Update modules/text_analysis/morpho_analysis.py
Browse files- modules/text_analysis/morpho_analysis.py +223 -256
modules/text_analysis/morpho_analysis.py
CHANGED
@@ -1,256 +1,223 @@
|
|
1 |
-
##modules/text_analysis/morpho_analysis.py
|
2 |
-
|
3 |
-
import spacy
|
4 |
-
from collections import Counter
|
5 |
-
from spacy import displacy
|
6 |
-
import re
|
7 |
-
from streamlit.components.v1 import html
|
8 |
-
import base64
|
9 |
-
|
10 |
-
from collections import Counter
|
11 |
-
import re
|
12 |
-
from ..utils.widget_utils import generate_unique_key
|
13 |
-
|
14 |
-
import logging
|
15 |
-
logger = logging.getLogger(__name__)
|
16 |
-
|
17 |
-
|
18 |
-
# Define colors for grammatical categories
|
19 |
-
POS_COLORS = {
|
20 |
-
'ADJ': '#FFA07A', # Light Salmon
|
21 |
-
'ADP': '#98FB98', # Pale Green
|
22 |
-
'ADV': '#87CEFA', # Light Sky Blue
|
23 |
-
'AUX': '#DDA0DD', # Plum
|
24 |
-
'CCONJ': '#F0E68C', # Khaki
|
25 |
-
'DET': '#FFB6C1', # Light Pink
|
26 |
-
'INTJ': '#FF6347', # Tomato
|
27 |
-
'NOUN': '#90EE90', # Light Green
|
28 |
-
'NUM': '#FAFAD2', # Light Goldenrod Yellow
|
29 |
-
'PART': '#D3D3D3', # Light Gray
|
30 |
-
'PRON': '#FFA500', # Orange
|
31 |
-
'PROPN': '#20B2AA', # Light Sea Green
|
32 |
-
'SCONJ': '#DEB887', # Burlywood
|
33 |
-
'SYM': '#7B68EE', # Medium Slate Blue
|
34 |
-
'VERB': '#FF69B4', # Hot Pink
|
35 |
-
'X': '#A9A9A9', # Dark Gray
|
36 |
-
}
|
37 |
-
|
38 |
-
POS_TRANSLATIONS = {
|
39 |
-
'es': {
|
40 |
-
'ADJ': 'Adjetivo',
|
41 |
-
'
|
42 |
-
'
|
43 |
-
'
|
44 |
-
'
|
45 |
-
|
46 |
-
|
47 |
-
'
|
48 |
-
'
|
49 |
-
'PART': '
|
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 |
-
# Verificar el idioma del modelo
|
225 |
-
model_lang = nlp.lang
|
226 |
-
logger.info(f"Realizando análisis con modelo de idioma: {model_lang}")
|
227 |
-
|
228 |
-
# Procesar el texto con el modelo específico del idioma
|
229 |
-
doc = nlp(text)
|
230 |
-
|
231 |
-
# Realizar análisis específico según el idioma
|
232 |
-
return {
|
233 |
-
'doc': doc,
|
234 |
-
'pos_analysis': get_detailed_pos_analysis(doc),
|
235 |
-
'morphological_analysis': get_morphological_analysis(doc),
|
236 |
-
'sentence_structure': get_sentence_structure_analysis(doc),
|
237 |
-
'arc_diagrams': generate_arc_diagram(doc), # Quitamos nlp.lang
|
238 |
-
'repeated_words': get_repeated_words_colors(doc),
|
239 |
-
'highlighted_text': highlight_repeated_words(doc, get_repeated_words_colors(doc))
|
240 |
-
}
|
241 |
-
except Exception as e:
|
242 |
-
logger.error(f"Error en análisis morfosintáctico: {str(e)}")
|
243 |
-
return None
|
244 |
-
|
245 |
-
# Al final del archivo morph_analysis.py
|
246 |
-
__all__ = [
|
247 |
-
'perform_advanced_morphosyntactic_analysis',
|
248 |
-
'get_repeated_words_colors',
|
249 |
-
'highlight_repeated_words',
|
250 |
-
'generate_arc_diagram',
|
251 |
-
'get_detailed_pos_analysis',
|
252 |
-
'get_morphological_analysis',
|
253 |
-
'get_sentence_structure_analysis',
|
254 |
-
'POS_COLORS',
|
255 |
-
'POS_TRANSLATIONS'
|
256 |
-
]
|
|
|
1 |
+
