File size: 10,320 Bytes
c58df45 |
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 |
import spacy
from spacy import displacy
from streamlit.components.v1 import html
import base64
from collections import Counter
import re
from ..utils.widget_utils import generate_unique_key
import logging
logger = logging.getLogger(__name__)
# Define colors for grammatical categories
POS_COLORS = {
'ADJ': '#FFA07A', # Light Salmon
'ADP': '#98FB98', # Pale Green
'ADV': '#87CEFA', # Light Sky Blue
'AUX': '#DDA0DD', # Plum
'CCONJ': '#F0E68C', # Khaki
'DET': '#FFB6C1', # Light Pink
'INTJ': '#FF6347', # Tomato
'NOUN': '#90EE90', # Light Green
'NUM': '#FAFAD2', # Light Goldenrod Yellow
'PART': '#D3D3D3', # Light Gray
'PRON': '#FFA500', # Orange
'PROPN': '#20B2AA', # Light Sea Green
'SCONJ': '#DEB887', # Burlywood
'SYM': '#7B68EE', # Medium Slate Blue
'VERB': '#FF69B4', # Hot Pink
'X': '#A9A9A9', # Dark Gray
}
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',
}
}
def generate_arc_diagram(doc):
arc_diagrams = []
for sent in doc.sents:
words = [token.text for token in sent]
# Calculamos el ancho del SVG basado en la longitud de la oración
svg_width = max(100, len(words) * 120)
# Altura fija para cada oración
svg_height = 300 # Controla la altura del SVG
# Renderizamos el diagrama de dependencias
html = displacy.render(sent, style="dep", options={
"add_lemma":False, # Introduced in version 2.2.4, this argument prints the lemma’s in a separate row below the token texts.
"arrow_spacing": 12, #This argument is used for adjusting the spacing between arrows in px to avoid overlaps.
"arrow_width": 2, #This argument is used for adjusting the width of arrow head in px.
"arrow_stroke": 2, #This argument is used for adjusting the width of arrow path in px.
"collapse_punct": True, #It attaches punctuation to the tokens.
"collapse_phrases": False, # This argument merges the noun phrases into one token.
"compact":False, # If you will take this argument as true, you will get the “Compact mode” with square arrows that takes up less space.
"color": "#ffffff",
"bg": "#0d6efd",
"compact": False, #Put the value of this argument True, if you want to use fine-grained part-of-speech tags (Token.tag_), instead of coarse-grained tags (Token.pos_).
"distance": 100, # Aumentamos la distancia entre palabras
"fine_grained": False, #Put the value of this argument True, if you want to use fine-grained part-of-speech tags (Token.tag_), instead of coarse-grained tags (Token.pos_).
"offset_x": 0, # This argument is used for spacing on left side of the SVG in px.
"word_spacing": 25, #This argument is used for adjusting the vertical spacing between words and arcs in px.
})
# Ajustamos el tamaño del SVG y el viewBox
html = re.sub(r'width="(\d+)"', f'width="{svg_width}"', html)
html = re.sub(r'height="(\d+)"', f'height="{svg_height}"', html)
html = re.sub(r'<svg', f'<svg viewBox="0 0 {svg_width} {svg_height}"', html)
#html = re.sub(r'<svg[^>]*>', lambda m: m.group(0).replace('height="450"', 'height="300"'), html)
#html = re.sub(r'<g [^>]*transform="translate\((\d+),(\d+)\)"', lambda m: f'<g transform="translate({m.group(1)},50)"', html)
# Movemos todo el contenido hacia abajo
#html = html.replace('<g', f'<g transform="translate(50, {svg_height - 200})"')
# Movemos todo el contenido hacia arriba para eliminar el espacio vacío en la parte superior
html = re.sub(r'<g transform="translate\((\d+),(\d+)\)"',
lambda m: f'<g transform="translate({m.group(1)},10)"', html)
# Ajustamos la posición de las etiquetas de las palabras
html = html.replace('dy="1em"', 'dy="-1em"')
# Ajustamos la posición de las etiquetas POS
html = html.replace('dy="0.25em"', 'dy="-3em"')
# Aumentamos el tamaño de la fuente para las etiquetas POS
html = html.replace('.displacy-tag {', '.displacy-tag { font-size: 14px;')
# Rotamos las etiquetas de las palabras para mejorar la legibilidad
#html = html.replace('class="displacy-label"', 'class="displacy-label" transform="rotate(30)"')
arc_diagrams.append(html)
return arc_diagrams
##################################################################################################################################
def perform_advanced_morphosyntactic_analysis(text, nlp):
logger.info(f"Performing advanced morphosyntactic analysis on text: {text[:50]}...")
