scale, noise_model, sparse, init_mode):
if noise_model is None:
raise ValueError("noise_model is None")
else:
if noise_model == "nb":
from batchglm.api.models.tf1.glm_nb import Estimator, InputDataGLM
elif noise_model == "norm":
from batchglm.api.models import Estimator, InputDataGLM
elif noise_model == "beta":
from batchglm.api.models.tf1.glm_beta import Estimator, InputDataGLM
else:
raise ValueError("noise_model not recognized")
batch_size = 2000
provide_optimizers = {
"gd": True,
"adam": True,
"adagrad": True,
"rmsprop": True,
"nr": True,
"nr_tr": True,
"irls": noise_model in ["nb", "norm"],
"irls_gd": noise_model in ["nb", "norm"],
"irls_tr": noise_model in ["nb", "norm"],
"irls_gd_tr": noise_model in ["nb", "norm"]
}
if sparse:
input_data = InputDataGLM(
data=scipy.sparse.csr_matrix(simulator.input_data.x),
design_loc=simulator.input_data.design_loc,
design_scale=simulator.input_data.design_scale,
design_loc_names=simulator.input_data.design_loc_names,
design_scale_names=simulator.input_data.design_scale_names,
constraints_loc=simulator.input_data.constraints_loc,
constraints_scale=simulator.input_data.constraints_scale,
size_factors=simulator.input_data.size_factors,
as_dask=False)
else:
input_data = InputDataGLM(
data=simulator.input_data.x,
design_loc=simulator.input_data.design_loc,
design_scale=simulator.input_data.design_scale,
design_loc_names=simulator.input_data.design_loc_names,
design_scale_names=simulator.input_data.design_scale_names,
constraints_loc=simulator.input_data.constraints_loc,
constraints_scale=simulator.input_data.constraints_scale,
size_factors=simulator.input_data.size_factors,
as_dask=False)
self.estimator = Estimator(input_data=input_data,
batch_size=batch_size,
quick_scale=quick_scale,
provide_optimizers=provide_optimizers,
provide_batched=True,
provide_fim=noise_model in ["nb", "norm"],
provide_hessian=True,
init_a=init_mode,
init_b=init_mode)
self.sim = simulator
def estimate(self, algo, batched, acc, lr):
self.estimator.initialize()
self.estimator.train_sequence(training_strategy=[
{
"learning_rate": lr,
"convergence_criteria": "all_converged",
"stopping_criteria": acc,
"use_batching": batched,
"optim_algo": algo,
},
])
def eval_estimation(self, batched, train_loc, train_scale):
if batched:
threshold_dev_a = 0.4
threshold_dev_b = 0.4
threshold_std_a = 2
threshold_std_b = 2
else:
threshold_dev_a = 0.2
threshold_dev_b = 0.2
threshold_std_a = 1
threshold_std_b = 1
success = True
if train_loc:
mean_rel_dev_a = np.mean(
(self.estimator.model.a_var - self.sim.a_var) / self.sim.a_var)
std_rel_dev_a = np.std(
(self.estimator.model.a_var - self.sim.a_var) / self.sim.a_var)
logging.getLogger("batchglm").info("mean_rel_dev_a %f" %
mean_rel_dev_a)
logging.getLogger("batchglm").info("std_rel_dev_a %f" %
std_rel_dev_a)
if np.abs(mean_rel_dev_a
) > threshold_dev_a or std_rel_dev_a > threshold_std_a:
success = False
if train_scale:
mean_rel_dev_b = np.mean(
(self.estimator.model.b_var - self.sim.b_var) / self.sim.b_var)
std_rel_dev_b = np.std(
(self.estimator.model.b_var - self.sim.b_var) / self.sim.b_var)
logging.getLogger("batchglm").info("mean_rel_dev_b %f" %
mean_rel_dev_b)
logging.getLogger("batchglm").info("std_rel_dev_b %f" %
std_rel_dev_b)
if np.abs(mean_rel_dev_b
) > threshold_dev_b or std_rel_dev_b > threshold_std_b:
success = False
return success