{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "dc7dbdb5-f895-4737-a8e6-e336d3f08a90",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "source": [
    "# Forecasting with Chronos\n",
    "\n",
    "## Feng Li\n",
    "\n",
    "### Guanghua School of Management\n",
    "### Peking University\n",
    "\n",
    "### [feng.li@gsm.pku.edu.cn](feng.li@gsm.pku.edu.cn)\n",
    "### Course home page: [https://feng.li/forecasting-with-ai](https://feng.li/forecasting-with-ai)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf4c3cba",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "source": [
    "## Chronos-2 Basics\n",
    "\n",
    "**Chronos-2** is a foundation model for time series forecasting that builds on [Chronos](https://arxiv.org/abs/2403.07815) and [Chronos-Bolt](https://aws.amazon.com/blogs/machine-learning/fast-and-accurate-zero-shot-forecasting-with-chronos-bolt-and-autogluon/). It offers significant improvements in capabilities and can handle diverse forecasting scenarios not supported by earlier models.\n",
    "\n",
    "| Capability | Chronos | Chronos-Bolt | Chronos-2 |\n",
    "|------------|---------|--------------|-----------|\n",
    "| Univariate Forecasting | ✅ | ✅ | ✅ |\n",
    "| Cross-learning across items | ❌ | ❌ | ✅ |\n",
    "| Multivariate Forecasting | ❌ | ❌ | ✅ |\n",
    "| Past-only (real/categorical) covariates | ❌ | ❌ | ✅ |\n",
    "| Known future (real/categorical) covariates | 🧩 | 🧩 | ✅ |\n",
    "| Fine-tuning support | ✅ | ✅ | ✅ |\n",
    "| Max. Context Length | 512 | 2048 | 8192 |\n",
    "\n",
    "🧩 Chronos/Chronos-Bolt do not natively support future covariates, but they can be combined with external covariate regressors (see [AutoGluon tutorial](https://auto.gluon.ai/stable/tutorials/timeseries/forecasting-chronos.html#incorporating-the-covariates)). This only models per-timestep effects, not effects across time. In contrast, Chronos-2 supports all covariate types natively.\n",
    "\n",
    "More details about Chronos-2 are available in the [technical report](https://www.arxiv.org/abs/2510.15821)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e1d5f2e6",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# pip install -U \"chronos-forecasting>=2.0\" \"pandas[pyarrow]\" \"matplotlib\" --break-system-packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "fcc7e496",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2025-11-14 11:24:09.328586: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
      "2025-11-14 11:24:09.345621: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
      "2025-11-14 11:24:09.350534: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
      "2025-11-14 11:24:09.363797: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
      "To enable the following instructions: AVX2 AVX512F FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
      "2025-11-14 11:24:10.185523: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loaded Chronos-2 from local dir on cpu\n"
     ]
    }
   ],
   "source": [
    "from chronos import BaseChronosPipeline, Chronos2Pipeline\n",
    "# https://huggingface.co/amazon/chronos-2\n",
    "LOCAL_MODEL_DIR = \"../data/chronos-2\" # Your offline pretrained time series foundation model\n",
    "pipeline: Chronos2Pipeline = BaseChronosPipeline.from_pretrained(\n",
    "    LOCAL_MODEL_DIR, device_map='cpu'\n",
    ")\n",
    "print(\"Loaded Chronos-2 from local dir on\", 'cpu')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ef707b6",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "source": [
    "## Univariate Forecasting\n",
    "\n",
    "We start with a simple univariate forecasting example using the pandas API."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "39de5d7e",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>item_id</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-01 00:00:00</td>\n",
       "      <td>605.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-01 01:00:00</td>\n",
       "      <td>586.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-01 02:00:00</td>\n",
       "      <td>586.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-01 03:00:00</td>\n",
       "      <td>559.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-01 04:00:00</td>\n",
       "      <td>511.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>353495</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-09 19:00:00</td>\n",
       "      <td>48.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>353496</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-09 20:00:00</td>\n",
       "      <td>41.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>353497</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-09 21:00:00</td>\n",
       "      <td>35.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>353498</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-09 22:00:00</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>353499</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-09 23:00:00</td>\n",
       "      <td>17.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>353500 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       item_id            timestamp  target\n",
       "0           H1  1750-01-01 00:00:00   605.0\n",
       "1           H1  1750-01-01 01:00:00   586.0\n",
       "2           H1  1750-01-01 02:00:00   586.0\n",
       "3           H1  1750-01-01 03:00:00   559.0\n",
       "4           H1  1750-01-01 04:00:00   511.0\n",
       "...        ...                  ...     ...\n",
       "353495    H414  1750-02-09 19:00:00    48.0\n",
       "353496    H414  1750-02-09 20:00:00    41.0\n",
       "353497    H414  1750-02-09 21:00:00    35.0\n",
       "353498    H414  1750-02-09 22:00:00    26.0\n",
       "353499    H414  1750-02-09 23:00:00    17.0\n",
       "\n",
       "[353500 rows x 3 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Load data as a long-format pandas data frame\n",
    "import pandas as pd\n",
    "\n",
    "context_df = pd.read_csv(\"../data/m4_hourly_train.csv\")\n",
    "context_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "5c047271-27b1-4bda-a1f8-1a37a17c0578",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from matplotlib.backends.backend_pdf import PdfPages\n",
    "\n",
    "def plot_multiple_items_random(context_df, pdf_path,\n",
    "                               n_items=20,\n",
    "                               timestamp_col=\"timestamp\",\n",
    "                               target_col=\"target\",\n",
    "                               recent_n=200):\n",
    "\n",
    "    # ---- 1. Randomly select 20 item_ids ----\n",
    "    unique_ids = context_df[\"item_id\"].unique()\n",
    "    selected_ids = np.random.choice(unique_ids, size=n_items, replace=False)\n",
    "\n",
    "    print(\"Selected item_ids:\", selected_ids)\n",
    "\n",
    "    fig_size = (12, 4)\n",
    "\n",
    "    with PdfPages(pdf_path) as pdf:\n",
    "\n",
    "        for item_id in selected_ids:\n",
    "            df = context_df[context_df[\"item_id\"] == item_id].copy()\n",
    "            df[timestamp_col] = pd.to_datetime(df[timestamp_col])\n",
    "\n",
    "            # ---- 200 most recent ----\n",
    "            df_recent = df.tail(recent_n).reset_index(drop=True)\n",
    "            x = df_recent[timestamp_col]\n",
    "            y = df_recent[target_col]\n",
    "\n",
    "            # 90% cutoff\n",
    "            n = len(df_recent)\n",
    "            cutoff_idx = int(n * 0.9)\n",
    "            x_cut = x.iloc[cutoff_idx - 1]   # cutoff timestamp\n",
    "\n",
    "            # =====================================================\n",
    "            #                A. FULL 200 + vertical bar\n",
    "            # =====================================================\n",
    "            figA, axA = plt.subplots(figsize=fig_size)\n",
    "            axA.plot(x, y, linewidth=1.2)\n",
    "\n",
    "            # Dense grid\n",
    "            axA.grid(which=\"major\", linestyle=\"--\", alpha=0.6)\n",
