File size: 4,624 Bytes
0707975 793b83e 0707975 793b83e 0707975 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 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
#semantic_analysis.py
import streamlit as st
import spacy
import networkx as nx
import matplotlib.pyplot as plt
from collections import Counter, defaultdict
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
# 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': 'Preposici贸n', 'ADV': 'Adverbio', 'AUX': 'Auxiliar',
'CCONJ': 'Conjunci贸n Coordinante', 'DET': 'Determinante', 'INTJ': 'Interjecci贸n',
'NOUN': 'Sustantivo', 'NUM': 'N煤mero', 'PART': 'Part铆cula', 'PRON': 'Pronombre',
'PROPN': 'Nombre Propio', 'SCONJ': 'Conjunci贸n Subordinante', 'SYM': 'S铆mbolo',
'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': 'Pr茅position', 'ADV': 'Adverbe', 'AUX': 'Auxiliaire',
'CCONJ': 'Conjonction de Coordination', 'DET': 'D茅terminant', '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])
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 Cl茅s"
}
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'] |