|
|
|
|
| import streamlit as st
|
| import matplotlib.pyplot as plt
|
| import networkx as nx
|
| import seaborn as sns
|
| from collections import Counter
|
| from itertools import combinations
|
| import numpy as np
|
| import matplotlib.patches as patches
|
| import logging
|
|
|
|
|
|
|
| logging.basicConfig(
|
| level=logging.INFO,
|
| format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
|
| handlers=[
|
| logging.StreamHandler(),
|
| logging.FileHandler('app.log')
|
| ]
|
| )
|
|
|
|
|
| logger = logging.getLogger(__name__)
|
|
|
|
|
|
|
| def correlate_metrics(scores):
|
| """
|
| Ajusta los scores para mantener correlaciones l贸gicas entre m茅tricas.
|
|
|
| Args:
|
| scores: dict con scores iniciales de vocabulario, estructura, cohesi贸n y claridad
|
|
|
| Returns:
|
| dict con scores ajustados
|
| """
|
| try:
|
|
|
|
|
| min_cohesion = scores['structure']['normalized_score'] * 0.7
|
| if scores['cohesion']['normalized_score'] < min_cohesion:
|
| scores['cohesion']['normalized_score'] = min_cohesion
|
|
|
|
|
|
|
| vocab_influence = scores['vocabulary']['normalized_score'] * 0.6
|
| scores['cohesion']['normalized_score'] = max(
|
| scores['cohesion']['normalized_score'],
|
| vocab_influence
|
| )
|
|
|
|
|
|
|
| max_clarity = scores['cohesion']['normalized_score'] * 1.2
|
| if scores['clarity']['normalized_score'] > max_clarity:
|
| scores['clarity']['normalized_score'] = max_clarity
|
|
|
|
|
|
|
| struct_max_clarity = scores['structure']['normalized_score'] * 1.1
|
| scores['clarity']['normalized_score'] = min(
|
| scores['clarity']['normalized_score'],
|
| struct_max_clarity
|
| )
|
|
|
|
|
| for metric in scores:
|
| scores[metric]['normalized_score'] = max(0.0, min(1.0, scores[metric]['normalized_score']))
|
|
|
| return scores
|
|
|
| except Exception as e:
|
| logger.error(f"Error en correlate_metrics: {str(e)}")
|
| return scores
|
|
|
|
|
|
|
| def analyze_text_dimensions(doc):
|
| """
|
| Analiza las dimensiones principales del texto manteniendo correlaciones l贸gicas.
|
| """
|
| try:
|
|
|
| vocab_score, vocab_details = analyze_vocabulary_diversity(doc)
|
| struct_score = analyze_structure(doc)
|
| cohesion_score = analyze_cohesion(doc)
|
| clarity_score, clarity_details = analyze_clarity(doc)
|
|
|
|
|
| scores = {
|
| 'vocabulary': {
|
| 'normalized_score': vocab_score,
|
| 'details': vocab_details
|
| },
|
| 'structure': {
|
| 'normalized_score': struct_score,
|
| 'details': None
|
| },
|
| 'cohesion': {
|
| 'normalized_score': cohesion_score,
|
| 'details': None
|
| },
|
| 'clarity': {
|
| 'normalized_score': clarity_score,
|
| 'details': clarity_details
|
| }
|
| }
|
|
|
|
|
| adjusted_scores = correlate_metrics(scores)
|
|
|
|
|
| logger.info(f"""
|
| Scores originales vs ajustados:
|
| Vocabulario: {vocab_score:.2f} -> {adjusted_scores['vocabulary']['normalized_score']:.2f}
|
| Estructura: {struct_score:.2f} -> {adjusted_scores['structure']['normalized_score']:.2f}
|
| Cohesi贸n: {cohesion_score:.2f} -> {adjusted_scores['cohesion']['normalized_score']:.2f}
|
| Claridad: {clarity_score:.2f} -> {adjusted_scores['clarity']['normalized_score']:.2f}
|
| """)
|
|
|
| return adjusted_scores
|
|
|
| except Exception as e:
|
| logger.error(f"Error en analyze_text_dimensions: {str(e)}")
|
| return {
|
| 'vocabulary': {'normalized_score': 0.0, 'details': {}},
|
| 'structure': {'normalized_score': 0.0, 'details': {}},
|
| 'cohesion': {'normalized_score': 0.0, 'details': {}},
|
| 'clarity': {'normalized_score': 0.0, 'details': {}}
|
| }
|
|
|
|
|
|
|
|
|
|
|
| def analyze_clarity(doc):
|
| """
|
| Analiza la claridad del texto considerando m煤ltiples factores.