try:
doc = nlp(text)
arc_diagram = generate_arc_diagram(doc)
logger.info(f"Arc diagram generated: {arc_diagram is not None}")
logger.debug(f"Arc diagram content: {arc_diagram[:500] if arc_diagram else 'None'}")
# Asegurar que arc_diagram sea una lista
if not isinstance(arc_diagram, list):
logger.warning("Warning: arc_diagram is not a list. Type: %s", type(arc_diagram))
arc_diagram = [arc_diagram] if arc_diagram else []
result = {
'arc_diagram': arc_diagram,
'pos_analysis': perform_pos_analysis(doc),
'morphological_analysis': perform_morphological_analysis(doc),
'sentence_structure': analyze_sentence_structure(doc),
'repeated_words': highlight_repeated_words(doc)
}
logger.info(f"Analysis result keys: {result.keys()}")
logger.info(f"Arc diagram in result: {result['arc_diagram'] is not None}")
return result
except Exception as e:
logger.error(f"Error in perform_advanced_morphosyntactic_analysis: {str(e)}", exc_info=True)
return None
###########################################################
def perform_pos_analysis(doc):
pos_counts = Counter(token.pos_ for token in doc)
total_tokens = len(doc)
pos_analysis = []
for pos, count in pos_counts.items():
percentage = (count / total_tokens) * 100
pos_analysis.append({
'pos': pos,
'count': count,
'percentage': round(percentage, 2),
'examples': [token.text for token in doc if token.pos_ == pos][:5] # Primeros 5 ejemplos
})
return sorted(pos_analysis, key=lambda x: x['count'], reverse=True)
def perform_morphological_analysis(doc):
return [{
'text': token.text,
'lemma': token.lemma_,
'pos': token.pos_,
'tag': token.tag_,
'dep': token.dep_,
'shape': token.shape_,
'is_alpha': token.is_alpha,
'is_stop': token.is_stop,
'morph': str(token.morph)
} for token in doc if token.pos_ in ['NOUN', 'VERB', 'ADJ', 'ADV']]
def analyze_sentence_structure(doc):
return [{
'text': sent.text,
'root': sent.root.text,
'root_pos': sent.root.pos_,
'num_tokens': len(sent),
'num_words': len([token for token in sent if token.is_alpha]),
'subjects': [token.text for token in sent if "subj" in token.dep_],
'objects': [token.text for token in sent if "obj" in token.dep_],
'verbs': [token.text for token in sent if token.pos_ == "VERB"]
} for sent in doc.sents]
def get_repeated_words_colors(doc):
word_counts = Counter(token.text.lower() for token in doc if token.pos_ != 'PUNCT')
repeated_words = {word: count for word, count in word_counts.items() if count > 1}
word_colors = {}
for token in doc:
if token.text.lower() in repeated_words:
word_colors[token.text.lower()] = POS_COLORS.get(token.pos_, '#FFFFFF')
return word_colors
def highlight_repeated_words(doc):
word_colors = get_repeated_words_colors(doc)
highlighted_text = []
for token in doc:
if token.text.lower() in word_colors:
color = word_colors[token.text.lower()]
highlighted_text.append(f'<span style="background-color: {color};">{token.text}</span>')
else:
highlighted_text.append(token.text)
return ' '.join(highlighted_text)
# Exportar todas las funciones y variables necesarias
__all__ = [
'get_repeated_words_colors',
'highlight_repeated_words',
'generate_arc_diagram',
'perform_pos_analysis',
'perform_morphological_analysis',
'analyze_sentence_structure',
'perform_advanced_morphosyntactic_analysis',
'POS_COLORS',
'POS_TRANSLATIONS'
] |