Update modules/text_analysis/semantic_analysis.py

modules/text_analysis/semantic_analysis.py

@@ -1,12 +1,67 @@
+#semantic_analysis.py
 import streamlit as st
 import spacy
 import networkx as nx
 import matplotlib.pyplot as plt
-from collections import Counter
+from collections import Counter, defaultdict
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 
-# ... (mantén las definiciones de POS_COLORS, POS_TRANSLATIONS, y ENTITY_LABELS como están)
+# Define colors for grammatical categories
+POS_COLORS = {
+    'ADJ': '#FFA07A', 'ADP': '#98FB98', 'ADV': '#87CEFA', 'AUX': '#DDA0DD',
+    'CCONJ': '#F0E68C', 'DET': '#FFB6C1', 'INTJ': '#FF6347', 'NOUN': '#90EE90',
+    'NUM': '#FAFAD2', 'PART': '#D3D3D3', 'PRON': '#FFA500', 'PROPN': '#20B2AA',
+    'SCONJ': '#DEB887', 'SYM': '#7B68EE', 'VERB': '#FF69B4', 'X': '#A9A9A9',
+}
+
+POS_TRANSLATIONS = {
+    'es': {
+        'ADJ': 'Adjetivo', 'ADP': 'Preposición', 'ADV': 'Adverbio', 'AUX': 'Auxiliar',
+        'CCONJ': 'Conjunción Coordinante', 'DET': 'Determinante', 'INTJ': 'Interjección',
+        'NOUN': 'Sustantivo', 'NUM': 'Número', 'PART': 'Partícula', 'PRON': 'Pronombre',
+        'PROPN': 'Nombre Propio', 'SCONJ': 'Conjunción Subordinante', 'SYM': 'Símbolo',
+        'VERB': 'Verbo', 'X': 'Otro',
+    },
+    'en': {
+        'ADJ': 'Adjective', 'ADP': 'Preposition', 'ADV': 'Adverb', 'AUX': 'Auxiliary',
+        'CCONJ': 'Coordinating Conjunction', 'DET': 'Determiner', 'INTJ': 'Interjection',
+        'NOUN': 'Noun', 'NUM': 'Number', 'PART': 'Particle', 'PRON': 'Pronoun',
+        'PROPN': 'Proper Noun', 'SCONJ': 'Subordinating Conjunction', 'SYM': 'Symbol',
+        'VERB': 'Verb', 'X': 'Other',
+    },
+    'fr': {
+        'ADJ': 'Adjectif', 'ADP': 'Préposition', 'ADV': 'Adverbe', 'AUX': 'Auxiliaire',
+        'CCONJ': 'Conjonction de Coordination', 'DET': 'Déterminant', 'INTJ': 'Interjection',
+        'NOUN': 'Nom', 'NUM': 'Nombre', 'PART': 'Particule', 'PRON': 'Pronom',
+        'PROPN': 'Nom Propre', 'SCONJ': 'Conjonction de Subordination', 'SYM': 'Symbole',
+        'VERB': 'Verbe', 'X': 'Autre',
+    }
+}
+
+ENTITY_LABELS = {
+    'es': {
+        "Personas": "lightblue",
+        "Lugares": "lightcoral",
+        "Inventos": "lightgreen",
+        "Fechas": "lightyellow",
+        "Conceptos": "lightpink"
+    },
+    'en': {
+        "People": "lightblue",
+        "Places": "lightcoral",
+        "Inventions": "lightgreen",
+        "Dates": "lightyellow",
+        "Concepts": "lightpink"
+    },
+    'fr': {
+        "Personnes": "lightblue",
+        "Lieux": "lightcoral",
+        "Inventions": "lightgreen",
+        "Dates": "lightyellow",
+        "Concepts": "lightpink"
+    }
+}
 
 def identify_key_concepts(doc):
     word_freq = Counter([token.lemma_.lower() for token in doc if token.pos_ in ['NOUN', 'VERB'] and not token.is_stop])