Update Gradio app with multiple files

app.py

@@ -35,11 +35,7 @@ def create_chart_analysis(ticker, interval):
         # Buat chart menggunakan MPLFINANCE (dikembalikan sebagai HTML)
         chart_html = create_mplfinance_chart(
             df, 
-            ticker=f'{
-ticker
-} ({
-interval
-})', 
+            ticker=f'{ticker} ({interval})', 
             predictions=predictions
         )
 
@@ -56,35 +52,20 @@ interval
         # Create metrics display
         metrics = {
             "Ticker": ticker,
-                        "Current Price": f"${current_price:.2f
-}",
+            "Current Price": f"${current_price:.2f}",
             "Signal": signal.upper(),
-            "Confidence": f"{
-confidence:.1%
-}",
-            "Take Profit": f"${
-tp:.2f
-}" if tp else "N/A",
-            "Stop Loss": f"${
-sl:.2f
-}" if sl else "N/A",
-            "RSI": f"{
-df['RSI'].iloc[-1]:.1f
-}",
-            "MACD": f"{
-df['MACD'].iloc[-1]:.4f
-}",
-            "Volume": f"{
-df['Volume'].iloc[-1]:,.0f
-}"
+            "Confidence": f"{confidence:.1%}",
+            "Take Profit": f"${tp:.2f}" if tp else "N/A",
+            "Stop Loss": f"${sl:.2f}" if sl else "N/A",
+            "RSI": f"{df['RSI'].iloc[-1]:.1f}",
+            "MACD": f"{df['MACD'].iloc[-1]:.4f}",
+            "Volume": f"{df['Volume'].iloc[-1]:,.0f}"
         }
         
         return chart_html, metrics
         
     except Exception as e:
-        return f"Error creating chart: {
-e
-}", None
+        return f"Error creating chart: {str(e)}", None
 
 def analyze_sentiment(ticker):
     """Analyze gold/crypto market sentiment"""
@@ -96,33 +77,19 @@ def analyze_sentiment(ticker):
     fig = go.Figure(go.Indicator(
         mode="gauge+number+delta",
         value=sentiment_score,
-        domain={
-'x': [0, 1], 'y': [0, 1]
-},
-        title={
-'text': f"{ticker
-} Market Sentiment (Simulated)"},
-        delta={
-'reference': 0
-},
+        domain={'x': [0, 1], 'y': [0, 1]},
+        title={'text': f"{ticker} Market Sentiment (Simulated)"},
+        delta={'reference': 0},
         gauge={
-            'axis': {'range': [-1, 1]
-},
-            'bar': {
-'color': "#FFD700"
-},
+            'axis': {'range': [-1, 1]},
+            'bar': {'color': "#FFD700"},
             'steps': [
-                {
-'range': [-1, -0.5], 'color': "rgba(255,0,0,0.5)"
-},
-                {
-'range': [gauge_range[1] * 0.7, gauge_range[1]], 'color': "rgba(0,255,0,0.5)"
-},
+                {'range': [-1, -0.5], 'color': "rgba(255,0,0,0.5)"},
+                {'range': [-0.5, 0.5], 'color': "rgba(100,100,100,0.3)"},
                 {'range': [0.5, 1], 'color': "rgba(0,255,0,0.5)"}
             ],
             'threshold': {
-                'line': {'color': "black", 'width': 4
-},
+                'line': {'color': "black", 'width': 4},
                 'thickness': 0.75,
                 'value': 0
             }
@@ -165,19 +132,12 @@ def get_fundamentals(ticker):
         fig = go.Figure(go.Indicator(
             mode="gauge+number",
             value=gauge_value,
-            title={
-'text': gauge_title
-},
+            title={'text': gauge_title},
             gauge={
-                'axis': {'range': gauge_range
-},
-                'bar': {
-'color': "#FFD700"
-},
+                'axis': {'range': gauge_range},
+                'bar': {'color': "#FFD700"},
                 'steps': [
-                    {
-'range': [gauge_range[0], gauge_range[1] * 0.3], 'color': "rgba(255,0,0,0.5)"
-},
+                    {'range': [gauge_range[0], gauge_range[1] * 0.3], 'color': "rgba(255,0,0,0.5)"},
                     {'range': [gauge_range[1] * 0.3, gauge_range[1] * 0.7], 'color': "rgba(100,100,100,0.3)"},
                     {'range': [gauge_range[1] * 0.7, gauge_range[1]], 'color': "rgba(0,255,0,0.5)"}
                 ]
@@ -202,40 +162,22 @@ with gr.Blocks(
     theme=gr.themes.Default(primary_hue="yellow", secondary_hue="yellow"),
     title="Ultimate Market Analysis & Prediction",
     css="""
-        .gradio-container {
-background-color: #f0f4f9; color: black
-}
-        .gr-button-primary {
-background-color: #FFD700 !important; color: #000000 !important
-}
-        .gr-button-secondary {
-border-color: #FFD700 !important; color: #000000 !important
-}
-        .gr-tab button {
-color: black !important
-}
-        .gr-tab button.selected {
-background-color: #FFD700 !important; color: #000000 !important
-}
-        .gr-highlighted {
-background-color: #CCCCCC !important
-}
-        .anycoder-link {
-color: #FFD700 !important; text-decoration: none; font-weight: bold
-}
+        .gradio-container {background-color: #f0f4f9; color: black}
+        .gr-button-primary {background-color: #FFD700 !important; color: #000000 !important}
+        .gr-button-secondary {border-color: #FFD700 !important; color: #000000 !important}
+        .gr-tab button {color: black !important}
+        .gr-tab button.selected {background-color: #FFD700 !important; color: #000000 !important}
+        .gr-highlighted {background-color: #CCCCCC !important}
+        .anycoder-link {color: #FFD700 !important; text-decoration: none; font-weight: bold}
         .mpl-chart-container {
             border: 1px solid #CCCCCC; 
-                        border-radius: 5px; 
-                        overflow: hidden; 
-                        background: white; 
-                        width: 100%;
-}
-        .chart-title {
-color: black !important;
-}
-        .metric-label {
-color: black !important;
-}
+            border-radius: 5px; 
+            overflow: hidden; 
+            background: white; 
+            width: 100%;
+        }
+        .chart-title {color: black !important;}
+        .metric-label {color: black !important;}
     """
 ) as demo:
     

