Update app.py

app.py

@@ -10,7 +10,6 @@ import numpy as np
 import pandas as pd
 import plotly.express as px
 import matplotlib.pyplot as plt
-from matplotlib import gridspec
 from datetime import datetime
 
 def plot_cum_returns(data, title, initial_capital=1000):
@@ -40,105 +39,16 @@ def plot_weights(weights):
     ax.axis('equal')
     return fig
 
-def plot_top_ticker_graphs(top_ticker, stock_data, portfolio_data, weights):
-    fig = plt.figure(figsize=(20, 20))
-    gs = gridspec.GridSpec(5, 2, wspace=0.3, hspace=0.3)
-
-    ax1 = plt.subplot(gs[0, 0])
-    # 포트폴리오 내 자산 배분 비율 그래프 (막대 그래프 또는 파이 차트)
-    ax1.pie(list(weights.values()), labels=list(weights.keys()), autopct='%1.1f%%')
-    ax1.axis('equal')
-    ax1.set_title('Portfolio Asset Allocation')
-
-    ax2 = plt.subplot(gs[0, 1])
-    # 포트폴리오의 연간 수익률 및 변동성 추이 그래프
-    portfolio_returns = portfolio_data.pct_change().dropna()
-    portfolio_returns = (portfolio_returns + 1).cumprod()
-    portfolio_returns.plot(ax=ax2)
-    ax2.set_title('Portfolio Annual Returns and Volatility')
-    ax2.set_ylabel('Cumulative Returns')
-
-    ax3 = plt.subplot(gs[1, 0])
-    # 포트폴리오의 샤프 비율(Sharpe Ratio) 추이 그래프
-    sharpe_ratio = portfolio_returns.mean() / portfolio_returns.std() * np.sqrt(252)
-    sharpe_ratio.plot(ax=ax3)
-    ax3.set_title('Portfolio Sharpe Ratio')
-    ax3.set_ylabel('Sharpe Ratio')
-
-    ax4 = plt.subplot(gs[1, 1])
-    # 개별 주식의 월별 수익률 그래프
-    stock_data[top_ticker].resample('M').last().pct_change().plot(ax=ax4)
-    ax4.set_title(f'{top_ticker} Monthly Returns')
-    ax4.set_ylabel('Returns')
-
-    ax5 = plt.subplot(gs[2, 0])
-    # 개별 주식의 연간 수익률 그래프
-    stock_data[top_ticker].resample('Y').last().pct_change().plot(ax=ax5)
-    ax5.set_title(f'{top_ticker} Annual Returns')
-    ax5.set_ylabel('Returns')
-
-    ax6 = plt.subplot(gs[2, 1])
-    # 개별 주식의 이동평균선(예: 20일, 50일, 200일) 그래프
-    stock_data[top_ticker].plot(ax=ax6)
-    stock_data[top_ticker].rolling(window=20).mean().plot(ax=ax6, label='20-day MA')
-    stock_data[top_ticker].rolling(window=50).mean().plot(ax=ax6, label='50-day MA')
-    stock_data[top_ticker].rolling(window=200).mean().plot(ax=ax6, label='200-day MA')
-    ax6.set_title(f'{top_ticker} Moving Averages')
-    ax6.set_ylabel('Price')
-    ax6.legend()
-
-    ax7 = plt.subplot(gs[3, 0])
-    # 포트폴리오의 드로다운(Drawdown) 그래프
-    portfolio_drawdown = (portfolio_returns.cummax() - portfolio_returns) / portfolio_returns.cummax()
-    portfolio_drawdown.plot(ax=ax7)
-    ax7.set_title('Portfolio Drawdown')
-    ax7.set_ylabel('Drawdown')
-
-    ax8 = plt.subplot(gs[3, 1])
-    # 개별 주식의 RSI(Relative Strength Index) 그래프
-    delta = stock_data[top_ticker].diff()
-    up = delta.clip(lower=0)
-    down = -1 * delta.clip(upper=0)
-    ema_up = up.ewm(com=13, adjust=False).mean()
-    ema_down = down.ewm(com=13, adjust=False).mean()
-    rs = ema_up / ema_down
-    rsi = 100 - (100 / (1 + rs))
-    rsi.plot(ax=ax8)
-    ax8.set_title(f'{top_ticker} RSI')
-    ax8.set_ylabel('RSI')
-
-    ax9 = plt.subplot(gs[4, 0])
-    # 개별 주식의 MACD(Moving Average Convergence Divergence) 그래프
-    exp1 = stock_data[top_ticker].ewm(span=12, adjust=False).mean()
-    exp2 = stock_data[top_ticker].ewm(span=26, adjust=False).mean()
-    macd = exp1 - exp2
-    signal = macd.ewm(span=9, adjust=False).mean()
-    ax9.plot(macd, label='MACD')
-    ax9.plot(signal, label='Signal')
-    ax9.set_title(f'{top_ticker} MACD')
-    ax9.set_ylabel('MACD')
-    ax9.legend()
-
-    ax10 = plt.subplot(gs[4, 1])
-    # 개별 주식의 볼린저 밴드(Bollinger Bands) 그래프
-    rolling_mean = stock_data[top_ticker].rolling(window=20).mean()
-    rolling_std = stock_data[top_ticker].rolling(window=20).std()
-    upper_band = rolling_mean + (rolling_std * 2)
-    lower_band = rolling_mean - (rolling_std * 2)
-    ax10.plot(stock_data[top_ticker], label='Price')
-    ax10.plot(rolling_mean, label='Moving Average')
-    ax10.plot(upper_band, label='Upper Band')
-    ax10.plot(lower_band, label='Lower Band')
-    ax10.set_title(f'{top_ticker} Bollinger Bands')
-    ax10.set_ylabel('Price')
-    ax10.legend()
-
-    plt.tight_layout()
+def plot_individual_volatility(data):
+# 개별 주식의 변동성 그래프 출력
+    rolling_std = data.pct_change().rolling(window=30).std() * np.sqrt(252)
+    fig = px.line(rolling_std, title='개별 주식의 변동성 (30일 롤링 연간화)')
     return fig
 
