Delete t5_engine.py

t5_engine.py

@@ -1,168 +0,0 @@
-import os
-import json
-import time
-import requests
-import joblib
-import pandas as pd
-import numpy as np
-from datetime import datetime, date
-from zoneinfo import ZoneInfo
-from features_t5 import extract_semantic_features_t5, extract_sequential_features_t5
-
-IST = ZoneInfo("Asia/Kolkata")
-DATA_DIR = os.path.dirname(__file__)
-MODELS_DIR = os.path.join(DATA_DIR, "models")
-PREDICTIONS_FILE_T5 = os.path.join(DATA_DIR, "predictions_t5.json")
-DAILY_DATA_FILE = os.path.join(DATA_DIR, "data", "nifty50_daily.parquet")
-
-TICKERS = [
-    'ADANIENT', 'ADANIPORTS', 'APOLLOHOSP', 'ASIANPAINT', 'AXISBANK', 'BAJAJ-AUTO', 'BAJAJFINSV', 'BAJFINANCE', 
-    'BHARTIARTL', 'BPCL', 'BRITANNIA', 'CIPLA', 'COALINDIA', 'DIVISLAB', 'DRREDDY', 'EICHERMOT', 'GRASIM', 
-    'HCLTECH', 'HDFCBANK', 'HDFCLIFE', 'HEROMOTOCO', 'HINDALCO', 'HINDUNILVR', 'ICICIBANK', 'INDUSINDBK', 
-    'INFY', 'ITC', 'JSWSTEEL', 'KOTAKBANK', 'LT', 'M&M', 'MARUTI', 'NESTLEIND', 'NTPC', 'ONGC', 'POWERGRID', 
-    'RELIANCE', 'SBILIFE', 'SBIN', 'SUNPHARMA', 'TATACONSUM', 'TATAMOTORS', 'TATASTEEL', 'TCS', 'TECHM', 
-    'TITAN', 'ULTRACEMCO', 'UPL', 'WIPRO'
-]
-
-def fetch_groww_t5_data(ticker: str, start_ts: int, end_ts: int):
-    url = f"https://groww.in/v1/api/charting_service/v2/chart/exchange/NSE/segment/CASH/{ticker}?endTimeInMillis={end_ts}&intervalInMinutes=1&startTimeInMillis={start_ts}"
-    headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
-        "Accept": "application/json"
-    }
-    
-    try:
-        response = requests.get(url, headers=headers, timeout=10)
-        if response.status_code == 200:
-            data = response.json()
-            if data and 'candles' in data and len(data['candles']) > 0:
-                rows = []
-                for c in data['candles']:
-                    rows.append({
-                        "date": datetime.fromtimestamp(c[0], IST).replace(tzinfo=None),
-                        "open": float(c[1]),
-                        "high": float(c[2]),
-                        "low": float(c[3]),
-                        "close": float(c[4]),
-                        "volume": float(c[5]),
-                        "ticker": ticker
-                    })
-                return pd.DataFrame(rows)
-        return None
-    except Exception as e:
-        print(f"Error fetching T+5 for {ticker}: {e}")
-        return None
-
-def fetch_all_t5_data(today: date):
-    # Market open 09:15 to 09:20
-    start_dt = datetime.combine(today, datetime.strptime("09:15", "%H:%M").time()).replace(tzinfo=IST)
-    end_dt = datetime.combine(today, datetime.strptime("09:25", "%H:%M").time()).replace(tzinfo=IST) # fetch slightly wider just in case
-    
-    start_ts = int(start_dt.timestamp() * 1000)
-    end_ts = int(end_dt.timestamp() * 1000)
-    
-    dfs = []
-    for ticker in TICKERS:
-        df_tick = fetch_groww_t5_data(ticker, start_ts, end_ts)
-        if df_tick is not None and not df_tick.empty:
-            dfs.append(df_tick)
-        time.sleep(0.1)
-        
-    if dfs:
-        return pd.concat(dfs, ignore_index=True)
-    return pd.DataFrame()
-
-def generate_t5_predictions():
-    now = datetime.now(IST)
-    today = now.date()
-    
-    df_live = fetch_all_t5_data(today)
-    if df_live.empty:
-        print("No live data fetched for T+5.")
-        return None
-        
-    df_live.set_index("date", inplace=True)
-    
-    # Load previous day's close for the gap feature
-    prev_closes = {}
-    if os.path.exists(DAILY_DATA_FILE):
-        df_daily = pd.read_parquet(DAILY_DATA_FILE)
-        df_daily = df_daily[df_daily['date'].dt.date < today]
-        if not df_daily.empty:
-            for ticker in TICKERS:
-                t_data = df_daily[df_daily['ticker'] == ticker]
-                if not t_data.empty:
-                    # Last row is yesterday's close
-                    t_data = t_data.sort_values("date")
-                    prev_closes[ticker] = t_data.iloc[-1]['close']
-                    
-    predictions = {}
-    
-    for ticker in TICKERS:
-        model_path = os.path.join(MODELS_DIR, f"{ticker}_t5.joblib")
-        if not os.path.exists(model_path):
-            continue
-            
-        feat_type, clf = joblib.load(model_path)
-        
-        # Build dummy dataframe for extraction
-        t_data = df_live[df_live['ticker'] == ticker].copy()
-        if t_data.empty:
-            continue
-            
-        # Insert yesterday's dummy row at 15:30 to populate prev_daily_close correctly
-        if ticker in prev_closes:
-            yday = datetime.combine(today - pd.Timedelta(days=1), datetime.strptime("15:30", "%H:%M").time())
-            t_data.loc[yday] = {"open": prev_closes[ticker], "high": prev_closes[ticker], "low": prev_closes[ticker], "close": prev_closes[ticker], "volume": 0, "ticker": ticker}
-            
-        t_data.sort_index(inplace=True)
-        
-        if feat_type == "semantic":
-            X, _, _ = extract_semantic_features_t5(t_data)
-        else:
-            X, _, _ = extract_sequential_features_t5(t_data)
-            
-        if X is None or X.empty:
-            continue
-            
-        # Get today's prediction
-        if today in X.index:
-            X_today = X.loc[[today]]
-            prob_up = clf.predict_proba(X_today)[0][1]
-            prob_dn = 1.0 - prob_up
-            
-            if prob_up > prob_dn:
-                pred_dir = "UP"
-                prob_val = prob_up
-            else:
-                pred_dir = "DOWN"
-                prob_val = prob_dn
-                
-            conf = "HIGH" if prob_val >= 0.55 else "NORMAL"
-            
-            predictions[ticker] = {
-                "prediction": pred_dir,
-                "probability": round(prob_val * 100, 2),
-                "confidence": conf
-            }
-
-    probs = [info["probability"] for info in predictions.values()]
-    mean_accuracy = round(np.mean(probs), 2) if probs else 0.0
-    median_accuracy = round(np.median(probs), 2) if probs else 0.0
-    
-    output = {
-        "generated_at": datetime.now().isoformat(),
-        "forecast_date": today.strftime('%Y-%m-%d'),
-        "mean_accuracy": mean_accuracy,
-        "median_accuracy": median_accuracy,
-        "predictions": predictions
-    }
-    
-    with open(PREDICTIONS_FILE_T5, "w") as f:
-        json.dump(output, f, indent=4)
-        
-    print(f"Generated T+5 predictions. Saved to {PREDICTIONS_FILE_T5}")
-    return output
-
-if __name__ == "__main__":
-    generate_t5_predictions()