Update modules/text_analysis/semantic_analysis.py
Browse files
modules/text_analysis/semantic_analysis.py
CHANGED
|
@@ -63,9 +63,10 @@ ENTITY_LABELS = {
|
|
| 63 |
}
|
| 64 |
}
|
| 65 |
|
| 66 |
-
def identify_key_concepts(doc):
|
| 67 |
-
|
| 68 |
-
|
|
|
|
| 69 |
|
| 70 |
def create_concept_graph(text, concepts):
|
| 71 |
vectorizer = TfidfVectorizer()
|
|
|
|
| 63 |
}
|
| 64 |
}
|
| 65 |
|
| 66 |
+
def identify_key_concepts(doc, top_n=10):
|
| 67 |
+
# Identificar sustantivos, verbos y adjetivos más frecuentes
|
| 68 |
+
word_freq = Counter([token.lemma_.lower() for token in doc if token.pos_ in ['NOUN', 'VERB', 'ADJ'] and not token.is_stop])
|
| 69 |
+
return word_freq.most_common(top_n)
|
| 70 |
|
| 71 |
def create_concept_graph(text, concepts):
|
| 72 |
vectorizer = TfidfVectorizer()
|