Integrate NCES in ontolearn-web service and fix dllearner binding script in examples

README.md

@@ -168,7 +168,52 @@ response = requests.get('http://0.0.0.0:8000/cel',
                               "model": "TDL"})
 print(response.json())
 ```
+NCES (another scalable learner). The following will first train NCES if the provided path `path_to_pretrained_nces` does not exist
+```python
+import json
+import requests
+with open(f"LPs/Mutagenesis/lps.json") as json_file:
+    learning_problems = json.load(json_file)["problems"]
+## This trains NCES before solving the provided learning problems. Expect poor performance for this number of epochs, and this training data size.
+## If GPU is available, set `num_of_training_learning_problems` t0 10_000 or more. Set `nces_train_epochs` to 300 or more, and increase `nces_batch_size`.
+for str_target_concept, examples in learning_problems.items():
+    response = requests.get('http://0.0.0.0:8000/cel',
+                            headers={'accept': 'application/json', 'Content-Type': 'application/json'},
+                            json={"pos": examples['positive_examples'],
+                                  "neg": examples['negative_examples'],
+                                  "model": "NCES",
+                                  "path_embeddings": "mutagenesis_embeddings/Keci_entity_embeddings.csv",
+                                  "path_to_pretrained_nces": None,
+                                  # if pretrained_nces exists, load weghts, otherwise train one and save it
+                                  "num_of_training_learning_problems": 100,
+                                  "nces_train_epochs": 5,
+                                  "nces_batch_size": 16
+                                  })
+    print(response.json())
+```
 
+Now this will use pretrained weights for NCES
+
+```python
+import json
+import requests
+with open(f"LPs/Mutagenesis/lps.json") as json_file:
+    learning_problems = json.load(json_file)["problems"]
+for str_target_concept, examples in learning_problems.items():
+    response = requests.get('http://0.0.0.0:8000/cel',
+                            headers={'accept': 'application/json', 'Content-Type': 'application/json'},
+                            json={"pos": examples['positive_examples'],
+                                  "neg": examples['negative_examples'],
+                                  "model": "NCES",
+                                  "path_embeddings": "./NCESData/mutagenesis/embeddings/ConEx_entity_embeddings.csv",
+                                  "path_to_pretrained_nces": "./NCESData/mutagenesis/trained_models/",
+                                  # if pretrained_nces exists, load weghts, otherwise train one and save it
+                                  "num_of_training_learning_problems": 100,
+                                  "nces_train_epochs": 5,
+                                  "nces_batch_size": 16
+                                  })
+    print(response.json())
+```
 
 </details>
 

examples/concept_learning_cv_evaluation.py

@@ -89,12 +89,14 @@ def dl_concept_learning(args):
               kwargs_classifier={"random_state": 1},
               max_runtime=args.max_runtime,
               verbose=0)
+
     nces = NCES(knowledge_base_path=args.kb,
                 quality_func=F1(),
                 path_of_embeddings=args.path_of_nces_embeddings,
-                pretrained_model_name=["LSTM", "GRU", "SetTransformer"],
+                learner_names=["LSTM", "GRU", "SetTransformer"],
                 num_predictions=100,
                 verbose=0)
+
     clip = CLIP(knowledge_base=kb,
                 refinement_operator=ModifiedCELOERefinement(kb),
                 quality_func=F1(),
@@ -260,7 +262,7 @@ def dl_concept_learning(args):
 
             start_time = time.time()
             # () Fit model training dataset
-            pred_nces = nces.fit(train_lp.pos, train_lp.neg).best_hypotheses(n=1)
+            pred_nces = nces.fit(train_lp).best_hypotheses(n=1)
             print("NCES ends..", end="\t")
             rt_nces = time.time() - start_time
 

examples/dl_learner.py

@@ -18,7 +18,12 @@
 Author: Caglar Demir
 """
 from ontolearn.binders import DLLearnerBinder
+from owlapy.iri import IRI
+from owlapy.owl_individual import OWLNamedIndividual
 import json
+
+from ontolearn.learning_problem import PosNegLPStandard
+
 # (1) Load learning problems
 with open('synthetic_problems.json') as json_file:
     settings = json.load(json_file)
@@ -36,9 +41,14 @@
     p = examples['positive_examples']
     n = examples['negative_examples']
 
-    best_pred_celoe = celoe.fit(pos=p, neg=n, max_runtime=1).best_hypothesis()
+    positives = {OWLNamedIndividual(IRI.create(i)) for i in p}
+    negatives = {OWLNamedIndividual(IRI.create(i)) for i in n}
+
+    lp = PosNegLPStandard(pos=positives, neg=positives)
+
+    best_pred_celoe = celoe.fit(lp, max_runtime=1).best_hypothesis()
     print(best_pred_celoe)
-    best_pred_ocel = ocel.fit(pos=p, neg=n, max_runtime=1).best_hypothesis()
+    best_pred_ocel = ocel.fit(lp, max_runtime=1).best_hypothesis()
     print(best_pred_ocel)
-    best_pred_eltl = eltl.fit(pos=p, neg=n, max_runtime=1).best_hypothesis()
+    best_pred_eltl = eltl.fit(lp, max_runtime=1).best_hypothesis()
     print(best_pred_eltl)