File size: 13,572 Bytes
46a1213
01cc880
 
 
 
 
ac10537
 
 
 
01cc880
 
 
 
ff68008
 
bed8651
ff68008
 
 
bed8651
ff68008
 
 
 
bed8651
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff68008
bed8651
 
 
 
 
 
 
 
 
 
 
 
ff68008
bed8651
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff68008
bed8651
ff68008
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ea9f452
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff68008
 
 
4272d5a
ea9f452
 
 
 
4272d5a
 
 
 
 
ea9f452
 
 
 
 
 
 
4272d5a
 
 
ff68008
0055018
ff68008
 
 
 
 
 
 
4272d5a
 
e7db8e8
ea9f452
bed8651
e7db8e8
 
bed8651
e7db8e8
 
bed8651
4272d5a
bed8651
 
 
e7db8e8
 
ea9f452
 
 
 
 
 
 
 
 
 
 
4272d5a
ea9f452
4272d5a
ea9f452
bed8651
ea9f452
e7db8e8
ea9f452
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e7db8e8
 
 
ff68008
0055018
ff68008
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
01cc880
 
 
 
ff68008
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
01cc880
 
 
 
ff68008
01cc880
ff68008
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0055018
 
 
4272d5a
0055018
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4272d5a
 
0055018
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
#v3/modules/studentact/current_situation_analysis.py

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

logger = logging.getLogger(__name__)

def analyze_text_dimensions(doc):
    """
    Analiza las dimensiones principales del texto.
    
    Args:
        doc: Documento procesado por spaCy
        
    Returns:
        dict: M茅tricas del an谩lisis
    """
    try:
        # An谩lisis de vocabulario
        vocab_score = analyze_vocabulary_diversity(doc)
        vocab_normalized = normalize_score(
            value=vocab_score,
            optimal_connections=len(doc) * 0.4  # 40% del total de palabras como conexiones 贸ptimas
        )

        # An谩lisis de estructura
        struct_score = analyze_structure(doc)
        struct_normalized = normalize_score(
            value=struct_score,
            optimal_length=20  # Longitud 贸ptima promedio de oraci贸n
        )

        # An谩lisis de cohesi贸n
        cohesion_score = analyze_cohesion(doc)
        cohesion_normalized = normalize_score(
            value=cohesion_score,
            optimal_value=0.7  # 70% de cohesi贸n como valor 贸ptimo
        )

        # An谩lisis de claridad
        clarity_score = analyze_clarity(doc)
        clarity_normalized = normalize_score(
            value=clarity_score,
            optimal_value=0.8  # 80% de claridad como valor 贸ptimo
        )

        return {
            'vocabulary': {
                'raw_score': vocab_score,
                'normalized_score': vocab_normalized
            },
            'structure': {
                'raw_score': struct_score,
                'normalized_score': struct_normalized
            },
            'cohesion': {
                'raw_score': cohesion_score,
                'normalized_score': cohesion_normalized
            },
            'clarity': {
                'raw_score': clarity_score,
                'normalized_score': clarity_normalized
            }
        }

    except Exception as e:
        logger.error(f"Error en analyze_text_dimensions: {str(e)}")
        raise

def analyze_clarity(doc):
    """Analiza la claridad basada en longitud de oraciones"""
    sentences = list(doc.sents)
    avg_length = sum(len(sent) for sent in sentences) / len(sentences)
    return normalize_score(avg_length, optimal_length=20)

def analyze_vocabulary_diversity(doc):
    """Analiza la diversidad del vocabulario"""
    unique_lemmas = {token.lemma_ for token in doc if token.is_alpha}
    total_words = len([token for token in doc if token.is_alpha])
    return len(unique_lemmas) / total_words if total_words > 0 else 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
            
        connections = 0
        for i in range(len(sentences)-1):
            sent1_words = {token.lemma_ for token in sentences[i]}
            sent2_words = {token.lemma_ for token in sentences[i+1]}
            connections += len(sent1_words.intersection(sent2_words))
            
        # Validar que haya conexiones antes de normalizar
        if connections == 0:
            logger.warning("No se encontraron conexiones entre oraciones")
            return 0.0
            
        return normalize_score(connections, optimal_connections=max(5, len(sentences) * 0.2))
    except Exception as e:
        logger.error(f"Error en analyze_cohesion: {str(e)}")
        return 0.0

def analyze_structure(doc):
    """Analiza la complejidad estructural"""
    try:
        if len(doc) == 0:
            logger.warning("Documento vac铆o")
            return 0.0
            
        root_distances = []
        for token in doc:
            if token.dep_ == 'ROOT':
                depths = get_dependency_depths(token)
                root_distances.extend(depths)
                
        if not root_distances:
            logger.warning("No se encontraron estructuras de dependencia")
            return 0.0
            
        avg_depth = sum(root_distances) / len(root_distances)
        return normalize_score(avg_depth, optimal_depth=max(3, len(doc) * 0.1))
    except Exception as e:
        logger.error(f"Error en analyze_structure: {str(e)}")
        return 0.0

# Funciones auxiliares de an谩lisis
def get_dependency_depths(token, depth=0):
    """Obtiene las profundidades de dependencia"""
    depths = [depth]
    for child in token.children:
        depths.extend(get_dependency_depths(child, depth + 1))
    return depths

def normalize_score(value, optimal_value=1.0, range_factor=2.0, optimal_length=None, 
                   optimal_connections=None, optimal_depth=None):
    """
    Normaliza un valor a una escala de 0-1 con manejo de casos extremos.
    