 def output_results(start_date, end_date, tickers_string):
     tickers = tickers_string.split(',')
     stocks_df = yf.download(tickers, start=start_date, end=end_date)['Adj Close']
+
     tickers_info = {}
     news_data = {}
     for ticker in tickers:
@@ -153,6 +63,7 @@ def output_results(start_date, end_date, tickers_string):
     fig_cum_returns = px.line(daily_cum_returns, title='개별 주식의 누적 수익률 ($1,000 시작)')
     corr_df = stocks_df.corr().round(2)
     fig_corr = px.imshow(corr_df, text_auto=True, title='주식 간 상관 관계')
+
     mu = expected_returns.mean_historical_return(stocks_df)
     S = risk_models.sample_cov(stocks_df)
     ef = EfficientFrontier(mu, S)
@@ -169,16 +80,14 @@ def output_results(start_date, end_date, tickers_string):
         for ticker in tickers
     ])
 
-    # 가장 수익률과 비중이 큰 종목 선택
-    top_ticker = max(cleaned_weights, key=cleaned_weights.get)
-    fig_top_ticker = plot_top_ticker_graphs(top_ticker, stocks_df, daily_cum_returns[top_ticker], cleaned_weights)
-
     return fig_cum_returns, fig_efficient_frontier, fig_corr, fig_indiv_prices, fig_weights, \
-           f"{expected_annual_return*100:.2f}%", f"{annual_volatility*100:.2f}%", f"{sharpe_ratio:.2f}", \
-           ticker_info_output, fig_top_ticker
+           f"{expected_annual_return*100:.2f}%", f"{annual_volatility*100:.2f}%", f"{sharpe_ratio:.2f}", ticker_info_output
+
+
 
 css = """footer { visibility: hidden; }"""
 
+
 with gr.Blocks(css=css) as app:
     gr.Markdown("""
     <style>
@@ -194,23 +103,18 @@ with gr.Blocks(css=css) as app:
         end_date = gr.Textbox(datetime.now().date(), label="종료 일자")
         tickers_string = gr.Textbox("NVDA,^GSPC,GC=F,MSFT,BTC-USD", label="주식 티커를 쉼표로 구분하여 입력하세요")
         btn = gr.Button("포트폴리오 최적화 결과 보기")
-
+    
     with gr.Row():
         expected_annual_return = gr.Text(label="예상 연간 수익률")
         annual_volatility = gr.Text(label="연간 변동성")
         sharpe_ratio = gr.Text(label="샤프 비율")
-
     with gr.Column():
         fig_cum_returns = gr.Plot(label="최적화된 포트폴리오의 누적 수익률 (시작 가격 $1,000)")
         fig_efficient_frontier = gr.Plot(label="효율적 투자선")
         fig_corr = gr.Plot(label="주식 간 상관 관계")
         fig_indiv_prices = gr.Plot(label="개별 주식 가격")
         fig_weights = gr.Plot(label="포트폴리오 최적 투자 비율")
-        fig_top_ticker = gr.Plot(label="가장 수익률과 비중이 큰 종목의 그래프")
         ticker_info_output = gr.Textbox(label="티커 정보 및 뉴스")
+    btn.click(fn=output_results, inputs=[start_date, end_date, tickers_string], outputs=[fig_cum_returns, fig_efficient_frontier, fig_corr, fig_indiv_prices, fig_weights, expected_annual_return, annual_volatility, sharpe_ratio, ticker_info_output])
 
-    btn.click(fn=output_results, inputs=[start_date, end_date, tickers_string],
-              outputs=[fig_cum_returns, fig_efficient_frontier, fig_corr, fig_indiv_prices, fig_weights,
-                       expected_annual_return, annual_volatility, sharpe_ratio, ticker_info_output, fig_top_ticker])
-
-app.launch()
+app.launch()