ARIMA sample code for Notebook

rice-arima.json

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Rice Price Prediction - Philippines\n",
    "This notebook uses an **ARIMA** model to forecast retail rice prices for the next 6 months."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from statsmodels.tsa.arima.model import ARIMA\n",
    "import io\n",
    "\n",
    "# 1. Create Mock Data (Replace this with your CSV upload)\n",
    "csv_data = '''Date,Price\n",
    "2024-01-01,50.20\n",
    "2024-02-01,51.50\n",
    "2024-03-01,52.80\n",
    "2024-04-01,54.10\n",
    "2024-05-01,55.00\n",
    "2024-06-01,54.50\n",
    "2024-07-01,53.80\n",
    "2024-08-01,53.20\n",
    "2024-09-01,52.90\n",
    "2024-10-01,52.50\n",
    "2024-11-01,51.80\n",
    "2024-12-01,52.20\n",
    "2025-01-01,52.80\n",
    "2025-02-01,53.50\n",
    "2025-03-01,54.20'''\n",
    "\n",
    "df = pd.read_csv(io.StringIO(csv_data))\n",
    "df['Date'] = pd.to_datetime(df['Date'])\n",
    "df.set_index('Date', inplace=True)\n",
    "df = df.asfreq('MS')\n",
    "\n",
    "# 2. Build ARIMA Model (p=1, d=1, q=1)\n",
    "model = ARIMA(df['Price'], order=(1, 1, 1))\n",
    "model_fit = model.fit()\n",
    "\n",
    "# 3. Forecast\n",
    "forecast_steps = 6\n",
    "forecast_res = model_fit.get_forecast(steps=forecast_steps)\n",
    "forecast_df = forecast_res.summary_frame()\n",
    "\n",
    "# 4. Plot\n",
    "plt.figure(figsize=(12, 6))\n",
    "plt.plot(df.index, df['Price'], label='Actual Price', marker='o')\n",
    "plt.plot(forecast_df.index, forecast_df['mean'], label='6-Month Forecast', color='red', linestyle='--')\n",
    "plt.fill_between(forecast_df.index, forecast_df['mean_ci_lower'], forecast_df['mean_ci_upper'], color='pink', alpha=0.3)\n",
    "plt.title('Rice Price Forecast (PHP/kg)')\n",
    "plt.xlabel('Date')\n",
    "plt.ylabel('Price')\n",
    "plt.legend()\n",
    "plt.grid(True)\n",
    "plt.show()\n",
    "\n",
    "print(\"Forecasted Prices for next 6 months:\")\n",
    "print(forecast_df['mean'])\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_light_renderer": "inkpot",
   "version": "3.10.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}