    "            axA.grid(which=\"minor\", linestyle=\":\", alpha=0.4)\n",
    "            axA.minorticks_on()\n",
    "\n",
    "            # ---- Vertical bar at 90% point ----\n",
    "            axA.axvline(x_cut, color=\"red\", linestyle=\"--\", linewidth=1)\n",
    "\n",
    "            axA.set_title(f\"[{item_id}] Recent 200 Points (with 90% marker)\")\n",
    "            axA.set_xlabel(\"Timestamp\")\n",
    "            axA.set_ylabel(\"Target\")\n",
    "            figA.tight_layout()\n",
    "\n",
    "            # Save axis limits for B\n",
    "            xlim_A = axA.get_xlim()\n",
    "            ylim_A = axA.get_ylim()\n",
    "\n",
    "            pdf.savefig(figA)\n",
    "            plt.close(figA)\n",
    "\n",
    "            # =====================================================\n",
    "            #              B. FIRST 90% + vertical bar\n",
    "            # =====================================================\n",
    "            figB, axB = plt.subplots(figsize=fig_size)\n",
    "            axB.plot(x[:cutoff_idx], y[:cutoff_idx], linewidth=1.2)\n",
    "\n",
    "            # Use A's limits → blank right region\n",
    "            axB.set_xlim(xlim_A)\n",
    "            axB.set_ylim(ylim_A)\n",
    "\n",
    "            # Dense grid\n",
    "            axB.grid(which=\"major\", linestyle=\"--\", alpha=0.6)\n",
    "            axB.grid(which=\"minor\", linestyle=\":\", alpha=0.4)\n",
    "            axB.minorticks_on()\n",
    "\n",
    "            # ---- Vertical bar at END of B (same location) ----\n",
    "            axB.axvline(x_cut, color=\"red\", linestyle=\"--\", linewidth=1)\n",
    "\n",
    "            axB.set_title(f\"[{item_id}] Left 90% (with boundary marker)\")\n",
    "            axB.set_xlabel(\"Timestamp\")\n",
    "            axB.set_ylabel(\"Target\")\n",
    "            figB.tight_layout()\n",
    "\n",
    "            pdf.savefig(figB)\n",
    "            plt.close(figB)\n",
    "\n",
    "    print(f\"Saved combined PDF: {pdf_path}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "30922330-2690-4448-ac65-4794358ba089",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Selected item_ids: ['H162' 'H34' 'H359' 'H197' 'H101' 'H302' 'H141' 'H194' 'H254' 'H60'\n",
      " 'H398' 'H315' 'H11' 'H169' 'H260' 'H191' 'H215' 'H8' 'H30' 'H183' 'H310'\n",
      " 'H159' 'H106' 'H223' 'H410' 'H282' 'H333' 'H381' 'H125' 'H78' 'H85'\n",
      " 'H294' 'H190' 'H109' 'H127' 'H387' 'H345' 'H251' 'H384' 'H372' 'H357'\n",
      " 'H314' 'H116' 'H94' 'H369' 'H15' 'H403' 'H173' 'H1' 'H92' 'H168' 'H108'\n",
      " 'H213' 'H279' 'H334' 'H44' 'H208' 'H241' 'H319' 'H328' 'H349' 'H93'\n",
      " 'H367' 'H386' 'H389' 'H375' 'H67' 'H54' 'H91' 'H63' 'H210' 'H76' 'H204'\n",
      " 'H336' 'H110' 'H27' 'H160' 'H198' 'H229' 'H317' 'H231' 'H339' 'H330'\n",
      " 'H340' 'H269' 'H259' 'H181' 'H118' 'H117' 'H171' 'H301' 'H298' 'H200'\n",
      " 'H355' 'H29' 'H248' 'H66' 'H138' 'H61' 'H385']\n",
      "Saved combined PDF: random100_items.pdf\n"
     ]
    }
   ],
   "source": [
    "plot_multiple_items_random(\n",
    "    context_df,\n",
    "    pdf_path=\"random100_items.pdf\",\n",
    "    n_items=100\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2e6b3a54-6d73-4cce-b201-1b5775ed13d0",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/fli/.local/lib/python3.12/site-packages/matplotlib/projections/__init__.py:63: UserWarning: Unable to import Axes3D. This may be due to multiple versions of Matplotlib being installed (e.g. as a system package and as a pip package). As a result, the 3D projection is not available.\n",
      "  warnings.warn(\"Unable to import Axes3D. This may be due to multiple versions of \"\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAhwAAAGJCAYAAADBveoRAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjcsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvTLEjVAAAAAlwSFlzAAAPYQAAD2EBqD+naQAATl1JREFUeJzt3XlYVGX/BvB7BmHYQZRVERAXQHE3RM0VBTRzq9SswF3DLbeiMlwjtdQWrTcr7S21slxKzX1LxT33FQO1FDUREZV1vr8/fDk/R3aYA4j357q4Ls45zzznOd85M3PPmXNmNCIiICIiIlKRtqwHQERERBUfAwcRERGpjoGDiIiIVMfAQURERKpj4CAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHGUV4eDg8PT3Lehhl5mnf/qKIj4+HRqPBhx9+WNZDAQAcPHgQLVu2hJWVFTQaDY4ePVrWQ8pXdv2WLFlS1kMp99q1a4d27dqV9TDofxg4KE8ajaZQfzt27CjroeYqPj4eAwYMgLe3N8zNzeHi4oI2bdogKiqqrIdmFO3atUP9+vXLehh5Wr9+PaZMmVLWw8hXRkYGXnzxRSQmJmLevHn47rvv4OHhkaOdp6dnoR4LhQkBCxcuLJOwsHTpUmg0GlhbW+dYduDAAbz++uto2rQpTE1NodFoCtXn7t27lW3/999/C3WbEydO4IUXXoCHhwfMzc1RrVo1dOrUCZ9++mmRtoeePJXKegBUfn333XcG0//973+xefPmHPN9fX2xaNEi6PX60hxevmJjY9G8eXNYWFhg4MCB8PT0xLVr13DkyBHMmjULU6dONer6ytv2lwfr16/HggULynXouHjxIi5duoRFixZh8ODBebabP38+UlJSlOn169dj+fLlmDdvHqpWrarMb9myZYHrXLhwIapWrYrw8PASjb0oUlJSMGnSJFhZWeW6fP369fjqq6/QoEED1KxZE+fPny+wT71ej1GjRsHKygr37t0r1Dj27t2L9u3bo0aNGhgyZAhcXFxw5coV7Nu3Dx9//DFGjRpVpO0qyKZNm4zaH5UMAwfl6ZVXXjGY3rdvHzZv3pxjfnk0b948pKSk4OjRoznesd64ccNo67l37x6srKxgampqtD6p9GTvC/b29vm269Gjh8F0QkICli9fjh49ejwRH6XNmDEDNjY2aN++PVavXp1j+YgRI/Dmm2/CwsICI0eOLFTg+PLLL3HlyhUMHjwYH3/8caHGMXPmTNjZ2eHgwYM5am7Mx+X9+/dhaWkJMzMzo/VJJcePVMgoHj+H4dHP6RcsWICaNWvC0tISnTt3xpUrVyAimD59OqpXrw4LCwt0794diYmJOfr9/fff8eyzz8LKygo2Njbo2rUrTp06VeB4Ll68iOrVq+d6eNzJyalY6wkPD4e1tTUuXryILl26wMbGBv379891+4GH7wDnz5+PevXqwdzcHM7Ozhg2bBhu375t0O7QoUMIDg5G1apVYWFhAS8vLwwcOLDAbSysomzbP//8gx49esDa2hqOjo6YMGECsrKyDNreunULr776KmxtbWFvb4+wsDAcO3bM4COF8PBwLFiwAIDhR3OP+/LLL+Ht7Q2dTofmzZvj4MGDBssTEhIwYMAAVK9eHTqdDq6urujevTvi4+ML3O5t27Yp221vb4/u3bvjzJkzBtvctm1bAMCLL74IjUZTos/7MzMzMX36dGV7PD098fbbbyMtLU1p4+npiVOnTmHnzp1KTbLXmZiYiAkTJsDf3x/W1tawtbVFaGgojh07VuwxAcCFCxcwb948zJ07F5Uq5f4e09nZGRYWFoXuMzExEe+++y6mTZtWYFh71MWLF1GvXr1cb5Pb4/L7779H06ZNYWFhAQcHB/Tt2xdXrlwxaJP90eLhw4fRpk0bWFpa4u2331aWPX6fpqWlISoqCrVq1YJOp4O7uzsmTZpkcD8BwObNm9G6dWvY29vD2toadevWVfql4uERDlLV0qVLkZ6ejlGjRiExMRGzZ8/GSy+9hA4dOmDHjh148803ERsbi08//RQTJkzAN998o9z2u+++Q1hYGIKDgzFr1izcv38fn3/+OVq3bo0///wz33eWHh4e2LJlC7Zt24YOHTrkO8airCczMxPBwcFo3bo1PvzwQ1haWubZ77Bhw7BkyRIMGDAAo0ePRlxcHD777DP8+eef2LNnD0xNTXHjxg107twZjo6OeOutt2Bvb4/4+HisXLmy0DU21rZlZWUhODgYAQEB+PDDD7FlyxZ89NFH8Pb2xogRIwA8DFHdunXDgQMHMGLECPj4+GDNmjUICwvLse1Xr17N9SO4bMuWLcPdu3cxbNgwaDQazJ49G7169cJff/2lHDHq3bs3Tp06hVGjRsHT0xM3btzA5s2bcfny5Xzv/y1btiA0NBQ1a9bElClT8ODBA3z66ado1aoVjhw5Ak9PTwwbNgzVqlXD+++/j9GjR6N58+ZwdnYudq0HDx6Mb7/9Fi+88ALGjx+P/fv3Izo6GmfOnMGqVasAPPxoZtSoUbC2tsY777wDAMo6//rrL6xevRovvvgivLy8cP36dfznP/9B27Ztcfr0abi5uRVrXGPHjkX79u3RpUsX/PTTT8XevkdNnjwZLi4uGDZsGKZPn17o23l4eCAmJgYnT54s8PyjmTNnYvLkyXjppZcwePBg3Lx5E59++inatGmDP//80yC03Lp1C6Ghoejbty9eeeWVPO9HvV6P559/Hrt378bQoUPh6+uLEydOYN68eTh//rxy9OfUqVN47rnn0KBBA0ybNg06nQ6xsbHYs2dPobeVciFEhRQRESF57TJhYWHi4eGhTMfFxQkAcXR0lKSkJGV+ZGSkAJCGDRtKRkaGMr9fv35iZmYmqampIiJy9+5dsbe3lyFDhhisJyEhQezs7HLMf9zJkyfFwsJCAEijRo1kzJgxsnr1arl3755Bu6KsJywsTADIW2+9VeD2//HHHwJAli5datBuw4YNBvNXrVolAOTgwYP5bk9u2rZtK/Xq1ctzeXG2bdq0aQZtGzduLE2bNlWmf/nlFwEg8+fPV+ZlZWVJhw4dBIAsXrxYmZ/X/pK9b1SpUkUSExOV+WvWrBEA8ttvv4mIyO3btwWAzJkzp4BK5NSoUSNxcnKSW7duKfOOHTsmWq1WXnvtNWXe9u3bBYCsWLGiSP3PmTNHAEhcXJyIiBw9elQAyODBgw3aTZgwQQDItm3blHn16tWTtm3b5ugzNTVVsrKyDObFxcWJTqczuF+y6/dorfOydu1aqVSpkpw6dUpEHt7PVlZW+d4mv8e5yMM6mpiYyMaNG0VEJCoqSgDIzZs3CxzPpk2bxMTERExMTCQwMFAmTZokGzdulPT0dIN28fHxYmJiIjNnzjSYf+LECalUqZLB/LZt2woA+eKLL3Ksr23btga1/u6770Sr1coff/xh0O6LL74QALJnzx4REZk3b16ht4kKjx+pkKpefPFF2NnZKdMBAQEAHp4f8ujh3YCAAKSnp+Off/4B8PBwZlJSEvr164d///1X+TMxMUFAQAC2b9+e73rr1auHo0eP4pVXXkF8fDw+/vhj9OjRA87Ozli0aJHSrjjryX63n58VK1bAzs4OnTp1Mui3adOmsLa2VvrNfpe2du1aZGRkFNhvURRn24YPH24w/eyzz+Kvv/5Spjds2ABTU1MMGTJEmafVahEREVHk8fXp0weVK1c2WBcAZX0WFhYwMzPDjh07cnwMlZ9r167h6NGjCA8Ph4ODgzK/QYMG6NSpE9avX1/ksRYku89x48YZzB8/fjwAYN26dQX2odPpoNU+fErOysrCrVu3lEP5R44cKfKY0tPT8cYbb2D48OHw8/Mr8u3zMnr0aISGhqJz585Fvm2nTp0QExOD559/HseOHcPs2bMRHByMatWq4ddff1XarVy5Enq9Hi+99JLBvuvi4oLatWvn2Hd1Oh0GDBhQ4PpXrFgBX19f+Pj4GPSbfRT08cflmjVreDK4EfEjFVJVjRo1DKazw4e7u3uu87NfWC5cuAAAeX4cYmtrW+C669Spg++++w5ZWVk4ffo01q5di9mzZ2Po0KHw8vJCUFBQkddTqVIlVK9evcB1X7hwAXfu3Mn1c2ng/0+Qa9u2LXr37o2pU6di3rx5aNeuHXr06IGXX34ZOp2uwPUUNAag8Ntmbm4OR0dHg3mVK1c2eLG/dOkSXF1dc3yUVKtWrSKP7/F9Izt8ZK9Pp9Nh1qxZGD9+PJydndGiRQs899xzeO211+Di4pJnv5cuXQIA1K1bN8cyX19fbNy4UTnZ11guXboErVabow4uLi6wt7dXxpQfvV6Pjz/+GAsXLkRcXJzBuTNVqlQp8pjmzZuHf//916hXZP3444/Yu3cvTp48Wew+mjdvjpUrVyI9PR3Hjh3DqlWrMG/ePLzwwgs4evQo/Pz8cOHCBYgIateunWsfj5+kXa1atUKdIHrhwgWcOXMmx36eLftx2adPH3z11VcYPHgw3nrrLXTs2BG9evXCCy+8oIRCKjoGDlKViYlJkeaLCAAo7yq+++67XF9c8jr5La91+fv7w9/fH4GBgWjfvj2WLl2KoKCgIq/n0Xeh+dHr9XBycsLSpUtzXZ79hKfRaPDzzz9j3759+O2337Bx40YMHDgQH330Efbt25frdyYUVlG3La/7RC0F7QPAw/MPunXrhtWrV2Pjxo2YPHkyoqOjsW3bNjRu3Li0hlpohf3+ity8//77mDx5MgYOHIjp06fDwcEBWq0WY8eOLfK77Dt37mDGjBl4/fXXkZycjOTkZAAPL48VEcTHx8PS0jLPQJyXiRMn4sUXX4SZmZly4m5SUhIA4MqVK0hPTy/0uSZmZmZo3rw5mjdvjjp16mDAgAFYsWIFoqKioNfrodFo8Pvvv+e6nzz+uCjsCa96vR7+/v6YO3dursuz3whZWFhg165d2L59O9atW4cNGzbgxx9/RIcOHbBp06ZSf6xUFAwcVC55e3sDeHjmelBQkNH6bdasGYCHh93VXI+3tze2bNmCVq1aFerJsEWLFmjRogVmzpyJZcuWoX///vjhhx/y/W6IwowBMO62eXh4YPv27cplh9liY2NztC3Ji++jvL29MX78eIwfPx4XLlxAo0aN8NFHH+H777/Pc4wAcO7cuRzLzp49i6pVqxr16Eb2OvV6PS5cuABfX19l/vXr15GUlGRwtVRedfn555/Rvn17fP311wbzk5KSDL7rozBu376NlJQUzJ49G7Nnz86x3MvLC927d8/1Etn8XLlyBcuWLcOyZctyLGvSpAkaNmxYrG9qze1xKSLw8vJCnTp1itxfXry9vXHs2DF07NixwP1Tq9WiY8eO6NixI+bOnYv3338f77zzDrZv327U54qnCY8NUbkUHBwMW1tbvP/++7me23Dz5s18b//HH3/kervsz9qzD7eXdD15eemll5CVlZXrGfyZmZnKu8Lbt28bvKMHgEaNGgFAjsv0ikqNbQsODkZGRobBeTB6vV65BPZR2S/q2dtaVPfv30dqaqrBPG9vb9jY2ORbG1dXVzRq1AjffvutwbpPnjyJTZs2oUuXLsUaT36y+5w/f77B/Ox30l27dlXmWVlZ5VoTExOTHPvCihUrlPOaisLJyQmrVq3K8de+fXuYm5tj1apViIyMLHK/ufXZp08fAA+/GHDevHn53n779u05thHI+bjs1asXTExMMHXq1BztRQS3bt0q8tiBh4/Lf/75x2D/zfbgwQPlC8xyu0TfWI/LpxmPcFC5ZGtri88//xyvvvoqmjRpgr59+8LR0RGXL1/GunXr0KpVK3z22Wd53n7WrFk4fPgwevXqhQYNGgAAjhw5gv/+979wcHDA2LFjjbKevLRt2xbDhg1DdHQ0jh49is6dO8PU1BQXLlzAihUr8PHHH+OFF17At99+i4ULF6Jnz57w9vbG3bt3sWjRItja2hbqhfHmzZuYMWNGjvleXl7o37+/0betR48eeOaZZzB+/HjExsbCx8cHv/76q/IE/ei7xqZNmwJ4eJJhcHAwTExM0Ldv30Kv6/z58+jYsSNeeukl+Pn5oVKlSli1ahWuX79eYD9z5sxBaGgoAgMDMWjQIOWyWDs7O1W++bRhw4YICwvDl19+iaSkJLRt2xYHDhzAt99+ix49eqB9+/ZK26ZNm+Lzzz/HjBkzUKtWLTg5OaFDhw547rnnMG3aNAwYMAAtW7bEiRMnsHTpUtSsWbPI47G0tMzxZWUAsHr1ahw4cCDHskuXLimXLx86dAgAlP3Kw8MDr776KoCcX4AGQDmiERoaWuCRmFGjRuH+/fvo2bMnfHx8kJ6ejr179+LHH3+Ep6encuKnt7c3ZsyYgcjISMTHx6NHjx6wsbFBXFwcVq1ahaFDh2LChAmFLYfi1VdfxU8//YThw4dj+/btaNWqFbKysnD27Fn89NNP2LhxI5o1a4Zp06Zh165d6Nq1Kzw8PHDjxg0sXLgQ1atXR+vWrYu8Xvqfsro8hp48xbks9vFLGvO6DHHx4sW5Xh66fft2CQ4OFjs7OzE3Nxdvb28JDw+XQ4cO5TvWPXv2SEREhNSvX1/s7OzE1NRUatSoIeHh4XLx4sUc7QuznvwuKXx8+7N9+eWX0rRpU7GwsBAbGxvx9/eXSZMmydWrV0VE5MiRI9KvXz+pUaOG6HQ6cXJykueee67A7RP5/8sBc/vr2LGjUbYt+5LHR928eVNefvllsbGxETs7OwkPD5c9e/YIAPnhhx+UdpmZmTJq1ChxdHQUjUaj9JPXviEiAkCioqJEROTff/+ViIgI8fHxESsrK7Gzs5OAgAD56aefCqyNiMiWLVukVatWYmFhIba2ttKtWzc5ffq0QRtjXRYrIpKRkSFTp04VLy8vMTU1FXd3d4mMjFQu9c6WkJAgXbt2FRsbGwGgXLaZmpoq48ePF1dXV7GwsJBWrVpJTExMjks7i3JZ7OPyup+z65DbX26X8D6qKJfF/v777zJw4EDx8fERa2trMTMzk1q1asmoUaPk+vXrOdr/8ssv0rp1a7GyshIrKyvx8fGRiIgIOXfunNImv8vDH6+diEh6errMmjVL6tWrJzqdTipXrixNmzaVqVOnyp07d0REZOvWrdK9e3dxc3MTMzMzcXNzk379+sn58+cL3EbKm0Ykl+NbRERFsHr1avTs2RO7d+9Gq1atyno4RFQOMXAQUZE8ePDA4ETYrKwsdO7cGYcOHUJCQkKRviKbiJ4ePIeDiIpk1KhRePDgAQIDA5GWloaVK1di7969eP/99xk2iChPPMJBREWybNkyfPTRR4iNjUVqaipq1aqFESNGYOTIkWU9NCIqxxg4iIiISHX8Hg4iIiJSHQMHERERqY4njeLhNyVevXoVNjY2Rvs6ZiIioqeBiODu3btwc3PL97emGDgAXL16NcevlxIREVHhXblyJd9f02bgAGBjYwPgYbEK87PnhaHX63Hz5k04Ojry54yLiTUsOdbQOFjHkmMNS6681jA5ORnu7u7Ka2leGDjw/7//YGtra9TAkZqaCltb23K1YzxJWMOSYw2Ng3UsOdaw5Mp7DQv8Bd5SGgcRERE9xRg4iIiISHVlGjiio6PRvHlz2NjYwMnJCT169MC5c+cM2rRr1w4ajcbgb/jw4QZtLl++jK5du8LS0hJOTk6YOHEiMjMzS3NTiIiIKB9leg7Hzp07ERERgebNmyMzMxNvv/02OnfujNOnT8PKykppN2TIEEybNk2ZtrS0VP7PyspC165d4eLigr179+LatWt47bXXYGpqivfff79Ut4eIiIhyV6aBY8OGDQbTS5YsgZOTEw4fPow2bdoo8y0tLeHi4pJrH5s2bcLp06exZcsWODs7o1GjRpg+fTrefPNNTJkyBWZmZjluk5aWhrS0NGU6OTkZwMMTcvR6vTE2DXq9HiJitP6eRqxhybGGxsE6lhxrWHLltYaFHU+5ukrlzp07AAAHBweD+UuXLsX3338PFxcXdOvWDZMnT1aOcsTExMDf3x/Ozs5K++DgYIwYMQKnTp1C48aNc6wnOjoaU6dOzTH/5s2bSE1NNcq26PV63LlzByJSLs8mfhKwhiXHGhoH61hyrGHJldca3r17t1Dtyk3g0Ov1GDt2LFq1aoX69esr819++WV4eHjAzc0Nx48fx5tvvolz585h5cqVAICEhASDsAFAmU5ISMh1XZGRkRg3bpwynX0NsaOjo1Evi9VoNOXueuknCWtYcqyhcbCOJccallx5raG5uXmh2pWbwBEREYGTJ09i9+7dBvOHDh2q/O/v7w9XV1d07NgRFy9ehLe3d7HWpdPpoNPpcszXarVGvRM1Go3R+3zasIYlxxoaB+tYcqxhyZXHGhZ2LOVixCNHjsTatWuxffv2fL8WFQACAgIAALGxsQAAFxcXXL9+3aBN9nRe530QERFR6SrTwCEiGDlyJFatWoVt27bBy8urwNscPXoUAODq6goACAwMxIkTJ3Djxg2lzebNm2Fraws/Pz9Vxk1ERERFU6YfqURERGDZsmVYs2YNbGxslHMu7OzsYGFhgYsXL2LZsmXo0qULqlSpguPHj+ONN95AmzZt0KBBAwBA586d4efnh1dffRWzZ89GQkIC3n33XUREROT6sQkRERGVvjINHJ9//jmAh1/u9ajFixcjPDwcZmZm2LJlC+bPn4979+7B3d0dvXv3xrvvvqu0NTExwdq1azFixAgEBgbCysoKYWFhBt/bQUREpCbPt9apvg4tBL6VBWdua6BH/r9bkp/4D7oacVSFV6aBQ0TyXe7u7o6dO3cW2I+HhwfWr19vrGERERGRkZWLk0aJiIioYmPgICIiItUxcBAREZHqGDiIiIhIdQwcREREpDoGDiIiIlIdAwcRERGpjoGDiIiIVMfAQURERKpj4CAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg4iIiFTHwEFERESqY+AgIiIi1TFwEBERkeoYOIiIiEh1DBxERESkOgYOIiIiUh0DBxEREamOgYOIiIhUx8BBREREqmPgICIiItUxcBAREZHqGDiIiIhIdQwcREREpDoGDiIiIlIdAwcRERGpjoGDiIiIVMfAQURERKpj4CAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg4iIiFTHwEFERESqY+AgIiIi1TFwEBERkeoYOIiIiEh1DBxERESkOgYOIiIiUh0DBxEREamOgYOIiIhUV6aBIzo6Gs2bN4eNjQ2cnJzQo0cPnDt3zqBNamoqIiIiUKVKFVhbW6N37964fv26QZvLly+ja9eusLS0hJOTEyZOnIjMzMzS3BQiIiLKR5kGjp07dyIiIgL79u3D5s2bkZGRgc6dO+PevXtKmzfeeAO//fYbVqxYgZ07d+Lq1avo1auXsjwrKwtdu3ZFeno69u7di2+//RZLlizBe++9VxabRERERLmoVJYr37Bhg8H0kiVL4OTkhMOHD6NNmza4c+cOvv76ayxbtgwdOnQAACxevBi+vr7Yt28fWrRogU2bNuH06dPYsmULnJ2d0ahRI0yfPh1vvvkmpkyZAjMzs7LYNCIiInpEmQaOx925cwcA4ODgAAA4fPgwMjIyEBQUpLTx8fFBjRo1EBMTgxYtWiAmJgb+/v5wdnZW2gQHB2PEiBE4deoUGjdunGM9aWlpSEtLU6aTk5MBAHq9Hnq93ijbotfrISJG6+9pxBqWHGtoHKxjyVX0GmohpbIODaTEH00Y+z4obH/lJnDo9XqMHTsWrVq1Qv369QEACQkJMDMzg729vUFbZ2dnJCQkKG0eDRvZy7OX5SY6OhpTp07NMf/mzZtITU0t6aYAeLg9d+7cgYhAq+W5ucXBGpYca2gcrGPJVfQa+lYujcABVLcGNAD0JQg4N27cMNqYAODu3buFalduAkdERAROnjyJ3bt3q76uyMhIjBs3TplOTk6Gu7s7HB0dYWtra5R16PV6aDQaODo6VsgHV2lgDUuONTQO1rHkKnoNz9zWqL4OLQQC4OxtQI/ir8/Jycl4gwJgbm5eqHblInCMHDkSa9euxa5du1C9enVlvouLC9LT05GUlGRwlOP69etwcXFR2hw4cMCgv+yrWLLbPE6n00Gn0+WYr9VqjfpA0Gg0Ru/zacMalhxraBysY8lV5BqWJAAUhfxvXSVZn7HrX9j+yvReFxGMHDkSq1atwrZt2+Dl5WWwvGnTpjA1NcXWrVuVeefOncPly5cRGBgIAAgMDMSJEycMDhFt3rwZtra28PPzK50NISIionyV6RGOiIgILFu2DGvWrIGNjY1yzoWdnR0sLCxgZ2eHQYMGYdy4cXBwcICtrS1GjRqFwMBAtGjRAgDQuXNn+Pn54dVXX8Xs2bORkJCAd999FxEREbkexSAiIqLSV6aB4/PPPwcAtGvXzmD+4sWLER4eDgCYN28etFotevfujbS0NAQHB2PhwoVKWxMTE6xduxYjRoxAYGAgrKysEBYWhmnTppXWZhAREVEByjRwiBR8lq25uTkWLFiABQsW5NnGw8MD69evN+bQiIiIyIgq3pk7REREVO4wcBAREZHqGDiIiIhIdQwcREREpDoGDiIiIlIdAwcRERGpjoGDiIiIVMfAQURERKpj4CAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg4iIiFTHwEFERESqY+AgIiIi1TFwEBERkeoYOIiIiEh1DBxERESkOgYOIiIiUh0DBxEREamOgYOIiIhUx8BBREREqmPgICIiItUxcBAREZHqGDiIiIhIdQwcREREpDoGDiIiIlIdAwcRERGprlJZD6AiG/TtQZy5rYEemrIeSr7iP+ha1kMgIqIKjkc4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg4iIiFTHwEFERESqY+AgIiIi1TFwEBERkeoYOIiIiEh1DBxERESkOgYOIiIiUh0DBxEREamOgYOIiIhUx8BBREREqmPgICIiItUxcBAREZHqGDiIiIhIdQwcREREpLoyDRy7du1Ct27d4ObmBo1Gg9WrVxssDw8Ph0ajMfgLCQkxaJOYmIj+/fvD1tYW9vb2GDRoEFJSUkpxK4iIiKggZRo47t27h4YNG2LBggV5tgkJCcG1a9eUv+XLlxss79+/P06dOoXNmzdj7dq12LVrF4YOHar20ImIiKgIKpXlykNDQxEaGppvG51OBxcXl1yXnTlzBhs2bMDBgwfRrFkzAMCnn36KLl264MMPP4Sbm5vRx0xERERFV6aBozB27NgBJycnVK5cGR06dMCMGTNQpUoVAEBMTAzs7e2VsAEAQUFB0Gq12L9/P3r27Jlrn2lpaUhLS1Omk5OTAQB6vR56vd4o49br9dBAnoiTZIy1zcam1+shIuV2fE8C1tA4WMeSq+g11EJKZR3GeF0x9n1Q2P7KdeAICQlBr1694OXlhYsXL+Ltt99GaGgoYmJiYGJigoSEBDg5ORncplKlSnBwcEBCQkKe/UZHR2Pq1Kk55t+8eROpqalGGbter4e7NaABoC+FHbEkbty4UdZDyJVer8edO3cgItBqn4ToVv6whsbBOpZcRa+hb+XSCBxAdSO8rhj7Of/u3buFaleuA0ffvn2V//39/dGgQQN4e3tjx44d6NixY7H7jYyMxLhx45Tp5ORkuLu7w9HREba2tiUacza9Xo8rKcDZ24AeGqP0qZbHQ1t5odfrodFo4OjoWCGfoEoDa2gcrGPJVfQanrmt/vO8FgJByV9XjP2cb25uXqh25TpwPK5mzZqoWrUqYmNj0bFjR7i4uORIapmZmUhMTMzzvA/g4XkhOp0ux3ytVmvUB4JAA/3//sqz8vzg12g0Rr9fnjasoXGwjiVXkWtYWs/z8r91lWR9xq5/Yft7ou71v//+G7du3YKrqysAIDAwEElJSTh8+LDSZtu2bdDr9QgICCirYRIREdFjyvQIR0pKCmJjY5XpuLg4HD16FA4ODnBwcMDUqVPRu3dvuLi44OLFi5g0aRJq1aqF4OBgAICvry9CQkIwZMgQfPHFF8jIyMDIkSPRt29fXqFCRERUjhTrCMeRI0dw4sQJZXrNmjXo0aMH3n77baSnpxe6n0OHDqFx48Zo3LgxAGDcuHFo3Lgx3nvvPZiYmOD48eN4/vnnUadOHQwaNAhNmzbFH3/8YfBxyNKlS+Hj44OOHTuiS5cuaN26Nb788svibBYRERGppFhHOIYNG4a33noL/v7++Ouvv9C3b1/07NkTK1aswP379zF//vxC9dOuXTuI5H2m7caNGwvsw8HBAcuWLSvs0ImIiKgMFOsIx/nz59GoUSMAwIoVK9CmTRssW7YMS5YswS+//GLM8REREVEFUKzA8eiXt2zZsgVdunQBALi7u+Pff/813uiIiIioQihW4GjWrBlmzJiB7777Djt37kTXrl0BPDzp09nZ2agDJCIioidfsQLHvHnzcOTIEYwcORLvvPMOatWqBQD4+eef0bJlS6MOkIiIiJ58xTpptGHDhgZXqWSbM2cOKlV6or5LjIiIiEpBsY5w1KxZE7du3coxPzU1FXXq1CnxoIiIiKhiKVbgiI+PR1ZWVo75aWlp+Pvvv0s8KCIiIqpYivT5x6+//qr8v3HjRtjZ2SnTWVlZ2Lp1K7y8vIw3OiIiIqoQihQ4evToAeDhD/CEhYUZLDM1NYWnpyc++ugjow2OiIiIKoYiBY7s797w8vLCwYMHUbVqVVUGRURERBVLsS4piYuLM/Y4iIiIqAIr9jWsW7duxdatW3Hjxg3lyEe2b775psQDIyIiooqjWIFj6tSpmDZtGpo1awZXV1doNBpjj4uIiIgqkGIFji+++AJLlizBq6++auzxEBERUQVUrO/hSE9P51eYExERUaEVK3AMHjwYy5YtM/ZYiIiIqIIq1kcqqamp+PLLL7FlyxY0aNAApqamBsvnzp1rlMERERFRxVCswHH8+HE0atQIAHDy5EmDZTyBlIiIiB5XrMCxfft2Y4+DiIiIKrBincNBREREVBTFOsLRvn37fD862bZtW7EHRERERBVPsQJH9vkb2TIyMnD06FGcPHkyx4+6ERERERUrcMybNy/X+VOmTEFKSkqJBkREREQVj1HP4XjllVf4OypERESUg1EDR0xMDMzNzY3ZJREREVUAxfpIpVevXgbTIoJr167h0KFDmDx5slEGRkRERBVHsQKHnZ2dwbRWq0XdunUxbdo0dO7c2SgDIyIiooqjWIFj8eLFxh4HERERVWDFChzZDh8+jDNnzgAA6tWrh8aNGxtlUERERFSxFCtw3LhxA3379sWOHTtgb28PAEhKSkL79u3xww8/wNHR0ZhjJCIioidcsa5SGTVqFO7evYtTp04hMTERiYmJOHnyJJKTkzF69Ghjj5GIiIiecMU6wrFhwwZs2bIFvr6+yjw/Pz8sWLCAJ40SERFRDsU6wqHX62FqappjvqmpKfR6fYkHRURERBVLsQJHhw4dMGbMGFy9elWZ988//+CNN95Ax44djTY4IiIiqhiKFTg+++wzJCcnw9PTE97e3vD29oaXlxeSk5Px6aefGnuMRERE9IQr1jkc7u7uOHLkCLZs2YKzZ88CAHx9fREUFGTUwREREVHFUKQjHNu2bYOfnx+Sk5Oh0WjQqVMnjBo1CqNGjULz5s1Rr149/PHHH2qNlYiIiJ5QRQoc8+fPx5AhQ2Bra5tjmZ2dHYYNG4a5c+cabXBERERUMRQpcBw7dgwhISF5Lu/cuTMOHz5c4kERERFRxVKkwHH9+vVcL4fNVqlSJdy8ebPEgyIiIqKKpUiBo1q1ajh58mSey48fPw5XV9cSD4qIiIgqliIFji5dumDy5MlITU3NsezBgweIiorCc889Z7TBERERUcVQpMti3333XaxcuRJ16tTByJEjUbduXQDA2bNnsWDBAmRlZeGdd95RZaBERET05CpS4HB2dsbevXsxYsQIREZGQkQAABqNBsHBwViwYAGcnZ1VGSgRERE9uYr8xV8eHh5Yv349bt++jdjYWIgIateujcqVK6sxPiIiIqoAivVNowBQuXJlNG/e3JhjISIiogqqWL+lQkRERFQUDBxERESkOgYOIiIiUl2ZBo5du3ahW7ducHNzg0ajwerVqw2Wiwjee+89uLq6wsLCAkFBQbhw4YJBm8TERPTv3x+2trawt7fHoEGDkJKSUopbQURERAUp08Bx7949NGzYEAsWLMh1+ezZs/HJJ5/giy++wP79+2FlZYXg4GCDLx7r378/Tp06hc2bN2Pt2rXYtWsXhg4dWlqbQERERIVQ7KtUjCE0NBShoaG5LhMRzJ8/H++++y66d+8OAPjvf/8LZ2dnrF69Gn379sWZM2ewYcMGHDx4EM2aNQMAfPrpp+jSpQs+/PBDuLm5ldq2EBERUd7KNHDkJy4uDgkJCQgKClLm2dnZISAgADExMejbty9iYmJgb2+vhA0ACAoKglarxf79+9GzZ89c+05LS0NaWpoynZycDADQ6/XQ6/VGGb9er4cG8kScJGOsbTY2vV4PESm343sSsIbGwTqWXEWvoRZSKuswxuuKse+DwvZXbgNHQkICAOT45lJnZ2dlWUJCApycnAyWV6pUCQ4ODkqb3ERHR2Pq1Kk55t+8eTPX34kpDr1eD3drQANAXwo7YkncuHGjrIeQK71ejzt37kBEoNU+CdGt/GENjYN1LLmKXkPfyqUROIDqRnhdMfZz/t27dwvVrtwGDjVFRkZi3LhxynRycjLc3d3h6OgIW1tbo6xDr9fjSgpw9jagh8Yofarl8dBWXuj1emg0Gjg6OlbIJ6jSwBoaB+tYchW9hmduq/88r4VAUPLXFWM/55ubmxeqXbkNHC4uLgCA69evG/zk/fXr19GoUSOlzeNJLTMzE4mJicrtc6PT6aDT6XLM12q1Rn0gCDTQ/++vPCvPD36NRmP0++VpwxoaB+tYchW5hqX1PC//W1dJ1mfs+he2v3J7r3t5ecHFxQVbt25V5iUnJ2P//v0IDAwEAAQGBiIpKQmHDx9W2mzbtg16vR4BAQGlPmYiIiLKXZke4UhJSUFsbKwyHRcXh6NHj8LBwQE1atTA2LFjMWPGDNSuXRteXl6YPHky3Nzc0KNHDwCAr68vQkJCMGTIEHzxxRfIyMjAyJEj0bdvX16hQkREVI6UaeA4dOgQ2rdvr0xnn1cRFhaGJUuWYNKkSbh37x6GDh2KpKQktG7dGhs2bDD4vGjp0qUYOXIkOnbsCK1Wi969e+OTTz4p9W0hIiKivJVp4GjXrh1E8j7TVqPRYNq0aZg2bVqebRwcHLBs2TI1hkdERERGUm7P4SAiIqKKg4GDiIiIVMfAQURERKpj4CAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg4iIiFTHwEFERESqY+AgIiIi1TFwEBERkeoYOIiIiEh1DBxERESkOgYOIiIiUh0DBxEREamOgYOIiIhUx8BBREREqmPgICIiItUxcBAREZHqGDiIiIhIdQwcREREpDoGDiIiIlIdAwcRERGpjoGDiIiIVMfAQURERKpj4CAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg4iIiFTHwEFERESqY+AgIiIi1TFwEBERkeoYOIiIiEh1DBxERESkOgYOIiIiUh0DBxEREamOgYOIiIhUx8BBREREqmPgICIiItUxcBAREZHqGDiIiIhIdQwcREREpDoGDiIiIlIdAwcRERGprlwHjilTpkCj0Rj8+fj4KMtTU1MRERGBKlWqwNraGr1798b169fLcMRERESUm3IdOACgXr16uHbtmvK3e/duZdkbb7yB3377DStWrMDOnTtx9epV9OrVqwxHS0RERLmpVNYDKEilSpXg4uKSY/6dO3fw9ddfY9myZejQoQMAYPHixfD19cW+ffvQokWL0h4qERER5aHcB44LFy7Azc0N5ubmCAwMRHR0NGrUqIHDhw8jIyMDQUFBSlsfHx/UqFEDMTEx+QaOtLQ0pKWlKdPJyckAAL1eD71eb5Rx6/V6aCDl/xASYLRtNja9Xg8RKbfjexKwhsbBOpZcRa+hFlIq6zDG64qx74PC9leuA0dAQACWLFmCunXr4tq1a5g6dSqeffZZnDx5EgkJCTAzM4O9vb3BbZydnZGQkJBvv9HR0Zg6dWqO+Tdv3kRqaqpRxq7X6+FuDWgA6EthRyyJGzdulPUQcqXX63Hnzh2ICLTaJyG6lT+soXGwjiVX0WvoW7k0AgdQ3QivK8Z+zr97926h2pXrwBEaGqr836BBAwQEBMDDwwM//fQTLCwsit1vZGQkxo0bp0wnJyfD3d0djo6OsLW1LdGYs+n1elxJAc7eBvTQGKVPtTg5OZX1EHKl1+uh0Wjg6OhYIZ+gSgNraBysY8lV9Bqeua3+87wWAkHJX1eM/Zxvbm5eqHblOnA8zt7eHnXq1EFsbCw6deqE9PR0JCUlGRzluH79eq7nfDxKp9NBp9PlmK/Vao36QBBooP/fX3lWnh/8Go3G6PfL04Y1NA7WseQqcg1L63le/reukqzP2PUvbH9P1L2ekpKCixcvwtXVFU2bNoWpqSm2bt2qLD937hwuX76MwMDAMhwlERERPa5cH+GYMGECunXrBg8PD1y9ehVRUVEwMTFBv379YGdnh0GDBmHcuHFwcHCAra0tRo0ahcDAQF6hQkREVM6U68Dx999/o1+/frh16xYcHR3RunVr7Nu3D46OjgCAefPmQavVonfv3khLS0NwcDAWLlxYxqMmIiKix5XrwPHDDz/ku9zc3BwLFizAggULSmlEREREVBxP1DkcRERE9GRi4CAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg4iIiFTHwEFERESqY+AgIiIi1TFwEBERkeoYOIiIiEh1DBxERESkOgYOIiIiUh0DBxEREamOgYOIiIhUx8BBREREqmPgICIiItUxcBAREZHqGDiIiIhIdQwcREREpDoGDiIiIlIdAwcRERGpjoGDiIiIVMfAQURERKpj4CAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg4iIiFTHwEFERESqY+AgIiIi1TFwEBERkeoYOIiIiEh1DBxERESkOgYOIiIiUh0DBxEREamOgYOIiIhUx8BBREREqmPgICIiItUxcBAREZHqGDiIiIhIdQwcREREpDoGDiIiIlIdAwcRERGpjoGDiIiIVMfAQURERKqrMIFjwYIF8PT0hLm5OQICAnDgwIGyHhIRERH9T4UIHD/++CPGjRuHqKgoHDlyBA0bNkRwcDBu3LhR1kMjIiIiVJDAMXfuXAwZMgQDBgyAn58fvvjiC1haWuKbb74p66ERERERgEplPYCSSk9Px+HDhxEZGanM02q1CAoKQkxMTK63SUtLQ1pamjJ9584dAEBSUhL0er1RxqXX65GZeg9I0wDQGKVPtSQlJZX1EHKl1+uRnJwMMzMzaLUVIhuXOtbQOFjHkqvwNUy7VworEWSmSolfV4z9nJ+cnAwAEJF82z3xgePff/9FVlYWnJ2dDeY7Ozvj7Nmzud4mOjoaU6dOzTHfw8NDlTGWd5Xnl/UIiIioMOKM0Idaz/l3796FnZ1dnsuf+MBRHJGRkRg3bpwyrdfrkZiYiCpVqkCjMc7RiOTkZLi7u+PKlSuwtbU1Sp9PG9aw5FhD42AdS441LLnyWkMRwd27d+Hm5pZvuyc+cFStWhUmJia4fv26wfzr16/DxcUl19vodDrodDqDefb29qqMz9bWtlztGE8i1rDkWEPjYB1LjjUsufJYw/yObGR74j9IMzMzQ9OmTbF161Zlnl6vx9atWxEYGFiGIyMiIqJsT/wRDgAYN24cwsLC0KxZMzzzzDOYP38+7t27hwEDBpT10IiIiAgVJHD06dMHN2/exHvvvYeEhAQ0atQIGzZsyHEiaWnS6XSIiorK8dENFR5rWHKsoXGwjiXHGpbck15DjRR0HQsRERFRCT3x53AQERFR+cfAQURERKpj4CAiIiLVMXAQERGR6hg4isDT0xMajSbHX0REBAAgNTUVERERqFKlCqytrdG7d+8cX0h2+fJldO3aFZaWlnBycsLEiRORmZlZFptTJgqqYbt27XIsGz58uEEfT3sNs7KyMHnyZHh5ecHCwgLe3t6YPn26we8YiAjee+89uLq6wsLCAkFBQbhw4YJBP4mJiejfvz9sbW1hb2+PQYMGISUlpbQ3p0wUpobh4eE59sWQkBCDfp7mGma7e/cuxo4dCw8PD1hYWKBly5Y4ePCgspz7YsEKqmGF2ReFCu3GjRty7do15W/z5s0CQLZv3y4iIsOHDxd3d3fZunWrHDp0SFq0aCEtW7ZUbp+ZmSn169eXoKAg+fPPP2X9+vVStWpViYyMLKMtKn0F1bBt27YyZMgQgzZ37txRbs8aisycOVOqVKkia9eulbi4OFmxYoVYW1vLxx9/rLT54IMPxM7OTlavXi3Hjh2T559/Xry8vOTBgwdKm5CQEGnYsKHs27dP/vjjD6lVq5b069evLDap1BWmhmFhYRISEmKwLyYmJhr08zTXMNtLL70kfn5+snPnTrlw4YJERUWJra2t/P333yLCfbEwCqphRdkXGThKYMyYMeLt7S16vV6SkpLE1NRUVqxYoSw/c+aMAJCYmBgREVm/fr1otVpJSEhQ2nz++edia2sraWlppT7+8uDRGoo8DBxjxozJsz1rKNK1a1cZOHCgwbxevXpJ//79RUREr9eLi4uLzJkzR1melJQkOp1Oli9fLiIip0+fFgBy8OBBpc3vv/8uGo1G/vnnn1LYirJVUA1FHj7Jd+/ePc8+nvYaiojcv39fTExMZO3atQbzmzRpIu+88w73xUIoqIYiFWdf5EcqxZSeno7vv/8eAwcOhEajweHDh5GRkYGgoCCljY+PD2rUqIGYmBgAQExMDPz9/Q2+kCw4OBjJyck4depUqW9DWXu8htmWLl2KqlWron79+oiMjMT9+/eVZawh0LJlS2zduhXnz58HABw7dgy7d+9GaGgoACAuLg4JCQkG+6KdnR0CAgIM9kV7e3s0a9ZMaRMUFAStVov9+/eX4taUjYJqmG3Hjh1wcnJC3bp1MWLECNy6dUtZ9rTXEAAyMzORlZUFc3Nzg/kWFhbYvXs398VCKKiG2SrCvlghvmm0LKxevRpJSUkIDw8HACQkJMDMzCzHj8A5OzsjISFBafP4t59mT2e3eZo8XkMAePnll+Hh4QE3NzccP34cb775Js6dO4eVK1cCYA0B4K233kJycjJ8fHxgYmKCrKwszJw5E/379wfw/3XIrU6P7otOTk4GyytVqgQHB4enoo4F1RAAQkJC0KtXL3h5eeHixYt4++23ERoaipiYGJiYmDz1NQQAGxsbBAYGYvr06fD19YWzszOWL1+OmJgY1KpVi/tiIRRUQ6Di7IsMHMX09ddfIzQ0tMCf46W85VbDoUOHKv/7+/vD1dUVHTt2xMWLF+Ht7V0Wwyx3fvrpJyxduhTLli1DvXr1cPToUYwdOxZubm4ICwsr6+E9EQpTw759+yrt/f390aBBA3h7e2PHjh3o2LFjWQ293Pnuu+8wcOBAVKtWDSYmJmjSpAn69euHw4cPl/XQnhgF1bCi7Iv8SKUYLl26hC1btmDw4MHKPBcXF6SnpyMpKcmg7fXr1+Hi4qK0efyqlezp7DZPi9xqmJuAgAAAQGxsLADWEAAmTpyIt956C3379oW/vz9effVVvPHGG4iOjgbw/3XIrU6P7os3btwwWJ6ZmYnExMSnoo4F1TA3NWvWRNWqVQ32xae5htm8vb2xc+dOpKSk4MqVKzhw4AAyMjJQs2ZN7ouFlF8Nc/Ok7osMHMWwePFiODk5oWvXrsq8pk2bwtTUFFu3blXmnTt3DpcvX0ZgYCAAIDAwECdOnDDYMTZv3gxbW1v4+fmV3gaUA7nVMDdHjx4FALi6ugJgDQHg/v370GoNH7omJibQ6/UAAC8vL7i4uBjsi8nJydi/f7/BvpiUlGTwLnTbtm3Q6/VKyKvICqphbv7++2/cunXLYF98mmv4OCsrK7i6uuL27dvYuHEjunfvzn2xiHKrYW6e2H2xrM9afdJkZWVJjRo15M0338yxbPjw4VKjRg3Ztm2bHDp0SAIDAyUwMFBZnn1JZ+fOneXo0aOyYcMGcXR0fKou6RTJu4axsbEybdo0OXTokMTFxcmaNWukZs2a0qZNG6UNa/jwjPVq1aopl3SuXLlSqlatKpMmTVLafPDBB2Jvby9r1qyR48ePS/fu3XO9FLFx48ayf/9+2b17t9SuXbvcXUanloJqePfuXZkwYYLExMRIXFycbNmyRZo0aSK1a9eW1NRUpZ+nuYbZNmzYIL///rv89ddfsmnTJmnYsKEEBARIenq6iHBfLIz8aliR9kUGjiLauHGjAJBz587lWPbgwQN5/fXXpXLlymJpaSk9e/aUa9euGbSJj4+X0NBQsbCwkKpVq8r48eMlIyOjtIZfLuRVw8uXL0ubNm3EwcFBdDqd1KpVSyZOnGjwPRwirGFycrKMGTNGatSoIebm5lKzZk155513DC4L1uv1MnnyZHF2dhadTicdO3bMUe9bt25Jv379xNraWmxtbWXAgAFy9+7d0t6cMlFQDe/fvy+dO3cWR0dHMTU1FQ8PDxkyZIjB5dgiT3cNs/34449Ss2ZNMTMzExcXF4mIiJCkpCRlOffFguVXw4q0L/Ln6YmIiEh1PIeDiIiIVMfAQURERKpj4CAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg55K8fHx0Gg0ym+1lAdnz55FixYtYG5ujkaNGpW4P09PT8yfP7/E/ZQXO3bsgEajyfEDiU8zjUaD1atXl/UwjKpdu3YYO3ZsWQ+DVMDAQWUiPDwcGo0GH3zwgcH81atXQ6PRlNGoylZUVBSsrKxw7tw5gx+7etyVK1cwcOBAuLm5wczMDB4eHhgzZgxu3bpViqNVV24vOi1btsS1a9dgZ2dXNoMqRUuWLIFGo8n3Lz4+HteuXUNoaGipj+/mzZsYMWIEatSoAZ1OBxcXFwQHB2PPnj0l7nvlypWYPn26EUZJ5Q0DB5UZc3NzzJo1C7dv3y7roRhNenp6sW978eJFtG7dGh4eHqhSpUqubf766y80a9YMFy5cwPLlyxEbG4svvvgCW7duRWBgIBITE4u9/pLKysrK99dWS8rMzAwuLi4VLpCKCDIzMw3m9enTB9euXVP+AgMDMWTIEIN57u7ucHFxgU6nK/Ux9+7dG3/++Se+/fZbnD9/Hr/++ivatWtXotCb/dhxcHCAjY2NsYZK5UkZ/5YLPaXCwsLkueeeEx8fH5k4caIyf9WqVfLobhkVFSUNGzY0uO28efPEw8PDoK/u3bvLzJkzxcnJSezs7GTq1KmSkZEhEyZMkMqVK0u1atXkm2++UW4TFxcnAGT58uUSGBgoOp1O6tWrJzt27DBY14kTJyQkJESsrKzEyclJXnnlFbl586ayvG3bthIRESFjxoyRKlWqSLt27XLd3qysLJk6dapUq1ZNzMzMpGHDhvL7778rywEY/EVFReXaT0hIiFSvXl3u379vMP/atWtiaWkpw4cPV+Z5eHjItGnTpG/fvmJpaSlubm7y2WefKcv1er1ERUWJu7u7mJmZiaurq4waNUpZnpqaKuPHjxc3NzextLSUZ555RrZv364sX7x4sdjZ2cmaNWvE19dXTExM5D//+Y/odDq5ffu2wfhGjx4t7du3FxGRf//9V/r27Stubm5iYWEh9evXl2XLliltw8LCctQjLi5Otm/fLgAM+v7555/Fz89PzMzMxMPDQz788EOD9Xp4eMjMmTNlwIABYm1tLe7u7vKf//xHWZ6WliYRERHi4uIiOp1OatSoIe+//36utc8eW/fu3WXKlClStWpVsbGxkWHDhhn8cF5WVpa8//774unpKebm5tKgQQNZsWKFsjx7O9avXy9NmjQRU1NTg7rmpm3btjJmzJgc8wHIqlWrROT/9+kff/xRWrduLebm5tKsWTM5d+6cHDhwQJo2bSpWVlYSEhIiN27cMOhn0aJF4uPjIzqdTurWrSsLFizIcyy3b98WADkeK7m1GzRokFKn9u3by9GjR5Xl2Y/tRYsWiaenp2g0mly3taD9MD4+Xp577jmxt7cXS0tL8fPzk3Xr1uU7NiobDBxUJrKfuFeuXCnm5uZy5coVESl+4LCxsZGIiAg5e/asfP311wJAgoODZebMmXL+/HmZPn26mJqaKuvJfnKuXr26/Pzzz3L69GkZPHiw2NjYyL///isiD58wHR0dJTIyUs6cOSNHjhyRTp06KS+cIg+fHK2trWXixIly9uxZOXv2bK7bO3fuXLG1tZXly5fL2bNnZdKkSWJqairnz58XkYeBoV69ejJ+/Hi5du1arr/yeOvWLdFoNHm+IA4ZMkQqV64ser1eRB6+2NrY2Eh0dLScO3dOPvnkEzExMZFNmzaJiMiKFSvE1tZW1q9fL5cuXZL9+/fLl19+qfQ3ePBgadmypezatUtiY2Nlzpw5otPplDEvXrxYTE1NpWXLlrJnzx45e/aspKSkiLOzs3z11VdKP5mZmQbz/v77b5kzZ478+eefcvHiRWVc+/fvFxGRpKQkCQwMlCFDhsi1a9fk2rVrkpmZmSNwHDp0SLRarUybNk3OnTsnixcvFgsLC1m8eLGybg8PD3FwcJAFCxbIhQsXJDo6WrRarXI/zZkzR9zd3WXXrl0SHx8vf/zxh0H4eVxYWJhYW1tLnz595OTJk7J27VpxdHSUt99+W2kzY8YM8fHxkQ0bNsjFixdl8eLFotPplBfo7O1o0KCBbNq0SWJjY+XWrVt5rlOkaIEje92nT5+WFi1aSNOmTaVdu3aye/duOXLkiNSqVcsgmH7//ffi6uoqv/zyi/z111/yyy+/iIODgyxZsiTXsWRkZIi1tbWMHTvW4OfRHxcUFCTdunWTgwcPyvnz52X8+PFSpUoVZVujoqKUAHTkyBE5duxYrtta0H7YtWtX6dSpkxw/flwuXrwov/32m+zcuTPfelLZYOCgMpEdOEREWrRoIQMHDhSR4gcODw8PycrKUubVrVtXnn32WWU6MzNTrKysZPny5SLy/0/OH3zwgdImIyNDqlevLrNmzRIRkenTp0vnzp0N1n3lyhUBoPy8dtu2baVx48YFbq+bm5vMnDnTYF7z5s3l9ddfV6YbNmyY55ENEZF9+/YZvMA8bu7cuQJArl+/LiIPX2xDQkIM2vTp00dCQ0NFROSjjz6SOnXqSHp6eo6+Ll26JCYmJvLPP/8YzO/YsaNERkaKyMPAAcDgXauIyJgxY6RDhw7K9MaNG3M96vGorl27yvjx45Xp3F5gHw8cL7/8snTq1MmgzcSJE8XPz0+Z9vDwkFdeeUWZ1uv14uTkJJ9//rmIiIwaNUo6dOighLSChIWFiYODg9y7d0+Z9/nnn4u1tbVkZWVJamqqWFpayt69ew1uN2jQIOnXr5/BdqxevbpQ6xQpWuB4NOwtX75cAMjWrVuVedHR0VK3bl1l2tvbO0fImj59ugQGBuY5np9//lkqV64s5ubm0rJlS4mMjFQCg4jIH3/8Iba2tjkCibe3t3KEKSoqSkxNTXMcbXl0WwuzH/r7+8uUKVPyHCuVHzyHg8rcrFmz8O233+LMmTPF7qNevXrQav9/d3Z2doa/v78ybWJigipVquDGjRsGtwsMDFT+r1SpEpo1a6aM49ixY9i+fTusra2VPx8fHwAPz7fI1rRp03zHlpycjKtXr6JVq1YG81u1alWsbRaRQrd9dPuyp7PX+eKLL+LBgweoWbMmhgwZglWrVinnEpw4cQJZWVmoU6eOwfbv3LnTYNvNzMzQoEEDg3X0798fO3bswNWrVwEAS5cuRdeuXWFvbw/g4bke06dPh7+/PxwcHGBtbY2NGzfi8uXLRarDmTNncq3phQsXkJWVpcx7dHwajQYuLi7KfhAeHo6jR4+ibt26GD16NDZt2lTgehs2bAhLS0tlOjAwECkpKbhy5QpiY2Nx//59dOrUyaBu//3vfw3qBgDNmjUr0vYW1qPb6+zsDAAGjwVnZ2dl++/du4eLFy9i0KBBBuOdMWNGjvE+qnfv3rh69Sp+/fVXhISEYMeOHWjSpAmWLFkC4OFjJyUlBVWqVDHoNy4uzqBfDw8PODo65rmewuyHo0ePxowZM9CqVStERUXh+PHjRS8alYpKZT0AojZt2iA4OBiRkZEIDw83WKbVanO8wGZkZOTow9TU1GBao9HkOq8oJzWmpKSgW7dumDVrVo5lrq6uyv9WVlaF7rMkatWqBY1GgzNnzqBnz545lp85cwaVK1fO9wn8Ue7u7jh37hy2bNmCzZs34/XXX8ecOXOwc+dOpKSkwMTEBIcPH4aJiYnB7aytrZX/LSwscpzE2bx5c3h7e+OHH37AiBEjsGrVKuWFCADmzJmDjz/+GPPnz4e/vz+srKwwduzYEp1wm5/89oMmTZogLi4Ov//+O7Zs2YKXXnoJQUFB+Pnnn4u1rpSUFADAunXrUK1aNYNlj5/cqdZ+8+j2Zt83j8/L3v7s8S5atAgBAQEG/Tx+vz/O3NwcnTp1QqdOnTB58mQMHjwYUVFRCA8PR0pKClxdXbFjx44ct8sOnkDBNSjMfjh48GAEBwdj3bp12LRpE6Kjo/HRRx9h1KhR+fZNpY+Bg8qFDz74AI0aNULdunUN5js6OiIhIQEiojx5GvO7M/bt24c2bdoAADIzM3H48GGMHDkSwMMXo19++QWenp6oVKn4DxVbW1u4ublhz549aNu2rTJ/z549eOaZZwrdT5UqVdCpUycsXLgQb7zxBiwsLJRlCQkJWLp0KV577TWDALBv3z6DPvbt2wdfX19l2sLCAt26dUO3bt0QEREBHx8fnDhxAo0bN0ZWVhZu3LiBZ599tsjb3L9/fyxduhTVq1eHVqtF165dDba7e/fueOWVVwAAer0e58+fh5+fn9LGzMzM4ChFbnx9fXNchrlnzx7UqVOnwBfLR9na2qJPnz7o06cPXnjhBYSEhCAxMREODg65tj927BgePHig1H/fvn2wtraGu7s7HBwcoNPpcPnyZYP7urxydnaGm5sb/vrrL/Tv379Effn5+SnfCdKkSRMkJCSgUqVK8PT0LHafhd0P3d3dMXz4cAwfPhyRkZFYtGgRA0c5xMBB5YK/vz/69++PTz75xGB+u3btcPPmTcyePRsvvPACNmzYgN9//x22trZGWe+CBQtQu3Zt+Pr6Yt68ebh9+zYGDhwIAIiIiMCiRYvQr18/TJo0CQ4ODoiNjcUPP/yAr776qkgvahMnTkRUVBS8vb3RqFEjLF68GEePHsXSpUuLNN7PPvsMLVu2RHBwMGbMmAEvLy+cOnUKEydORLVq1TBz5kyD9nv27MHs2bPRo0cPbN68GStWrMC6desAPPyuh6ysLAQEBMDS0hLff/89LCwslMty+/fvj9deew0fffQRGjdujJs3b2Lr1q1o0KCBQYDITf/+/TFlyhTMnDkTL7zwgsG7+9q1a+Pnn3/G3r17UblyZcydOxfXr183CByenp7Yv38/4uPjYW1tneuL//jx49G8eXNMnz4dffr0QUxMDD777DMsXLiw0PWcO3cuXF1d0bhxY2i1WqxYsQIuLi4G78Ifl56ejkGDBuHdd99FfHw8oqKiMHLkSGi1WtjY2GDChAl44403oNfr0bp1a9y5cwd79uyBra0twsLCCj220jJ16lSMHj0adnZ2CAkJQVpaGg4dOoTbt29j3LhxOdrfunULL774IgYOHIgGDRrAxsYGhw4dwuzZs9G9e3cAQFBQEAIDA9GjRw/Mnj0bderUwdWrV7Fu3Tr07Nmz0B8n1alTp8D9cOzYsQgNDUWdOnVw+/ZtbN++3SBUU/nBczio3Jg2bVqOjzx8fX2xcOFCLFiwAA0bNsSBAwcwYcIEo63zgw8+wAcffICGDRti9+7d+PXXX1G1alUAUI5KZGVloXPnzvD398fYsWNhb29vcL5IYYwePRrjxo3D+PHj4e/vjw0bNuDXX39F7dq1i9RP7dq1cejQIdSsWRMvvfQSvL29MXToULRv3x4xMTE5XpjHjx+PQ4cOoXHjxpgxYwbmzp2L4OBgAA8PbS9atAitWrVCgwYNsGXLFvz222/Kd4AsXrwYr732GsaPH4+6deuiR48eOHjwIGrUqFHgOGvVqoVnnnkGx48fz/HO+d1330WTJk0QHByMdu3awcXFBT169DBoM2HCBJiYmMDPzw+Ojo65nt/RpEkT/PTTT/jhhx9Qv359vPfee5g2bVqOj+XyY2Njg9mzZ6NZs2Zo3rw54uPjsX79+nzv344dO6J27dpo06YN+vTpg+effx5TpkxRlk+fPh2TJ09GdHQ0fH19ERISgnXr1sHLy6vQ4ypNgwcPxldffYXFixfD398fbdu2xZIlS/Icr7W1NQICAjBv3jy0adMG9evXx+TJkzFkyBB89tlnAB5+bLN+/Xq0adMGAwYMQJ06ddC3b19cunRJOa+ksAraD7OyshAREaHUuk6dOkUKnVR6NFKUM9CIiJ5i4eHhSEpKqnBfJ05UGniEg4iIiFTHwEFERESq40cqREREpDoe4SAiIiLVMXAQERGR6hg4iIiISHUMHERERKQ6Bg4iIiJSHQMHERERqY6Bg4iIiFTHwEFERESq+z8DiFOUlGmU9gAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 600x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Count number of unique time series and number of observations per item_id\n",
    "n_unique_series = context_df['item_id'].nunique()\n",
    "lengths = context_df.groupby('item_id')['timestamp'].count()\n",
    "\n",
    "# Plot the distribution\n",
    "plt.figure(figsize=(6, 4))\n",
    "plt.hist(lengths)\n",
    "plt.title(f'Time Series Lengths of Total {n_unique_series} Series')\n",
    "plt.xlabel('Number of Observations per Time Series')\n",
    "plt.ylabel('Counts')\n",
    "plt.grid(alpha=0.3)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "7ebac5c4",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.12/dist-packages/torch/utils/data/dataloader.py:665: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used.\n",
      "  warnings.warn(warn_msg)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>item_id</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>target_name</th>\n",
       "      <th>predictions</th>\n",
       "      <th>0.1</th>\n",
       "      <th>0.9</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-30 04:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>624.867920</td>\n",
       "      <td>611.385071</td>\n",
       "      <td>638.598694</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-30 05:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>563.703125</td>\n",
       "      <td>546.655029</td>\n",
       "      <td>578.665649</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-30 06:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>521.589905</td>\n",
       "      <td>505.747437</td>\n",