##modules/text_analysis/morpho_analysis.py
|
2 |
+
|
3 |
+
import spacy
|
4 |
+
from collections import Counter
|
5 |
+
from spacy import displacy
|
6 |
+
import re
|
7 |
+
from streamlit.components.v1 import html
|
8 |
+
import base64
|
9 |
+
|
10 |
+
from collections import Counter
|
11 |
+
import re
|
12 |
+
from ..utils.widget_utils import generate_unique_key
|
13 |
+
|
14 |
+
import logging
|
15 |
+
logger = logging.getLogger(__name__)
|
16 |
+
|
17 |
+
|
18 |
+
# Define colors for grammatical categories
|
19 |
+
POS_COLORS = {
|
20 |
+
'ADJ': '#FFA07A', # Light Salmon
|
21 |
+
'ADP': '#98FB98', # Pale Green
|
22 |
+
'ADV': '#87CEFA', # Light Sky Blue
|
23 |
+
'AUX': '#DDA0DD', # Plum
|
24 |
+
'CCONJ': '#F0E68C', # Khaki
|
25 |
+
'DET': '#FFB6C1', # Light Pink
|
26 |
+
'INTJ': '#FF6347', # Tomato
|
27 |
+
'NOUN': '#90EE90', # Light Green
|
28 |
+
'NUM': '#FAFAD2', # Light Goldenrod Yellow
|
29 |
+
'PART': '#D3D3D3', # Light Gray
|
30 |
+
'PRON': '#FFA500', # Orange
|
31 |
+
'PROPN': '#20B2AA', # Light Sea Green
|
32 |
+
'SCONJ': '#DEB887', # Burlywood
|
33 |
+
'SYM': '#7B68EE', # Medium Slate Blue
|
34 |
+
'VERB': '#FF69B4', # Hot Pink
|
35 |
+
'X': '#A9A9A9', # Dark Gray
|
36 |
+
}
|
37 |
+
|
38 |
+
POS_TRANSLATIONS = {
|
39 |
+
'es': {
|
40 |
+
'ADJ': 'Adjetivo', 'ADP': 'Preposición', 'ADV': 'Adverbio', 'AUX': 'Auxiliar',
|
41 |
+
'CCONJ': 'Conjunción Coordinante', 'DET': 'Determinante', 'INTJ': 'Interjección',
|
42 |
+
'NOUN': 'Sustantivo', 'NUM': 'Número', 'PART': 'Partícula', 'PRON': 'Pronombre',
|
43 |
+
'PROPN': 'Nombre Propio', 'SCONJ': 'Conjunción Subordinante', 'SYM': 'Símbolo',
|
44 |
+
'VERB': 'Verbo', 'X': 'Otro',
|
45 |
+
},
|
46 |
+
'en': {
|
47 |
+
'ADJ': 'Adjective', 'ADP': 'Preposition', 'ADV': 'Adverb', 'AUX': 'Auxiliary',
|
48 |
+
'CCONJ': 'Coordinating Conjunction', 'DET': 'Determiner', 'INTJ': 'Interjection',
|
49 |
+
'NOUN': 'Noun', 'NUM': 'Number', 'PART': 'Particle', 'PRON': 'Pronoun',
|
50 |
+
'PROPN': 'Proper Noun', 'SCONJ': 'Subordinating Conjunction', 'SYM': 'Symbol',
|
51 |
+
'VERB': 'Verb', 'X': 'Other',
|
52 |
+
},
|
53 |
+
'uk': {
|
54 |
+
'ADJ': 'Прикметник', 'ADP': 'Прийменник', 'ADV': 'Прислівник', 'AUX': 'Допоміжне дієслово',
|
55 |
+
'CCONJ': 'Сурядний сполучник', 'DET': 'Означник', 'INTJ': 'Вигук',
|
56 |
+
'NOUN': 'Іменник', 'NUM': 'Число', 'PART': 'Частка', 'PRON': 'Займенник',
|
57 |
+
'PROPN': 'Власна назва', 'SCONJ': 'Підрядний сполучник', 'SYM': 'Символ',
|
58 |
+
'VERB': 'Дієслово', 'X': 'Інше',
|
59 |
+
}
|
60 |
+
}
|
61 |
+
|
62 |
+
#############################################################################################
|
63 |
+
def get_repeated_words_colors(doc):
|
64 |
+
word_counts = Counter(token.text.lower() for token in doc if token.pos_ != 'PUNCT')
|
65 |
+
repeated_words = {word: count for word, count in word_counts.items() if count > 1}
|
66 |
+
|
67 |
+
word_colors = {}
|
68 |
+
for token in doc:
|
69 |
+
if token.text.lower() in repeated_words:
|
70 |
+
word_colors[token.text.lower()] = POS_COLORS.get(token.pos_, '#FFFFFF')