data_processor.py

@@ -4,15 +4,12 @@ import numpy as np
 from datetime import datetime, timedelta
 
 class DataProcessor:
-    # Hapus self.ticker di __init__
     def __init__(self):
         self.fundamentals_cache = {}
     
-    # Tambahkan 'ticker' sebagai argumen pertama
     def get_market_data(self, ticker="GC=F", interval="1d"):
         """Fetch market data from Yahoo Finance for a given ticker"""
         try:
-            # Map internal intervals to yfinance format
             interval_map = {
                 "5m": "5m",
                 "15m": "15m",
@@ -27,9 +24,8 @@ class DataProcessor:
             
             yf_interval = interval_map.get(interval, "1d")
             
-            # Determine appropriate period based on interval
             if interval in ["5m", "15m", "30m", "1h", "4h"]:
-                period = "60d"  # Intraday data limited to 60 days
+                period = "60d"
             elif interval in ["1d"]:
                 period = "1y"
             elif interval in ["1wk"]:
@@ -37,43 +33,42 @@ class DataProcessor:
             else:
                 period = "max"
             
-            # Use the passed ticker
             ticker_obj = yf.Ticker(ticker)
             df = ticker_obj.history(interval=yf_interval, period=period)
             
             if df.empty:
                 raise ValueError(f"No data retrieved from Yahoo Finance for {ticker}")
             
-            # Ensure proper column names
             df.columns = [col.capitalize() for col in df.columns]
             
-            # mplfinance requires a datetime index (already provided by yfinance)
-            
             return df
             
         except Exception as e:
             print(f"Error fetching data for {ticker}: {e}")
             return pd.DataFrame()
     
-    # calculate_indicators tetap sama, tidak perlu perubahan
     def calculate_indicators(self, df):
         """Calculate technical indicators"""
         if df.empty:
             return df
         
-        # Simple Moving Averages
+        # Simple Moving Averages (5, 20 as requested)
+        df['SMA_5'] = df['Close'].rolling(window=5).mean()
         df['SMA_20'] = df['Close'].rolling(window=20).mean()
-        df['SMA_50'] = df['Close'].rolling(window=50).mean()
         