|
| """
|
| try:
|
| sentences = list(doc.sents)
|
| if not sentences:
|
| return 0.0, {}
|
|
|
|
|
| sentence_lengths = [len(sent) for sent in sentences]
|
| avg_length = sum(sentence_lengths) / len(sentences)
|
|
|
|
|
| length_score = normalize_score(
|
| value=avg_length,
|
| metric_type='clarity',
|
| optimal_length=20,
|
| min_threshold=0.60,
|
| target_threshold=0.75
|
| )
|
|
|
|
|
| connector_count = 0
|
| connector_weights = {
|
| 'CCONJ': 1.0,
|
| 'SCONJ': 1.2,
|
| 'ADV': 0.8
|
| }
|
|
|
| for token in doc:
|
| if token.pos_ in connector_weights and token.dep_ in ['cc', 'mark', 'advmod']:
|
| connector_count += connector_weights[token.pos_]
|
|
|
|
|
| connectors_per_sentence = connector_count / len(sentences) if sentences else 0
|
| connector_score = normalize_score(
|
| value=connectors_per_sentence,
|
| metric_type='clarity',
|
| optimal_connections=1.5,
|
| min_threshold=0.60,
|
| target_threshold=0.75
|
| )
|
|
|
|
|
| clause_count = 0
|
| for sent in sentences:
|
| verbs = [token for token in sent if token.pos_ == 'VERB']
|
| clause_count += len(verbs)
|
|
|
| complexity_raw = clause_count / len(sentences) if sentences else 0
|
| complexity_score = normalize_score(
|
| value=complexity_raw,
|
| metric_type='clarity',
|
| optimal_depth=2.0,
|
| min_threshold=0.60,
|
| target_threshold=0.75
|
| )
|
|
|
|
|
| content_words = len([token for token in doc if token.pos_ in ['NOUN', 'VERB', 'ADJ', 'ADV']])
|
| total_words = len([token for token in doc if token.is_alpha])
|
| density = content_words / total_words if total_words > 0 else 0
|
|
|
| density_score = normalize_score(
|
| value=density,
|
| metric_type='clarity',
|
| optimal_connections=0.6,
|
| min_threshold=0.60,
|
| target_threshold=0.75
|
| )
|
|
|
|
|
| weights = {
|
| 'length': 0.3,
|
| 'connectors': 0.3,
|
| 'complexity': 0.2,
|
| 'density': 0.2
|
| }
|
|
|
| clarity_score = (
|
| weights['length'] * length_score +
|
| weights['connectors'] * connector_score +
|
| weights['complexity'] * complexity_score +
|
| weights['density'] * density_score
|
| )
|
|
|
| details = {
|
| 'length_score': length_score,
|
| 'connector_score': connector_score,
|
| 'complexity_score': complexity_score,
|
| 'density_score': density_score,
|
| 'avg_sentence_length': avg_length,
|
| 'connectors_per_sentence': connectors_per_sentence,
|
| 'density': density
|
| }
|
|
|
|
|
| logger.info(f"""
|
| Scores de Claridad:
|
| - Longitud: {length_score:.2f} (avg={avg_length:.1f} palabras)
|
| - Conectores: {connector_score:.2f} (avg={connectors_per_sentence:.1f} por oraci贸n)
|
| - Complejidad: {complexity_score:.2f} (avg={complexity_raw:.1f} cl谩usulas)
|
| - Densidad: {density_score:.2f} ({density*100:.1f}% palabras de contenido)
|
| - Score Final: {clarity_score:.2f}
|
| """)
|
|
|
| return clarity_score, details
|
|
|
| except Exception as e:
|
| logger.error(f"Error en analyze_clarity: {str(e)}")
|
| return 0.0, {}
|
|
|
|
|
| def analyze_vocabulary_diversity(doc):
|
| """An谩lisis mejorado de la diversidad y calidad del vocabulario"""
|
| try:
|
|
|
| unique_lemmas = {token.lemma_ for token in doc if token.is_alpha}
|
| total_words = len([token for token in doc if token.is_alpha])
|
| basic_diversity = len(unique_lemmas) / total_words if total_words > 0 else 0
|
|
|
|
|
| academic_words = 0
|
| narrative_words = 0
|
| technical_terms = 0
|
|
|
|
|
| for token in doc:
|
| if token.is_alpha:
|
|
|
| if token.pos_ in ['NOUN', 'VERB', 'ADJ']:
|
| if any(parent.pos_ == 'NOUN' for parent in token.ancestors):
|
| technical_terms += 1
|
|
|
| if token.pos_ in ['VERB', 'ADV'] and token.dep_ in ['ROOT', 'advcl']:
|
| narrative_words += 1
|
|
|
|
