Upload 6 files

app.py

@@ -0,0 +1,67 @@
+import os
+import json
+from datetime import datetime, time, date
+from fastapi import FastAPI, BackgroundTasks, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from zoneinfo import ZoneInfo
+from data_updater import update_daily_data, is_trading_day
+from forecaster_engine import generate_predictions
+
+IST = ZoneInfo("Asia/Kolkata")
+MARKET_CLOSE_BUFFER = time(15, 45) # Update runs after 3:45 PM
+PREDICTIONS_FILE = os.path.join(os.path.dirname(__file__), "predictions.json")
+
+app = FastAPI(title="HF NIFTY Forecaster Backend")
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+def run_update_pipeline():
+    try:
+        # Step 1: Update data
+        res = update_daily_data()
+        if res.get("status") == "error":
+            print(f"Update failed: {res.get('reason')}")
+            return
+            
+        # Step 2: Generate predictions
+        generate_predictions()
+    except Exception as e:
+        print(f"Pipeline error: {e}")
+
+@app.get("/predictions")
+def get_predictions():
+    if not os.path.exists(PREDICTIONS_FILE):
+        raise HTTPException(status_code=404, detail="Predictions not yet generated")
+    
+    with open(PREDICTIONS_FILE, "r") as f:
+        data = json.load(f)
+        
+    return data
+
+@app.post("/cron/update")
+def cron_trigger(background_tasks: BackgroundTasks):
+    now = datetime.now(IST)
+    today = now.date()
+    current_time = now.time()
+    
+    # 1. Check if it's a trading day
+    if not is_trading_day(today):
+        return {"status": "skipped", "reason": f"{today} is a holiday or weekend"}
+        
+    # 2. Check if it's past 3:45 PM
+    if current_time < MARKET_CLOSE_BUFFER:
+        return {"status": "skipped", "reason": "Market is still open or buffer not reached. Runs after 3:45 PM IST."}
+        
+    # Trigger the full pipeline in the background so Netlify doesn't timeout
+    background_tasks.add_task(run_update_pipeline)
+    
+    return {"status": "triggered", "message": "Update and forecast pipeline started in the background."}
+
+@app.get("/health")
+def health_check():
+    return {"status": "alive", "server_time_ist": datetime.now(IST).isoformat()}

data/nifty50_daily.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ec56e84aa6a133397cbc6000ac563883df0f9287d2cafb434e9c7efcf7778a
+size 1377561

data_updater.py

@@ -0,0 +1,105 @@
+import os
+import time
+import requests
+import pandas as pd
+from datetime import datetime, date, timedelta
+from zoneinfo import ZoneInfo
+import pandas_market_calendars as mcal
+
+IST = ZoneInfo("Asia/Kolkata")
+DATA_FILE = os.path.join(os.path.dirname(__file__), "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 is_trading_day(target_date: date) -> bool:
+    try:
+        nse = mcal.get_calendar('NSE')
+        schedule = nse.schedule(start_date=target_date, end_date=target_date)
+        return not schedule.empty
+    except Exception as e:
+        print(f"Calendar check failed: {e}")
+        # Fallback: assume Monday-Friday is trading day
+        return target_date.weekday() < 5
+
+def fetch_groww_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:
+                # Candles format: [timestamp, open, high, low, close, volume]
+                last_candle = data['candles'][-1]
+                return last_candle[4] # Close price
+        return None
+    except Exception as e:
+        print(f"Error fetching {ticker}: {e}")
+        return None
+
+def update_daily_data():
+    now = datetime.now(IST)
+    today = now.date()
+    
+    if not is_trading_day(today):
+        print(f"{today} is not a trading day. Skipping update.")
+        return {"status": "skipped", "reason": "not a trading day"}
+        
+    if not os.path.exists(DATA_FILE):
+        print(f"Data file {DATA_FILE} not found!")
+        return {"status": "error", "reason": "data file missing"}
+        
+    # Read existing data
+    df = pd.read_parquet(DATA_FILE)
+    
+    # Check if we already updated today
+    if not df.empty and pd.to_datetime(today) in df['date'].dt.date.values:
+        # We might have partial data or want to overwrite, but for safety:
+        # Let's delete today's entries if they exist so we can cleanly append
+        df = df[df['date'].dt.date != today]
+        
+    print(f"Fetching data for {today}...")
+    
+    # Market hours: 09:15 to 15:30 IST
+    start_dt = datetime.combine(today, datetime.strptime("09:15", "%H:%M").time()).replace(tzinfo=IST)
+    end_dt = datetime.combine(today, datetime.strptime("15:30", "%H:%M").time()).replace(tzinfo=IST)
+    
+    start_ts = int(start_dt.timestamp() * 1000)
+    end_ts = int(end_dt.timestamp() * 1000)
+    
+    new_rows = []
+    
+    for ticker in TICKERS:
+        close_price = fetch_groww_data(ticker, start_ts, end_ts)
+        if close_price is not None:
+            new_rows.append({
+                'date': pd.to_datetime(today),
+                'close': float(close_price),
+                'ticker': ticker
+            })
+        time.sleep(0.5) # Rate limiting
+        
+    if new_rows:
+        new_df = pd.DataFrame(new_rows)
+        updated_df = pd.concat([df, new_df], ignore_index=True)
+        updated_df.sort_values(by=['ticker', 'date'], inplace=True)
+        updated_df.to_parquet(DATA_FILE)
+        print(f"Successfully updated {len(new_rows)} tickers for {today}")
+        return {"status": "success", "updated_count": len(new_rows)}
+    else:
+        print("No new data fetched.")
+        return {"status": "error", "reason": "fetch failed for all tickers"}
+
+if __name__ == "__main__":
+    update_daily_data()

