Update app.py

app.py

@@ -1,29 +1,35 @@
 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
 import nltk
 from nltk.tokenize import word_tokenize
-import nltk
 from nltk.corpus import stopwords
 from nltk.stem import PorterStemmer, WordNetLemmatizer
 from nltk.tag import pos_tag
 
-nltk.download('punkt')
-nltk.download('stopwords')
-nltk.download('wordnet')
-nltk.download('averaged_perceptron_tagger')
-
 from docs import NOVEL_TEXT
 
-# Initialize lemmatizer and stop words
-lemmatizer = WordNetLemmatizer()
-stop_words = set(stopwords.words('english'))
+def download_nltk_library():
+    try:
+        nltk.download('punkt')
+        nltk.download('stopwords')
+        nltk.download('wordnet')
+        nltk.download('averaged_perceptron_tagger')
+        nltk.download('punkt_tab')
+        return True
+    except:
+        return False
 
 # Function to process each sentence
 def process_text(text):
+
+    lemmatizer = WordNetLemmatizer()
+    stop_words = set(stopwords.words('english'))
+    
     # Tokenization
     tokens = word_tokenize(text.lower())
 
@@ -35,43 +41,36 @@ def process_text(text):
 
     return processed_tokens
 
-# Split text into sentences
-sentences = nltk.sent_tokenize(NOVEL_TEXT)
-
-# Process each sentence in the corpus
-processed_corpus = [process_text(sentence) for sentence in sentences]
-
-import random
-
-emotion_words = ['emotion', 'joy', 'fear', 'anger', 'sadness', 'disgust', 'anxiety', 'team', 'console', 'headquarters', 'feelings']
-hockey_words = ['hockey', 'game', 'team', 'skates', 'stick', 'rink', 'practice', 'championship', 'score', 'goal', 'penalty']
-memory_words = ['memory', 'sphere', 'shelves', 'life', 'experience', 'recall', 'remember', 'color', 'happy', 'sad', 'joyful']
-friend_words = ['friend', 'riley', 'grace', 'bree', 'team', 'support', 'help', 'together', 'loyal', 'fun', 'friendship']
-school_words = ['school', 'class', 'teacher', 'student', 'homework', 'study', 'exam', 'lesson', 'classmates', 'learn']
-
-train_data = []
+# Word2Vec 모델 학습 함수
+def train_word2vec(sentences):
+    model = Word2Vec(sentences, vector_size=100, window=3, min_count=2, workers=4, sg=0, epochs=100)
+    return model
 
-for _ in range(40):
-    train_data.append(random.sample(emotion_words, k=random.randint(4, 6)))
-    train_data.append(random.sample(hockey_words, k=random.randint(4, 6)))
-    train_data.append(random.sample(memory_words, k=random.randint(4, 6)))
-    train_data.append(random.sample(friend_words, k=random.randint(4, 6)))
-    train_data.append(random.sample(school_words, k=random.randint(4, 6)))
+# def preprocess_text(file_path):
+#     with open(file_path, 'r', encoding='utf-8') as file:
+#         text = file.read()
 
+#     # 토큰화 및 품사 태깅
+#     tokens = word_tokenize(text)
+#     tagged = pos_tag(tokens)
 
-random.shuffle(train_data)
+#     # 명사만 추출 (NN, NNS, NNP, NNPS)
+#     nouns = [word.lower() for word, pos in tagged if pos.startswith('NN')]
 
+#     # 중복 제거 및 정렬
+#     unique_nouns = sorted(set(nouns))
 
+#     # 간단한 문장 생성 (각 명사를 개별 문장으로 취급)
+#     sentences = [[noun] for noun in unique_nouns]
 
-def train_word2vec(sentences):
-    model = Word2Vec(sentences, vector_size=100, window=3, min_count=2, workers=4, sg=0, epochs=100)
-    return model
+#     return sentences, unique_nouns
 
 def apply_pca(word_vectors):
     pca = PCA(n_components=3)
     return pca.fit_transform(word_vectors)
 