|
| avg_sentence_length = sum(len(sent) for sent in doc.sents) / len(list(doc.sents))
|
|
|
|
|
| weights = {
|
| 'diversity': 0.3,
|
| 'technical': 0.3,
|
| 'narrative': 0.2,
|
| 'complexity': 0.2
|
| }
|
|
|
| scores = {
|
| 'diversity': basic_diversity,
|
| 'technical': technical_terms / total_words if total_words > 0 else 0,
|
| 'narrative': narrative_words / total_words if total_words > 0 else 0,
|
| 'complexity': min(1.0, avg_sentence_length / 20)
|
| }
|
|
|
|
|
| final_score = sum(weights[key] * scores[key] for key in weights)
|
|
|
|
|
| details = {
|
| 'text_type': 'narrative' if scores['narrative'] > scores['technical'] else 'academic',
|
| 'scores': scores
|
| }
|
|
|
| return final_score, details
|
|
|
| except Exception as e:
|
| logger.error(f"Error en analyze_vocabulary_diversity: {str(e)}")
|
| return 0.0, {}
|
|
|
|
|
| def analyze_cohesion(doc):
|
| """Analiza la cohesi贸n textual"""
|
| try:
|
| sentences = list(doc.sents)
|
| if len(sentences) < 2:
|
| logger.warning("Texto demasiado corto para an谩lisis de cohesi贸n")
|
| return 0.0
|
|
|
|
|
| lexical_connections = 0
|
| total_possible_connections = 0
|
|
|
| for i in range(len(sentences)-1):
|
|
|
| sent1_words = {token.lemma_ for token in sentences[i]
|
| if token.is_alpha and not token.is_stop}
|
| sent2_words = {token.lemma_ for token in sentences[i+1]
|
| if token.is_alpha and not token.is_stop}
|
|
|
| if sent1_words and sent2_words:
|
| intersection = len(sent1_words.intersection(sent2_words))
|
| total_possible = min(len(sent1_words), len(sent2_words))
|
|
|
| if total_possible > 0:
|
| lexical_score = intersection / total_possible
|
| lexical_connections += lexical_score
|
| total_possible_connections += 1
|
|
|
|
|
| connector_count = 0
|
| connector_types = {
|
| 'CCONJ': 1.0,
|
| 'SCONJ': 1.2,
|
| 'ADV': 0.8
|
| }
|
|
|
| for token in doc:
|
| if (token.pos_ in connector_types and
|
| token.dep_ in ['cc', 'mark', 'advmod'] and
|
| not token.is_stop):
|
| connector_count += connector_types[token.pos_]
|
|
|
|
|
| if total_possible_connections > 0:
|
| lexical_cohesion = lexical_connections / total_possible_connections
|
| else:
|
| lexical_cohesion = 0
|
|
|
| if len(sentences) > 1:
|
| connector_cohesion = min(1.0, connector_count / (len(sentences) - 1))
|
| else:
|
| connector_cohesion = 0
|
|
|
|
|
| weights = {
|
| 'lexical': 0.7,
|
| 'connectors': 0.3
|
| }
|
|
|
| cohesion_score = (
|
| weights['lexical'] * lexical_cohesion +
|
| weights['connectors'] * connector_cohesion
|
| )
|
|
|
|
|
| logger.info(f"""
|
| An谩lisis de Cohesi贸n:
|
| - Conexiones l茅xicas encontradas: {lexical_connections}
|
| - Conexiones posibles: {total_possible_connections}
|
| - Lexical cohesion score: {lexical_cohesion}
|
| - Conectores encontrados: {connector_count}
|
| - Connector cohesion score: {connector_cohesion}
|
| - Score final: {cohesion_score}
|
| """)
|
|
|
| return cohesion_score
|
|
|
| except Exception as e:
|
| logger.error(f"Error en analyze_cohesion: {str(e)}")
|
| return 0.0
|
|
|
|
|
| def analyze_structure(doc):
|
| try:
|
| if len(doc) == 0:
|
| return 0.0
|
|
|
| structure_scores = []
|
| for token in doc:
|
| if token.dep_ == 'ROOT':
|
| result = get_dependency_depths(token)
|
| structure_scores.append(result['final_score'])
|
|
|
| if not structure_scores:
|
| return 0.0
|
|
|
| return min(1.0, sum(structure_scores) / len(structure_scores))
|
|
|
| except Exception as e:
|
| logger.error(f"Error en analyze_structure: {str(e)}")
|
| return 0.0
|
|
|
|
|
|
|
| def get_dependency_depths(token, depth=0, analyzed_tokens=None):
|
| """
|
| Analiza la profundidad y calidad de las relaciones de dependencia.
