# app.py
import os
os.environ["STREAMLIT_CONFIG_DIR"] = "./.streamlit"
os.makedirs("./.streamlit", exist_ok=True)


import pandas as pd
import numpy as np
from datetime import datetime, timedelta
from prophet import Prophet
import streamlit as st
import matplotlib.pyplot as plt

# Simulate factory sensor data
def simulate_factory_data(days=30, freq='H'):
    date_rng = pd.date_range(end=datetime.now(), periods=24*days, freq=freq)
    df = pd.DataFrame(date_rng, columns=['ds'])
    df['temperature'] = np.random.normal(loc=70, scale=5, size=(len(date_rng)))
    df['vibration'] = np.random.normal(loc=20, scale=3, size=(len(date_rng)))
    df['power_usage'] = np.random.normal(loc=120, scale=10, size=(len(date_rng)))
    return df

# Forecast temperature using Prophet
def forecast_temperature(df):
    model = Prophet()
    df_temp = df[['ds', 'temperature']].rename(columns={"temperature": "y"})
    model.fit(df_temp)
    future = model.make_future_dataframe(periods=48, freq='H')
    forecast = model.predict(future)
    return forecast

# Streamlit UI
st.title("🧠 Smart Factory AI Dashboard")
st.markdown("Forecasting machine temperature to predict maintenance needs.")

df = simulate_factory_data()
forecast = forecast_temperature(df)

# Plot forecast
st.subheader("📈 Machine Temperature Forecast (Next 48 hours)")
fig, ax = plt.subplots()
ax.plot(df['ds'], df['temperature'], label='Actual')
ax.plot(forecast['ds'], forecast['yhat'], label='Forecast')
ax.fill_between(forecast['ds'], forecast['yhat_lower'], forecast['yhat_upper'], alpha=0.2, label='Confidence Interval')
ax.set_xlabel("Time")
ax.set_ylabel("Temperature (°C)")
ax.legend()
st.pyplot(fig)