Create main.py

main.py

@@ -0,0 +1,158 @@
+from fastapi import FastAPI, HTTPException, Query
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from typing import Dict, Any, List, Optional
+
+# Import core logic modules
+from data_processor import DataProcessor
+from sentiment_analyzer import SentimentAnalyzer
+from model_handler import ModelHandler
+from trading_logic import TradingLogic
+from plotter import create_mplfinance_chart
+
+# Initialize core components
+data_processor = DataProcessor()
+sentiment_analyzer = SentimentAnalyzer()
+model_handler = ModelHandler()
+trading_logic = TradingLogic()
+
+# FastAPI app setup
+app = FastAPI(
+    title="Ultimate Market Analysis & Prediction API",
+    version="1.0.0",
+    description="API for fetching market data, technical indicators, Chronos-2 predictions, and simulated analysis for GC=F and BTC-USD."
+)
+
+# Add CORS middleware for frontend access
+# HATI-HATI: Ganti "*" dengan domain frontend React Anda saat deployment produksi
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"], 
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# --- Skema Respon Pydantic ---
+
+class TradingMetrics(BaseModel):
+    Ticker: str
+    Current_Price: str
+    Signal: str
+    Confidence: str
+    Take_Profit: str
+    Stop_Loss: str
+    RSI: str
+    MACD: str
+    Volume: str
+
+class ChartAnalysisResponse(BaseModel):
+    chart_html_base64: Optional[str] = None # String base64 gambar, siap untuk tag <img src="data:image/png;base64,...">
+    metrics: Optional[TradingMetrics] = None
+    raw_predictions: Optional[List[float]] = None
+    error: Optional[str] = None
+
+class SentimentAnalysisResponse(BaseModel):
+    sentiment_score: float
+    news_summary_html: str
+
+class FundamentalsResponse(BaseModel):
+    fundamentals_data: Dict[str, Any]
+
+# --- Endpoint API ---
+
+@app.get("/")
+def read_root():
+    return {"message": "Welcome to the Ultimate Market Analysis API. Use /docs for API documentation."}
+
+@app.get("/analysis/chart", response_model=ChartAnalysisResponse)
+def get_chart_analysis(
+    ticker: str = Query(..., description="Market Ticker (e.g., GC=F, BTC-USD)"), 
+    interval: str = Query(..., description="Time Interval (e.g., 1d, 1h, 5m)")
+):
+    """
+    Mengambil data pasar, menghitung indikator, menghasilkan prediksi, 
+    dan mengembalikan gambar chart (Base64) serta metrik trading.
+    """
+    try:
+        # 1. Fetch data
+        df = data_processor.get_market_data(ticker, interval)
+        if df.empty:
+            return ChartAnalysisResponse(error=f"No data available for {ticker} at {interval}")
+        
+        # 2. Calculate Indicators
+        df = data_processor.calculate_indicators(df)
+        
+        # 3. Prepare and Predict
+        prepared_data = data_processor.prepare_for_chronos(df)
+        predictions = model_handler.predict(prepared_data, horizon=10)
+        
+        current_price = df['Close'].iloc[-1]
+        
+        # 4. Generate Chart (returns Base64 HTML string)
+        chart_html = create_mplfinance_chart(
+            df, 
+            ticker=f'{ticker} ({interval})', 
+            predictions=predictions
+        )
+
+        # 5. Generate Signal and Metrics
+        signal, confidence = trading_logic.generate_signal(
+            predictions, current_price, df
+        )
+        
+        tp, sl = trading_logic.calculate_tp_sl(
+            current_price, df['ATR'].iloc[-1], signal
+        )
+        
+        # 6. Format Metrics
+        metrics = TradingMetrics(
+            Ticker=ticker,
+            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}"
+        )
+        
+        return ChartAnalysisResponse(
+            chart_html_base64=chart_html, 
+            metrics=metrics,
+            raw_predictions=predictions.tolist()
+        )
+        
+    except Exception as e:
+        # Gunakan HTTPException untuk penanganan kesalahan API
+        raise HTTPException(status_code=500, detail=f"Error in chart analysis: {str(e)}")
+
+@app.get("/analysis/sentiment", response_model=SentimentAnalysisResponse)
+def get_sentiment_analysis(ticker: str = Query(..., description="Market Ticker (e.g., GC=F, BTC-USD)")):
+    """
+    Menganalisis dan mengembalikan skor sentimen pasar dan ringkasan berita (Simulasi).
+    """
+    try:
+        sentiment_score, news_summary_html = sentiment_analyzer.analyze_market_sentiment(ticker)
+        
+        return SentimentAnalysisResponse(
+            sentiment_score=sentiment_score,
+            news_summary_html=news_summary_html
+        )
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error in sentiment analysis: {str(e)}")
+
+@app.get("/analysis/fundamentals", response_model=FundamentalsResponse)
+def get_fundamentals_analysis(ticker: str = Query(..., description="Market Ticker (e.g., GC=F, BTC-USD)")):
+    """
+    Mengambil data fundamental pasar utama (Simulasi).
+    """
+    try:
+        fundamentals = data_processor.get_fundamental_data(ticker)
+        
+        return FundamentalsResponse(fundamentals_data=fundamentals)
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error in fundamentals analysis: {str(e)}")