forecaster_engine.py

@@ -0,0 +1,123 @@
+import os
+import json
+import pandas as pd
+import numpy as np
+from datetime import datetime
+
+DATA_FILE = os.path.join(os.path.dirname(__file__), "data", "nifty50_daily.parquet")
+PREDICTIONS_FILE = os.path.join(os.path.dirname(__file__), "predictions.json")
+
+def generate_predictions():
+    if not os.path.exists(DATA_FILE):
+        print(f"Data file missing: {DATA_FILE}")
+        return
+        
+    df_all = pd.read_parquet(DATA_FILE)
+    tickers = df_all['ticker'].unique()
+    
+    predictions = {}
+    forecast_date = None
+    
+    for ticker in tickers:
+        df = df_all[df_all['ticker'] == ticker].copy()
+        df.sort_values('date', inplace=True)
+        df.set_index('date', inplace=True)
+        
+        if len(df) < 130:
+            continue
+            
+        forecast_date_ts = df.index[-1] + pd.Timedelta(days=1)
+        # Advance past weekends roughly for display
+        if forecast_date_ts.weekday() >= 5:
+            forecast_date_ts += pd.Timedelta(days=(7 - forecast_date_ts.weekday()))
+            
+        if forecast_date is None:
+            forecast_date = forecast_date_ts.strftime('%Y-%m-%d')
+            
+        daily_close = df['close']
+        
+        # Features
+        delta = daily_close.diff()
+        gain = (delta.where(delta > 0, 0)).rolling(window=2).mean()
+        loss = (-delta.where(delta < 0, 0)).rolling(window=2).mean()
+        rs = gain / loss
+        rsi_2 = 100 - (100 / (1 + rs))
+        
+        sma_3 = daily_close.rolling(window=3).mean()
+        dist_sma3 = daily_close / sma_3
+        
+        sma_5 = daily_close.rolling(window=5).mean()
+        dist_sma5 = daily_close / sma_5
+        
+        df_eval = pd.DataFrame({
+            'close': daily_close,
+            'rsi_2': rsi_2,
+            'dist_sma3': dist_sma3,
+            'dist_sma5': dist_sma5,
+            '1d_ret': daily_close.pct_change()
+        }).dropna()
+        
+        # Target for historical testing
+        df_eval['actual_dir'] = np.where(df_eval['close'].shift(-1) > df_eval['close'], 1, -1)
+        
+        # The last row is TODAY. We don't have tomorrow's close, so actual_dir is wrong for the last row.
+        # We test on the 120 days BEFORE today
+        test_set = df_eval.iloc[-121:-1]
+        today_data = df_eval.iloc[-1]
+        
+        best_acc = 0
+        best_rule = None
+        
+        # 1. RSI-2 threshold
+        for thresh in [10, 20, 30, 40, 50, 60, 70, 80, 90]:
+            for op in ['<', '>']:
+                sig = np.where(test_set['rsi_2'] < thresh if op == '<' else test_set['rsi_2'] > thresh, 1, -1)
+                acc = (sig == test_set['actual_dir']).mean()
+                if acc > best_acc:
+                    best_acc = acc
+                    best_rule = ('rsi_2', thresh, op)
+                    
+        # 2. SMA distance threshold
+        for feature in ['dist_sma3', 'dist_sma5']:
+            for thresh in [0.95, 0.98, 1.0, 1.02, 1.05]:
+                sig = np.where(test_set[feature] < thresh, 1, -1)
+                acc = (sig == test_set['actual_dir']).mean()
+                if acc > best_acc:
+                    best_acc = acc
+                    best_rule = (feature, thresh, '<')
+                    
+        # 3. 1d return
+        sig = np.where(test_set['1d_ret'] < 0, 1, -1)
+        acc = (sig == test_set['actual_dir']).mean()
+        if acc > best_acc:
+            best_acc = acc
+            best_rule = ('1d_ret', 0, '<')
+            
+        feature, thresh, op = best_rule
+        val = today_data[feature]
+        
+        if op == '<':
+            prediction = 1 if val < thresh else -1
+        else:
+            prediction = 1 if val > thresh else -1
+            
+        predictions[ticker] = {
+            "prediction": "UP" if prediction == 1 else "DOWN",
+            "probability": round(best_acc * 100, 2),
+            "rule_used": f"{feature} {op} {thresh}"
+        }
+        
+    output = {
+        "generated_at": datetime.now().isoformat(),
+        "forecast_date": forecast_date,
+        "predictions": predictions
+    }
+    
+    with open(PREDICTIONS_FILE, "w") as f:
+        json.dump(output, f, indent=4)
+        
+    print(f"Generated predictions for {forecast_date}. Saved to {PREDICTIONS_FILE}")
+    return output
+
+if __name__ == "__main__":
+    generate_predictions()