|
|
|
| Args:
|
| token: Token a analizar
|
| depth: Profundidad actual en el 谩rbol
|
| analyzed_tokens: Set para evitar ciclos en el an谩lisis
|
|
|
| Returns:
|
| dict: Informaci贸n detallada sobre las dependencias
|
| - depths: Lista de profundidades
|
| - relations: Diccionario con tipos de relaciones encontradas
|
| - complexity_score: Puntuaci贸n de complejidad
|
| """
|
| if analyzed_tokens is None:
|
| analyzed_tokens = set()
|
|
|
|
|
| if token.i in analyzed_tokens:
|
| return {
|
| 'depths': [],
|
| 'relations': {},
|
| 'complexity_score': 0
|
| }
|
|
|
| analyzed_tokens.add(token.i)
|
|
|
|
|
| dependency_weights = {
|
|
|
| 'nsubj': 1.2,
|
| 'obj': 1.1,
|
| 'iobj': 1.1,
|
| 'ROOT': 1.3,
|
|
|
|
|
| 'amod': 0.8,
|
| 'advmod': 0.8,
|
| 'nmod': 0.9,
|
|
|
|
|
| 'csubj': 1.4,
|
| 'ccomp': 1.3,
|
| 'xcomp': 1.2,
|
| 'advcl': 1.2,
|
|
|
|
|
| 'conj': 1.1,
|
| 'cc': 0.7,
|
| 'mark': 0.8,
|
|
|
|
|
| 'det': 0.5,
|
| 'case': 0.5,
|
| 'punct': 0.1
|
| }
|
|
|
|
|
| current_result = {
|
| 'depths': [depth],
|
| 'relations': {token.dep_: 1},
|
| 'complexity_score': dependency_weights.get(token.dep_, 0.5) * (depth + 1)
|
| }
|
|
|
|
|
| for child in token.children:
|
| child_result = get_dependency_depths(child, depth + 1, analyzed_tokens)
|
|
|
|
|
| current_result['depths'].extend(child_result['depths'])
|
|
|
|
|
| for rel, count in child_result['relations'].items():
|
| current_result['relations'][rel] = current_result['relations'].get(rel, 0) + count
|
|
|
|
|
| current_result['complexity_score'] += child_result['complexity_score']
|
|
|
|
|
| current_result['max_depth'] = max(current_result['depths'])
|
| current_result['avg_depth'] = sum(current_result['depths']) / len(current_result['depths'])
|
| current_result['relation_diversity'] = len(current_result['relations'])
|
|
|
|
|
| structure_bonus = 0
|
|
|
|
|
| if 'csubj' in current_result['relations'] or 'ccomp' in current_result['relations']:
|
| structure_bonus += 0.3
|
|
|
|
|
| if 'conj' in current_result['relations'] and 'cc' in current_result['relations']:
|
| structure_bonus += 0.2
|
|
|
|
|
| if len(set(['amod', 'advmod', 'nmod']) & set(current_result['relations'])) >= 2:
|
| structure_bonus += 0.2
|
|
|
| current_result['final_score'] = (
|
| current_result['complexity_score'] * (1 + structure_bonus)
|
| )
|
|
|
| return current_result
|
|
|
|
|
| def normalize_score(value, metric_type,
|
| min_threshold=0.0, target_threshold=1.0,
|
| range_factor=2.0, optimal_length=None,
|
| optimal_connections=None, optimal_depth=None):
|
| """
|
| Normaliza un valor considerando umbrales espec铆ficos por tipo de m茅trica.
