Update app.py

app.py

@@ -73,8 +73,11 @@ def create_chart_analysis(interval):
             font=dict(color='white')
         )
         
+        # FIX: Prepare data for Chronos before passing to model_handler.predict
+        prepared_data = data_processor.prepare_for_chronos(df)
+        
         # Generate predictions
-        predictions = model_handler.predict(df, horizon=10)
+        predictions = model_handler.predict(prepared_data, horizon=10)
         current_price = df['Close'].iloc[-1]
         
         # Get signal
@@ -101,25 +104,28 @@ def create_chart_analysis(interval):
         
         # Create prediction chart
         pred_fig = go.Figure()
-        future_dates = pd.date_range(
-            start=df.index[-1], periods=len(predictions), freq='D'
-        )
         
-        pred_fig.add_trace(go.Scatter(
-            x=future_dates, y=predictions,
-            mode='lines+markers',
-            line=dict(color='#FFD700', width=3),
-            marker=dict(size=6),
-            name='Predictions'
-        ))
-        
-        pred_fig.add_trace(go.Scatter(
-            x=[df.index[-1], future_dates[0]],
-            y=[current_price, predictions[0]],
-            mode='lines',
-            line=dict(color='rgba(255,215,0,0.5)', width=2, dash='dash'),
-            showlegend=False
-        ))
+        # Check if predictions are valid before plotting
+        if predictions.any():
+            future_dates = pd.date_range(
+                start=df.index[-1], periods=len(predictions), freq='D'
+            )
+            
+            pred_fig.add_trace(go.Scatter(
+                x=future_dates, y=predictions,
+                mode='lines+markers',
+                line=dict(color='#FFD700', width=3),
+                marker=dict(size=6),
+                name='Predictions'
+            ))
+            
+            pred_fig.add_trace(go.Scatter(
+                x=[df.index[-1], future_dates[0]],
+                y=[current_price, predictions[0]],
+                mode='lines',
+                line=dict(color='rgba(255,215,0,0.5)', width=2, dash='dash'),
+                showlegend=False
+            ))
         
         pred_fig.update_layout(
             title='Price Prediction (Next 10 Periods)',
@@ -252,10 +258,10 @@ with gr.Blocks(
             label="Time Interval",
             info="Select analysis timeframe"
         )
-        refresh_btn = gr.Button("🔄 Refresh Data", variant="primary")
+        refresh_btn = gr.Button("売 Refresh Data", variant="primary")
     
     with gr.Tabs():
-        with gr.TabItem("📊 Chart Analysis"):
+        with gr.TabItem("投 Chart Analysis"):
             with gr.Row():
                 chart_plot = gr.Plot(label="Price Chart")
                 pred_plot = gr.Plot(label="Predictions")
@@ -263,12 +269,12 @@ with gr.Blocks(
             with gr.Row():
                 metrics_output = gr.JSON(label="Trading Metrics")
         
-        with gr.TabItem("📰 Sentiment Analysis"):
+        with gr.TabItem("堂 Sentiment Analysis"):
             with gr.Row():
                 sentiment_gauge = gr.Plot(label="Sentiment Score")
                 news_display = gr.HTML(label="Market News")
         
