word2vec / app.py
kkosmi's picture
Update app.py
1432ce2 verified
import numpy as np
import pandas as pd
import random
from gensim.models import Word2Vec
import gradio as gr
from sklearn.decomposition import PCA
import plotly.graph_objects as go
# Word2Vec ๋ชจ๋ธ ํ•™์Šต ํ•จ์ˆ˜
def train_word2vec(sentences):
# model = Word2Vec(sentences, vector_size=100, window=4, min_count=6, workers=4, sg=0, epochs=100)
model = Word2Vec(sentences, vector_size=50, window=4, min_count=1, sg=0, epochs=100)
return model
def apply_pca(word_vectors):
pca = PCA(n_components=3)
return pca.fit_transform(word_vectors)
def get_unique(model):
vocablist1=list(model.wv.index_to_key)
vocablist =[]
for i in vocablist1:
vocablist.append(i)
return vocablist
def train_model(sentence):
# ์ „์ฒ˜๋ฆฌ
sentences=sentence
# Word2Vec ๋ชจ๋ธ ํ•™์Šต
model = train_word2vec(sentences)
unique_words = get_unique(model)
return model, unique_words
def process_text(target_word):
target_word =target_word.lower() #################
# Word2Vec ๋ชจ๋ธ ๋กœ๋“œ
model = Word2Vec.load("word2vec.model")
unique_words = get_unique(model)
# ๊ฐ ๋‹จ์–ด์˜ ์ž„๋ฒ ๋”ฉ ๋ฒกํ„ฐ ์ถ”์ถœ
word_vectors = np.array([model.wv[word] for word in unique_words])
# PCA๋กœ ์ฐจ์› ์ถ•์†Œ
word_vectors_3d = apply_pca(word_vectors)
# ์ƒ‰์ƒ ์„ค์ • (ํˆฌ๋ช…๋„ ์ถ”๊ฐ€)
colors = ['rgba(255, 255, 255, 0.15)' if word != target_word else 'rgba(255, 20, 147, 0.9)' for word in unique_words]
# ๊ฐ€์žฅ ๊ฐ€๊นŒ์šด ๋‹จ์–ด 10๊ฐœ ์ฐพ๊ธฐ
if target_word in model.wv:
similar_words = model.wv.most_similar(target_word, topn=10)
similar_word_indices = [unique_words.index(word) for word, _ in similar_words]
for idx in similar_word_indices:
colors[idx] = 'rgba(255, 165, 0, 1)' # ๊ฐ€๊นŒ์šด ๋‹จ์–ด๋“ค์„ ์ฃผํ™ฉ์ƒ‰์œผ๋กœ ํ‘œ์‹œ
# ๊ฐ€์žฅ ๋จผ ๋‹จ์–ด 10๊ฐœ ์ฐพ๊ธฐ
if target_word in model.wv:
all_words = model.wv.index_to_key # ๋ชจ๋ธ์— ํฌํ•จ๋œ ๋ชจ๋“  ๋‹จ์–ด ๋ฆฌ์ŠคํŠธ
dissimilar_words = sorted(
[(word, model.wv.similarity(target_word, word)) for word in all_words if word != target_word],
key=lambda x: x[1]
