def test_kernels(self):
from GPy.kern import RBF,Linear,MLP,Bias,White
Q = self.Z.shape[1]
kernels = [RBF(Q,ARD=True), Linear(Q,ARD=True),MLP(Q,ARD=True), RBF(Q,ARD=True)+Linear(Q,ARD=True)+Bias(Q)+White(Q)
,RBF(Q,ARD=True)+Bias(Q)+White(Q), Linear(Q,ARD=True)+Bias(Q)+White(Q)]
for k in kernels:
k.randomize()
self._test_kernel_param(k)
self._test_Z(k)
self._test_qX(k)
self._test_kernel_param(k, psi2n=True)
self._test_Z(k, psi2n=True)
self._test_qX(k, psi2n=True)
def _create_kernel(self, V):
self._kerns = [
RBF(1, ARD=True, active_dims=[i]) for i in range(self.n_dims)
]
self._kernf = Fixed(self.n_dims, tdot(V))
self._kernb = Bias(self.n_dims)
self.kernel = np.sum(self._kerns) + self._kernf + self._kernb
def gp_on_fold(feature_sets, train, test, y, y_all, learn_options):
sequences = np.array([str(x) for x in y_all.index.get_level_values(0).tolist()])
kern = WeightedDegree(
1, sequences, d=learn_options["kernel degree"], active_dims=[0]
)
X = np.arange(len(train))[:, None]
current_dim = 1
if "gc_count" in feature_sets:
kern += RBF(1, active_dims=[current_dim], name="GC_rbf")
X = np.concatenate((X, feature_sets["gc_count"].values), axis=1)
current_dim += 1
if X.shape[1] != current_dim:
raise AssertionError("incorrect number of columns")
if "drug" in feature_sets:
Q = feature_sets["drug"].values.shape[1]
kern += Linear(
Q, active_dims=range(current_dim, current_dim + Q), name="drug_lin"
)
X = np.concatenate((X, feature_sets["drug"].values), axis=1)
current_dim += Q
if X.shape[1] != current_dim:
raise AssertionError("incorrect number or columns")
if "gene effect" in feature_sets:
Q = feature_sets["gene effect"].values.shape[1]
kern += Linear(
Q, active_dims=range(current_dim, current_dim + Q), name="gene_lin"
)
X = np.concatenate((X, feature_sets["gene effect"].values), axis=1)
current_dim += Q
if X.shape[1] != current_dim:
raise AssertionError("incorrect number or columns")
if "Percent Peptide" in feature_sets:
Q = feature_sets["Percent Peptide"].values.shape[1]
kern += RBF(
Q, active_dims=range(current_dim, current_dim + Q), name="percent_pept"
)
X = np.concatenate((X, feature_sets["Percent Peptide"].values), axis=1)
current_dim += Q
if X.shape[1] != current_dim:
raise AssertionError("incorrect number or columns")
if "Nucleotide cut position" in feature_sets:
Q = feature_sets["Nucleotide cut position"].values.shape[1]
kern += RBF(
Q, active_dims=range(current_dim, current_dim + Q), name="nucleo_cut"
)
X = np.concatenate((X, feature_sets["Nucleotide cut position"].values), axis=1)
current_dim += Q
if X.shape[1] != current_dim:
raise AssertionError("incorrect number or columns")
if "Strand effect" in feature_sets:
Q = feature_sets["Strand effect"].values.shape[1]
kern += Linear(
Q, active_dims=range(current_dim, current_dim + Q), name="strand"
)
X = np.concatenate((X, feature_sets["Strand effect"].values), axis=1)
current_dim += Q
if X.shape[1] != current_dim:
raise AssertionError("incorrect number or columns")
if "NGGX" in feature_sets:
Q = feature_sets["NGGX"].values.shape[1]
kern += Linear(Q, active_dims=range(current_dim, current_dim + Q), name="NGGX")
X = np.concatenate((X, feature_sets["NGGX"].values), axis=1)
current_dim += Q
if X.shape[1] != current_dim:
raise AssertionError("incorrect number or columns")
if "TM" in feature_sets:
Q = feature_sets["TM"].values.shape[1]
kern += RBF(
Q, ARD=True, active_dims=range(current_dim, current_dim + Q), name="TM"
)
X = np.concatenate((X, feature_sets["TM"].values), axis=1)
current_dim += Q
if X.shape[1] != current_dim:
raise AssertionError("incorrect number or columns")
if "gene features" in feature_sets:
Q = feature_sets["gene features"].values.shape[1]
kern += Linear(
Q,
ARD=True,
active_dims=range(current_dim, current_dim + Q),
name="genefeat",
)
X = np.concatenate((X, feature_sets["gene features"].values), axis=1)
current_dim += Q
if X.shape[1] != current_dim:
raise AssertionError("incorrect number or columns")
kern += Bias(X.shape[1])
if learn_options["warpedGP"]:
m = WarpedGP(X[train], y[train], kernel=kern)
else:
m = GPRegression(X[train], y[train], kernel=kern)
m.optimize_restarts(3)
y_pred, _ = m.predict(X[test])
# TODO add offset such that low scores are around 0 (not -4 or so)
return y_pred, m[:]