         # Exponential Moving Averages
         df['EMA_12'] = df['Close'].ewm(span=12, adjust=False).mean()
         df['EMA_26'] = df['Close'].ewm(span=26, adjust=False).mean()
         
-        # MACD
+        # MACD (12, 26, 9)
         df['MACD'] = df['EMA_12'] - df['EMA_26']
         df['MACD_signal'] = df['MACD'].ewm(span=9, adjust=False).mean()
         df['MACD_histogram'] = df['MACD'] - df['MACD_signal']
         
+        # Split histogram into positive and negative for plotting
+        df['MACD_bar_positive'] = df['MACD_histogram'].where(df['MACD_histogram'] > 0, 0)
+        df['MACD_bar_negative'] = df['MACD_histogram'].where(df['MACD_histogram'] < 0, 0)
+        
         # RSI
         delta = df['Close'].diff()
         gain = (delta.where(delta > 0, 0)).rolling(window=14).mean()
@@ -99,63 +94,54 @@ class DataProcessor:
         df['Volume_SMA'] = df['Volume'].rolling(window=20).mean()
         df['Volume_ratio'] = df['Volume'] / df['Volume_SMA']
         
+        # Stochastic Oscillator (14, 3)
+        low_14 = df['Low'].rolling(window=14).min()
+        high_14 = df['High'].rolling(window=14).max()
+        df['%K'] = 100 * (df['Close'] - low_14) / (high_14 - low_14)
+        df['%D'] = df['%K'].rolling(window=3).mean()
+        df['%SD'] = df['%D'].rolling(window=3).mean()
+        df['UL'] = 70  # Upper limit
+        df['DL'] = 30  # Lower limit
+        
         return df
     
-    # get_fundamental_data tetap sama (mock)
     def get_fundamental_data(self, ticker="GC=F"):
         """Get fundamental gold market data (now generalized/mocked)"""
         try:
-            # Note: We keep this mocked as per previous discussion, but now accept ticker
-            
             if ticker == "BTC-USD":
                 fundamentals = {
                     "Crypto Volatility Index": round(np.random.uniform(50, 150), 1),
                     "Dominance Index": f"{np.random.uniform(40, 60):.2f}%",
                     "Fear & Greed Index": np.random.choice(["Extreme Fear", "Fear", "Neutral", "Greed", "Extreme Greed"]),
                     "Hash Rate Trend": np.random.choice(["Increasing", "Stable", "Decreasing"]),
-                    "Institutional Flow (Net)": f"{
-np.random.uniform(-100, 100):,.0f
-}M USD",
+                    "Institutional Flow (Net)": f"{np.random.uniform(-100, 100):,.0f}M USD",
                     "Market Sentiment": np.random.choice(["Bullish", "Neutral", "Bearish"]),
                 }
-            else: # Default Gold (GC=F)
+            else:
                 fundamentals = {
                     "Gold Strength Index": round(np.random.uniform(30, 80), 1),
                     "Dollar Index (DXY)": round(np.random.uniform(90, 110), 1),
                     "Real Interest Rate": f"{np.random.uniform(-2, 5):.2f}%",
-                    "Gold Volatility": f"{
-np.random.uniform(10, 40):.1f
-}%",
-                    "Commercial Hedgers (Net)": f"{
-np.random.uniform(-50000, 50000):,.0f
-}",
-                    "Managed Money (Net)": f"{
-np.random.uniform(-100000, 100000):,.0f
-}",
+                    "Gold Volatility": f"{np.random.uniform(10, 40):.1f}%",
+                    "Commercial Hedgers (Net)": f"{np.random.uniform(-50000, 50000):,.0f}",
+                    "Managed Money (Net)": f"{np.random.uniform(-100000, 100000):,.0f}",
                     "Market Sentiment": np.random.choice(["Bullish", "Neutral", "Bearish"]),
                 }
             
             return fundamentals
             
         except Exception as e:
-            print(f"Error fetching fundamentals: {
-e
-}")
-            return {
-"Error": str(e)
-}
+            print(f"Error fetching fundamentals: {e}")
+            return {"Error": str(e)}
     
-    # prepare_for_chronos tetap sama, tidak perlu perubahan
     def prepare_for_chronos(self, df, lookback=100):
         """Prepare data for Chronos model"""
         if df.empty or len(df) < lookback:
             return None
         