)[:10] # ์œ ์‚ฌ๋„๊ฐ€ ๊ฐ€์žฅ ๋‚ฎ์€ 10๊ฐœ ๋‹จ์–ด ์„ ํƒ
dissimilar_word_indices = [unique_words.index(word) for word, _ in dissimilar_words]
for idx in dissimilar_word_indices:
colors[idx] = 'rgba(138, 43, 226, 0.8)' # ๊ฐ€์žฅ ๋จผ ๋‹จ์–ด๋“ค์„ ๋ณด๋ผ์ƒ‰์œผ๋กœ ํ‘œ์‹œ
# Plotly๋ฅผ ์‚ฌ์šฉํ•œ 3D ์‚ฐ์ ๋„ ์ƒ์„ฑ
fig = go.Figure(data=[go.Scatter3d(
x=word_vectors_3d[:, 0],
y=word_vectors_3d[:, 1],
z=word_vectors_3d[:, 2],
mode='markers+text',
text=unique_words,
textposition="top center",
marker=dict(
size=4,
color=colors,
)
)])
fig.update_layout(
title="Word Embeddings 3D Visualization",
scene=dict(
xaxis_title="X",
yaxis_title="Y",
zaxis_title="Z"
),
width=1100,
height=900
)
# ๊ฐ€์žฅ ๊ฐ€๊นŒ์šด ๋‹จ์–ด 10๊ฐœ ๋ชฉ๋ก ์ƒ์„ฑ
similar_words_text = ""
if target_word in model.wv:
similar_words_text = "\n".join([f"{word}: {score:.4f}" for word, score in similar_words])
dissimlar_words_Text=""
if target_word in model.wv:
dissimilar_words_text = "\n".join([f"{word}: {score:.4f}" for word, score in dissimilar_words])
return fig, similar_words_text, dissimilar_words_text
# Gradio ์ธํ„ฐํŽ˜์ด์Šค ์ˆ˜์ •
with gr.Blocks(css="""
#input-box {
background-color: #ffeef3; /* ์—ฐํ•œ ํŒŒ์Šคํ…” ํ•‘ํฌ */
border: 2px solid #ffccd5; /* ์—ฐํ•œ ํ•‘ํฌ ํ…Œ๋‘๋ฆฌ */
color: #000; /* ํ…์ŠคํŠธ ์ƒ‰์ƒ */
border-radius: 8px; /* ๋‘ฅ๊ทผ ํ…Œ๋‘๋ฆฌ */
}
#submit-btn {
background-color: #ebfbea; /* ์—ฐํ•œ ํŒŒ์Šคํ…” ์—ฐ๋‘์ƒ‰ */
border: 2px solid #d6f5d6; /* ์—ฐํ•œ ์—ฐ๋‘์ƒ‰ ํ…Œ๋‘๋ฆฌ */
color: #000; /* ํ…์ŠคํŠธ ์ƒ‰์ƒ */
border-radius: 8px; /* ๋‘ฅ๊ทผ ํ…Œ๋‘๋ฆฌ */
}
#bulletin {
background-color: #eaf9ff; /* ์—ฐํ•œ ํŒŒ์Šคํ…” ํ•˜๋Š˜์ƒ‰ */
border: 2px solid #d3f0f7; /* ์—ฐํ•œ ํ•˜๋Š˜์ƒ‰ ํ…Œ๋‘๋ฆฌ */
color: #000; /* ํ…์ŠคํŠธ ์ƒ‰์ƒ */
border-radius: 8px; /* ๋‘ฅ๊ทผ ํ…Œ๋‘๋ฆฌ */
}
#similar-words {
background-color: #fff0e6; /* ์—ฐํ•œ ํŒŒ์Šคํ…” ์ฃผํ™ฉ์ƒ‰ */
border: 2px solid #ffe3cc; /* ์—ฐํ•œ ์ฃผํ™ฉ ํ…Œ๋‘๋ฆฌ */
color: #000; /* ํ…์ŠคํŠธ ์ƒ‰์ƒ */
border-radius: 8px; /* ๋‘ฅ๊ทผ ํ…Œ๋‘๋ฆฌ */
}
#dissimilar-words {
background-color: #f2e6ff; /* ์—ฐํ•œ ํŒŒ์Šคํ…” ๋ณด๋ผ์ƒ‰ */
