fixing some bugs

textflow/IronityAnalyzer.py

@@ -14,7 +14,7 @@ class IronityAnalyzer(Analyzer):
         maxEmbedding: The number of max_position_embedings in the config.json of the model selected.
     """
 
-    def __init__(self, task = "text-classification",modelIronity = 'dtomas/roberta-base-bne-irony', allScores = True, maxEmbedding = 512):
+    def __init__(self, task = "text-classification",modelIronity = 'dtomas/roberta-base-bne-irony', allScores = True, maxEmbedding = 514):
         """
         Create an ironic analyzer.
 
@@ -28,8 +28,8 @@ class IronityAnalyzer(Analyzer):
             model = AutoModelForSequenceClassification.from_pretrained(modelIronity)
             model.config.id2label = {0: 'NI', 1: 'I'}
             model.config.label2id = {'NI': 0, 'I': 1}
-            tokenizer = AutoTokenizer.from_pretrained(modelIronity, model_max_length=512)
-            self.ironityClassifier = pipeline(task,model= model, tokenizer=tokenizer,return_all_scores=allScores)
+            tokenizer = AutoTokenizer.from_pretrained(modelIronity)
+            self.ironityClassifier = pipeline(task,model= model, tokenizer=tokenizer,return_all_scores=allScores, truncation=True)
         else:
             self.ironityClassifier = pipeline(task,model= modelIronity, return_all_scores=allScores)
         self.maxEmbeding = maxEmbedding

textflow/NERAnalyzer.py

@@ -78,7 +78,6 @@ class NERAnalyzer(Analyzer):
                 textner.append(doc[i].ent_type_)
             else:
                 textner.append(doc[i].text)
-        print(textner)
         self.textNER = " ".join(textner) 
         for ent in doc.ents:
             #Guardamos el diccionario obtenido para la categoria de la palabra (si este existe)

textflow/Sequence.py

@@ -199,10 +199,10 @@ class Sequence(ABC):
         ruta = level.split("/")
         children = [self.children]
         results=[]
-        for r in ruta:
+        for idx, r in enumerate(ruta):
             for child in children:
                 if r in child:
-                    if r == ruta[-1]:
+                    if r == ruta[-1] and idx == len(ruta)-1:
                         results.extend(child[r])
                     else:
                         children = [c.children for c in child[r]]
@@ -230,8 +230,8 @@ class Sequence(ABC):
         children = [self.children]
         metadata = [self.metadata]
         results=[]
-        for r in ruta:
-            if r == ruta[-1]:
+        for idx, r in enumerate(ruta):
+            if r == ruta[-1] and idx == len(ruta)-1:
                 for m in metadata:
                     if r in m:
                         results.append(m[r])