File size: 7,874 Bytes
738b9a7
355f3ac
6bf8d03
e031c18
 
 
 
0e46985
e031c18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0e46985
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e031c18
bd04299
738b9a7
eece828
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6a23e42
 
 
7dcf2f9
 
 
 
 
 
 
eece828
 
 
 
738b9a7
7dcf2f9
eece828
738b9a7
eece828
738b9a7
eece828
738b9a7
eece828
 
738b9a7
 
eece828
738b9a7
 
eece828
 
7dcf2f9
738b9a7
 
 
 
 
 
 
90f97d8
7dcf2f9
 
 
738b9a7
 
 
 
 
 
 
eece828
 
738b9a7
 
7dcf2f9
 
 
738b9a7
90f97d8
738b9a7
 
 
 
eece828
738b9a7
90f97d8
 
 
 
 
 
 
 
 
 
 
e031c18
738b9a7
 
e031c18
90f97d8
e031c18
90f97d8
 
e031c18
 
 
 
eece828
 
 
 
 
 
e031c18
 
90f97d8
 
 
738b9a7
e031c18
 
 
eece828
 
738b9a7
 
eece828
 
 
 
 
 
738b9a7
 
7dcf2f9
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
#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',
    }
}
########################################################################################################################################

# 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')

import spacy
import networkx as nx
import matplotlib.pyplot as plt
from collections import Counter

# Mant茅n las definiciones de POS_COLORS y POS_TRANSLATIONS que ya tienes

#############################################################################################################################
def extract_entities(doc, lang):
    entities = {label: [] for label in ENTITY_LABELS[lang].keys()}
    
    for ent in doc.ents:
        if ent.label_ == "PERSON":
            entities[list(ENTITY_LABELS[lang].keys())[0]].append(ent.text)
        elif ent.label_ in ["LOC", "GPE"]:
            entities[list(ENTITY_LABELS[lang].keys())[2]].append(ent.text)
        elif ent.label_ == "DATE":
            entities[list(ENTITY_LABELS[lang].keys())[3]].append(ent.text)
        else:
            entities[list(ENTITY_LABELS[lang].keys())[1]].append(ent.text)
    
    return entities

#####################################################################################################################
def visualize_context_graph(doc, lang):
    G = nx.Graph()
    entities = extract_entities(doc, lang)
    color_map = ENTITY_LABELS[lang]

    # 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 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].text, sent_entities[j].text)

    # Visualize
    plt.figure(figsize=(20, 15))
    pos = nx.spring_layout(G, k=0.5, iterations=50)

    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=5000, 
            font_size=12, font_weight='bold')

    # Add a legend
    legend_elements = [plt.Rectangle((0,0),1,1,fc=color, edgecolor='none', label=category) 
                       for category, color in color_map.items()]
    plt.legend(handles=legend_elements, loc='upper left', bbox_to_anchor=(1, 1))

    plt.title("An谩lisis del Contexto" if lang == 'es' else "Context Analysis" if lang == 'en' else "Analyse du Contexte", fontsize=20)
    plt.axis('off')

    return plt

############################################################################################################################################
def visualize_semantic_relations(doc, lang):
    G = nx.Graph()
    word_freq = Counter(token.text.lower() for token in doc if token.pos_ not in ['PUNCT', 'SPACE'])
    top_words = [word for word, _ in word_freq.most_common(20)]  # Top 20 most frequent words

    for token in doc:
        if token.text.lower() in top_words:
            G.add_node(token.text, pos=token.pos_)

    for token in doc:
        if token.text.lower() in top_words and token.head.text.lower() in top_words:
            G.add_edge(token.text, token.head.text, label=token.dep_)

    plt.figure(figsize=(24, 18))
    pos = nx.spring_layout(G, k=0.9, 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, 
            font_size=10, font_weight='bold', arrows=True, arrowsize=20, width=2, edge_color='gray')

    edge_labels = nx.get_edge_attributes(G, 'label')
    nx.draw_networkx_edge_labels(G, pos, edge_labels=edge_labels, font_size=8)

    title = {
        'es': "Relaciones Sem谩nticas Relevantes",
        'en': "Relevant Semantic Relations",
        'fr': "Relations S茅mantiques Pertinentes"
    }
    plt.title(title[lang], fontsize=20, fontweight='bold')
    plt.axis('off')

    legend_elements = [plt.Rectangle((0,0),1,1, facecolor=POS_COLORS.get(pos, '#CCCCCC'), edgecolor='none', 
                       label=f"{POS_TRANSLATIONS[lang].get(pos, pos)}")
                       for 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)
    
    # Imprimir entidades para depuraci贸n
    print(f"Entidades encontradas ({lang}):")
    for ent in doc.ents:
        print(f"{ent.text} - {ent.label_}")
    
    context_graph = visualize_context_graph(doc, lang)
    relations_graph = visualize_semantic_relations(doc, lang)
    return context_graph, relations_graph