def test_VerboseClassifier(self):
nn = MLPC(layers=[L("Softmax")], verbose=1, n_iter=1)
a_in, a_out = numpy.zeros((8,16)), numpy.zeros((8,1), dtype=numpy.int32)
nn.fit(a_in, a_out)
assert_in("Epoch Training Error Validation Error Time", self.buf.getvalue())
assert_in(" 1 ", self.buf.getvalue())
assert_in(" N/A ", self.buf.getvalue())
def test_CaughtRuntimeError(self):
nn = MLPC(layers=[L("Linear")], learning_rate=float("nan"), n_iter=1)
a_in, a_out = numpy.zeros((8, 16)), numpy.zeros((8, 1),
dtype=numpy.int32)
assert_raises(RuntimeError, nn.fit, a_in, a_out)
assert_in("A runtime exception was caught during training.",
self.buf.getvalue())
def check(self, a_in, a_out, a_mask, act='Softmax'):
nn = MLPC(layers=[L(act)],
learning_rule='adam',
learning_rate=0.05,
n_iter=250,
n_stable=25)
nn.fit(a_in, a_out, a_mask)
return nn.predict_proba(a_in)
def test_Classifier(self):
a_in = numpy.random.uniform(0.0, 1.0, (64, 16))
a_out = numpy.random.randint(0, 4, (64, ))
cross_val_score(MLPC(layers=[L("Linear")], n_iter=1),
a_in,
a_out,
cv=5)
def test_GetParamValues(self):
nn = MLPC(layers=[L("Linear")],
learning_rate=0.05,
n_iter=456,
n_stable=123,
valid_size=0.2,
dropout_rate=0.25)
params = nn.get_params()
self.check_values(params)
def test_CloneWithValues(self):
nn = MLPC(layers=[L("Linear")],
learning_rate=0.05,
n_iter=456,
n_stable=123,
valid_size=0.2,
dropout_rate=0.25)
cc = clone(nn)
params = cc.get_params()
self.check_values(params)
def test_SingleVote(self):
a_in, a_out = numpy.random.uniform(0.0, 1.0, (64, 16)), numpy.zeros(
(64, ))
vc = VotingClassifier([('nn1', MLPC(layers=[L("Softmax")], n_iter=1))])
vc.fit(a_in, a_out)
vc.predict(a_in)
def check(self, a_in, a_out, a_mask, act='Softmax', n_iter=100):
nn = MLPC(layers=[L(act)], learning_rule='rmsprop', n_iter=n_iter)
nn.fit(a_in, a_out, a_mask)
return nn.predict_proba(a_in)
def setUp(self):
cc = MLPC(layers=[L("Sigmoid")], n_iter=1)
self.nn = clone(cc)
def test_RepresentationConvolution(self):
nn = MLPC(layers=[C("Rectifier")])
r = repr(nn)
assert_equal(str, type(r))
assert_in("sknn.nn.Convolution `Rectifier`", r)
def setUp(self):
self.nn = MLPC(layers=[L("Linear")], n_iter=1)
def test_RepresentationDenseLayer(self):
nn = MLPC(layers=[L("Gaussian")])
r = repr(nn)
assert_equal(str, type(r))
assert_in("sknn.nn.Layer `Gaussian`", r)
def test_ConvertToString(self):
nn = MLPC(layers=[L("Gaussian")])
assert_equal(str, type(str(nn)))
def test_CloneDefaults(self):
nn = MLPC(layers=[L("Gaussian")])
cc = clone(nn)
params = cc.get_params()
self.check_defaults(params)
def test_GetParamDefaults(self):
nn = MLPC(layers=[L("Gaussian")])
params = nn.get_params()
self.check_defaults(params)
def setUp(self):
self.nn = MLPC(layers=[L("Softmax")], n_iter=1)
def setUp(self):
cc = MLPC(layers=[L("Linear")], n_iter=1)
self.nn = clone(cc)
def test_Representation(self):
nn = MLPC(layers=[L("Gaussian")])
assert_equal(str, type(repr(nn)))
