Upload app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import numpy as np
|
| 2 |
+
from gensim.models import Word2Vec
|
| 3 |
+
import gradio as gr
|
| 4 |
+
from sklearn.decomposition import PCA
|
| 5 |
+
import plotly.graph_objects as go
|
| 6 |
+
import nltk
|
| 7 |
+
from nltk.tokenize import word_tokenize
|
| 8 |
+
from nltk.tag import pos_tag
|
| 9 |
+
|
| 10 |
+
nltk.download('punkt')
|
| 11 |
+
nltk.download('averaged_perceptron_tagger')
|
| 12 |
+
|
| 13 |
+
# Word2Vec ๋ชจ๋ธ ํ์ต ํจ์
|
| 14 |
+
def train_word2vec(sentences):
|
| 15 |
+
model = Word2Vec(sentences, vector_size=100, window=5, min_count=1)
|
| 16 |
+
return model
|
| 17 |
+
|
| 18 |
+
def preprocess_text(file_path):
|
| 19 |
+
with open(file_path, 'r', encoding='utf-8') as file:
|
| 20 |
+
text = file.read()
|
| 21 |
+
|
| 22 |
+
# ํ ํฐํ ๋ฐ ํ์ฌ ํ๊น
|
| 23 |
+
tokens = word_tokenize(text)
|
| 24 |
+
tagged = pos_tag(tokens)
|
| 25 |
+
|
| 26 |
+
# ๋ช
์ฌ๋ง ์ถ์ถ (NN, NNS, NNP, NNPS)
|
| 27 |
+
nouns = [word.lower() for word, pos in tagged if pos.startswith('NN')]
|
| 28 |
+
|
| 29 |
+
# ์ค๋ณต ์ ๊ฑฐ ๋ฐ ์ ๋ ฌ
|
| 30 |
+
unique_nouns = sorted(set(nouns))
|
| 31 |
+
|
| 32 |
+
# ๊ฐ๋จํ ๋ฌธ์ฅ ์์ฑ (๊ฐ ๋ช
์ฌ๋ฅผ ๊ฐ๋ณ ๋ฌธ์ฅ์ผ๋ก ์ทจ๊ธ)
|
| 33 |
+
sentences = [[noun] for noun in unique_nouns]
|
| 34 |
+
|
| 35 |
+
return sentences, unique_nouns
|
| 36 |
+
|
| 37 |
+
def apply_pca(word_vectors):
|
| 38 |
+
pca = PCA(n_components=3)
|
| 39 |
+
return pca.fit_transform(word_vectors)
|
| 40 |
+
|
| 41 |
+
def process_text(file_path, target_word):
|
| 42 |
+
# ์ ์ฒ๋ฆฌ
|
| 43 |
+
sentences, unique_words = preprocess_text(file_path)
|
| 44 |
+
|
| 45 |
+
# Word2Vec ๋ชจ๋ธ ํ์ต
|
| 46 |
+
model = train_word2vec(sentences)
|
| 47 |
+
|
| 48 |
+
# ๊ฐ ๋จ์ด์ ์๋ฒ ๋ฉ ๋ฒกํฐ ์ถ์ถ
|
| 49 |
+
word_vectors = np.array([model.wv[word] for word in unique_words])
|
| 50 |
+
|
| 51 |
+
# PCA๋ก ์ฐจ์ ์ถ์
|
| 52 |
+
word_vectors_3d = apply_pca(word_vectors)
|
| 53 |
+
|
| 54 |
+
# ์์ ์ค์ (ํฌ๋ช
๋ ์ถ๊ฐ)
|
| 55 |
+
colors = ['rgba(128, 128, 128, 0.3)' if word != target_word else 'rgba(255, 0, 0, 1)' for word in unique_words]
|
| 56 |
+
|
| 57 |
+
# ๊ฐ์ฅ ๊ฐ๊น์ด ๋จ์ด 10๊ฐ ์ฐพ๊ธฐ
|
| 58 |
+
if target_word in model.wv:
|
| 59 |
+
similar_words = model.wv.most_similar(target_word, topn=10)
