modules/text_analysis/semantic_analysis.py

#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': 'Preposición', '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': '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': 'Préposition', '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',
    }
}

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, top_n=10):
    # Identificar sustantivos, verbos y adjetivos más frecuentes
    word_freq = Counter([token.lemma_.lower() for token in doc if token.pos_ in ['NOUN', 'VERB', 'ADJ'] and not token.is_stop])
    return word_freq.most_common(top_n)

def create_concept_graph(doc, key_concepts):
    G = nx.Graph()
    
    # Añadir nodos
    for concept, freq in key_concepts:
        G.add_node(concept, weight=freq)
    
    # Añadir aristas basadas en la co-ocurrencia en oraciones
    for sent in doc.sents:
        sent_concepts = [token.lemma_.lower() for token in sent if token.lemma_.lower() in dict(key_concepts)]
        for i, concept1 in enumerate(sent_concepts):
            for concept2 in sent_concepts[i+1:]:
                if G.has_edge(concept1, concept2):
                    G[concept1][concept2]['weight'] += 1
                else:
                    G.add_edge(concept1, concept2, weight=1)
    
    return G

def visualize_concept_graph(G, lang):
    fig, ax = plt.subplots(figsize=(12, 8))
    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)
    
    edge_weights = [G[u][v]['weight'] for u, v in G.edges()]
    nx.draw_networkx_edges(G, pos, width=edge_weights, alpha=0.5, 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(doc, 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']