File size: 2,486 Bytes
793b83e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
import streamlit as st
import spacy
import networkx as nx
import matplotlib.pyplot as plt
from collections import Counter
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)
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])
return word_freq.most_common(10) # Top 10 conceptos clave
def create_concept_graph(text, concepts):
vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform([text])
concept_vectors = vectorizer.transform([c[0] for c in concepts])
similarity_matrix = cosine_similarity(concept_vectors, concept_vectors)
G = nx.Graph()
for i, (concept, weight) in enumerate(concepts):
G.add_node(concept, weight=weight)
for j in range(i+1, len(concepts)):
if similarity_matrix[i][j] > 0.1:
G.add_edge(concept, concepts[j][0], weight=similarity_matrix[i][j])
return G
def visualize_concept_graph(G, lang):
fig, ax = plt.subplots(figsize=(15, 10))
pos = nx.spring_layout(G, k=0.5, iterations=50)
node_sizes = [G.nodes[node]['weight'] * 100 for node in G.nodes()]
nx.draw_networkx_nodes(G, pos, node_size=node_sizes, node_color='lightblue', alpha=0.8, ax=ax)
nx.draw_networkx_labels(G, pos, font_size=10, font_weight="bold", ax=ax)
nx.draw_networkx_edges(G, pos, width=1, alpha=0.5, ax=ax)
edge_labels = nx.get_edge_attributes(G, 'weight')
nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels, font_size=8, ax=ax)
title = {
'es': "Relaciones entre Conceptos Clave",
'en': "Key Concept Relations",
'fr': "Relations entre Concepts Clés"
}
ax.set_title(title[lang], fontsize=16)
ax.axis('off')
plt.tight_layout()
return fig
def perform_semantic_analysis(text, nlp, lang):
doc = nlp(text)
# Identificar conceptos clave
key_concepts = identify_key_concepts(doc)
# Crear y visualizar grafo de conceptos
concept_graph = create_concept_graph(text, key_concepts)
relations_graph = visualize_concept_graph(concept_graph, lang)
return {
'key_concepts': key_concepts,
'relations_graph': relations_graph
}
__all__ = ['perform_semantic_analysis', 'ENTITY_LABELS', 'POS_TRANSLATIONS'] |