       "      <td>537.950806</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-30 07:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>489.910706</td>\n",
       "      <td>473.671814</td>\n",
       "      <td>508.854126</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>H1</td>\n",
       "      <td>1750-01-30 08:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>471.144501</td>\n",
       "      <td>452.199371</td>\n",
       "      <td>491.050354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9931</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-10 19:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>61.697693</td>\n",
       "      <td>49.787407</td>\n",
       "      <td>75.447968</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9932</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-10 20:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>52.210609</td>\n",
       "      <td>41.923550</td>\n",
       "      <td>65.115601</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9933</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-10 21:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>46.259827</td>\n",
       "      <td>36.681183</td>\n",
       "      <td>55.795212</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9934</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-10 22:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>33.600002</td>\n",
       "      <td>26.682114</td>\n",
       "      <td>41.483673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9935</th>\n",
       "      <td>H414</td>\n",
       "      <td>1750-02-10 23:00:00</td>\n",
       "      <td>target</td>\n",
       "      <td>22.696373</td>\n",
       "      <td>17.629684</td>\n",
       "      <td>26.969643</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>9936 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     item_id           timestamp target_name  predictions         0.1  \\\n",
       "0         H1 1750-01-30 04:00:00      target   624.867920  611.385071   \n",
       "1         H1 1750-01-30 05:00:00      target   563.703125  546.655029   \n",
       "2         H1 1750-01-30 06:00:00      target   521.589905  505.747437   \n",
       "3         H1 1750-01-30 07:00:00      target   489.910706  473.671814   \n",
       "4         H1 1750-01-30 08:00:00      target   471.144501  452.199371   \n",
       "...      ...                 ...         ...          ...         ...   \n",
       "9931    H414 1750-02-10 19:00:00      target    61.697693   49.787407   \n",
       "9932    H414 1750-02-10 20:00:00      target    52.210609   41.923550   \n",
       "9933    H414 1750-02-10 21:00:00      target    46.259827   36.681183   \n",
       "9934    H414 1750-02-10 22:00:00      target    33.600002   26.682114   \n",
       "9935    H414 1750-02-10 23:00:00      target    22.696373   17.629684   \n",
       "\n",
       "             0.9  \n",
       "0     638.598694  \n",
       "1     578.665649  \n",
       "2     537.950806  \n",
       "3     508.854126  \n",
       "4     491.050354  \n",
       "...          ...  \n",
       "9931   75.447968  \n",
       "9932   65.115601  \n",
       "9933   55.795212  \n",
       "9934   41.483673  \n",
       "9935   26.969643  \n",
       "\n",
       "[9936 rows x 6 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred_df = pipeline.predict_df(context_df, id_column=\"item_id\", target=\"target\", timestamp_column=\"timestamp\", \n",
    "                              prediction_length=24, quantile_levels=[0.1, 0.9])\n",
    "pred_df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fbb49405",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "source": [
    "## Retail Demand Forecasting\n",
    "\n",
    "Forecast next quarter's weekly store sales using historical sales, historical customer footfall (Customers), and known covariates indicating store operation (Open), promotion periods (Promo), and holidays (SchoolHoliday, StateHoliday)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "cef8aa47",
   "metadata": {
    "editable": true,
    "lines_to_next_cell": 1,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "# Visualization helper function\n",
    "def plot_forecast(\n",
    "    context_df: pd.DataFrame,\n",
    "    pred_df: pd.DataFrame,\n",
    "    test_df: pd.DataFrame,\n",
    "    target_column: str,\n",
    "    timeseries_id: str,\n",
    "    id_column: str = \"id\",\n",
    "    timestamp_column: str = \"timestamp\",\n",
    "    history_length: int = 256,\n",
    "    title_suffix: str = \"\",\n",
    "):\n",
    "\n",
    "    # Simple type correction\n",
    "    timeseries_id = int(timeseries_id)\n",
    "    context_df[timestamp_column] = pd.to_datetime(context_df[timestamp_column])\n",
    "    pred_df[timestamp_column] = pd.to_datetime(pred_df[timestamp_column])\n",
    "    test_df[timestamp_column] = pd.to_datetime(test_df[timestamp_column])\n",
    "    \n",
    "    ts_context = context_df.query(f\"{id_column} == @timeseries_id\").set_index(timestamp_column)[target_column]\n",
    "    ts_pred = pred_df.query(f\"{id_column} == @timeseries_id and target_name == @target_column\").set_index(\n",
    "        timestamp_column\n",
    "    )[[\"0.1\", \"predictions\", \"0.9\"]]\n",
    "    ts_ground_truth = test_df.query(f\"{id_column} == @timeseries_id\").set_index(timestamp_column)[target_column]\n",
    "\n",
    "    last_date = ts_context.index.max()\n",
    "    start_idx = max(0, len(ts_context) - history_length)\n",
    "    print(start_idx)\n",
    "    plot_cutoff = ts_context.index[start_idx]\n",
    "    ts_context = ts_context[ts_context.index >= plot_cutoff]\n",
    "    ts_pred = ts_pred[ts_pred.index >= plot_cutoff]\n",
    "    ts_ground_truth = ts_ground_truth[ts_ground_truth.index >= plot_cutoff]\n",
    "\n",
    "    fig = plt.figure(figsize=(12, 3))\n",
    "    ax = fig.gca()\n",
    "    ts_context.plot(ax=ax, label=f\"historical {target_column}\", color=\"xkcd:azure\")\n",
    "    ts_ground_truth.plot(ax=ax, label=f\"future {target_column} (ground truth)\", color=\"xkcd:grass green\")\n",
    "    ts_pred[\"predictions\"].plot(ax=ax, label=\"forecast\", color=\"xkcd:violet\")\n",
    "    ax.fill_between(\n",
    "        ts_pred.index,\n",
    "        ts_pred[\"0.1\"],\n",
    "        ts_pred[\"0.9\"],\n",
    "        alpha=0.7,\n",
    "        label=\"prediction interval\",\n",
    "        color=\"xkcd:light lavender\",\n",
    "    )\n",
    "    ax.axvline(x=last_date, color=\"black\", linestyle=\"--\", alpha=0.5)\n",
    "    ax.legend(loc=\"upper left\")\n",
    "    ax.set_title(f\"{target_column} forecast for {timeseries_id} {title_suffix}\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "48a4b732",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>Sales</th>\n",
       "      <th>Open</th>\n",
       "      <th>Promo</th>\n",
       "      <th>SchoolHoliday</th>\n",
       "      <th>StateHoliday</th>\n",
       "      <th>Customers</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2013-01-13</td>\n",
       "      <td>32952.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3918.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2013-01-20</td>\n",
       "      <td>25978.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3417.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2013-01-27</td>\n",
       "      <td>33071.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3862.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2013-02-03</td>\n",
       "      <td>28693.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3561.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2013-02-10</td>\n",
       "      <td>35771.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4094.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133795</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-03-29</td>\n",
       "      <td>43358.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3252.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133796</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-04-05</td>\n",
