def test_nlp_padded_valid(self):
num_words = 1024
(x_train,
y_train), (x_test,
y_test) = TestUtil.get_random_variable_length_dataset(
max_value=num_words)
explained_model = RandomForestClassifier(n_estimators=64,
max_depth=5,
random_state=1)
counter = CountVectoriser(num_words)
tfidf_transformer = TfidfTransformer()
explained_model = Pipeline([('counts', counter),
('tfidf', tfidf_transformer),
('model', explained_model)])
explained_model.fit(x_train, y_train)
model_builder = RNNModelBuilder(embedding_size=num_words,
with_embedding=True,
num_layers=2,
num_units=32,
activation="relu",
p_dropout=0.2,
verbose=0,
batch_size=32,
learning_rate=0.001,
num_epochs=2,
early_stopping_patience=128)
masking_operation = WordDropMasking()
loss = binary_crossentropy
explainer = CXPlain(explained_model, model_builder, masking_operation,
loss)
x_train = pad_sequences(x_train,
padding="post",
truncating="post",
dtype=int)
x_test = pad_sequences(x_test,
padding="post",
truncating="post",
dtype=int,
maxlen=x_train.shape[1])
explainer.fit(x_train, y_train)
eval_score = explainer.score(x_test, y_test)
train_score = explainer.get_last_fit_score()
median = explainer.predict(x_test)
self.assertTrue(median.shape == x_test.shape)
def test_boston_housing_valid(self):
(x_train, y_train), (x_test, y_test) = TestUtil.get_boston_housing()
explained_model = RandomForestRegressor(n_estimators=64,
max_depth=5,
random_state=1)
explained_model.fit(x_train, y_train)
model_builder = MLPModelBuilder(num_layers=2,
num_units=32,
activation="relu",
p_dropout=0.2,
verbose=0,
batch_size=32,
learning_rate=0.001,
num_epochs=3,
early_stopping_patience=128)
masking_operation = ZeroMasking()
loss = mean_squared_error
for num_models in [2, 5, 10]:
explainer = CXPlain(explained_model,
model_builder,
masking_operation,
loss,
num_models=num_models)
explainer.fit(x_train, y_train)
eval_score = explainer.score(x_test, y_test)
train_score = explainer.get_last_fit_score()
median, confidence = explainer.predict(x_test,
confidence_level=0.95)
self.assertTrue(median.shape == x_test.shape)
self.assertTrue(confidence.shape == x_test.shape + (2, ))
# Flatten predictions for iteration below.
median = median.reshape((len(x_test), -1))
confidence = confidence.reshape((len(x_test), -1, 2))
for sample_idx in range(len(x_test)):
for feature_idx in range(len(x_test[sample_idx])):
self.assertTrue(confidence[sample_idx][feature_idx][0] <=
median[sample_idx][feature_idx] <=
confidence[sample_idx][feature_idx][1])
self.assertTrue(
confidence[sample_idx][feature_idx][0] >= 0)
self.assertTrue(
confidence[sample_idx][feature_idx][1] >= 0)
def test_mnist_unet_valid(self):
num_subsamples = 100
(x_train,
y_train), (x_test,
y_test) = TestUtil.get_mnist(flattened=False,
num_subsamples=num_subsamples)
explained_model = MLPClassifier(solver='lbfgs',
alpha=1e-5,
hidden_layer_sizes=(64, 32),
random_state=1)
explained_model.fit(x_train.reshape((len(x_train), -1)), y_train)
masking_operation = ZeroMasking()
loss = categorical_crossentropy
downsample_factors = [(2, 2), (4, 4), (4, 7), (7, 4), (7, 7)]
with_bns = [
True if i % 2 == 0 else False
for i in range(len(downsample_factors))
]
for downsample_factor, with_bn in zip(downsample_factors, with_bns):
model_builder = UNetModelBuilder(downsample_factor,
num_layers=2,
num_units=64,
activation="relu",
p_dropout=0.2,
verbose=0,
batch_size=256,
learning_rate=0.001,
num_epochs=2,
early_stopping_patience=128,
with_bn=with_bn)
explainer = CXPlain(explained_model,
model_builder,
masking_operation,
loss,
downsample_factors=downsample_factor,
flatten_for_explained_model=True)
explainer.fit(x_train, y_train)
eval_score = explainer.score(x_test, y_test)
train_score = explainer.get_last_fit_score()
median = explainer.predict(x_test)
self.assertTrue(median.shape == x_test.shape)
def test_boston_housing_valid(self):
(x_train, y_train), (x_test, y_test) = TestUtil.get_boston_housing()
explained_model = RandomForestRegressor(n_estimators=64, max_depth=5, random_state=1)
explained_model.fit(x_train, y_train)
model_builder = MLPModelBuilder(num_layers=2, num_units=32, activation="relu", p_dropout=0.2, verbose=0,
batch_size=32, learning_rate=0.001, num_epochs=2, early_stopping_patience=128)
masking_operation = ZeroMasking()
loss = mean_squared_error
explainer = CXPlain(explained_model, model_builder, masking_operation, loss)
explainer.fit(x_train, y_train)
self.assertEqual(explainer.prediction_model.output_shape, (None, np.prod(x_test.shape[1:])))
eval_score = explainer.score(x_test, y_test)
train_score = explainer.get_last_fit_score()
median = explainer.predict(x_test)
self.assertTrue(median.shape == x_test.shape)
def test_time_series_valid(self):
num_samples = 1024
fixed_length = 99
(x_train, y_train), (x_test, y_test) = TestUtil.get_random_fixed_length_dataset(num_samples=num_samples,
fixed_length=fixed_length)
model_builder = RNNModelBuilder(with_embedding=False, num_layers=2, num_units=32,
activation="relu", p_dropout=0.2, verbose=0,
batch_size=32, learning_rate=0.001, num_epochs=2,
early_stopping_patience=128)
explained_model = MLPClassifier()
explained_model.fit(x_train.reshape((-1, np.prod(x_train.shape[1:]))), y_train)
masking_operation = ZeroMasking()
loss = binary_crossentropy
explainer = CXPlain(explained_model, model_builder, masking_operation, loss,
flatten_for_explained_model=True)
explainer.fit(x_train, y_train)
eval_score = explainer.score(x_test, y_test)
train_score = explainer.get_last_fit_score()
median = explainer.predict(x_test)
self.assertTrue(median.shape == x_test.shape)