-        # Use close prices and normalize
         prices = df['Close'].iloc[-lookback:].values
         prices = prices.astype(np.float32)
         
-        # Normalize to help model performance
         mean = np.mean(prices)
         std = np.std(prices)
         normalized = (prices - mean) / (std + 1e-8)

plotter.py

@@ -7,75 +7,73 @@ import matplotlib.pyplot as plt
 def create_mplfinance_chart(df, ticker, predictions=None):
     """
     Creates a custom mplfinance candlestick chart and returns it as a base64 encoded image.
-    Style: white, black, with accent #f0f4f9.
+    Implements the exact layout: Candlestick + Volume + MACD + Stochastic.
     """
     if df.empty:
         return None
 
-    # --- 1. Define Custom Style ---
+    # Define style - Yahoo style as requested
     mc = mpf.make_marketcolors(
-        up='green', down='red',  # Candlestick body colors (yfinance default)
-        edge='inherit',
+        up='#00ff00', down='#ff0000',  # Green/Red candles
         wick='black',
-        volume='#f0f4f9', # Accent color for volume
+        edge='black',
+        volume='#00bfff',
         inherit=True
     )
 
     s = mpf.make_mpf_style(
-        base_mpf_style='nightclouds', # Start with a dark base
+        base_mpf_style='yahoo',
         marketcolors=mc,
-        # Customize background and grid to achieve white/black contrast
-        facecolor='#f0f4f9', # Background accent color (very light gray/off-white)
+        facecolor='white',
         edgecolor='black',
-        gridcolor='gray',
-        gridstyle=':',
+        gridcolor='lightgray',
+        gridstyle='-',
         figcolor='white',
         rc={'axes.labelcolor': 'black',
             'xtick.color': 'black',
             'ytick.color': 'black',
-            'figure.titlesize': 14,
-            'axes.titlesize': 16}
+            'figure.titlesize': 16,
+            'axes.titlesize': 14,
+            'axes.titleweight': 'bold'}
     )
 
-    # --- 2. Define Technical Indicators (Apanels) ---
+    # Define panels: [Candlestick, Volume, MACD, Stochastic]
     apds = []
-    # MACD Subplot
+    
+    # MACD Panel (Panel 2 - index 1 for addplot)
+    # MACD Line
+    apds.append(
+        mpf.make_addplot(df['MACD'], color='#606060', panel=2, ylabel='MACD', secondary_y=False)
+    )
+    # Signal Line
+    apds.append(
+        mpf.make_addplot(df['MACD_signal'], color='#1f77b4', panel=2, secondary_y=False)
+    )
+    # Positive Histogram Bars
     apds.append(
-        mpf.make_addplot(df['MACD'], color='black', panel=2, title='MACD'),
+        mpf.make_addplot(df['MACD_bar_positive'], type='bar', color='#4dc790', panel=2, width=0.8)
     )
+    # Negative Histogram Bars
     apds.append(
-        mpf.make_addplot(df['MACD_signal'], color='#FFA500', panel=2),
+        mpf.make_addplot(df['MACD_bar_negative'], type='bar', color='#fd6b6c', panel=2, width=0.8)
     )
     
-    # RSI Subplot
+    # Stochastic Panel (Panel 3 - index 2 for addplot)
     apds.append(
-        mpf.make_addplot(df['RSI'], color='red', panel=3, title='RSI', y_on_right=True),
+        mpf.make_addplot(df[['%D', '%SD', 'UL', 'DL']], panel=3, ylabel='Stoch (14,3)', ylim=[0, 100])
     )
 
-    # Overlays on Main Chart (MAs and BB)
-    apds.extend([
-        mpf.make_addplot(df['SMA_20'], color='#FFD700', linestyle='-', width=1.5),
-        mpf.make_addplot(df['SMA_50'], color='#FFA500', linestyle='-', width=1.5),
-        mpf.make_addplot(df['BB_upper'], color='grey', linestyle='--', width=0.5),
-        mpf.make_addplot(df['BB_lower'], color='grey', linestyle='--', width=0.5),
-    ])
-
-    # --- 3. Prediction Plotting (Trace as Overlay) ---
+    # Prediction overlay on main chart
     if predictions is not None and predictions.any():
-        
-        # Calculate future index (assuming daily frequency for simplicity)
         last_date = df.index[-1]
         future_index = pd.date_range(start=last_date, periods=len(predictions) + 1, freq=df.index.freq or 'D')[1:]
-        
-        # Create a series to align with the main DataFrame index for plotting
         future_series = pd.Series(predictions, index=future_index)
         