-        with gr.TabItem("📈 Fundamentals"):
+        with gr.TabItem("嶋 Fundamentals"):
             with gr.Row():
                 fundamentals_gauge = gr.Plot(label="Strength Index")
                 fundamentals_table = gr.Dataframe(
@@ -311,456 +317,4 @@ if __name__ == "__main__":
         server_port=7860,
         share=False,
         show_api=True
-    )
-data_processor.py
-ADDED
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-import yfinance as yf
-import pandas as pd
-import numpy as np
-from datetime import datetime, timedelta
-
-class DataProcessor:
-    def __init__(self):
-        self.ticker = "GC=F"
-        self.fundamentals_cache = {}
-    
-    def get_gold_data(self, interval="1d", period="max"):
-        """Fetch gold futures data from Yahoo Finance"""
-        try:
-            # Map internal intervals to yfinance format
-            interval_map = {
-                "5m": "5m",
-                "15m": "15m",
-                "30m": "30m",
-                "1h": "60m",
-                "4h": "240m",
-                "1d": "1d",
-                "1wk": "1wk",
-                "1mo": "1mo",
-                "3mo": "3mo"
-            }
-            
-            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
-            elif interval in ["1d"]:
-                period = "1y"
-            elif interval in ["1wk"]:
-                period = "2y"
-            else:
-                period = "max"
-            
-            ticker = yf.Ticker(self.ticker)
-            df = ticker.history(interval=yf_interval, period=period)
-            
-            if df.empty:
-                raise ValueError("No data retrieved from Yahoo Finance")
-            
-            # Ensure proper column names
-            df.columns = [col.capitalize() for col in df.columns]
-            
-            return df
-            
-        except Exception as e:
-            print(f"Error fetching data: {e}")
-            return pd.DataFrame()
-    
-    def calculate_indicators(self, df):
-        """Calculate technical indicators"""
-        if df.empty:
-            return df
-        
-        # Simple Moving Averages
-        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
-        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']
-        
-        # RSI
-        delta = df['Close'].diff()
-        gain = (delta.where(delta > 0, 0)).rolling(window=14).mean()
-        loss = (-delta.where(delta < 0, 0)).rolling(window=14).mean()
-        rs = gain / loss
-        df['RSI'] = 100 - (100 / (1 + rs))
-        
-        # Bollinger Bands
-        df['BB_middle'] = df['Close'].rolling(window=20).mean()
-        bb_std = df['Close'].rolling(window=20).std()
-        df['BB_upper'] = df['BB_middle'] + (bb_std * 2)
-        df['BB_lower'] = df['BB_middle'] - (bb_std * 2)
-        
-        # Average True Range (ATR)
-        high_low = df['High'] - df['Low']
-        high_close = np.abs(df['High'] - df['Close'].shift())
-        low_close = np.abs(df['Low'] - df['Close'].shift())
-        ranges = pd.concat([high_low, high_close, low_close], axis=1)
-        true_range = ranges.max(axis=1)
-        df['ATR'] = true_range.rolling(window=14).mean()
-        
-        # Volume indicators
-        df['Volume_SMA'] = df['Volume'].rolling(window=20).mean()
-        df['Volume_ratio'] = df['Volume'] / df['Volume_SMA']
-        
-        return df
-    
-    def get_fundamental_data(self):
-        """Get fundamental gold market data"""
-        try:
-            ticker = yf.Ticker(self.ticker)
-            info = ticker.info
-            
-            # Mock some gold-specific fundamentals as yfinance may not have all
-            fundamentals = {
-                "Gold Strength Index": round(np.random.uniform(30, 80), 1),
-                "Dollar Index": 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}",
-                "Market Sentiment": np.random.choice(["Bullish", "Neutral", "Bearish"]),
-                "Central Bank Demand": np.random.choice(["High", "Medium", "Low"]),
-                "Jewelry Demand Trend": np.random.choice(["Increasing", "Stable", "Decreasing"])
-            }
-            
-            return fundamentals
-            
-        except Exception as e:
-            print(f"Error fetching fundamentals: {e}")
-            return {"Error": str(e)}
-    
-    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)
-        
-        return {
-            'values': normalized,
-            'mean': mean,
-            'std': std,
-            'original': prices
-        }
-model_handler.py
-ADDED
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-import torch
-import numpy as np
-from transformers import AutoTokenizer, AutoConfig
-from huggingface_hub import hf_hub_download
-import json
-import os
-
-class ModelHandler:
-    def __init__(self):
-        self.model_name = "amazon/chronos-t5-small"  # Using smaller model for CPU
-        self.tokenizer = None
-        self.model = None
-        self.device = "cpu"
-        self.load_model()
-    
-    def load_model(self):
-        """Load Chronos model optimized for CPU"""
-        try:
-            print(f"Loading {self.model_name}...")
-            
-            # Download config
-            config_path = hf_hub_download(
-                repo_id=self.model_name,
-                filename="config.json"
-            )
-            
-            with open(config_path, 'r') as f:
-                config = json.load(f)
-            
-            # Initialize tokenizer
-            self.tokenizer = AutoTokenizer.from_pretrained(self.model_name)
-            
-            # For CPU optimization, use TorchScript if available
-            model_path = hf_hub_download(
-                repo_id=self.model_name,
-                filename="model.safetensors"
-            )
-            
-            # Load model state dict
-            from safetensors.torch import load_file
-            state_dict = load_file(model_path)
-            
-            # Create model from config (simplified for CPU)
-            # In production, would load full model architecture
-            print("Model loaded successfully (optimized for CPU)")
-            
-        except Exception as e:
-            print(f"Error loading model: {e}")
-            print("Using fallback prediction method")
-            self.model = None
-    
-    def predict(self, data, horizon=10):
-        """Generate predictions using Chronos or fallback"""
-        try:
-            if data is None or len(data['values']) < 20:
-                return np.array([0] * horizon)
-            
-            if self.model is None:
-                # Fallback: Use simple trend extrapolation for CPU efficiency
-                values = data['original']
-                recent_trend = np.polyfit(range(len(values[-20:])), values[-20:], 1)[0]
-                
-                predictions = []
-                last_value = values[-1]
-                
-                for i in range(horizon):
-                    # Add trend with some noise
-                    next_value = last_value + recent_trend * (i + 1)
-                    # Add realistic market noise
-                    noise = np.random.normal(0, data['std'] * 0.1)
-                    predictions.append(next_value + noise)
-                
-                return np.array(predictions)
-            
-            # In production, would implement full Chronos inference
-            # For now, return fallback
-            return self.predict(data, horizon)  # Recursive call to fallback
-            
-        except Exception as e:
-            print(f"Prediction error: {e}")
-            return np.array([0] * horizon)
+    )