|
|
|
| Args:
|
| value: Valor a normalizar
|
| metric_type: Tipo de m茅trica ('vocabulary', 'structure', 'cohesion', 'clarity')
|
| min_threshold: Valor m铆nimo aceptable
|
| target_threshold: Valor objetivo
|
| range_factor: Factor para ajustar el rango
|
| optimal_length: Longitud 贸ptima (opcional)
|
| optimal_connections: N煤mero 贸ptimo de conexiones (opcional)
|
| optimal_depth: Profundidad 贸ptima de estructura (opcional)
|
|
|
| Returns:
|
| float: Valor normalizado entre 0 y 1
|
| """
|
| try:
|
|
|
| METRIC_THRESHOLDS = {
|
| 'vocabulary': {
|
| 'min': 0.60,
|
| 'target': 0.75,
|
| 'range_factor': 1.5
|
| },
|
| 'structure': {
|
| 'min': 0.65,
|
| 'target': 0.80,
|
| 'range_factor': 1.8
|
| },
|
| 'cohesion': {
|
| 'min': 0.55,
|
| 'target': 0.70,
|
| 'range_factor': 1.6
|
| },
|
| 'clarity': {
|
| 'min': 0.60,
|
| 'target': 0.75,
|
| 'range_factor': 1.7
|
| }
|
| }
|
|
|
|
|
| if value < 0:
|
| logger.warning(f"Valor negativo recibido: {value}")
|
| return 0.0
|
|
|
|
|
| if value == 0:
|
| logger.warning("Valor cero recibido")
|
| return 0.0
|
|
|
|
|
| thresholds = METRIC_THRESHOLDS.get(metric_type, {
|
| 'min': min_threshold,
|
| 'target': target_threshold,
|
| 'range_factor': range_factor
|
| })
|
|
|
|
|
| if optimal_depth is not None:
|
| reference = optimal_depth
|
| elif optimal_connections is not None:
|
| reference = optimal_connections
|
| elif optimal_length is not None:
|
| reference = optimal_length
|
| else:
|
| reference = thresholds['target']
|
|
|
|
|
| if reference <= 0:
|
| logger.warning(f"Valor de referencia inv谩lido: {reference}")
|
| return 0.0
|
|
|
|
|
| if value < thresholds['min']:
|
|
|
| score = (value / thresholds['min']) * 0.5
|
| elif value < thresholds['target']:
|
|
|
| range_size = thresholds['target'] - thresholds['min']
|
| progress = (value - thresholds['min']) / range_size
|
| score = 0.5 + (progress * 0.5)
|
| else:
|
|
|
| score = 1.0
|
|
|
|
|
| if value > (thresholds['target'] * thresholds['range_factor']):
|
| excess = (value - thresholds['target']) / (thresholds['target'] * thresholds['range_factor'])
|
| score = max(0.7, 1.0 - excess)
|
|
|
|
|
| return max(0.0, min(1.0, score))
|
|
|
| except Exception as e:
|
| logger.error(f"Error en normalize_score: {str(e)}")
|
| return 0.0
|
|
|
|
|
|
|
|
|
| def generate_recommendations(metrics, text_type, lang_code='es'):
|
| """
|
| Genera recomendaciones personalizadas basadas en las m茅tricas del texto y el tipo de texto.
|
|
|
| Args:
|
| metrics: Diccionario con las m茅tricas analizadas
|
| text_type: Tipo de texto ('academic_article', 'student_essay', 'general_communication')
|
| lang_code: C贸digo del idioma para las recomendaciones (es, en, uk)
|
|
|
| Returns:
|
| dict: Recomendaciones organizadas por categor铆a en el idioma correspondiente
|
| """
|
| try:
|
|
|
| logger.info(f"generate_recommendations llamado con idioma: {lang_code}")
|
|
|
|
|
| logger.info(f"Idiomas disponibles en RECOMMENDATIONS: {list(RECOMMENDATIONS.keys())}")
|
|
|
|
|
| thresholds = TEXT_TYPES[text_type]['thresholds']
|
|
|
|
|
| if lang_code not in RECOMMENDATIONS:
|
| logger.warning(f"Idioma {lang_code} no soportado para recomendaciones, usando espa帽ol")
|
| lang_code = 'es'
|
|
|
|
|
| translations = RECOMMENDATIONS[lang_code]
|
|
|
|
|
| recommendations = {
|