-        # Create an 'scatter' addplot for the prediction line
         apds.append(
-            mpf.make_addplot(future_series, color='blue', linestyle='-.', width=2, marker='o', markersize=5)
+            mpf.make_addplot(future_series, color='blue', linestyle='-.', width=2, marker='o', markersize=4)
         )
 
-    # --- 4. Plotting ---
+    # Plotting
     fig, axes = mpf.plot(
         df,
         type='candle',
@@ -83,18 +81,18 @@ def create_mplfinance_chart(df, ticker, predictions=None):
         title=f'{ticker} Price Chart and Analysis',
         ylabel='Price (USD)',
         volume=True,
-        volume_panel=1,
         addplot=apds,
-        figratio=(16,9),
+        mav=(5, 20),  # Moving averages as requested
+        figratio=(16, 9),
         figscale=1.5,
+        panel_ratios=(3, 1, 3, 3),  # Ratio as requested
         returnfig=True
     )
     
-    # --- 5. Convert to Base64 (for Gradio) ---
+    # Convert to Base64
     buf = BytesIO()
-    fig.savefig(buf, format='png', bbox_inches='tight')
-    plt.close(fig) # Close the figure to free memory
+    fig.savefig(buf, format='png', bbox_inches='tight', dpi=100)
+    plt.close(fig)
     image_base64 = base64.b64encode(buf.getvalue()).decode('utf-8')
     
-    # Gradio expects an HTML tag for raw HTML image display
     return f'<img src="data:image/png;base64,{image_base64}" style="width: 100%; height: auto;">'

requirements.txt

@@ -1,13 +1,19 @@
-gradio
-yfinance
-torch
-transformers
 pandas
-numpy
 plotly
-scipy
-scikit-learn
-safetensors
-huggingface-hub
-chronos-forecasting
+numpy
+gradio
 mplfinance
+openpyxl
+requests
+Pillow
+matplotlib
+scikit-learn
+nltk
+torch
+git+https://github.com/huggingface/transformers
+sentencepiece
+accelerate
+tokenizers
+yfinance
+scipy
+joblib

sentiment_analyzer.py

@@ -50,25 +50,17 @@ class SentimentAnalyzer:
             
             # Tampilan News (menggunakan background terang #E0E0E0 agar terlihat di tema putih)
             news_html = "<div style='max-height: 200px; overflow-y: auto; color: black;'>"
-            news_html += f"<h4 style='color: {
-title_color
-};'>Latest {
-ticker
-} News (Simulated)</h4>"
+            news_html += f"<h4 style='color: {title_color};'>Latest {ticker} News (Simulated)</h4>"
             
             for news in selected_news:
                 sentiment_label = "🟢" if "positive" in news or "rising" in news or "support" in news or "bullish" in news or "accumulation" in news else \
                                   "🔴" if "sell-off" in news or "weighs" in news or "outflows" in news or "Profit-taking" in news or "fear" in news else \
                                   "🟡"
-                news_html += f"<p style='margin: 10px 0; padding: 10px; background: #E0E0E0; border-radius: 5px; color: black;'>{
-sentiment_label
-} {news}</p>"
+                news_html += f"<p style='margin: 10px 0; padding: 10px; background: #E0E0E0; border-radius: 5px; color: black;'>{sentiment_label} {news}</p>"
             
             news_html += "</div>"
             
             return sentiment, news_html
             
         except Exception as e:
-            return 0, f"<p>Error analyzing sentiment: {
-str(e)
-}</p>"
+            return 0, f"<p>Error analyzing sentiment: {str(e)}</p>"

trading_logic.py

@@ -80,9 +80,7 @@ class TradingLogic:
             return signal, confidence
             
         except Exception as e:
-            print(f"Signal generation error: {
-e
-}")
+            print(f"Signal generation error: {e}")
             return "hold", 0.0
     
     def calculate_tp_sl(self, current_price, atr, signal):