BDSS Tree generator fixed (thanks to Manolo Perez)

README.md

@@ -196,3 +196,4 @@ and 10, superspreading fraction between 0.05 and 0.20).
 The time related parameters (infectious and eventually incubation period for BDEI model) are in the same units as the 
 branches of input tree, here in years (9.78 years). The covered parameter space for time related parameters is large 
 due to internal rescaling of all input trees. It should apply to any tree.
+

phylodeep/model_load.py

@@ -2,11 +2,11 @@
 import pickle as pk
 import warnings
 
+import tensorflow as tf
+tf.get_logger().setLevel('ERROR')
+
 import numpy as np
-from tensorflow import keras
 
-warnings.filterwarnings('ignore')
-os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
 
 PRETRAINED_MODELS_DIR = os.path.join(os.path.abspath(os.path.dirname(__file__)), 'pretrained_models')
 PRETRAINED_PCA_DIR = os.path.join(os.path.abspath(os.path.dirname(__file__)), 'pca_a_priori')
@@ -36,7 +36,7 @@ def model_scale_load_ffnn(tree_size, model):
     # model_ffnn = keras.models.model_from_json(loaded_model)
     # model_ffnn.load_weights(os.path.join(PRETRAINED_MODELS_DIR, 'weights',
     #                                      '{}_{}_{}.h5'.format(model, tree_size, pred_method)))
-    model_ffnn = keras.models.load_model(
+    model_ffnn = tf.keras.models.load_model(
         os.path.join(PRETRAINED_MODELS_DIR, 'models', '{}_{}_{}.h5'.format(model, tree_size, pred_method)),
         compile=False)
 
@@ -56,7 +56,7 @@ def model_load_cnn(tree_size, model):
     # model_cnn = keras.models.model_from_json(loaded_model)
     # model_cnn.load_weights(os.path.join(PRETRAINED_MODELS_DIR, 'weights',
     #                                     '{}_{}_{}.h5'.format(model, tree_size, pred_method)))
-    model_cnn = keras.models.load_model(
+    model_cnn = tf.keras.models.load_model(
         os.path.join(PRETRAINED_MODELS_DIR, 'models', '{}_{}_{}.h5'.format(model, tree_size, pred_method)),
         compile=False)
 

simulators/bd_models/TreeGen_BDSS_refactored.py

@@ -165,7 +165,7 @@ def removal(removed_type):
         else:
             nb_which_leaf = np.random.randint(0, metrics['number_inf2_leaves'])
             which_leaf = leaves_dict['inf2_leaves'][nb_which_leaf]
-            leaves_dict['inf2_leaves'][nb_which_leaf]
+            del leaves_dict['inf2_leaves'][nb_which_leaf]
             metrics['number_inf2_leaves'] -= 1
 
         # which_leaf becomes a tip