    Args:
        value: Valor a normalizar
        optimal_value: Valor 贸ptimo de referencia
        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:
        # Validar valores negativos o cero
        if value < 0:
            logger.warning(f"Valor negativo recibido: {value}")
            return 0.0
            
        # Manejar caso donde el valor es cero
        if value == 0:
            logger.warning("Valor cero recibido")
            return 0.0

        # Identificar el valor de referencia a usar
        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 = optimal_value

        # Validar valor de referencia
        if reference <= 0:
            logger.warning(f"Valor de referencia inv谩lido: {reference}")
            return 0.0

        # Calcular diferencia y m谩xima diferencia permitida
        diff = abs(value - reference)
        max_diff = reference * range_factor

        # Validar max_diff
        if max_diff <= 0:
            logger.warning(f"M谩xima diferencia inv谩lida: {max_diff}")
            return 0.0

        # Calcular score normalizado
        score = 1.0 - min(diff / max_diff, 1.0)
        
        # Asegurar que el resultado est茅 entre 0 y 1
        return max(0.0, min(1.0, score))

    except Exception as e:
        logger.error(f"Error en normalize_score: {str(e)}")
        return 0.0

# Funciones de generaci贸n de gr谩ficos
def generate_sentence_graphs(doc):
    """Genera visualizaciones de estructura de oraciones"""
    fig, ax = plt.subplots(figsize=(10, 6))
    # Implementar visualizaci贸n
    plt.close()
    return fig

def generate_word_connections(doc):
    """Genera red de conexiones de palabras"""
    fig, ax = plt.subplots(figsize=(10, 6))
    # Implementar visualizaci贸n
    plt.close()
    return fig

def generate_connection_paths(doc):
    """Genera patrones de conexi贸n"""
    fig, ax = plt.subplots(figsize=(10, 6))
    # Implementar visualizaci贸n
    plt.close()
    return fig

def create_vocabulary_network(doc):
    """
    Genera el grafo de red de vocabulario.
    """
    G = nx.Graph()
    
    # Crear nodos para palabras significativas
    words = [token.text.lower() for token in doc if token.is_alpha and not token.is_stop]
    word_freq = Counter(words)
    
    # A帽adir nodos con tama帽o basado en frecuencia
    for word, freq in word_freq.items():
        G.add_node(word, size=freq)
    
    # Crear conexiones basadas en co-ocurrencia
    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)
    
    # Crear visualizaci贸n
    fig, ax = plt.subplots(figsize=(12, 8))
    pos = nx.spring_layout(G)
    
    # Dibujar nodos
    nx.draw_networkx_nodes(G, pos, 
                          node_size=[G.nodes[node]['size']*100 for node in G.nodes],
                          node_color='lightblue',
                          alpha=0.7)
    
    # Dibujar conexiones
    nx.draw_networkx_edges(G, pos, 
                          width=[G[u][v]['weight']*0.5 for u,v in G.edges],
                          alpha=0.5)
    
    # A帽adir etiquetas
    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:
        # Preparar datos para la visualizaci贸n
        sentences = list(doc.sents)
        if not sentences:
            return None
            
        # Crear figura para el gr谩fico
        fig, ax = plt.subplots(figsize=(12, len(sentences) * 2))
        
        # Colores para diferentes niveles de profundidad
        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))
            
            # Dibujar palabras
            plt.plot(x_positions, [y_offset] * len(words), 'k-', alpha=0.2)
            plt.scatter(x_positions, [y_offset] * len(words), alpha=0)
            
            # A帽adir texto
            for i, word in enumerate(words):
                plt.annotate(word, (i, y_offset), xytext=(0, -10), 
                           textcoords='offset points', ha='center')
            
            # Dibujar arcos de dependencia
            for token in sent:
                if token.dep_ != "ROOT":
                    # Calcular profundidad de dependencia
                    depth = 0
                    current = token
                    while current.head != current:
                        depth += 1
                        current = current.head
                    
                    # Determinar posiciones para el arco
                    start = token.i - sent[0].i
                    end = token.head.i - sent[0].i
                    
                    # Altura del arco basada en la distancia entre palabras
                    height = 0.5 * abs(end - start)
                    
                    # Color basado en la profundidad
                    color = depth_colors[min(depth, len(depth_colors)-1)]
                    
                    # Crear arco
                    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
        
        # Configurar el gr谩fico
        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)  # Corregido aqu铆
                    union = len(sent1_lemmas | sent2_lemmas)  # Y aqu铆
                    similarity_matrix[i, j] = intersection / union if union > 0 else 0
        
        # Crear visualizaci贸n
        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