def test_simple_numeric_predictor():
predictor = Predictor(inputs=[NumericInput(dim=30)],
outputs=[Output(dim=1, activation="sigmoid")],
dense_layer_sizes=[30],
dense_activation="relu")
y = predictor.predict(randn(10, 30))
eq_(len(y), 10)
def test_simple_sequence_predictor_named():
predictor = Predictor(
inputs=[SequenceInput(length=4, name="x", variable_length=True)],
outputs=[Output(dim=1, activation="sigmoid", name="y")],
hidden_layer_sizes=[30],
hidden_activation="relu")
y = predictor.predict({"x": ["SFY-"] * 10})["y"]
eq_(len(y), 10)
def test_simple_numeric_predictor_named():
predictor = Predictor(
inputs=[NumericInput(name="x", dim=30)],
outputs=[Output(dim=1, name="y", activation="sigmoid")],
hidden_layer_sizes=[30],
hidden_activation="relu")
y = predictor.predict({"x": randn(10, 30)})["y"]
eq_(len(y), 10)
def test_simple_sequence_predictor():
predictor = Predictor(
inputs=[SequenceInput(length=4, variable_length=True)],
outputs=[Output(dim=1, activation="sigmoid")],
dense_layer_sizes=[30],
dense_activation="relu")
y = predictor.predict(["SFY-"] * 10)
eq_(len(y), 10)
def test_fixed_length_hotshot():
model = Predictor(inputs=SequenceInput(length=9,
variable_length=False,
encoding="onehot"),
outputs=Output(1, activation="sigmoid"))
seqs = ["A" * 9, "L" * 9]
y = model.predict(seqs)
eq_(len(y), 2)
def test_two_input_predictor():
predictor = Predictor(
inputs=[
SequenceInput(length=4, name="x1", variable_length=True),
NumericInput(dim=30, name="x2")
],
outputs=[Output(name="y", dim=1, activation="sigmoid")],
dense_layer_sizes=[30],
dense_activation="relu")
y = predictor.predict({"x1": ["SFY-"] * 10, "x2": randn(10, 30)})["y"]
eq_(len(y), 10)
def test_basic_rnn():
pred = Predictor(inputs=SequenceInput(name="x",
length=4,
variable_length=True,
encoding="embedding",
rnn_layer_sizes=[20],
rnn_type="lstm",
rnn_bidirectional=True),
outputs=Output(dim=1, activation="sigmoid", name="y"))
x = ["SF", "Y", "AALL"]
y = pred.predict({"x": x})["y"]
eq_(len(x), len(y))
found_rnn_layer = any("bidirectional" in layer.name
for layer in pred.model.layers)
assert found_rnn_layer
def test_predictor_output_transform():
predictor = Predictor(inputs=[NumericInput(dim=30, name="x")],
outputs=[
Output(name="y",
dim=1,
activation="sigmoid",
transform=log,
inverse_transform=exp)
],
dense_layer_sizes=[30],
dense_activation="relu")
y = predictor.predict({"x": randn(10, 30)})["y"]
eq_(len(y), 10)
# make sure transformed outputs are within given bounds
assert exp(0.0) <= y.min() <= exp(1.0)
assert exp(0.0) <= y.max() <= exp(1.0)
def test_predictor_on_more_data():
predictor = Predictor(
inputs=[SequenceInput(length=20, name="x", variable_length=True)],
outputs=[Output(dim=1, activation="sigmoid", name="y")],
dense_layer_sizes=[30],
dense_activation="relu")
train_df = synthetic_peptides_by_subsequence(1000)
test_df = synthetic_peptides_by_subsequence(1000)
predictor.fit({"x": train_df.index.values},
train_df.binder.values,
epochs=20)
y_pred = predictor.predict({"x": test_df.index.values})['y']
y_pred = pandas.Series(y_pred, index=test_df.index)
binder_mean_pred = y_pred[test_df.binder].mean()
nonbinder_mean_pred = y_pred[~test_df.binder].mean()
print(binder_mean_pred, nonbinder_mean_pred)
assert binder_mean_pred > nonbinder_mean_pred * 2, (binder_mean_pred,
nonbinder_mean_pred)
def test_model_with_fixed_length_context():
model = Predictor(inputs={
"upstream":
SequenceInput(length=1, variable_length=False),
"downstream":
SequenceInput(length=1, variable_length=False),
"peptide":
SequenceInput(length=3, variable_length=True)
},
outputs=Output(1, activation="sigmoid"))
Y = np.array([True, False, True, False])
input_dict = {
"upstream": ["Q", "A", "L", "I"],
"downstream": ["S"] * 4,
"peptide": ["SYF", "QQ", "C", "GLL"]
}
model.fit(input_dict, Y, epochs=20)
Y_pred = model.predict(input_dict)
assert (Y == (Y_pred > 0.5)).all(), (Y, Y_pred)
def test_discrete_input_with_str_tokens():
pred = Predictor(inputs=DiscreteInput(choices=["x", "y", "z"],
embedding_dim=2),
outputs=Output(1, "sigmoid"))
pred.fit(["x", "x", "y", "z"], [0, 0, 0.5, 1.0], epochs=20)
assert pred.predict(["x"]) < pred.predict(["z"])
