debug_stats_fast.py

import asyncio
import os
import pandas as pd
from motor.motor_asyncio import AsyncIOMotorClient
from datetime import datetime, timedelta
from dotenv import load_dotenv

load_dotenv()
# Try different env variable names or default
MONGODB_URI = os.getenv("MONGODB_URI") or "mongodb://localhost:27017"

async def check_stats():
    print(f"Connecting to: {MONGODB_URI}")
    client = AsyncIOMotorClient(MONGODB_URI, serverSelectionTimeoutMS=5000)
    try:
        db = client['smart_office_raw']
        collection = db['device_raw_data']
        
        # JUST LAST 15 DAYS for speed
        fifteen_days_ago = datetime.utcnow() - timedelta(days=15)
        pipeline = [
            {"$match": {"timestamp": {"$gte": fifteen_days_ago}}},
            {"$project": {
                "timestamp": 1,
                "device_name": 1,
                "power": {"$ifNull": ["$status.cur_power", {"$ifNull": ["$status.power", 0]}]}
            }},
            {"$addFields": {
                "hour_bucket": {"$dateToString": {"format": "%Y-%m-%dT%H:00:00", "date": "$timestamp"}}
            }},
            {"$group": {
                "_id": {"hour": "$hour_bucket", "device": "$device_name"},
                "avg_power": {"$avg": "$power"}
            }},
            {"$group": {
                "_id": "$_id.hour",
                "total_power": {"$sum": "$avg_power"}
            }},
            {"$sort": {"_id": 1}}
        ]
        
        cursor = collection.aggregate(pipeline)
        logs = await cursor.to_list(length=1000)
        
        if not logs:
            db = client['smart_office_dashboard']
            collection = db['device_logs']
            cursor = collection.aggregate(pipeline)
            logs = await cursor.to_list(length=1000)
            
        if not logs:
            print("No data found")
            return

        rows = []
        for bucket in logs:
            rows.append({
                "ds": pd.to_datetime(bucket["_id"]),
                "y": float(bucket["total_power"])
            })
        
        df = pd.DataFrame(rows)
        df_daily = df.copy()
        df_daily['date'] = df_daily['ds'].dt.date
        
        df_daily_kwh = df_daily.groupby('date')['y'].apply(lambda g: g.mean() * len(g) / 1000.0)
        
        print(f"\n--- Last 15 Days Daily kWh Stats ---")
        print(df_daily_kwh.describe())
        print(f"95th Percentile: {df_daily_kwh.quantile(0.95):.2f}")
        print(f"Median: {df_daily_kwh.median():.2f}")
        print(f"Max: {df_daily_kwh.max():.2f}")
        
        p95 = df_daily_kwh.quantile(0.95)
        median = df_daily_kwh.median()
        cap_val = min(p95 * 1.15, median * 2.1)
        print(f"\nCalculated Cap (Target): {max(cap_val, 20.0):.2f}")
        
    except Exception as e:
        print(f"Error: {e}")
    finally:
        client.close()

if __name__ == "__main__":
    asyncio.run(check_stats())