predictions.json

@@ -0,0 +1,251 @@
+{
+    "generated_at": "2026-06-18T16:56:32.759921",
+    "forecast_date": "2026-06-16",
+    "predictions": {
+        "ADANIENT": {
+            "prediction": "DOWN",
+            "probability": 55.83,
+            "rule_used": "rsi_2 < 10"
+        },
+        "ADANIPORTS": {
+            "prediction": "UP",
+            "probability": 56.67,
+            "rule_used": "dist_sma5 < 1.0"
+        },
+        "APOLLOHOSP": {
+            "prediction": "DOWN",
+            "probability": 55.83,
+            "rule_used": "rsi_2 > 10"
+        },
+        "ASIANPAINT": {
+            "prediction": "DOWN",
+            "probability": 55.83,
+            "rule_used": "dist_sma5 < 0.95"
+        },
+        "AXISBANK": {
+            "prediction": "UP",
+            "probability": 59.17,
+            "rule_used": "rsi_2 > 90"
+        },
+        "BAJAJ-AUTO": {
+            "prediction": "UP",
+            "probability": 57.5,
+            "rule_used": "rsi_2 < 40"
+        },
+        "BAJAJFINSV": {
+            "prediction": "DOWN",
+            "probability": 55.0,
+            "rule_used": "rsi_2 < 20"
+        },
+        "BAJFINANCE": {
+            "prediction": "DOWN",
+            "probability": 56.67,
+            "rule_used": "dist_sma5 < 1.0"
+        },
+        "BHARTIARTL": {
+            "prediction": "DOWN",
+            "probability": 55.0,
+            "rule_used": "rsi_2 < 20"
+        },
+        "BPCL": {
+            "prediction": "DOWN",
+            "probability": 64.17,
+            "rule_used": "rsi_2 < 10"
+        },
+        "BRITANNIA": {
+            "prediction": "DOWN",
+            "probability": 54.17,
+            "rule_used": "rsi_2 < 70"
+        },
+        "CIPLA": {
+            "prediction": "DOWN",
+            "probability": 56.67,
+            "rule_used": "dist_sma3 < 0.95"
+        },
+        "COALINDIA": {
+            "prediction": "DOWN",
+            "probability": 57.5,
+            "rule_used": "rsi_2 < 30"
+        },
+        "DIVISLAB": {
+            "prediction": "UP",
+            "probability": 57.5,
+            "rule_used": "dist_sma5 < 1.0"
+        },
+        "DRREDDY": {
+            "prediction": "UP",
+            "probability": 65.0,
+            "rule_used": "rsi_2 < 60"
+        },
+        "EICHERMOT": {
+            "prediction": "DOWN",
+            "probability": 57.5,
+            "rule_used": "rsi_2 < 90"
+        },
+        "GRASIM": {
+            "prediction": "DOWN",
+            "probability": 63.33,
+            "rule_used": "1d_ret < 0"
+        },
+        "HCLTECH": {
+            "prediction": "UP",
+            "probability": 54.17,
+            "rule_used": "rsi_2 > 20"
+        },
+        "HDFCBANK": {
+            "prediction": "DOWN",
+            "probability": 59.17,
+            "rule_used": "dist_sma3 < 0.98"
+        },
+        "HDFCLIFE": {
+            "prediction": "DOWN",
+            "probability": 63.33,
+            "rule_used": "dist_sma3 < 0.98"
+        },
+        "HEROMOTOCO": {
+            "prediction": "DOWN",
+            "probability": 55.0,
+            "rule_used": "rsi_2 < 30"
+        },
+        "HINDALCO": {
+            "prediction": "UP",
+            "probability": 63.33,
+            "rule_used": "dist_sma5 < 1.05"
+        },
+        "HINDUNILVR": {
+            "prediction": "UP",
+            "probability": 53.33,
+            "rule_used": "rsi_2 > 20"
+        },
+        "ICICIBANK": {
+            "prediction": "DOWN",
+            "probability": 55.83,
+            "rule_used": "dist_sma5 < 0.98"
+        },
+        "INDUSINDBK": {
+            "prediction": "DOWN",
