import pandas as pd
import json
import os
import numpy as np
from datetime import datetime
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix

class HougaardAnalyzer:
    def __init__(self, file_path):
        self.file_path = file_path
        self.df = None
        self.results = {}

    def load_data(self):
        """Loads Freqtrade/Bybit JSON format and converts to DataFrame."""
        print(f"Loading data from {self.file_path}...")
        with open(self.file_path, 'r') as f:
            data = json.load(f)
        
        # Format: [timestamp, open, high, low, close, volume]
        cols = ['date', 'open', 'high', 'low', 'close', 'volume']
        self.df = pd.DataFrame(data, columns=cols)
        
        # Convert timestamp (ms) to datetime
        self.df['date'] = pd.to_datetime(self.df['date'], unit='ms', utc=True)
        self.df.set_index('date', inplace=True)
        print(f"Loaded {len(self.df)} candles.")

    def engineer_features(self):
        """Creates Hougaard-style features."""
        print("Engineering features...")
        df = self.df
        
        # 1. Time-based features
        df['hour'] = df.index.hour
        df['day_of_week'] = df.index.dayofweek
        
        # 2. Overnight Range (00:00 - 08:00 UTC)
        # We group by day and calculate High-Low for the 0-8h window
        df['date_only'] = df.index.date
        
        overnight = df.between_time('00:00', '08:00').groupby('date_only').agg({
            'high': 'max',
            'low': 'min',
            'open': 'first'
        }).rename(columns={'high': 'on_high', 'low': 'on_low', 'open': 'on_open'})
        
        overnight['on_range_pct'] = (overnight['on_high'] - overnight['on_low']) / overnight['on_open']
        
        # Map back to main DF
        df = df.join(overnight, on='date_only')
        
        # 3. Distance from Overnight High/Low at 08:00
        df['dist_from_on_high'] = (df['close'] - df['on_high']) / df['on_high']
        df['dist_from_on_low'] = (df['close'] - df['on_low']) / df['on_low']
        
        # 4. Volatility (ATR-like)
        df['body_size'] = abs(df['close'] - df['open']) / df['open']
        df['wick_size'] = (df['high'] - np.maximum(df['open'], df['close'])) / df['open']
        
        self.df = df.dropna()

    def label_data(self, target_pct=0.01, stop_pct=0.005, horizon_candles=48):
        """
        Labels a 'Long' setup at 08:00 UTC.
        1: Hits target before stop
        0: Hits stop before target or expires
        """
        print(f"Labeling data (Target: {target_pct*100}%, Stop: {stop_pct*100}%)...")
        # We only look at the 08:00 candle (London Open)
        setups = self.df[self.df.index.hour == 8].copy()
        
        labels = []
        for idx, row in setups.iterrows():
            entry_price = row['close']
            target_price = entry_price * (1 + target_pct)
            stop_price = entry_price * (1 - stop_pct)
            
            # Look ahead
            future_data = self.df.loc[idx:].iloc[1:horizon_candles]
            
            success = 0
            for f_idx, f_row in future_data.iterrows():
                if f_row['high'] >= target_price:
                    success = 1
                    break
                if f_row['low'] <= stop_price:
                    success = 0
                    break
            labels.append(success)
            
        setups['label'] = labels
        return setups

    def run_analysis(self):
        self.load_data()
        self.engineer_features()
        
        setups = self.label_data()
        
        # Features for the model
        features = ['hour', 'day_of_week', 'on_range_pct', 'dist_from_on_high', 'dist_from_on_low', 'body_size', 'wick_size']
        X = setups[features]
        y = setups['label']
        
        if len(y.unique()) < 2:
            print("Error: Not enough variance in labels. Adjust target/stop.")
            return

        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
        
        model = RandomForestClassifier(n_estimators=100, random_state=42)
        model.fit(X_train, y_train)
        
        # Importance
        importances = pd.Series(model.feature_importances_, index=features).sort_values(ascending=False)
        print("\n--- Feature Importance (Hougaard Insights) ---")
        print(importances)
        
        # Accuracy
        y_pred = model.predict(X_test)
        print("\n--- Model Performance ---")
        print(classification_report(y_test, y_pred))

if __name__ == "__main__":
    # Test with BTC 5m data
    data_path = "/Volumes/Alpha SSD/Coding/freqtrade/user_data/data/bybit/BTC_USDT-5m-futures.json"
    analyzer = HougaardAnalyzer(data_path)
    analyzer.run_analysis()