tf.gather(tf.constant(types), x)), y))
ds_test = tf.data.Dataset.from_tensor_slices((idx_test, y_label[idx_test]))
ds_test = ds_test.batch(len(idx_test), drop_remainder=False)
ds_test = ds_test.map(lambda x, y: (
(five_p_loader(x, ragged_output=True), three_p_loader(
x, ragged_output=True), ref_loader(x, ragged_output=True),
alt_loader(x, ragged_output=True), strand_loader(x, ragged_output=True),
tf.gather(tf.constant(types), x)), y))
histories = []
evaluations = []
weights = []
for i in range(3):
sequence_encoder = InstanceModels.VariantSequence(6, 4, 2, [16, 16, 8, 8])
sample_encoder = SampleModels.Type(shape=(), dim=len(np.unique(types)))
# mil = RaggedModels.MIL(instance_encoders=[sequence_encoder.model], sample_encoders=[sample_encoder.model], sample_layers=[64, ], output_dim=1, pooling='both', output_type='other', pooled_layers=[32, ])
mil = RaggedModels.MIL(instance_encoders=[sequence_encoder.model],
sample_encoders=[sample_encoder.model],
fusion='before',
output_dim=1,
pooling='both',
output_type='other',
pooled_layers=[
32,
])
losses = ['mse']
mil.model.compile(loss=losses,
metrics=['mse'],
optimizer=tf.keras.optimizers.Adam(
learning_rate=0.001, ))
##if using tcga cancer types
y_strat = np.argmax(samples['histology'], axis=-1)
##if using NCI-T labels
# label_counts = sample_df['NCI-T Label'].value_counts().to_dict()
# mask = sample_df['NCI-T Label'].map(lambda x: label_counts.get(x, 0) >= 36)
# y_label = y_label[mask]
# counts = counts[mask]
# labels = [i for i in sorted(label_counts.keys()) if label_counts[i] >= 36]
# y_strat = sample_df['NCI-T Label'][mask].map(lambda x: labels.index(x)).values
losses = [Losses.QuantileLoss()]
metrics = [Metrics.QuantileLoss()]
pass_encoder = InstanceModels.PassThrough(shape=(1, ))
type_encoder = SampleModels.Type(shape=(), dim=max(y_strat) + 1)
weights = pickle.load(
open(
cwd / 'figures' / 'tmb' / 'tcga' / 'MDA_409' / 'results' /
'run_naive_sample_tcga.pkl', 'rb'))
mil = RaggedModels.MIL(
sample_encoders=[pass_encoder.model, type_encoder.model],
output_dim=1,
mil_hidden=(64, 32, 16),
output_type='quantiles',
regularization=0,
mode='none')
##test eval