|
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 |
|
|
|
|
|
|
|
def train_word2vec(sentences): |
|
|
|
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): |
|
|
|
sentences=sentence |
|
|
|
|
|
model = train_word2vec(sentences) |
|
unique_words = get_unique(model) |
|
|
|
return model, unique_words |
|
|
|
def process_text(target_word): |
|
target_word =target_word.lower() |
|
|
|
|
|
model = Word2Vec.load("word2vec.model") |
|
unique_words = get_unique(model) |
|
|
|
|
|
word_vectors = np.array([model.wv[word] for word in unique_words]) |
|
|
|
|
|
word_vectors_3d = apply_pca(word_vectors) |
|
|
|
|
|
colors = ['rgba(255, 255, 255, 0.15)' if word != target_word else 'rgba(255, 20, 147, 0.9)' for word in unique_words] |
|
|
|
|
|
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)' |
|
|
|
|
|
if target_word in model.wv: |
|
all_words = model.wv.index_to_key |
|
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] |
|
|
|
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)' |
|
|
|
|
|
|
|
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 |
|
) |
|
|
|
|
|
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 |
|
|
|
|
|
|
|
with gr.Blocks(css=""" |
|
#input-box { |
|
background-color: #ffeef3; /* ์ฐํ ํ์คํ
ํํฌ */ |
|
border: 2px solid #ffccd5; /* ์ฐํ ํํฌ ํ
๋๋ฆฌ */ |
|
color: #000; /* ํ
์คํธ ์์ */ |
|
border-radius: 8px; /* ๋ฅ๊ทผ ํ
๋๋ฆฌ */ |
|
} |
|
#submit-btn { |
|
background-color: #ebfbea; /* ์ฐํ ํ์คํ
์ฐ๋์ */ |
|
border: 2px solid #d6f5d6; /* ์ฐํ ์ฐ๋์ ํ
๋๋ฆฌ */ |
|
color: #000; /* ํ
์คํธ ์์ */ |
|
border-radius: 8px; /* ๋ฅ๊ทผ ํ
๋๋ฆฌ */ |
|
} |
|
#bulletin { |
|
background-color: #eaf9ff; /* ์ฐํ ํ์คํ
ํ๋์ */ |
|
border: 2px solid #d3f0f7; /* ์ฐํ ํ๋์ ํ
๋๋ฆฌ */ |
|
color: #000; /* ํ
์คํธ ์์ */ |
|
border-radius: 8px; /* ๋ฅ๊ทผ ํ
๋๋ฆฌ */ |
|
} |
|
#similar-words { |
|
background-color: #fff0e6; /* ์ฐํ ํ์คํ
์ฃผํฉ์ */ |
|
border: 2px solid #ffe3cc; /* ์ฐํ ์ฃผํฉ ํ
๋๋ฆฌ */ |
|
color: #000; /* ํ
์คํธ ์์ */ |
|
border-radius: 8px; /* ๋ฅ๊ทผ ํ
๋๋ฆฌ */ |
|
} |
|
#dissimilar-words { |
|
background-color: #f2e6ff; /* ์ฐํ ํ์คํ
๋ณด๋ผ์ */ |
|
border: 2px solid #e0ccff; /* ์ฐํ ๋ณด๋ผ ํ
๋๋ฆฌ */ |
|
color: #000; /* ํ
์คํธ ์์ */ |
|
border-radius: 8px; /* ๋ฅ๊ทผ ํ
๋๋ฆฌ */ |
|
} |
|
label { |
|
font-weight: bold; /* ์ ๋ชฉ ๋ณผ๋์ฒด */ |
|
} |
|
""") as iface: |
|
gr.Markdown("# <Inside Out 2> ๋จ์ด ์๋ฏธ ์ง๋ 3D ์๊ฐํ") |
|
|
|
|
|
with gr.Row(): |
|
|
|
with gr.Column(): |
|
word_input = gr.Textbox( |
|
label="**๋จ์ด ์
๋ ฅ**", |
|
elem_id="input-box", |
|
placeholder="ex. emotion, puberty, hockey, friend, anxiety, memory, ...", |
|
lines=1 |
|
) |
|
submit_btn = gr.Button("์ ์ถ", elem_id="submit-btn") |
|
bulletin = gr.Textbox( |
|
label="์ฌ์ฉ๋ฒ ์๋ด", |
|
interactive=False, |
|
lines=4, |
|
value=( |
|
"1. ์์ค์ ๋์จ ๋จ์ด๋ฅผ ์
๋ ฅํ๊ณ [์ ์ถ]์ด๋ [Enter]๋ฅผ ๋๋ฅด์ธ์\n" |
|
"2. ์
๋ ฅ ๋จ์ด๋ ๋นจ๊ฐ์, ๊ฐ๊น์ด ๋จ์ด๋ค์ ์ฃผํฉ์, ๋จผ ๋จ์ด๋ค์ ๋ณด๋ผ์์ผ๋ก ๊ฐ์กฐ๋ฉ๋๋ค.\n" |
|
"3. <Error>๊ฐ ๋ํ๋๋ ๊ฒฝ์ฐ, ๋ค๋ฅธ ๋จ์ด๋ฅผ ์
๋ ฅํด๋ณด์ธ์.\n" |
|
"4. ๋ง์ฐ์ค ๋๋๊ทธ ๋ฐ ์คํฌ๋กค์ ํ์ฉํ์ฌ 3D ํ๋ฉด์ ์ดํด๋ณด์ธ์.\n" |
|
"5. ๋จ์ด ์
๋ ฅ์ฐฝ์ ๋ค๋ฅธ ๋จ์ด๋ค๋ ์
๋ ฅํด๋ณด์ธ์." |
|
), |
|
elem_id="bulletin" |
|
) |
|
|
|
with gr.Row(): |
|
|
|
plot_output = gr.Plot(label="Word Embedding 3D ์๊ฐํ", elem_id="plot-box") |
|
|
|
with gr.Column(scale=0.3): |
|
similar_words_output = gr.Textbox( |
|
label="๊ฐ์ฅ ๊ฐ๊น์ด ๋จ์ด 10๊ฐ", |
|
interactive=False, |
|
lines=5, |
|
elem_id="similar-words" |
|
) |
|
dissimilar_words_output = gr.Textbox( |
|
label="๊ฐ์ฅ ๋จผ ๋จ์ด 10๊ฐ", |
|
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 "" |
|
) |
|
|
|
if __name__ == "__main__": |
|
iface.launch() |