|
71 |
+
|
72 |
+
return word_colors
|
73 |
+
|
74 |
+
######################################################################################################
|
75 |
+
def highlight_repeated_words(doc, word_colors):
|
76 |
+
highlighted_text = []
|
77 |
+
for token in doc:
|
78 |
+
if token.text.lower() in word_colors:
|
79 |
+
color = word_colors[token.text.lower()]
|
80 |
+
highlighted_text.append(f'<span style="background-color: {color};">{token.text}</span>')
|
81 |
+
else:
|
82 |
+
highlighted_text.append(token.text)
|
83 |
+
return ' '.join(highlighted_text)
|
84 |
+
|
85 |
+
#################################################################################################
|
86 |
+
|
87 |
+
def generate_arc_diagram(doc):
|
88 |
+
"""
|
89 |
+
Genera diagramas de arco para cada oración en el documento usando spacy-streamlit.
|
90 |
+
|
91 |
+
Args:
|
92 |
+
doc: Documento procesado por spaCy
|
93 |
+
Returns:
|
94 |
+
list: Lista de diagramas en formato HTML
|
95 |
+
"""
|
96 |
+
arc_diagrams = []
|
97 |
+
try:
|
98 |
+
options = {
|
99 |
+
"compact": False,
|
100 |
+
"color": "#ffffff",
|
101 |
+
"bg": "#0d6efd",
|
102 |
+
"font": "Arial",
|
103 |
+
"offset_x": 50,
|
104 |
+
"distance": 100,
|
105 |
+
"arrow_spacing": 12,
|
106 |
+
"arrow_width": 2,
|
107 |
+
"arrow_stroke": 2,
|
108 |
+
"word_spacing": 25,
|
109 |
+
"maxZoom": 2
|
110 |
+
}
|
111 |
+
|
112 |
+
for sent in doc.sents:
|
113 |
+
try:
|
114 |
+
# Usar el método render de displacy directamente con las opciones
|
115 |
+
html = displacy.render(sent, style="dep", options=options)
|
116 |
+
arc_diagrams.append(html)
|
117 |
+
except Exception as e:
|
118 |
+
logger.error(f"Error al renderizar oración: {str(e)}")
|
119 |
+
continue
|
120 |
+
|
121 |
+
return arc_diagrams
|
122 |
+
except Exception as e:
|
123 |
+
logger.error(f"Error general en generate_arc_diagram: {str(e)}")
|
124 |
+
return None
|
125 |
+
|
126 |
+
|
127 |
+
#################################################################################################
|
128 |
+
def get_detailed_pos_analysis(doc):
|
129 |
+
"""
|
130 |
+
Realiza un análisis detallado de las categorías gramaticales (POS) en el texto.
|
131 |
+
"""
|
132 |
+
pos_counts = Counter(token.pos_ for token in doc)
|
133 |
+
total_tokens = len(doc)
|
134 |
+
pos_analysis = []
|
135 |
+
for pos, count in pos_counts.items():
|
136 |
+
percentage = (count / total_tokens) * 100
|
137 |
+
pos_analysis.append({
|
138 |
+
'pos': pos,
|
139 |
+
'count': count,
|
140 |
+
'percentage': round(percentage, 2),
|
141 |
+
'examples': [token.text for token in doc if token.pos_ == pos][:5] # Primeros 5 ejemplos
|
142 |
+
})
|
143 |
+
return sorted(pos_analysis, key=lambda x: x['count'], reverse=True)
|
144 |
+
|
145 |
+
#################################################################################################
|
146 |
+
def get_morphological_analysis(doc):
|
147 |
+
"""
|
148 |
+
Realiza un análisis morfológico detallado de las palabras en el texto.
