def test_mnist_unet_with_shape_valid(self):
num_subsamples = 100
(x_train,
y_train), (x_test,
y_test) = TestUtil.get_mnist(flattened=False,
num_subsamples=num_subsamples)
explained_model_builder = MLPModelBuilder(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)
input_shape = x_train.shape[1:]
input_layer = Input(shape=input_shape)
last_layer = Flatten()(input_layer)
last_layer = explained_model_builder.build(last_layer)
last_layer = Dense(y_train.shape[-1], activation="softmax")(last_layer)
explained_model = Model(input_layer, last_layer)
explained_model.compile(loss="categorical_crossentropy",
optimizer="adam")
explained_model.fit(x_train, 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)
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_no_fit_invalid(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)
with self.assertRaises(AssertionError):
explainer.predict(x_test, y_test)
with self.assertRaises(AssertionError):
explainer.score(x_test, y_test)
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_boston_housing_confidence_level_invalid(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
num_models = 2
explainer = CXPlain(explained_model,
model_builder,
masking_operation,
loss,
num_models=num_models)
explainer.fit(x_train, y_train)
invalid_confidence_levels = [1.01, -0.5, -0.01]
for confidence_level in invalid_confidence_levels:
with self.assertRaises(ValueError):
explainer.predict(x_test, confidence_level=confidence_level)
def test_boston_housing_load_save_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
num_models_settings = [1, 2]
for num_models in num_models_settings:
explainer = CXPlain(explained_model, model_builder, masking_operation, loss,
num_models=num_models)
explainer.fit(x_train, y_train)
median_1 = explainer.predict(x_test)
tmp_dir_name = tempfile.mkdtemp()
explainer.save(tmp_dir_name)
with self.assertRaises(ValueError):
explainer.save(tmp_dir_name, overwrite=False)
explainer.save(tmp_dir_name, overwrite=True)
explainer.load(tmp_dir_name)
median_2 = explainer.predict(x_test)
self.assertTrue(np.array_equal(median_1, median_2))
shutil.rmtree(tmp_dir_name) # Cleanup.
def test_mnist_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)
model_builder = MLPModelBuilder(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)
masking_operation = ZeroMasking()
loss = categorical_crossentropy
downsample_factors = [(2, 2), (4, 4), (4, 7), (7, 4), (7, 7)]
for downsample_factor in downsample_factors:
explainer = CXPlain(explained_model, model_builder, masking_operation, loss,
downsample_factors=downsample_factor, flatten_for_explained_model=True)
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_mnist_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)
model_builder = MLPModelBuilder(num_layers=2,
num_units=64,
activation="relu",
p_dropout=0.2,
verbose=0,
batch_size=256,
learning_rate=0.001,
num_epochs=3,
early_stopping_patience=128)
masking_operation = ZeroMasking()
loss = categorical_crossentropy
downsample_factors = [(2, 2), (4, 4), (4, 7), (7, 4), (7, 7)]
for downsample_factor in downsample_factors:
explainer = CXPlain(explained_model,
model_builder,
masking_operation,
loss,
num_models=2,
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, confidence = explainer.predict(x_test,
confidence_level=0.95)
self.assertTrue(median.shape == x_test.shape)
self.assertTrue(confidence.shape == x_test.shape[:-1] + (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_overwrite_ensemble_model_invalid(self):
(x_train, y_train), (x_test, y_test) = TestUtil.get_boston_housing()
model_builder = MLPModelBuilder()
explained_model = RandomForestRegressor(n_estimators=64,
max_depth=5,
random_state=1)
explained_model.fit(x_train, y_train)
masking_operation = ZeroMasking()
loss = binary_crossentropy
num_models = 5
explainer = CXPlain(explained_model,
model_builder,
masking_operation,
loss,
num_models=num_models)
file_names = [
CXPlain.get_config_file_name(),
CXPlain.get_explained_model_file_name(".pkl"),
CXPlain.get_loss_pkl_file_name(),
CXPlain.get_model_builder_pkl_file_name(),
CXPlain.get_masking_operation_pkl_file_name()
]
# Test with untrained explanation model.
for file_name in file_names:
tmp_dir = TestExplanationModel.make_at_tmp(file_name)
with self.assertRaises(ValueError):
explainer.save(tmp_dir, overwrite=False)
# Test with trained explanation model.
explainer.fit(x_train, y_train)
file_names = [
CXPlain.get_config_file_name(),
CXPlain.get_explained_model_file_name(".pkl"),
CXPlain.get_loss_pkl_file_name(),
CXPlain.get_model_builder_pkl_file_name(),
CXPlain.get_masking_operation_pkl_file_name()
] + [
CXPlain.get_prediction_model_h5_file_name(i)
for i in range(num_models)
]
for file_name in file_names:
tmp_dir = TestExplanationModel.make_at_tmp(file_name)
with self.assertRaises(ValueError):
explainer.save(tmp_dir, overwrite=False)
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 find_genes_CX(drug, model, meta, gdsc_expr, gdsc_dr, test_tcga_expr,
save_dir):
torch.manual_seed(SEED)
np.random.seed(SEED)
print('obtaining masked data...')
masked_data = get_masked_data_for_CXPlain(model, gdsc_expr)
print('obtained masked data...')
# get_masked_data_for_CXPlain(model, test_tcga_expr)
import tensorflow as tf
tf.compat.v1.disable_v2_behavior()
tf.keras.backend.clear_session()
tf.random.set_seed(SEED)
from tensorflow.python.keras.losses import mean_squared_error as loss
from cxplain import MLPModelBuilder, CXPlain
# from cxplain.backend.masking.zero_masking import FastZeroMasking
model_builder = MLPModelBuilder(num_layers=2,
num_units=512,
batch_size=8,
learning_rate=0.001)
# masking_operation = FastZeroMasking()
print(gdsc_expr.values.shape, gdsc_dr.values.shape)
print("Fitting CXPlain model")
explainer = CXPlain(model, model_builder, None, loss)
explainer.fit(gdsc_expr.values, gdsc_dr.values, masked_data=masked_data)
print("Attributing using CXPlain")
attr = explainer.explain(test_tcga_expr.values)
attr = pd.DataFrame(attr, index=test_tcga_expr.index, columns=dataset.hgnc)
borda = get_ranked_list(attr)
attr_mean = list(np.abs(attr).mean(axis=0).nlargest(200).index)
out = pd.DataFrame(columns=['borda', 'mean'])
out['borda'] = borda
out['mean'] = attr_mean
out.to_csv(save_dir + '/genes.csv', index=False)
if not os.path.exists(save_dir + '/explainer/'):
os.mkdir(save_dir + '/explainer/')
explainer.save(save_dir + '/explainer/')
def test_mnist_confidence_levels_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)
model_builder = MLPModelBuilder(num_layers=2,
num_units=64,
activation="relu",
p_dropout=0.2,
verbose=0,
batch_size=256,
learning_rate=0.001,
num_epochs=3,
early_stopping_patience=128)
masking_operation = ZeroMasking()
loss = categorical_crossentropy
confidence_levels = [0.0, 1.0, 1.01, -0.01]
for confidence_level in confidence_levels:
downsample_factor = (2, 2)
explainer = CXPlain(explained_model,
model_builder,
masking_operation,
loss,
num_models=2,
downsample_factors=downsample_factor,
flatten_for_explained_model=True)
explainer.fit(x_train, y_train)
with self.assertRaises(ValueError):
_ = explainer.predict(x_test,
confidence_level=confidence_level)