-    
+# def process_text(file_path, target_word):
+
 def get_unique(model):
     vocablist1=list(model.wv.index_to_key)
     vocablist =[]
@@ -79,14 +78,22 @@ def get_unique(model):
         vocablist.append(i)
     return vocablist
 
-def process_text(target_word):
+def train_model(sentence):
     # 전처리
-    sentences=X
+    sentences=sentence
 
     # Word2Vec 모델 학습
     model = train_word2vec(sentences)
     unique_words = get_unique(model)
+    
+    return  model, unique_words
+
+def process_model(target_word):
 
+    # Word2Vec 모델 로드
+    model = Word2Vec.load("word2vec.model")
+    unique_words = get_unique(model)
+    
     # 각 단어의 임베딩 벡터 추출
     word_vectors = np.array([model.wv[word] for word in unique_words])
 
@@ -106,14 +113,15 @@ def process_text(target_word):
     # 가장 먼 단어 10개 찾기
     if target_word in model.wv:
         all_words = model.wv.index_to_key  # 모델에 포함된 모든 단어 리스트
-        dissimilar_words = sorted([(word, model.wv.similarity(target_word, word)) 
+        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]  # 유사도가 가장 낮은 10개 단어 선택
-    
+
         dissimilar_word_indices = [unique_words.index(word) for word, _ in dissimilar_words]
         for idx in dissimilar_word_indices:
             colors[idx] = 'rgba(128, 0, 128, 1)'  # 가장 먼 단어들을 보라색으로 표시
 
+
     # Plotly를 사용한 3D 산점도 생성
     fig = go.Figure(data=[go.Scatter3d(
         x=word_vectors_3d[:, 0],
@@ -147,25 +155,29 @@ def process_text(target_word):
     return fig, similar_words_text
 
 
-# Gradio 인터페이스
-with gr.Blocks() as iface:
+# Gradio 인터페이스 수정
+with gr.Blocks(css=".plot-box {width: 70%; height: 500px;}") as iface:
     gr.Markdown("# Word Embedding 3D 시각화")
     gr.Markdown("단어를 입력하세요. Word2Vec과 PCA를 사용하여 단어 임베딩을 3D로 시각화합니다. 입력한 단어는 빨간색으로, 가장 유사한 10개 단어는 초록색, 가장 먼 단어는 보라색으로 강조됩니다. 유사한 단어 목록은 그래프 아래에 표시됩니다.")
 
     with gr.Row():
-        # file_input = gr.File(label="텍스트 파일 업로드 (.txt)", file_types=[".txt"])
-        word_input = gr.Textbox(label="강조할 단어 입력")
-        submit_btn = gr.Button("제출")
+        # 사용자 입력 박스를 강조하기 위해 스타일을 변경
+        word_input = gr.Textbox(label="**강조할 단어 입력**", elem_id="input-box", placeholder="단어를 입력하세요", lines=1)
+        submit_btn = gr.Button("제출", elem_id="submit-btn")
 
+    with gr.Row():
+        # 시각화 화면의 크기를 CSS로 증가
+        plot_output = gr.Plot(label="Word Embedding 3D 시각화", elem_id="plot-box")
 
-    plot_output = gr.Plot(label="Word Embedding 3D 시각화")
-    similar_words_output = gr.Textbox(label="유사한 단어")
+        with gr.Column(scale=0.3):  # 컬럼의 너비를 줄이기 위해 scale 값을 낮춤
+            similar_words_output = gr.Textbox(label="유사한 단어", interactive=False, lines=5)
+            dissimilar_words_output = gr.Textbox(label="유사하지 않은 단어", interactive=False, lines=5)
 
     submit_btn.click(
         fn=process_text,
         inputs=[word_input],
-        outputs=[plot_output, similar_words_output]
+        outputs=[plot_output, similar_words_output, dissimilar_words_output]
     )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch()