File size: 3,970 Bytes
e39e070 8a20582 e39e070 a6b40c5 e39e070 a6b40c5 e39e070 8a20582 e39e070 8a20582 e39e070 8a20582 5217f33 8a20582 |
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 |
# /modules/morpho_analysis.py
import spacy
from collections import Counter
from spacy import displacy
import re
# 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': 'Adposici贸n',
'ADV': 'Adverbio',
'AUX': 'Auxiliar',
'CCONJ': 'Conjunci贸n Coordinante',
'DET': 'Determinante',
'INTJ': 'Interjecci贸n',
'NOUN': 'Sustantivo',
'NUM': 'N煤mero',
'PART': 'Part铆cula',
'PRON': 'Pronombre',
'PROPN': 'Nombre Propio',
'SCONJ': 'Conjunci贸n Subordinante',
'SYM': 'S铆mbolo',
'VERB': 'Verbo',
'X': 'Otro',
},
'en': {
'ADJ': 'Adjective',
'ADP': 'Adposition',
'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': 'Adposition',
'ADV': 'Adverbe',
'AUX': 'Auxiliaire',
'CCONJ': 'Conjonction de Coordination',
'DET': 'D茅terminant',
'INTJ': 'Interjection',
'NOUN': 'Nom',
'NUM': 'Nombre',
'PART': 'Particule',
'PRON': 'Pronom',
'PROPN': 'Nom Propre',
'SCONJ': 'Conjonction de Subordination',
'SYM': 'Symbole',
'VERB': 'Verbe',
'X': 'Autre',
}
}
#############################################################################################
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):
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)
#################################################################################################
def generate_arc_diagram(doc, lang_code):
sentences = list(doc.sents)
arc_diagrams = []
for sent in sentences:
html = displacy.render(sent, style="dep", options={"distance": 100})
html = html.replace('height="375"', 'height="200"')
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)
arc_diagrams.append(html)
return arc_diagrams |