       "      <td>69663.0</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4424.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133797</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-04-12</td>\n",
       "      <td>35267.0</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>5.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2771.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133798</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-04-19</td>\n",
       "      <td>63849.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4230.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>133799</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-04-26</td>\n",
       "      <td>39247.0</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3027.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>133800 rows × 8 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         id   timestamp    Sales      Open     Promo  SchoolHoliday  \\\n",
       "0         1  2013-01-13  32952.0  0.857143  0.714286            5.0   \n",
       "1         1  2013-01-20  25978.0  0.857143  0.000000            0.0   \n",
       "2         1  2013-01-27  33071.0  0.857143  0.714286            0.0   \n",
       "3         1  2013-02-03  28693.0  0.857143  0.000000            0.0   \n",
       "4         1  2013-02-10  35771.0  0.857143  0.714286            0.0   \n",
       "...     ...         ...      ...       ...       ...            ...   \n",
       "133795  999  2015-03-29  43358.0  0.857143  0.000000            0.0   \n",
       "133796  999  2015-04-05  69663.0  0.714286  0.714286            2.0   \n",
       "133797  999  2015-04-12  35267.0  0.714286  0.000000            5.0   \n",
       "133798  999  2015-04-19  63849.0  0.857143  0.714286            0.0   \n",
       "133799  999  2015-04-26  39247.0  0.857143  0.000000            0.0   \n",
       "\n",
       "        StateHoliday  Customers  \n",
       "0                0.0     3918.0  \n",
       "1                0.0     3417.0  \n",
       "2                0.0     3862.0  \n",
       "3                0.0     3561.0  \n",
       "4                0.0     4094.0  \n",
       "...              ...        ...  \n",
       "133795           0.0     3252.0  \n",
       "133796           1.0     4424.0  \n",
       "133797           1.0     2771.0  \n",
       "133798           0.0     4230.0  \n",
       "133799           0.0     3027.0  \n",
       "\n",
       "[133800 rows x 8 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Retail forecasting configuration\n",
    "target = \"Sales\"  # Column name containing sales values to forecast\n",
    "prediction_length = 13  # Number of days to forecast ahead\n",
    "id_column = \"id\"  # Column identifying different products/stores\n",
    "timestamp_column = \"timestamp\"  # Column containing datetime information\n",
    "timeseries_id = \"1\"  # Specific time series to visualize (product/store ID)\n",
    "\n",
    "# Load historical sales and past values of covariates\n",
    "# sales_context_df = pd.read_parquet(\"../data/retail_sales_train.parquet\")\n",
    "sales_context_df = pd.read_csv(\"../data/retail_sales_train.csv\")\n",
    "sales_context_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e69d12ff-0430-4db9-8969-e97df36af5b1",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>Open</th>\n",
       "      <th>Promo</th>\n",
       "      <th>SchoolHoliday</th>\n",
       "      <th>StateHoliday</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-03</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-10</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-17</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-24</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-31</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14490</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-06-28</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14491</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-05</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14492</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-12</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14493</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-19</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14494</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-26</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>14495 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        id   timestamp      Open     Promo  SchoolHoliday  StateHoliday\n",
       "0        1  2015-05-03  0.714286  0.714286            0.0           1.0\n",
       "1        1  2015-05-10  0.857143  0.714286            0.0           0.0\n",
       "2        1  2015-05-17  0.714286  0.000000            0.0           1.0\n",
       "3        1  2015-05-24  0.857143  0.714286            0.0           0.0\n",
       "4        1  2015-05-31  0.714286  0.000000            0.0           1.0\n",
       "...    ...         ...       ...       ...            ...           ...\n",
       "14490  999  2015-06-28  0.857143  0.000000            0.0           0.0\n",
       "14491  999  2015-07-05  0.857143  0.714286            0.0           0.0\n",
       "14492  999  2015-07-12  0.857143  0.000000            0.0           0.0\n",
       "14493  999  2015-07-19  0.857143  0.714286            5.0           0.0\n",
       "14494  999  2015-07-26  0.857143  0.000000            5.0           0.0\n",
       "\n",
       "[14495 rows x 6 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Load future values of covariates\n",
    "# sales_test_df = pd.read_parquet(\"../data/retail_sales_test.parquet\")\n",
    "sales_test_df = pd.read_csv(\"../data/retail_sales_test.csv\")\n",
    "\n",
    "sales_future_df = sales_test_df.drop(columns=target)\n",
    "sales_future_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "55f94cc5-68af-4d38-ab5e-9ab2e7739c28",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.12/dist-packages/torch/utils/data/dataloader.py:665: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used.\n",
      "  warnings.warn(warn_msg)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>target_name</th>\n",
       "      <th>predictions</th>\n",
       "      <th>0.1</th>\n",
       "      <th>0.9</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-03</td>\n",
       "      <td>Sales</td>\n",
       "      <td>28868.748047</td>\n",
       "      <td>24831.210938</td>\n",
       "      <td>32377.041016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-10</td>\n",
       "      <td>Sales</td>\n",
       "      <td>23496.941406</td>\n",
       "      <td>20528.724609</td>\n",
       "      <td>28279.544922</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-17</td>\n",
       "      <td>Sales</td>\n",
       "      <td>28338.820312</td>\n",
       "      <td>23889.726562</td>\n",
       "      <td>32065.578125</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-24</td>\n",
       "      <td>Sales</td>\n",
       "      <td>24089.554688</td>\n",
       "      <td>20643.382812</td>\n",
       "      <td>29365.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-31</td>\n",
       "      <td>Sales</td>\n",
       "      <td>27662.677734</td>\n",
       "      <td>22583.529297</td>\n",
       "      <td>31700.175781</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14490</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-06-28</td>\n",
       "      <td>Sales</td>\n",
       "      <td>53684.523438</td>\n",
       "      <td>38193.703125</td>\n",
       "      <td>66396.875000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14491</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-05</td>\n",
       "      <td>Sales</td>\n",
       "      <td>56915.792969</td>\n",
       "      <td>38879.417969</td>\n",
       "      <td>66857.273438</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14492</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-12</td>\n",
       "      <td>Sales</td>\n",
       "      <td>53435.722656</td>\n",