| 'vocabulary': [],
|
| 'structure': [],
|
| 'cohesion': [],
|
| 'clarity': [],
|
| 'specific': [],
|
| 'priority': {
|
| 'area': 'general',
|
| 'tips': []
|
| },
|
| 'text_type_name': translations['text_types'][text_type],
|
| 'dimension_names': translations['dimension_names'],
|
| 'ui_text': {
|
| 'priority_intro': translations['priority_intro'],
|
| 'detailed_recommendations': translations['detailed_recommendations'],
|
| 'save_button': translations['save_button'],
|
| 'save_success': translations['save_success'],
|
| 'save_error': translations['save_error'],
|
| 'area_priority': translations['area_priority']
|
| }
|
| }
|
|
|
|
|
| dimensions = ['vocabulary', 'structure', 'cohesion', 'clarity']
|
| scores = {}
|
|
|
| for dim in dimensions:
|
| score = metrics[dim]['normalized_score']
|
| scores[dim] = score
|
|
|
|
|
| if score < thresholds[dim]['min']:
|
| level = 'low'
|
| elif score < thresholds[dim]['target']:
|
| level = 'medium'
|
| else:
|
| level = 'high'
|
|
|
|
|
| recommendations[dim] = translations[dim][level]
|
|
|
|
|
| recommendations['specific'] = translations[text_type]
|
|
|
|
|
| priority_dimension = min(scores, key=scores.get)
|
| recommendations['priority']['area'] = priority_dimension
|
| recommendations['priority']['tips'] = recommendations[priority_dimension]
|
|
|
| logger.info(f"Generadas recomendaciones en {lang_code} para texto tipo {text_type}")
|
| return recommendations
|
|
|
| except Exception as e:
|
| logger.error(f"Error en generate_recommendations: {str(e)}")
|
|
|
|
|
|
|
| fallback_translations = {
|
| 'en': {
|
| 'basic_recommendations': {
|
| 'vocabulary': ["Try enriching your vocabulary"],
|
| 'structure': ["Work on the structure of your sentences"],
|
| 'cohesion': ["Improve the connection between your ideas"],
|
| 'clarity': ["Try to express your ideas more clearly"],
|
| 'specific': ["Adapt your text according to its purpose"],
|
| },
|
| 'dimension_names': {
|
| 'vocabulary': 'Vocabulary',
|
| 'structure': 'Structure',
|
| 'cohesion': 'Cohesion',
|
| 'clarity': 'Clarity',
|
| 'general': 'General'
|
| },
|
| 'ui_text': {
|
| 'priority_intro': "This is where you should focus your efforts.",
|
| 'detailed_recommendations': "Detailed recommendations",
|
| 'save_button': "Save analysis",
|
| 'save_success': "Analysis saved successfully",
|
| 'save_error': "Error saving analysis",
|
| 'area_priority': "Priority area"
|
| }
|
| },
|
| 'uk': {
|
| 'basic_recommendations': {
|
| 'vocabulary': ["袪芯蟹褕懈褉褌械 褋胁褨泄 褋谢芯胁薪懈泻芯胁懈泄 蟹邪锌邪褋"],
|
| 'structure': ["袩芯泻褉邪褖褨褌褜 褋褌褉褍泻褌褍褉褍 胁邪褕懈褏 褉械褔械薪褜"],
|
| 'cohesion': ["袩芯泻褉邪褖褨褌褜 蟹胁'褟蟹芯泻 屑褨卸 胁邪褕懈屑懈 褨写械褟屑懈"],
|
| 'clarity': ["袙懈褋谢芯胁谢褞泄褌械 褋胁芯褩 褨写械褩 褟褋薪褨褕械"],
|
| 'specific': ["袗写邪锌褌褍泄褌械 褋胁褨泄 褌械泻褋褌 胁褨写锌芯胁褨写薪芯 写芯 泄芯谐芯 屑械褌懈"],
|
| },
|
| 'dimension_names': {
|
| 'vocabulary': '小谢芯胁薪懈泻芯胁懈泄 蟹邪锌邪褋',
|
| 'structure': '小褌褉褍泻褌褍褉邪',
|
| 'cohesion': '袟胁\'褟蟹薪褨褋褌褜',
|
| 'clarity': '携褋薪褨褋褌褜',
|
| 'general': '袟邪谐邪谢褜薪械'
|
| },
|
| 'ui_text': {
|
| 'priority_intro': "笑械 芯斜谢邪褋褌褜, 写械 胁懈 锌芯胁懈薪薪褨 蟹芯褋械褉械写懈褌懈 褋胁芯褩 蟹褍褋懈谢谢褟.",
|
| 'detailed_recommendations': "袛械褌邪谢褜薪褨 褉械泻芯屑械薪写邪褑褨褩",
|
| 'save_button': "袟斜械褉械谐褌懈 邪薪邪谢褨蟹",
|
| 'save_success': "袗薪邪谢褨蟹 褍褋锌褨褕薪芯 蟹斜械褉械卸械薪芯",
|
| 'save_error': "袩芯屑懈谢泻邪 锌褉懈 蟹斜械褉械卸械薪薪褨 邪薪邪谢褨蟹褍",
|
| 'area_priority': "袩褉褨芯褉懈褌械褌薪邪 芯斜谢邪褋褌褜"
|
| }
|
| },
|
| 'es': {
|
