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 find_genes_CX(drug, model, gdsc_expr, gdsc_dr, test_tcga_expr):
print('obtaining masked data...')
# masked_data, list_of_baselines = get_masked_data_for_CXPlain(model, gdsc_expr, pathway_matrix)
masked_data, list_of_baselines = get_masked_data_for_CXPlain(model, gdsc_expr, pathway_matrix, subtract_mean=True)
lb = np.concatenate(list_of_baselines).reshape(len(gdsc_expr), -1)
lb = pd.DataFrame(lb, index=gdsc_expr.index, columns=pathway_names)
lb.to_csv(res_dir + drug + '/baselines.csv')
# print(lb.shape)
# exit()
print('obtained masked data...')
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 CXPlain
from cxplain.backend.model_builders.custom_mlp import CustomMLPModelBuilder
# from cxplain.backend.masking.zero_masking import FastZeroMasking
n_pathways = len(pathway_names)
model_builder = CustomMLPModelBuilder(num_layers=2, num_units=512, batch_size=16, learning_rate=0.001, n_feature_groups=n_pathways)
# masking_operation = FastZeroMasking()
print(gdsc_expr.values.shape, gdsc_dr.values.shape)
print("Fitting CXPlain model")
explainer = CXPlain(model, model_builder, None, loss, num_models=3)
explainer.fit(gdsc_expr.values, gdsc_dr.values, masked_data=masked_data)
print("Attributing using CXPlain")
attr,_ = explainer.explain_groups(test_tcga_expr.values)
print('attr')
attr = pd.DataFrame(attr, index=test_tcga_expr.index, columns=pathway_names)
borda = get_ranked_list(attr, k=n_pathways)
attr_mean = list(np.abs(attr).mean(axis=0).nlargest(n_pathways).index)
out = pd.DataFrame(columns=['borda', 'mean'])
out['borda'] = borda
out['mean'] = attr_mean
out.to_csv(res_dir + drug + '/pathways.csv', index=False)
if not os.path.exists(res_dir + drug + '/explainer/'):
os.mkdir(res_dir + drug + '/explainer/')
explainer.save(res_dir + drug + '/explainer/', custom_model_saver=None)
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_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 find_genes_CX(drug, model, gdsc_expr, gdsc_dr, test_tcga_expr):
print('obtaining precalculating omegas...')
loss = torch.nn.MSELoss(reduction='none')
# idx = gdsc_expr.index[:10]
# gdsc_expr = gdsc_expr.loc[idx]
# gdsc_dr = gdsc_dr[idx]
# omegas, lb = precalculate_omegas(model, gdsc_expr, gdsc_dr, pathway_matrix, loss)
# omegas, lb = precalculate_omegas_scaled(model, gdsc_expr, gdsc_dr, pathway_matrix, loss)
# omegas, lb = precalculate_omegas(model, gdsc_expr, gdsc_dr, pathway_matrix, loss,mode='scaled-difference')
# omegas, lb = precalculate_omegas(model, gdsc_expr, gdsc_dr, pathway_matrix, loss, mode='delta-of-delta')
omegas, lb = precalculate_omegas(model,
gdsc_expr,
gdsc_dr,
pathway_matrix,
loss,
mode='delta-scaled')
if lb is not None:
lb = pd.DataFrame(lb, index=gdsc_expr.index, columns=pathway_names)
lb.to_csv(res_dir + drug + '/baselines.csv')
print('obtained masked data...')
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 CXPlain
from cxplain.backend.model_builders.custom_mlp_precalc import CustomMLPModelBuilder
# from cxplain.backend.masking.zero_masking import FastZeroMasking
n_pathways = len(pathway_names)
model_builder = CustomMLPModelBuilder(num_layers=2,
num_units=512,
batch_size=16,
learning_rate=0.001,
n_feature_groups=n_pathways)
# masking_operation = FastZeroMasking()
print(gdsc_expr.values.shape, gdsc_dr.values.shape)
print("Fitting CXPlain model")
explainer = CXPlain(model, model_builder, None, loss, num_models=3)
explainer.fit_precalc(gdsc_expr.values, gdsc_dr.values, omega=omegas)
print("Attributing using CXPlain")
attr, _ = explainer.explain_groups(test_tcga_expr.values)
print('attr')
attr = pd.DataFrame(attr,
index=test_tcga_expr.index,
columns=pathway_names)
borda = get_ranked_list(attr, k=n_pathways)
attr_mean = list(np.abs(attr).mean(axis=0).nlargest(n_pathways).index)
out = pd.DataFrame(columns=['borda', 'mean'])
out['borda'] = borda
out['mean'] = attr_mean
out.to_csv(res_dir + drug + '/pathways.csv', index=False)
if not os.path.exists(res_dir + drug + '/explainer/'):
os.mkdir(res_dir + drug + '/explainer/')
explainer.save(res_dir + drug + '/explainer/', custom_model_saver=None)