Update app.py

app.py

@@ -2,22 +2,12 @@ import gradio as gr
 import pandas as pd
 from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
-import networkx as nx
-import matplotlib.pyplot as plt
 import csv
 import io
-import matplotlib.font_manager as fm
-from datetime import datetime, timedelta
 
 # 한국어 처리를 위한 KoSentence-BERT 모델 로드
 model = SentenceTransformer('jhgan/ko-sbert-sts')
 
-font_path = "./NanumBarunGothic.ttf"
-font_prop = fm.FontProperties(fname=font_path)
-plt.rcParams['font.family'] = 'NanumBarunGothic'
-plt.rcParams['font.sans-serif'] = ['NanumBarunGothic']
-fm.fontManager.addfont(font_path)
-
 # 전역 변수
 global_recommendations = None
 global_csv_string = None
@@ -32,19 +22,6 @@ def create_csv_string(recommendations):
         writer.writerow(rec)
     return output.getvalue()
 
-def create_chart(G):
-    plt.figure(figsize=(10, 8))
-    pos = nx.spring_layout(G)
-    nx.draw(G, pos, with_labels=True, node_color='lightblue', node_size=3000, font_size=10, font_weight='bold', edge_color='gray')
-    plt.title("직원과 프로그램 간의 관계", fontsize=14, fontweight='bold')
-    plt.tight_layout(pad=1.0)
-    
-    buf = io.BytesIO()
-    plt.savefig(buf, format='png', bbox_inches='tight')
-    buf.seek(0)
-    plt.close()
-    return buf
-
 # 열 매칭 함수
 def auto_match_columns(df, required_cols):
     matched_cols = {}
@@ -76,7 +53,6 @@ def validate_and_get_columns(employee_df, program_df):
     return None, employee_cols, program_cols
 
 # 유튜브 데이터 열 선택 함수
-
 def select_youtube_columns(youtube_file):
     global youtube_columns
     if youtube_file is None:
@@ -121,7 +97,7 @@ def match_youtube_content(program_skills, youtube_df, model):
     similarities = cosine_similarity(program_embeddings, youtube_embeddings)
     return similarities
 
-# 직원 데이터를 분석하여 교육 프로그램을 추천하고, 테이블과 그래프를 생성하는 함수
+# 직원 데이터를 분석하여 교육 프로그램을 추천하고, 테이블을 생성하는 함수
 def hybrid_rag(employee_file, program_file, youtube_file, title_col, description_col, url_col, upload_date_col):
     global global_recommendations
     global global_csv_string
@@ -132,7 +108,7 @@ def hybrid_rag(employee_file, program_file, youtube_file, title_col, description
 
     error_msg, employee_cols, program_cols = validate_and_get_columns(employee_df, program_df)
     if error_msg:
-        return error_msg, None, None, None
+        return error_msg, None, None
 
     employee_skills = employee_df[employee_cols["current_skills"]].tolist()
     program_skills = program_df[program_cols["skills_acquired"]].tolist()
@@ -176,21 +152,6 @@ def hybrid_rag(employee_file, program_file, youtube_file, title_col, description
         recommendations.append(recommendation + "\n" + youtube_recommendation)
 
     global_recommendations = recommendation_rows
-
-    G = nx.Graph()
-    for employee in employee_df[employee_cols['employee_name']]:
-        G.add_node(employee, type='employee')
-
-    for program in program_df[program_cols['program_name']]:
-        G.add_node(program, type='program')
-
-    for i, employee in employee_df.iterrows():
-        for j, program in program_df.iterrows():
-            if similarities[i][j] > 0.5:
-                G.add_edge(employee[employee_cols['employee_name']], program[program_cols['program_name']])
-
-    # 차트 생성
-    chart_buffer = create_chart(G)
     
     # CSV 문자열 생성
     global_csv_string = create_csv_string(recommendation_rows)
@@ -198,7 +159,7 @@ def hybrid_rag(employee_file, program_file, youtube_file, title_col, description
     # 결과 테이블 데이터프레임 생성
     result_df = pd.DataFrame(recommendation_rows, columns=["Employee ID", "Employee Name", "Recommended Programs", "Recommended YouTube Content"])
 
-    return result_df, chart_buffer, gr.File(value=global_csv_string, visible=True), gr.Button(value="CSV 다운로드", visible=True)
+    return result_df, gr.File(value=global_csv_string, visible=True), gr.Button(value="CSV 다운로드", visible=True)
     
 # 채팅 응답 함수
 def chat_response(message, history):
@@ -241,20 +202,16 @@ with gr.Blocks(css=".gradio-button {background-color: #007bff; color: white;} .g
             csv_download = gr.File(label="추천 결과 다운로드", visible=False)
             download_button = gr.Button("CSV 다운로드", visible=False)
 
-        with gr.Column(scale=2, min_width=500):
-            gr.Markdown("<h3 style='color: #34495e;'>2. 분석 결과 및 시각화</h3>")
-            chart_output = gr.Image(label="시각화 차트")
-
-    gr.Markdown("<h3 style='color: #34495e;'>3. 직원별 추천 프로그램 및 유튜브 콘텐츠 확인</h3>")
+    gr.Markdown("<h3 style='color: #34495e;'>2. 직원별 추천 프로그램 및 유튜브 콘텐츠 확인</h3>")
     chatbot = gr.Chatbot()
     msg = gr.Textbox(label="직원 이름을 입력하세요")
     clear = gr.Button("대화 내역 지우기")
 
-    # 분석 버튼 클릭 시 테이블, 차트, 파일 다운로드를 업데이트
+    # 분석 버튼 클릭 시 테이블, 파일 다운로드를 업데이트
     analyze_button.click(
         hybrid_rag, 
         inputs=[employee_file, program_file, youtube_file, title_col, description_col, url_col, upload_date_col], 
-        outputs=[output_table, chart_output, csv_download, download_button]
+        outputs=[output_table, csv_download, download_button]
     )
 
     # CSV 다운로드 버튼