File size: 9,007 Bytes
726d44a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 |
#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 defaultdict
# Define colors for grammatical categories
POS_COLORS = {
'ADJ': '#FFA07A', # Light Salmon
'ADP': '#98FB98', # Pale Green
'ADV': '#87CEFA', # Light Sky Blue
'AUX': '#DDA0DD', # Plum
'CCONJ': '#F0E68C', # Khaki
'DET': '#FFB6C1', # Light Pink
'INTJ': '#FF6347', # Tomato
'NOUN': '#90EE90', # Light Green
'NUM': '#FAFAD2', # Light Goldenrod Yellow
'PART': '#D3D3D3', # Light Gray
'PRON': '#FFA500', # Orange
'PROPN': '#20B2AA', # Light Sea Green
'SCONJ': '#DEB887', # Burlywood
'SYM': '#7B68EE', # Medium Slate Blue
'VERB': '#FF69B4', # Hot Pink
'X': '#A9A9A9', # Dark Gray
}
POS_TRANSLATIONS = {
'es': {
'ADJ': 'Adjetivo',
'ADP': 'Adposición',
'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': 'Adposition',
'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': 'Adposition',
'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',
}
}
########################################################################################################################################
# Definimos las etiquetas y colores para cada idioma
ENTITY_LABELS = {
'es': {
"Personas": "lightblue",
"Conceptos": "lightgreen",
"Lugares": "lightcoral",
"Fechas": "lightyellow"
},
'en': {
"People": "lightblue",
"Concepts": "lightgreen",
"Places": "lightcoral",
"Dates": "lightyellow"
},
'fr': {
"Personnes": "lightblue",
"Concepts": "lightgreen",
"Lieux": "lightcoral",
"Dates": "lightyellow"
}
}
#########################################################################################################
def count_pos(doc):
return Counter(token.pos_ for token in doc if token.pos_ != 'PUNCT')
#####################################################################################################################
def create_semantic_graph(doc, lang):
G = nx.Graph()
word_freq = defaultdict(int)
lemma_to_word = {}
lemma_to_pos = {}
# Count frequencies of lemmas and map lemmas to their most common word form and POS
for token in doc:
if token.pos_ in ['NOUN', 'VERB']:
lemma = token.lemma_.lower()
word_freq[lemma] += 1
if lemma not in lemma_to_word or token.text.lower() == lemma:
lemma_to_word[lemma] = token.text
lemma_to_pos[lemma] = token.pos_
# Get top 20 most frequent lemmas
top_lemmas = [lemma for lemma, _ in sorted(word_freq.items(), key=lambda x: x[1], reverse=True)[:20]]
# Add nodes
for lemma in top_lemmas:
word = lemma_to_word[lemma]
G.add_node(word, pos=lemma_to_pos[lemma])
# Add edges
for token in doc:
if token.lemma_.lower() in top_lemmas:
if token.head.lemma_.lower() in top_lemmas:
source = lemma_to_word[token.lemma_.lower()]
target = lemma_to_word[token.head.lemma_.lower()]
if source != target: # Avoid self-loops
G.add_edge(source, target, label=token.dep_)
return G, word_freq
############################################################################################################################################
def visualize_semantic_relations(doc, lang):
G = nx.Graph()
word_freq = defaultdict(int)
lemma_to_word = {}
lemma_to_pos = {}
# Count frequencies of lemmas and map lemmas to their most common word form and POS
for token in doc:
if token.pos_ in ['NOUN', 'VERB']:
lemma = token.lemma_.lower()
word_freq[lemma] += 1
if lemma not in lemma_to_word or token.text.lower() == lemma:
lemma_to_word[lemma] = token.text
lemma_to_pos[lemma] = token.pos_
# Get top 20 most frequent lemmas
top_lemmas = [lemma for lemma, _ in sorted(word_freq.items(), key=lambda x: x[1], reverse=True)[:20]]
# Add nodes
for lemma in top_lemmas:
word = lemma_to_word[lemma]
G.add_node(word, pos=lemma_to_pos[lemma])
# Add edges
for token in doc:
if token.lemma_.lower() in top_lemmas:
if token.head.lemma_.lower() in top_lemmas:
source = lemma_to_word[token.lemma_.lower()]
target = lemma_to_word[token.head.lemma_.lower()]
if source != target: # Avoid self-loops
G.add_edge(source, target, label=token.dep_)
fig, ax = plt.subplots(figsize=(36, 27))
pos = nx.spring_layout(G, k=0.7, iterations=50)
node_colors = [POS_COLORS.get(G.nodes[node]['pos'], '#CCCCCC') for node in G.nodes()]
nx.draw(G, pos, node_color=node_colors, with_labels=True,
node_size=10000,
font_size=16,
font_weight='bold',
arrows=True,
arrowsize=30,
width=3,
edge_color='gray',
ax=ax)
edge_labels = nx.get_edge_attributes(G, 'label')
nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels, font_size=14, ax=ax)
title = {
'es': "Relaciones Semánticas Relevantes",
'en': "Relevant Semantic Relations",
'fr': "Relations Sémantiques Pertinentes"
}
ax.set_title(title[lang], fontsize=24, fontweight='bold')
ax.axis('off')
legend_elements = [plt.Rectangle((0,0),1,1,fc=POS_COLORS.get(pos, '#CCCCCC'), edgecolor='none',
label=f"{POS_TRANSLATIONS[lang].get(pos, pos)}")
for pos in ['NOUN', 'VERB']]
ax.legend(handles=legend_elements, loc='center left', bbox_to_anchor=(1, 0.5), fontsize=16)
return fig
############################################################################################################################################
def identify_and_contextualize_entities(doc, lang):
entities = []
for ent in doc.ents:
# Obtener el contexto (3 palabras antes y después de la entidad)
start = max(0, ent.start - 3)
end = min(len(doc), ent.end + 3)
context = doc[start:end].text
entities.append({
'text': ent.text,
'label': ent.label_,
'start': ent.start,
'end': ent.end,
'context': context
})
# Identificar conceptos clave (usando sustantivos y verbos más frecuentes)
word_freq = Counter([token.lemma_.lower() for token in doc if token.pos_ in ['NOUN', 'VERB'] and not token.is_stop])
key_concepts = word_freq.most_common(10) # Top 10 conceptos clave
return entities, key_concepts
############################################################################################################################################
def perform_semantic_analysis(text, nlp, lang):
doc = nlp(text)
# Identificar entidades y conceptos clave
entities, key_concepts = identify_and_contextualize_entities(doc, lang)
# Visualizar relaciones semánticas
relations_graph = visualize_semantic_relations(doc, lang)
# Imprimir entidades para depuración
print(f"Entidades encontradas ({lang}):")
for ent in doc.ents:
print(f"{ent.text} - {ent.label_}")
relations_graph = visualize_semantic_relations(doc, lang)
return {
'entities': entities,
'key_concepts': key_concepts,
'relations_graph': relations_graph
}
__all__ = ['visualize_semantic_relations', 'create_semantic_graph', 'POS_COLORS', 'POS_TRANSLATIONS', 'identify_and_contextualize_entities']
|