border: 2px solid #e0ccff; /* ์—ฐํ•œ ๋ณด๋ผ ํ…Œ๋‘๋ฆฌ */
color: #000; /* ํ…์ŠคํŠธ ์ƒ‰์ƒ */
border-radius: 8px; /* ๋‘ฅ๊ทผ ํ…Œ๋‘๋ฆฌ */
}
label {
font-weight: bold; /* ์ œ๋ชฉ ๋ณผ๋“œ์ฒด */
}
""") as iface:
gr.Markdown("# <Inside Out 2> ๋‹จ์–ด ์˜๋ฏธ ์ง€๋„ 3D ์‹œ๊ฐํ™”")
# gr.Markdown("<Inside Out 2> ๋‹จ์–ด ์˜๋ฏธ ์ง€๋„(์ž„๋ฒ ๋”ฉ ๋ฒกํ„ฐ) 3D ์‹œ๊ฐํ™” ๋„๊ตฌ")
with gr.Row():
# ์‚ฌ์šฉ์ž ์ž…๋ ฅ ๋ฐ•์Šค๋ฅผ ๊ฐ•์กฐํ•˜๊ธฐ ์œ„ํ•ด ์Šคํƒ€์ผ์„ ๋ณ€๊ฒฝ
with gr.Column():
word_input = gr.Textbox(
label="**๋‹จ์–ด ์ž…๋ ฅ**",
elem_id="input-box",
placeholder="ex. emotion, puberty, hockey, friend, anxiety, memory, ...",
lines=1
)
submit_btn = gr.Button("์ œ์ถœ", elem_id="submit-btn")
bulletin = gr.Textbox(
label="์‚ฌ์šฉ๋ฒ• ์•ˆ๋‚ด",
interactive=False,
lines=4,
value=(
"1. ์†Œ์„ค์— ๋‚˜์˜จ ๋‹จ์–ด๋ฅผ ์ž…๋ ฅํ•˜๊ณ  [์ œ์ถœ]์ด๋‚˜ [Enter]๋ฅผ ๋ˆ„๋ฅด์„ธ์š”\n"
"2. ์ž…๋ ฅ ๋‹จ์–ด๋Š” ๋นจ๊ฐ„์ƒ‰, ๊ฐ€๊นŒ์šด ๋‹จ์–ด๋“ค์€ ์ฃผํ™ฉ์ƒ‰, ๋จผ ๋‹จ์–ด๋“ค์€ ๋ณด๋ผ์ƒ‰์œผ๋กœ ๊ฐ•์กฐ๋ฉ๋‹ˆ๋‹ค.\n"
"3. <Error>๊ฐ€ ๋‚˜ํƒ€๋‚˜๋Š” ๊ฒฝ์šฐ, ๋‹ค๋ฅธ ๋‹จ์–ด๋ฅผ ์ž…๋ ฅํ•ด๋ณด์„ธ์š”.\n"
"4. ๋งˆ์šฐ์Šค ๋“œ๋ž˜๊ทธ ๋ฐ ์Šคํฌ๋กค์„ ํ™œ์šฉํ•˜์—ฌ 3D ํ™”๋ฉด์„ ์‚ดํŽด๋ณด์„ธ์š”.\n"
"5. ๋‹จ์–ด ์ž…๋ ฅ์ฐฝ์— ๋‹ค๋ฅธ ๋‹จ์–ด๋“ค๋„ ์ž…๋ ฅํ•ด๋ณด์„ธ์š”."
),
elem_id="bulletin"
)
with gr.Row():
# ์‹œ๊ฐํ™” ํ™”๋ฉด์˜ ํฌ๊ธฐ๋ฅผ CSS๋กœ ์ฆ๊ฐ€
plot_output = gr.Plot(label="Word Embedding 3D ์‹œ๊ฐํ™”", elem_id="plot-box")
with gr.Column(scale=0.3): # ์ปฌ๋Ÿผ์˜ ๋„ˆ๋น„๋ฅผ ์ค„์ด๊ธฐ ์œ„ํ•ด scale ๊ฐ’์„ ๋‚ฎ์ถค
similar_words_output = gr.Textbox(
label="๊ฐ€์žฅ ๊ฐ€๊นŒ์šด ๋‹จ์–ด 10๊ฐœ",
interactive=False,
lines=5,
elem_id="similar-words"
)
dissimilar_words_output = gr.Textbox(
label="๊ฐ€์žฅ ๋จผ ๋‹จ์–ด 10๊ฐœ",
interactive=False,
lines=5,
elem_id="dissimilar-words"
)
submit_btn.click(
fn=process_text,
inputs=[word_input],
outputs=[plot_output, similar_words_output, dissimilar_words_output]
)
word_input.submit(
fn=process_text,
inputs=[word_input],
outputs=[plot_output, similar_words_output, dissimilar_words_output],
preprocess=lambda word: word.lower() if word else "" # None ์ฒดํฌ ํ›„ ์†Œ๋ฌธ์ž ๋ณ€ํ™˜
)
if __name__ == "__main__":
iface.launch()