File size: 6,131 Bytes
738b9a7 355f3ac 6bf8d03 e031c18 0e46985 e031c18 0e46985 e031c18 bd04299 738b9a7 0e46985 e031c18 738b9a7 e031c18 70dc026 738b9a7 e031c18 70dc026 738b9a7 e031c18 738b9a7 e031c18 70dc026 e031c18 738b9a7 e031c18 738b9a7 |
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 |
#semantic_analysis.py
import streamlit as st
import spacy
import networkx as nx
import matplotlib.pyplot as plt
from collections import Counter
# Remove the global nlp model loading
# 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': 'Adposici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': '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': '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',
}
}
########################################################################################################################################
def extract_entities(doc):
entities = {
"Personas": [],
"Conceptos": [],
"Lugares": [],
"Fechas": []
}
for ent in doc.ents:
if ent.label_ == "PER":
entities["Personas"].append(ent.text)
elif ent.label_ in ["LOC", "GPE"]:
entities["Lugares"].append(ent.text)
elif ent.label_ == "DATE":
entities["Fechas"].append(ent.text)
else:
entities["Conceptos"].append(ent.text)
return entities
def visualize_context_graph(doc, lang):
G = nx.Graph()
entities = extract_entities(doc)
# Add nodes
for category, items in entities.items():
for item in items:
G.add_node(item, category=category)
# Add edges
for sent in doc.sents:
sent_entities = [ent.text for ent in sent.ents if ent.text in G.nodes()]
for i in range(len(sent_entities)):
for j in range(i+1, len(sent_entities)):
G.add_edge(sent_entities[i], sent_entities[j])
# Visualize
plt.figure(figsize=(20, 15))
pos = nx.spring_layout(G, k=0.5, iterations=50)
color_map = {"Personas": "lightblue", "Conceptos": "lightgreen", "Lugares": "lightcoral", "Fechas": "lightyellow"}
node_colors = [color_map[G.nodes[node]['category']] for node in G.nodes()]
nx.draw(G, pos, node_color=node_colors, with_labels=True, node_size=3000, font_size=8, font_weight='bold')
# Add a legend
legend_elements = [plt.Rectangle((0,0),1,1,fc=color, edgecolor='none') for color in color_map.values()]
plt.legend(legend_elements, color_map.keys(), loc='upper left', bbox_to_anchor=(1, 1))
plt.title("An谩lisis de Contexto" if lang == 'es' else "Context Analysis" if lang == 'en' else "Analyse de Contexte", fontsize=20)
plt.axis('off')
return plt
def visualize_semantic_relations(doc, lang):
# Esta funci贸n puede mantener la l贸gica que ya tienes en visualize_syntax_graph
# con algunas modificaciones para enfocarse en relaciones sem谩nticas
G, word_colors = create_syntax_graph(doc, lang)
plt.figure(figsize=(24, 18))
pos = nx.spring_layout(G, k=0.9, iterations=50)
node_colors = [data['color'] for _, data in G.nodes(data=True)]
node_sizes = [data['size'] for _, data in G.nodes(data=True)]
nx.draw(G, pos, with_labels=False, node_color=node_colors, node_size=node_sizes, arrows=True,
arrowsize=20, width=2, edge_color='gray')
nx.draw_networkx_labels(G, pos, {node: data['label'] for node, data in G.nodes(data=True)},
font_size=10, font_weight='bold')
edge_labels = nx.get_edge_attributes(G, 'label')
nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels, font_size=8)
plt.title("An谩lisis de Relaciones Sem谩nticas" if lang == 'es' else "Semantic Relations Analysis" if lang == 'en' else "Analyse des Relations S茅mantiques",
fontsize=20, fontweight='bold')
plt.axis('off')
legend_elements = [plt.Rectangle((0,0),1,1, facecolor=color, edgecolor='none',
label=f"{POS_TRANSLATIONS[lang][pos]} ({count_pos(doc)[pos]})")
for pos, color in POS_COLORS.items() if pos in set(nx.get_node_attributes(G, 'pos').values())]
plt.legend(handles=legend_elements, loc='center left', bbox_to_anchor=(1, 0.5), fontsize=12)
return plt
def perform_semantic_analysis(text, nlp, lang):
doc = nlp(text)
context_graph = visualize_context_graph(doc, lang)
relations_graph = visualize_semantic_relations(doc, lang)
return context_graph, relations_graph |