def train(regress_type='hybrid', seed=1, **kwargs):
X_obs = kwargs['X_obs']
y_obs = kwargs['y_obs']
Kds = kwargs['Kds']
kwargs['regress_type'] = regress_type
# Debug.
#X_obs = X_obs[:10]
#y_obs = y_obs[:10]
# Fit the model.
if regress_type == 'baseline':
from baseline import Baseline
regressor = Baseline()
elif regress_type == 'mlper1':
regressor = mlp_ensemble(
n_neurons=200,
n_regressors=1,
n_epochs=50,
seed=seed,
)
elif regress_type == 'dmlper1':
regressor = mlp_ensemble(
n_neurons=1000,
n_regressors=1,
n_hidden_layers=15,
n_epochs=300,
seed=seed,
)
elif regress_type == 'mlper1g':
regressor = mlp_ensemble(
n_neurons=100,
n_regressors=1,
n_epochs=100,
loss='gaussian_nll',
seed=seed,
)
elif regress_type == 'mlper5':
regressor = mlp_ensemble(
n_neurons=200,
n_regressors=5,
n_epochs=100,
seed=seed,
)
elif regress_type == 'mlper5g':
regressor = mlp_ensemble(
n_neurons=200,
n_regressors=5,
n_epochs=50,
loss='gaussian_nll',
seed=seed,
)
elif regress_type == 'bayesnn':
from bayesian_neural_network import BayesianNN
regressor = BayesianNN(
n_hidden1=200,
n_hidden2=200,
n_iter=1000,
n_posterior_samples=100,
random_state=seed,
verbose=True,
)
elif regress_type == 'cmf':
from cmf_regressor import CMFRegressor
regressor = CMFRegressor(
n_components=30,
seed=seed,
)
regressor.fit(
kwargs['chems'],
kwargs['prots'],
kwargs['chem2feature'],
kwargs['prot2feature'],
kwargs['Kds'],
kwargs['idx_obs'],
)
elif regress_type == 'gp':
from gaussian_process import GPRegressor
from sklearn.gaussian_process.kernels import RBF, ConstantKernel as C
regressor = GPRegressor(
kernel=C(10000., 'fixed') * RBF(1., 'fixed'),
backend='sklearn',
n_jobs=10,
verbose=True
)
elif regress_type == 'gpfactorized':
from gaussian_process import GPRegressor
from sklearn.gaussian_process.kernels import ConstantKernel as C
from kernels import FactorizedRBF
n_features_chem = kwargs['n_features_chem']
n_features_prot = kwargs['n_features_prot']
regressor = GPRegressor(
kernel=C(1., 'fixed') * FactorizedRBF(
[ 1.1, 1. ], [ n_features_chem, n_features_prot ], 'fixed'
),
backend='sklearn',
n_restarts=0,
n_jobs=10,
verbose=True
)
elif regress_type == 'sparsegp':
from gaussian_process import SparseGPRegressor
regressor = SparseGPRegressor(
method='geosketch',
n_inducing=8000,
backend='sklearn',
n_restarts=10,
n_jobs=10,
verbose=True
)
elif regress_type == 'hybrid':
from gaussian_process import GPRegressor
from hybrid import HybridMLPEnsembleGP
regressor = HybridMLPEnsembleGP(
mlp_ensemble(
n_neurons=200,
n_regressors=1,
n_epochs=50,
seed=seed,
),
GPRegressor(
backend='sklearn',#'gpytorch',
n_restarts=10,
n_jobs=10,
verbose=True,
),
)
elif regress_type == 'dhybrid':
from gaussian_process import GPRegressor
from hybrid import HybridMLPEnsembleGP
regressor = HybridMLPEnsembleGP(
mlp_ensemble(
n_neurons=1000,
n_regressors=1,
n_hidden_layers=15,
n_epochs=300,
seed=seed,
),
GPRegressor(
backend='sklearn',#'gpytorch',
n_restarts=10,
n_jobs=10,
verbose=True,
),
)
elif regress_type == 'sparsehybrid':
from gaussian_process import SparseGPRegressor
from hybrid import HybridMLPEnsembleGP
from sklearn.gaussian_process.kernels import RBF, ConstantKernel as C
regressor = HybridMLPEnsembleGP(
mlp_ensemble(
n_neurons=200,
n_regressors=1,
n_epochs=50,
seed=seed,
),
SparseGPRegressor(
method='geosketch',
n_inducing=8000,
backend='sklearn',
n_restarts=10,
n_jobs=10,
verbose=True
),
)
if regress_type not in { 'cmf' }:
regressor.fit(X_obs, y_obs)
#print(regressor.model_.kernel_.get_params()) # Debug.
kwargs['regressor'] = regressor
return kwargs
