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, test_tcga_expr):
tf.keras.backend.clear_session()
attr_ind = []
for seed in range(1, 11):
exp = CXPlain.load('gene_finding/results/CX_ind1/%s/seed%d/explainer' %
(drug, seed),
relpath=True)
attr = exp.explain(test_tcga_expr.values)
attr = pd.DataFrame(attr,
index=test_tcga_expr.index,
columns=dataset.hgnc)
attr_ind.append(attr)
all_attr = pd.DataFrame(columns=['seed', 'sample'] + list(dataset.hgnc))
i = 0
for sample in attr_ind[0].index:
for seed in range(10):
all_attr.loc[i] = [seed, sample] + list(attr_ind[seed].loc[sample])
i += 1
print('boat')
boat = borda_of_all_tuples(all_attr)
print('seed then sample')
seed_then_sample = sample_borda_of_seed_bordas(all_attr,
test_tcga_expr.index)
print('sample then seed')
sample_then_seed = seed_borda_of_sample_bordas(all_attr, range(10))
return boat, seed_then_sample, sample_then_seed
# _, _, _, test_tcga_expr = dataset.filter_and_normalize_data(drug)
# exp = CXPlain.load('gene_finding/results/%s/%s/explainer'%(folder, drug), custom_model_loader=None, relpath=True)
# attr,_ = exp.explain(test_tcga_expr.values)
# attr = pd.DataFrame(attr, index=test_tcga_expr.index, columns=dataset.genes)
# attr_dict[drug]=attr
attr_dict = {}
conf_dict = {}
for i, drug in enumerate(drugs):
print(drug)
_, _, _, test_tcga_expr = dataset.filter_and_normalize_data(drug)
attr_all = np.zeros((len(test_tcga_expr.index), len(dataset.genes)))
for seed in range(1, 11):
exp = CXPlain.load('gene_finding/results/%s/%s/seed%d/explainer'%(folder, drug, seed), custom_model_loader=None, relpath=True)
attr = exp.explain(test_tcga_expr.values)
attr_all += attr
attr = pd.DataFrame(attr_all/10.0, index=test_tcga_expr.index, columns=dataset.genes)
attr_dict[drug]=attr
fig, axes = plt.subplots(7, 2, figsize=(14, 35))
writer_a = pd.ExcelWriter('gene_finding/results/%s/top_genes_mean_of_means_aggregation.xlsx'%folder, engine='xlsxwriter')
conv = pd.DataFrame(index=dataset.genes, columns=['hgnc'])
conv['hgnc'] = dataset.hgnc
for i, drug in enumerate(drugs):