File size: 5,310 Bytes
7701918 |
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 |
import gradio as gr
import nltk
from nltk.tokenize import sent_tokenize, word_tokenize
from nltk.corpus import stopwords, wordnet, brown
from nltk.stem import PorterStemmer, WordNetLemmatizer
from nltk import pos_tag, ne_chunk, ngrams
from nltk.collocations import BigramCollocationFinder
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import movie_reviews
import random
# Tải các tài nguyên cần thiết
nltk.download('punkt')
nltk.download('punkt_tab')
nltk.download('averaged_perceptron_tagger')
nltk.download('maxent_ne_chunker')
nltk.download('words')
nltk.download('stopwords')
nltk.download('wordnet')
nltk.download('brown')
nltk.download('movie_reviews')
# Khởi tạo các công cụ
stemmer = PorterStemmer()
lemmatizer = WordNetLemmatizer()
stop_words = set(stopwords.words('english'))
# Hàm huấn luyện classifier đơn giản
def train_classifier():
pos_reviews = [({"word": word}, 'positive') for word in movie_reviews.words('pos')[:100]]
neg_reviews = [({"word": word}, 'negative') for word in movie_reviews.words('neg')[:100]]
train_set = pos_reviews + neg_reviews
random.shuffle(train_set)
return NaiveBayesClassifier.train(train_set)
classifier = train_classifier()
# Hàm chính xử lý các chức năng
def nlp_tool(input_text, function):
if not input_text:
return "Vui lòng nhập văn bản!"
if function == "Sentence Tokenization":
return "\n".join(sent_tokenize(input_text))
elif function == "Word Tokenization":
return "\n".join(word_tokenize(input_text))
elif function == "Part-of-Speech Tagging":
words = word_tokenize(input_text)
return "\n".join([f"{word}: {tag}" for word, tag in pos_tag(words)])
elif function == "Stemming":
words = word_tokenize(input_text)
return "\n".join([stemmer.stem(word) for word in words])
elif function == "Lemmatization":
words = word_tokenize(input_text)
return "\n".join([lemmatizer.lemmatize(word) for word in words])
elif function == "Remove Stop Words":
words = word_tokenize(input_text)
return "\n".join([word for word in words if word.lower() not in stop_words])
elif function == "Named Entity Recognition":
words = word_tokenize(input_text)
pos_tags = pos_tag(words)
entities = ne_chunk(pos_tags)
return str(entities)
elif function == "Text Classification":
words = word_tokenize(input_text)
result = classifier.classify({word: True for word in words})
return f"Sentiment: {result}"
elif function == "N-grams (Bigrams)":
words = word_tokenize(input_text)
bigrams = list(ngrams(words, 2))
return "\n".join([f"{w1} - {w2}" for w1, w2 in bigrams])
elif function == "Collocations":
words = word_tokenize(input_text)
finder = BigramCollocationFinder.from_words(words)
collocations = finder.nbest(nltk.collocations.BigramAssocMeasures().pmi, 5)
return "\n".join([f"{w1} - {w2}" for w1, w2 in collocations])
elif function == "WordNet Synsets":
words = word_tokenize(input_text)
first_word = words[0] if words else ""
synsets = wordnet.synsets(first_word)
if synsets:
return f"Definition: {synsets[0].definition()}\nExamples: {synsets[0].examples()}"
return "Không tìm thấy từ trong WordNet!"
elif function == "Sample from Brown Corpus":
return " ".join(brown.words()[:50])
return "Chức năng chưa được triển khai!"
# Tạo giao diện Gradio
with gr.Blocks(theme=gr.themes.Soft()) as demo:
gr.Markdown(
"""
# Công cụ xử lý ngôn ngữ tự nhiên với NLTK
Nhập văn bản và chọn chức năng để khám phá các khả năng của NLTK!
"""
)
with gr.Row():
with gr.Column(scale=1):
input_text = gr.Textbox(
label="Nhập văn bản",
placeholder="Ví dụ: I love coding in Python.",
lines=5
)
function_dropdown = gr.Dropdown(
label="Chọn chức năng",
choices=[
"Sentence Tokenization",
"Word Tokenization",
"Part-of-Speech Tagging",
"Stemming",
"Lemmatization",
"Remove Stop Words",
"Named Entity Recognition",
"Text Classification",
"N-grams (Bigrams)",
"Collocations",
"WordNet Synsets",
"Sample from Brown Corpus"
],
value="Sentence Tokenization"
)
submit_btn = gr.Button("Xử lý", variant="primary")
with gr.Column(scale=2):
output_text = gr.Textbox(
label="Kết quả",
lines=10,
interactive=False
)
# Kết nối nút bấm với hàm xử lý
submit_btn.click(
fn=nlp_tool,
inputs=[input_text, function_dropdown],
outputs=output_text
)
# Chạy giao diện
demo.launch() |