       "      <td>37711.125000</td>\n",
       "      <td>66004.101562</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14493</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-19</td>\n",
       "      <td>Sales</td>\n",
       "      <td>56994.824219</td>\n",
       "      <td>38699.746094</td>\n",
       "      <td>66507.718750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14494</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-26</td>\n",
       "      <td>Sales</td>\n",
       "      <td>51786.867188</td>\n",
       "      <td>37531.007812</td>\n",
       "      <td>65674.789062</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>14495 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        id  timestamp target_name   predictions           0.1           0.9\n",
       "0        1 2015-05-03       Sales  28868.748047  24831.210938  32377.041016\n",
       "1        1 2015-05-10       Sales  23496.941406  20528.724609  28279.544922\n",
       "2        1 2015-05-17       Sales  28338.820312  23889.726562  32065.578125\n",
       "3        1 2015-05-24       Sales  24089.554688  20643.382812  29365.500000\n",
       "4        1 2015-05-31       Sales  27662.677734  22583.529297  31700.175781\n",
       "...    ...        ...         ...           ...           ...           ...\n",
       "14490  999 2015-06-28       Sales  53684.523438  38193.703125  66396.875000\n",
       "14491  999 2015-07-05       Sales  56915.792969  38879.417969  66857.273438\n",
       "14492  999 2015-07-12       Sales  53435.722656  37711.125000  66004.101562\n",
       "14493  999 2015-07-19       Sales  56994.824219  38699.746094  66507.718750\n",
       "14494  999 2015-07-26       Sales  51786.867188  37531.007812  65674.789062\n",
       "\n",
       "[14495 rows x 6 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# forecast without covariates\n",
    "sales_pred_no_cov_df = pipeline.predict_df(\n",
    "    sales_context_df[[id_column, timestamp_column, target]],\n",
    "    future_df=None,\n",
    "    prediction_length=prediction_length,\n",
    "    quantile_levels=[0.1, 0.9],\n",
    "    id_column=id_column,\n",
    "    timestamp_column=timestamp_column,\n",
    "    target=target,\n",
    ")\n",
    "sales_pred_no_cov_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a56cf59c",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.12/dist-packages/torch/utils/data/dataloader.py:665: UserWarning: 'pin_memory' argument is set as true but no accelerator is found, then device pinned memory won't be used.\n",
      "  warnings.warn(warn_msg)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>id</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>target_name</th>\n",
       "      <th>predictions</th>\n",
       "      <th>0.1</th>\n",
       "      <th>0.9</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-03</td>\n",
       "      <td>Sales</td>\n",
       "      <td>28939.392578</td>\n",
       "      <td>25214.275391</td>\n",
       "      <td>32411.097656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-10</td>\n",
       "      <td>Sales</td>\n",
       "      <td>25541.919922</td>\n",
       "      <td>21921.328125</td>\n",
       "      <td>29191.929688</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-17</td>\n",
       "      <td>Sales</td>\n",
       "      <td>23640.240234</td>\n",
       "      <td>20500.343750</td>\n",
       "      <td>26884.666016</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-24</td>\n",
       "      <td>Sales</td>\n",
       "      <td>26778.261719</td>\n",
       "      <td>23318.353516</td>\n",
       "      <td>30162.820312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2015-05-31</td>\n",
       "      <td>Sales</td>\n",
       "      <td>22679.357422</td>\n",
       "      <td>19722.281250</td>\n",
       "      <td>25990.042969</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14490</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-06-28</td>\n",
       "      <td>Sales</td>\n",
       "      <td>40080.484375</td>\n",
       "      <td>34807.414062</td>\n",
       "      <td>47214.660156</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14491</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-05</td>\n",
       "      <td>Sales</td>\n",
       "      <td>68556.195312</td>\n",
       "      <td>61109.796875</td>\n",
       "      <td>75537.335938</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14492</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-12</td>\n",
       "      <td>Sales</td>\n",
       "      <td>40855.218750</td>\n",
       "      <td>35225.363281</td>\n",
       "      <td>48365.933594</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14493</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-19</td>\n",
       "      <td>Sales</td>\n",
       "      <td>66134.984375</td>\n",
       "      <td>59100.578125</td>\n",
       "      <td>73635.484375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14494</th>\n",
       "      <td>999</td>\n",
       "      <td>2015-07-26</td>\n",
       "      <td>Sales</td>\n",
       "      <td>39742.546875</td>\n",
       "      <td>34394.359375</td>\n",
       "      <td>46101.925781</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>14495 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        id  timestamp target_name   predictions           0.1           0.9\n",
       "0        1 2015-05-03       Sales  28939.392578  25214.275391  32411.097656\n",
       "1        1 2015-05-10       Sales  25541.919922  21921.328125  29191.929688\n",
       "2        1 2015-05-17       Sales  23640.240234  20500.343750  26884.666016\n",
       "3        1 2015-05-24       Sales  26778.261719  23318.353516  30162.820312\n",
       "4        1 2015-05-31       Sales  22679.357422  19722.281250  25990.042969\n",
       "...    ...        ...         ...           ...           ...           ...\n",
       "14490  999 2015-06-28       Sales  40080.484375  34807.414062  47214.660156\n",
       "14491  999 2015-07-05       Sales  68556.195312  61109.796875  75537.335938\n",
       "14492  999 2015-07-12       Sales  40855.218750  35225.363281  48365.933594\n",
       "14493  999 2015-07-19       Sales  66134.984375  59100.578125  73635.484375\n",
       "14494  999 2015-07-26       Sales  39742.546875  34394.359375  46101.925781\n",
       "\n",
       "[14495 rows x 6 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Generate predictions with covariates\n",
    "sales_pred_df = pipeline.predict_df(\n",
    "    sales_context_df,\n",
    "    future_df=sales_future_df,\n",
    "    prediction_length=prediction_length,\n",
    "    quantile_levels=[0.1, 0.9],\n",
    "    id_column=id_column,\n",
    "    timestamp_column=timestamp_column,\n",
    "    target=target,\n",
    ")\n",
    "sales_pred_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "d5974142",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x300 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_forecast(\n",
    "    sales_context_df,\n",
    "    sales_pred_no_cov_df,\n",
    "    sales_test_df,\n",
    "    target_column=target,\n",
    "    timeseries_id=timeseries_id,\n",
    "    title_suffix=\"(without covariates)\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "447aab3e",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x300 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualize forecast with covariates\n",
    "plot_forecast(\n",
    "    sales_context_df,\n",
    "    sales_pred_df,\n",
    "    sales_test_df,\n",
    "    target_column=target,\n",
    "    timeseries_id=timeseries_id,\n",
    "    title_suffix=\"(with covariates)\",\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "jupytext": {
   "cell_metadata_filter": "-all",
   "main_language": "python",
   "notebook_metadata_filter": "-all"
  },
  "kernelspec": {
   "display_name": "/usr/bin/python (ipykernel)",
   "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_lexer": "ipython3",
   "version": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}