|
149 |
+
"""
|
150 |
+
morphology_analysis = []
|
151 |
+
for token in doc:
|
152 |
+
if token.pos_ in ['NOUN', 'VERB', 'ADJ', 'ADV']: # Enfocarse en categorías principales
|
153 |
+
morphology_analysis.append({
|
154 |
+
'text': token.text,
|
155 |
+
'lemma': token.lemma_,
|
156 |
+
'pos': token.pos_,
|
157 |
+
'tag': token.tag_,
|
158 |
+
'dep': token.dep_,
|
159 |
+
'shape': token.shape_,
|
160 |
+
'is_alpha': token.is_alpha,
|
161 |
+
'is_stop': token.is_stop,
|
162 |
+
'morph': str(token.morph)
|
163 |
+
})
|
164 |
+
return morphology_analysis
|
165 |
+
|
166 |
+
#################################################################################################
|
167 |
+
def get_sentence_structure_analysis(doc):
|
168 |
+
"""
|
169 |
+
Analiza la estructura de las oraciones en el texto.
|
170 |
+
"""
|
171 |
+
sentence_analysis = []
|
172 |
+
for sent in doc.sents:
|
173 |
+
sentence_analysis.append({
|
174 |
+
'text': sent.text,
|
175 |
+
'root': sent.root.text,
|
176 |
+
'root_pos': sent.root.pos_,
|
177 |
+
'num_tokens': len(sent),
|
178 |
+
'num_words': len([token for token in sent if token.is_alpha]),
|
179 |
+
'subjects': [token.text for token in sent if "subj" in token.dep_],
|
180 |
+
'objects': [token.text for token in sent if "obj" in token.dep_],
|
181 |
+
'verbs': [token.text for token in sent if token.pos_ == "VERB"]
|
182 |
+
})
|
183 |
+
return sentence_analysis
|
184 |
+
|
185 |
+
#################################################################################################
|
186 |
+
def perform_advanced_morphosyntactic_analysis(text, nlp):
|
187 |
+
"""
|
188 |
+
Realiza un análisis morfosintáctico avanzado del texto.
|
189 |
+
"""
|
190 |
+
try:
|
191 |
+
# Verificar el idioma del modelo
|
192 |
+
model_lang = nlp.lang
|
193 |
+
logger.info(f"Realizando análisis con modelo de idioma: {model_lang}")
|
194 |
+
|
195 |
+
# Procesar el texto con el modelo específico del idioma
|
196 |
+
doc = nlp(text)
|
197 |
+
|
198 |
+
# Realizar análisis específico según el idioma
|
199 |
+
return {
|
200 |
+
'doc': doc,
|
201 |
+
'pos_analysis': get_detailed_pos_analysis(doc),
|
202 |
+
'morphological_analysis': get_morphological_analysis(doc),
|
203 |
+
'sentence_structure': get_sentence_structure_analysis(doc),
|
204 |
+
'arc_diagrams': generate_arc_diagram(doc), # Quitamos nlp.lang
|
205 |
+
'repeated_words': get_repeated_words_colors(doc),
|
206 |
+
'highlighted_text': highlight_repeated_words(doc, get_repeated_words_colors(doc))
|
207 |
+
}
|
208 |
+
except Exception as e:
|
209 |
+
logger.error(f"Error en análisis morfosintáctico: {str(e)}")
|
210 |
+
return None
|
211 |
+
|
212 |
+
# Al final del archivo morph_analysis.py
|
213 |
+
__all__ = [
|
214 |
+
'perform_advanced_morphosyntactic_analysis',
|
215 |
+
'get_repeated_words_colors',
|
216 |
+
'highlight_repeated_words',
|
217 |
+
'generate_arc_diagram',
|
218 |
+
'get_detailed_pos_analysis',
|
219 |
+
'get_morphological_analysis',
|
220 |
+
'get_sentence_structure_analysis',
|
221 |
+
'POS_COLORS',
|
222 |
+
'POS_TRANSLATIONS'
|
223 |
+
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|