| 'basic_recommendations': {
|
| 'vocabulary': ["Intenta enriquecer tu vocabulario"],
|
| 'structure': ["Trabaja en la estructura de tus oraciones"],
|
| 'cohesion': ["Mejora la conexi贸n entre tus ideas"],
|
| 'clarity': ["Busca expresar tus ideas con mayor claridad"],
|
| 'specific': ["Adapta tu texto seg煤n su prop贸sito"],
|
| },
|
| 'dimension_names': {
|
| 'vocabulary': 'Vocabulario',
|
| 'structure': 'Estructura',
|
| 'cohesion': 'Cohesi贸n',
|
| 'clarity': 'Claridad',
|
| 'general': 'General'
|
| },
|
| 'ui_text': {
|
| 'priority_intro': "Esta es el 谩rea donde debes concentrar tus esfuerzos.",
|
| 'detailed_recommendations': "Recomendaciones detalladas",
|
| 'save_button': "Guardar an谩lisis",
|
| 'save_success': "An谩lisis guardado con 茅xito",
|
| 'save_error': "Error al guardar el an谩lisis",
|
| 'area_priority': "脕rea prioritaria"
|
| }
|
| }
|
| }
|
|
|
|
|
| current_lang = fallback_translations.get(lang_code,
|
| fallback_translations.get('en',
|
| fallback_translations['es']))
|
|
|
| basic_recommendations = current_lang['basic_recommendations']
|
|
|
| return {
|
| 'vocabulary': basic_recommendations['vocabulary'],
|
| 'structure': basic_recommendations['structure'],
|
| 'cohesion': basic_recommendations['cohesion'],
|
| 'clarity': basic_recommendations['clarity'],
|
| 'specific': basic_recommendations['specific'],
|
| 'priority': {
|
| 'area': 'general',
|
| 'tips': ["Busca retroalimentaci贸n espec铆fica de un tutor o profesor"]
|
| },
|
| 'dimension_names': current_lang['dimension_names'],
|
| 'ui_text': current_lang['ui_text']
|
| }
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| def generate_sentence_graphs(doc):
|
| """Genera visualizaciones de estructura de oraciones"""
|
| fig, ax = plt.subplots(figsize=(10, 6))
|
|
|
| plt.close()
|
| return fig
|
|
|
|
|
| def generate_word_connections(doc):
|
| """Genera red de conexiones de palabras"""
|
| fig, ax = plt.subplots(figsize=(10, 6))
|
|
|
| plt.close()
|
| return fig
|
|
|
|
|
| def generate_connection_paths(doc):
|
| """Genera patrones de conexi贸n"""
|
| fig, ax = plt.subplots(figsize=(10, 6))
|
|
|
| plt.close()
|
| return fig
|
|
|
|
|
| def create_vocabulary_network(doc):
|
| """
|
| Genera el grafo de red de vocabulario.
|
| """
|
| G = nx.Graph()
|
|
|
|
|
| words = [token.text.lower() for token in doc if token.is_alpha and not token.is_stop]
|
| word_freq = Counter(words)
|
|
|
|
|
| for word, freq in word_freq.items():
|
| G.add_node(word, size=freq)
|
|
|
|
|
| window_size = 5
|
| for i in range(len(words) - window_size):
|
| window = words[i:i+window_size]
|
| for w1, w2 in combinations(set(window), 2):
|
| if G.has_edge(w1, w2):
|
| G[w1][w2]['weight'] += 1
|
| else:
|
| G.add_edge(w1, w2, weight=1)
|
|
|
|
|
| fig, ax = plt.subplots(figsize=(12, 8))
|
| pos = nx.spring_layout(G)
|
|
|
|
|
| nx.draw_networkx_nodes(G, pos,
|
| node_size=[G.nodes[node]['size']*100 for node in G.nodes],
|
| node_color='lightblue',
|
| alpha=0.7)
|
|
|
|
|
| nx.draw_networkx_edges(G, pos,
|
| width=[G[u][v]['weight']*0.5 for u,v in G.edges],
|
| alpha=0.5)
|
|
|
|
|
| nx.draw_networkx_labels(G, pos)
|
|
|
| plt.title("Red de Vocabulario")
|
| plt.axis('off')
|
| return fig
|
|
|
|
|
| def create_syntax_complexity_graph(doc):
|
| """
|
| Genera el diagrama de arco de complejidad sint谩ctica.
