tiger transform back online

tiger.py

@@ -130,8 +130,8 @@ def calibrate_predictions(predictions: np.array, num_mismatches: np.array, param
     return correction * predictions
 
 
-def prediction_transform(predictions: np.array, **params):
-    if len(params) == 0:
+def transform_predictions(predictions: np.array, params: dict = None):
+    if params is None:
         with open('transform_params.pkl', 'rb') as f:
             params = pickle.load(f)
 
@@ -179,7 +179,7 @@ def get_on_target_predictions(transcripts: pd.DataFrame, model: tf.keras.Model,
 
         # get predictions
         lfc_estimate = model.predict(model_inputs, batch_size=BATCH_SIZE_COMPUTE, verbose=False)
-        scores = prediction_transform(tf.squeeze(lfc_estimate).numpy())
+        scores = transform_predictions(tf.squeeze(lfc_estimate).numpy())
         predictions = pd.concat([predictions, pd.DataFrame({
             ID_COL: [index] * len(scores),
             TARGET_COL: target_seq,
@@ -307,7 +307,7 @@ def predict_off_target(off_targets: pd.DataFrame, model: tf.keras.Model):
         tf.reshape(one_hot_encode_sequence(off_targets[GUIDE_COL], add_context_padding=True), [len(off_targets), -1]),
         ], axis=-1)
     lfc_estimate = model.predict(model_inputs, batch_size=BATCH_SIZE_COMPUTE, verbose=False)
-    off_targets[SCORE_COL] = prediction_transform(tf.squeeze(lfc_estimate).numpy())
+    off_targets[SCORE_COL] = transform_predictions(tf.squeeze(lfc_estimate).numpy())
 
     return off_targets.reset_index(drop=True)