Update modules/text_analysis/discourse_analysis.py
Browse files
modules/text_analysis/discourse_analysis.py
CHANGED
@@ -18,6 +18,9 @@ from .semantic_analysis import (
|
|
18 |
POS_TRANSLATIONS,
|
19 |
ENTITY_LABELS
|
20 |
)
|
|
|
|
|
|
|
21 |
#####################
|
22 |
# Define colors for grammatical categories
|
23 |
POS_COLORS = {
|
@@ -75,98 +78,6 @@ ENTITY_LABELS = {
|
|
75 |
}
|
76 |
}
|
77 |
|
78 |
-
CUSTOM_STOPWORDS = {
|
79 |
-
'es': {
|
80 |
-
# Artículos
|
81 |
-
'el', 'la', 'los', 'las', 'un', 'una', 'unos', 'unas',
|
82 |
-
# Preposiciones comunes
|
83 |
-
'a', 'ante', 'bajo', 'con', 'contra', 'de', 'desde', 'en',
|
84 |
-
'entre', 'hacia', 'hasta', 'para', 'por', 'según', 'sin',
|
85 |
-
'sobre', 'tras', 'durante', 'mediante',
|
86 |
-
# Conjunciones
|
87 |
-
'y', 'e', 'ni', 'o', 'u', 'pero', 'sino', 'porque',
|
88 |
-
# Pronombres
|
89 |
-
'yo', 'tú', 'él', 'ella', 'nosotros', 'vosotros', 'ellos',
|
90 |
-
'ellas', 'este', 'esta', 'ese', 'esa', 'aquel', 'aquella',
|
91 |
-
# Verbos auxiliares comunes
|
92 |
-
'ser', 'estar', 'haber', 'tener',
|
93 |
-
# Palabras comunes en textos académicos
|
94 |
-
'además', 'también', 'asimismo', 'sin embargo', 'no obstante',
|
95 |
-
'por lo tanto', 'entonces', 'así', 'luego', 'pues',
|
96 |
-
# Números escritos
|
97 |
-
'uno', 'dos', 'tres', 'primer', 'primera', 'segundo', 'segunda',
|
98 |
-
# Otras palabras comunes
|
99 |
-
'cada', 'todo', 'toda', 'todos', 'todas', 'otro', 'otra',
|
100 |
-
'donde', 'cuando', 'como', 'que', 'cual', 'quien',
|
101 |
-
'cuyo', 'cuya', 'hay', 'solo', 'ver', 'si', 'no',
|
102 |
-
# Símbolos y caracteres especiales
|
103 |
-
'#', '@', '/', '*', '+', '-', '=', '$', '%'
|
104 |
-
},
|
105 |
-
'en': {
|
106 |
-
# Articles
|
107 |
-
'the', 'a', 'an',
|
108 |
-
# Common prepositions
|
109 |
-
'in', 'on', 'at', 'by', 'for', 'with', 'about', 'against',
|
110 |
-
'between', 'into', 'through', 'during', 'before', 'after',
|
111 |
-
'above', 'below', 'to', 'from', 'up', 'down', 'of',
|
112 |
-
# Conjunctions
|
113 |
-
'and', 'or', 'but', 'nor', 'so', 'for', 'yet',
|
114 |
-
# Pronouns
|
115 |
-
'i', 'you', 'he', 'she', 'it', 'we', 'they', 'this',
|
116 |
-
'that', 'these', 'those', 'my', 'your', 'his', 'her',
|
117 |
-
# Auxiliary verbs
|
118 |
-
'be', 'am', 'is', 'are', 'was', 'were', 'been', 'have',
|
119 |
-
'has', 'had', 'do', 'does', 'did',
|
120 |
-
# Common academic words
|
121 |
-
'therefore', 'however', 'thus', 'hence', 'moreover',
|
122 |
-
'furthermore', 'nevertheless',
|
123 |
-
# Numbers written
|
124 |
-
'one', 'two', 'three', 'first', 'second', 'third',
|
125 |
-
# Other common words
|
126 |
-
'where', 'when', 'how', 'what', 'which', 'who',
|
127 |
-
'whom', 'whose', 'there', 'here', 'just', 'only',
|
128 |
-
# Symbols and special characters
|
129 |
-
'#', '@', '/', '*', '+', '-', '=', '$', '%'
|
130 |
-
},
|
131 |
-
'fr': {
|
132 |
-
# Articles
|
133 |
-
'le', 'la', 'les', 'un', 'une', 'des',
|
134 |
-
# Prepositions
|
135 |
-
'à', 'de', 'dans', 'sur', 'en', 'par', 'pour', 'avec',
|
136 |
-
'sans', 'sous', 'entre', 'derrière', 'chez', 'avant',
|
137 |
-
# Conjunctions
|
138 |
-
'et', 'ou', 'mais', 'donc', 'car', 'ni', 'or',
|
139 |
-
# Pronouns
|
140 |
-
'je', 'tu', 'il', 'elle', 'nous', 'vous', 'ils',
|
141 |
-
'elles', 'ce', 'cette', 'ces', 'celui', 'celle',
|
142 |
-
# Auxiliary verbs
|
143 |
-
'être', 'avoir', 'faire',
|
144 |
-
# Academic words
|
145 |
-
'donc', 'cependant', 'néanmoins', 'ainsi', 'toutefois',
|
146 |
-
'pourtant', 'alors',
|
147 |
-
# Numbers
|
148 |
-
'un', 'deux', 'trois', 'premier', 'première', 'second',
|
149 |
-
# Other common words
|
150 |
-
'où', 'quand', 'comment', 'que', 'qui', 'quoi',
|
151 |
-
'quel', 'quelle', 'plus', 'moins',
|
152 |
-
# Symbols
|
153 |
-
'#', '@', '/', '*', '+', '-', '=', '$', '%'
|
154 |
-
}
|
155 |
-
}
|
156 |
-
|
157 |
-
##############################################################################################################
|
158 |
-
def get_stopwords(lang_code):
|
159 |
-
"""
|
160 |
-
Obtiene el conjunto de stopwords para un idioma específico.
|
161 |
-
Combina las stopwords de spaCy con las personalizadas.
|
162 |
-
"""
|
163 |
-
try:
|
164 |
-
nlp = spacy.load(f'{lang_code}_core_news_sm')
|
165 |
-
spacy_stopwords = nlp.Defaults.stop_words
|
166 |
-
custom_stopwords = CUSTOM_STOPWORDS.get(lang_code, set())
|
167 |
-
return spacy_stopwords.union(custom_stopwords)
|
168 |
-
except:
|
169 |
-
return CUSTOM_STOPWORDS.get(lang_code, set())
|
170 |
|
171 |
#################
|
172 |
def compare_semantic_analysis(text1, text2, nlp, lang):
|
|
|
18 |
POS_TRANSLATIONS,
|
19 |
ENTITY_LABELS
|
20 |
)
|
21 |
+
|
22 |
+
from .stopwords import get_custom_stopwords
|
23 |
+
|
24 |
#####################
|
25 |
# Define colors for grammatical categories
|
26 |
POS_COLORS = {
|
|
|
78 |
}
|
79 |
}
|
80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
|
82 |
#################
|
83 |
def compare_semantic_analysis(text1, text2, nlp, lang):
|