|
| Muestra la estructura de dependencias con colores basados en la complejidad.
|
| """
|
| try:
|
|
|
| sentences = list(doc.sents)
|
| if not sentences:
|
| return None
|
|
|
|
|
| fig, ax = plt.subplots(figsize=(12, len(sentences) * 2))
|
|
|
|
|
| depth_colors = plt.cm.viridis(np.linspace(0, 1, 6))
|
|
|
| y_offset = 0
|
| max_x = 0
|
|
|
| for sent in sentences:
|
| words = [token.text for token in sent]
|
| x_positions = range(len(words))
|
| max_x = max(max_x, len(words))
|
|
|
|
|
| plt.plot(x_positions, [y_offset] * len(words), 'k-', alpha=0.2)
|
| plt.scatter(x_positions, [y_offset] * len(words), alpha=0)
|
|
|
|
|
| for i, word in enumerate(words):
|
| plt.annotate(word, (i, y_offset), xytext=(0, -10),
|
| textcoords='offset points', ha='center')
|
|
|
|
|
| for token in sent:
|
| if token.dep_ != "ROOT":
|
|
|
| depth = 0
|
| current = token
|
| while current.head != current:
|
| depth += 1
|
| current = current.head
|
|
|
|
|
| start = token.i - sent[0].i
|
| end = token.head.i - sent[0].i
|
|
|
|
|
| height = 0.5 * abs(end - start)
|
|
|
|
|
| color = depth_colors[min(depth, len(depth_colors)-1)]
|
|
|
|
|
| arc = patches.Arc((min(start, end) + abs(end - start)/2, y_offset),
|
| width=abs(end - start),
|
| height=height,
|
| angle=0,
|
| theta1=0,
|
| theta2=180,
|
| color=color,
|
| alpha=0.6)
|
| ax.add_patch(arc)
|
|
|
| y_offset -= 2
|
|
|
|
|
| plt.xlim(-1, max_x)
|
| plt.ylim(y_offset - 1, 1)
|
| plt.axis('off')
|
| plt.title("Complejidad Sint谩ctica")
|
|
|
| return fig
|
|
|
| except Exception as e:
|
| logger.error(f"Error en create_syntax_complexity_graph: {str(e)}")
|
| return None
|
|
|
|
|
| def create_cohesion_heatmap(doc):
|
| """Genera un mapa de calor que muestra la cohesi贸n entre p谩rrafos/oraciones."""
|
| try:
|
| sentences = list(doc.sents)
|
| n_sentences = len(sentences)
|
|
|
| if n_sentences < 2:
|
| return None
|
|
|
| similarity_matrix = np.zeros((n_sentences, n_sentences))
|
|
|
| for i in range(n_sentences):
|
| for j in range(n_sentences):
|
| sent1_lemmas = {token.lemma_ for token in sentences[i]
|
| if token.is_alpha and not token.is_stop}
|
| sent2_lemmas = {token.lemma_ for token in sentences[j]
|
| if token.is_alpha and not token.is_stop}
|
|
|
| if sent1_lemmas and sent2_lemmas:
|
| intersection = len(sent1_lemmas & sent2_lemmas)
|
| union = len(sent1_lemmas | sent2_lemmas)
|
| similarity_matrix[i, j] = intersection / union if union > 0 else 0
|
|
|
|
|
| fig, ax = plt.subplots(figsize=(10, 8))
|
|
|
| sns.heatmap(similarity_matrix,
|
| cmap='YlOrRd',
|
| square=True,
|
| xticklabels=False,
|
| yticklabels=False,
|
| cbar_kws={'label': 'Cohesi贸n'},
|
| ax=ax)
|
|
|
| plt.title("Mapa de Cohesi贸n Textual")
|
| plt.xlabel("Oraciones")
|
| plt.ylabel("Oraciones")
|
|
|
| plt.tight_layout()
|
| return fig
|
|
|
| except Exception as e:
|
| logger.error(f"Error en create_cohesion_heatmap: {str(e)}")
|
| return None
|
|
|