|
| 60 |
+
similar_word_indices = [unique_words.index(word) for word, _ in similar_words]
|
| 61 |
+
for idx in similar_word_indices:
|
| 62 |
+
colors[idx] = 'rgba(0, 255, 0, 1)' # ๊ฐ๊น์ด ๋จ์ด๋ค์ ์ด๋ก์์ผ๋ก ํ์
|
| 63 |
+
|
| 64 |
+
# Plotly๋ฅผ ์ฌ์ฉํ 3D ์ฐ์ ๋ ์์ฑ
|
| 65 |
+
fig = go.Figure(data=[go.Scatter3d(
|
| 66 |
+
x=word_vectors_3d[:, 0],
|
| 67 |
+
y=word_vectors_3d[:, 1],
|
| 68 |
+
z=word_vectors_3d[:, 2],
|
| 69 |
+
mode='markers+text',
|
| 70 |
+
text=unique_words,
|
| 71 |
+
textposition="top center",
|
| 72 |
+
marker=dict(
|
| 73 |
+
size=8,
|
| 74 |
+
color=colors,
|
| 75 |
+
)
|
| 76 |
+
)])
|
| 77 |
+
|
| 78 |
+
fig.update_layout(
|
| 79 |
+
title="Word Embeddings 3D Visualization",
|
| 80 |
+
scene=dict(
|
| 81 |
+
xaxis_title="PCA 1",
|
| 82 |
+
yaxis_title="PCA 2",
|
| 83 |
+
zaxis_title="PCA 3"
|
| 84 |
+
),
|
| 85 |
+
width=800,
|
| 86 |
+
height=800
|
| 87 |
+
)
|
| 88 |
+
|
| 89 |
+
# ๊ฐ์ฅ ๊ฐ๊น์ด ๋จ์ด 10๊ฐ ๋ชฉ๋ก ์์ฑ
|
| 90 |
+
similar_words_text = ""
|
| 91 |
+
if target_word in model.wv:
|
| 92 |
+
similar_words_text = "๊ฐ์ฅ ๊ฐ๊น์ด ๋จ์ด 10๊ฐ:\n" + "\n".join([f"{word}: {score:.4f}" for word, score in similar_words])
|
| 93 |
+
|
| 94 |
+
return fig, similar_words_text
|
| 95 |
+
|
| 96 |
+
# Gradio ์ธํฐํ์ด์ค ์์
|
| 97 |
+
with gr.Blocks() as iface:
|
| 98 |
+
gr.Markdown("# Word Embedding 3D ์๊ฐํ")
|
| 99 |
+
gr.Markdown("ํ
์คํธ ํ์ผ(.txt)์ ์
๋ก๋ํ๊ณ ๊ฐ์กฐํ ๋จ์ด๋ฅผ ์
๋ ฅํ์ธ์. Word2Vec๊ณผ PCA๋ฅผ ์ฌ์ฉํ์ฌ ๋จ์ด ์๋ฒ ๋ฉ์ 3D๋ก ์๊ฐํํฉ๋๋ค. ์
๋ ฅํ ๋จ์ด๋ ๋นจ๊ฐ์์ผ๋ก, ๊ฐ์ฅ ์ ์ฌํ 10๊ฐ ๋จ์ด๋ ์ด๋ก์์ผ๋ก ๊ฐ์กฐ๋ฉ๋๋ค. ์ ์ฌํ ๋จ์ด ๋ชฉ๋ก์ ๊ทธ๋ํ ์๋์ ํ์๋ฉ๋๋ค.")
|
| 100 |
+
|
| 101 |
+
with gr.Row():
|
| 102 |
+
file_input = gr.File(label="ํ
์คํธ ํ์ผ ์
๋ก๋ (.txt)", file_types=[".txt"])
|
| 103 |
+
word_input = gr.Textbox(label="๊ฐ์กฐํ ๋จ์ด ์
๋ ฅ")
|
| 104 |
+
|
| 105 |
+
submit_btn = gr.Button("์ ์ถ")
|
| 106 |
+
|
| 107 |
+
plot_output = gr.Plot(label="Word Embedding 3D ์๊ฐํ")
|
| 108 |
+
similar_words_output = gr.Textbox(label="์ ์ฌํ ๋จ์ด")
|
| 109 |
+
|
| 110 |
+
submit_btn.click(
|
| 111 |
+
fn=process_text,
|
| 112 |
+
inputs=[file_input, word_input],
|
| 113 |
+
outputs=[plot_output, similar_words_output]
|
| 114 |
+
)
|
| 115 |
+
|
| 116 |
+
if __name__ == "__main__":
|
| 117 |
+
iface.launch()
|