+            "probability": 54.17,
+            "rule_used": "rsi_2 < 30"
+        },
+        "INFY": {
+            "prediction": "DOWN",
+            "probability": 55.0,
+            "rule_used": "dist_sma3 < 0.95"
+        },
+        "ITC": {
+            "prediction": "DOWN",
+            "probability": 56.67,
+            "rule_used": "dist_sma3 < 0.95"
+        },
+        "JSWSTEEL": {
+            "prediction": "DOWN",
+            "probability": 61.67,
+            "rule_used": "rsi_2 < 40"
+        },
+        "KOTAKBANK": {
+            "prediction": "DOWN",
+            "probability": 53.33,
+            "rule_used": "rsi_2 < 10"
+        },
+        "LTIM": {
+            "prediction": "UP",
+            "probability": 60.0,
+            "rule_used": "1d_ret < 0"
+        },
+        "LT": {
+            "prediction": "DOWN",
+            "probability": 58.33,
+            "rule_used": "1d_ret < 0"
+        },
+        "MARUTI": {
+            "prediction": "DOWN",
+            "probability": 61.67,
+            "rule_used": "rsi_2 < 40"
+        },
+        "MM": {
+            "prediction": "DOWN",
+            "probability": 55.0,
+            "rule_used": "rsi_2 < 30"
+        },
+        "NESTLEIND": {
+            "prediction": "UP",
+            "probability": 57.5,
+            "rule_used": "rsi_2 < 70"
+        },
+        "NTPC": {
+            "prediction": "UP",
+            "probability": 57.5,
+            "rule_used": "rsi_2 < 80"
+        },
+        "ONGC": {
+            "prediction": "UP",
+            "probability": 58.33,
+            "rule_used": "rsi_2 < 40"
+        },
+        "POWERGRID": {
+            "prediction": "DOWN",
+            "probability": 55.0,
+            "rule_used": "rsi_2 > 70"
+        },
+        "RELIANCE": {
+            "prediction": "DOWN",
+            "probability": 55.0,
+            "rule_used": "dist_sma5 < 0.98"
+        },
+        "SBILIFE": {
+            "prediction": "DOWN",
+            "probability": 60.83,
+            "rule_used": "1d_ret < 0"
+        },
+        "SBIN": {
+            "prediction": "UP",
+            "probability": 55.83,
+            "rule_used": "rsi_2 > 10"
+        },
+        "SUNPHARMA": {
+            "prediction": "UP",
+            "probability": 54.17,
+            "rule_used": "rsi_2 > 60"
+        },
+        "TATACONSUM": {
+            "prediction": "UP",
+            "probability": 57.5,
+            "rule_used": "dist_sma3 < 1.0"
+        },
+        "TATASTEEL": {
+            "prediction": "UP",
+            "probability": 55.83,
+            "rule_used": "rsi_2 < 10"
+        },
+        "TCS": {
+            "prediction": "UP",
+            "probability": 57.5,
+            "rule_used": "rsi_2 > 20"
+        },
+        "TECHM": {
+            "prediction": "UP",
+            "probability": 57.5,
+            "rule_used": "dist_sma3 < 1.02"
+        },
+        "TITAN": {
+            "prediction": "DOWN",
+            "probability": 55.0,
+            "rule_used": "rsi_2 < 40"
+        },
+        "ULTRACEMCO": {
+            "prediction": "DOWN",
+            "probability": 57.5,
+            "rule_used": "rsi_2 < 50"
+        },
+        "UPL": {
+            "prediction": "DOWN",
+            "probability": 60.0,
+            "rule_used": "dist_sma5 < 1.0"
+        },
+        "WIPRO": {
+            "prediction": "UP",
+            "probability": 60.83,
+            "rule_used": "rsi_2 > 10"
+        }
+    }
+}

requirements.txt

@@ -0,0 +1,7 @@
+fastapi==0.103.1
+uvicorn==0.23.2
+pandas==2.1.0
+requests==2.31.0
+pandas_market_calendars==4.3.0
+pyarrow==13.0.0
+fastparquet==2023.8.0