{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-12-30T16:25:18.445730Z",
     "iopub.status.busy": "2023-12-30T16:25:18.445137Z",
     "iopub.status.idle": "2023-12-30T16:25:19.177511Z",
     "shell.execute_reply": "2023-12-30T16:25:19.176731Z"
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import warnings\n",
    "import tqdm\n",
    "import pandas as pd\n",
    "warnings.simplefilter(action='ignore', category=pd.errors.PerformanceWarning)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-12-30T16:25:19.179665Z",
     "iopub.status.busy": "2023-12-30T16:25:19.179444Z",
     "iopub.status.idle": "2023-12-30T16:25:20.476390Z",
     "shell.execute_reply": "2023-12-30T16:25:20.475737Z"
    }
   },
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "import socceraction.atomic.spadl as atomicspadl\n",
    "import socceraction.atomic.vaep.features as fs\n",
    "import socceraction.atomic.vaep.labels as lab"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Select data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-12-30T16:25:20.479504Z",
     "iopub.status.busy": "2023-12-30T16:25:20.479037Z",
     "iopub.status.idle": "2023-12-30T16:25:20.500962Z",
     "shell.execute_reply": "2023-12-30T16:25:20.500410Z"
    }
   },
   "outputs": [],
   "source": [
    "# Configure file and folder names\n",
    "datafolder = \"../data-fifa\"\n",
    "spadl_h5 = os.path.join(datafolder, \"atomic-spadl-statsbomb.h5\")\n",
    "features_h5 = os.path.join(datafolder, \"atomic-features.h5\")\n",
    "labels_h5 = os.path.join(datafolder, \"atomic-labels.h5\")\n",
    "predictions_h5 = os.path.join(datafolder, \"atomic-predictions.h5\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-12-30T16:25:20.503432Z",
     "iopub.status.busy": "2023-12-30T16:25:20.503252Z",
     "iopub.status.idle": "2023-12-30T16:25:21.770152Z",
     "shell.execute_reply": "2023-12-30T16:25:21.769573Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "nb of games: 64\n"
     ]
    }
   ],
   "source": [
    "games = pd.read_hdf(spadl_h5, \"games\")\n",
    "print(\"nb of games:\", len(games))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Compute features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-12-30T16:25:21.772204Z",
     "iopub.status.busy": "2023-12-30T16:25:21.772046Z",
     "iopub.status.idle": "2023-12-30T16:25:33.475534Z",
     "shell.execute_reply": "2023-12-30T16:25:33.474820Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Generating and storing features in ../data-fifa/atomic-features.h5: 100%|██████████████| 64/64 [00:10<00:00,  5.88it/s]\n"
     ]
    }
   ],
   "source": [
    "xfns = [\n",
    "    fs.actiontype,\n",
    "    fs.actiontype_onehot,\n",
    "    fs.bodypart,\n",
    "    fs.bodypart_onehot,\n",
    "    fs.goalscore,\n",
    "    fs.location,\n",
    "    fs.polar,\n",
    "    fs.direction,\n",
    "    fs.team,\n",
    "    fs.time,\n",
    "    fs.time_delta\n",
    "]\n",
    "\n",
    "with pd.HDFStore(spadl_h5) as spadlstore, pd.HDFStore(features_h5) as featurestore:\n",
    "    for game in tqdm.tqdm(list(games.itertuples()),desc=f\"Generating and storing features in {features_h5}\"):\n",
    "        actions = spadlstore[f\"atomic_actions/game_{game.game_id}\"]\n",
    "        gamestates = fs.gamestates(atomicspadl.add_names(actions), 2)\n",
    "        gamestates = fs.play_left_to_right(gamestates, game.home_team_id)\n",
    "\n",
    "        X = pd.concat([fn(gamestates) for fn in xfns], axis=1)\n",
    "        featurestore.put(f\"game_{game.game_id}\", X, format='table')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Compute labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-12-30T16:25:33.479309Z",
     "iopub.status.busy": "2023-12-30T16:25:33.479100Z",
     "iopub.status.idle": "2023-12-30T16:25:39.134673Z",
     "shell.execute_reply": "2023-12-30T16:25:39.133462Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Computing and storing labels in ../data-fifa/atomic-labels.h5: 100%|███████████████████| 64/64 [00:05<00:00, 11.56it/s]\n"
     ]
    }
   ],
   "source": [
    "yfns = [lab.scores, lab.concedes, lab.goal_from_shot]\n",
    "\n",
    "with pd.HDFStore(spadl_h5) as spadlstore, pd.HDFStore(labels_h5) as labelstore:\n",
    "    for game in tqdm.tqdm(list(games.itertuples()), desc=f\"Computing and storing labels in {labels_h5}\"):\n",
    "        actions = spadlstore[f\"atomic_actions/game_{game.game_id}\"]\n",
    "        Y = pd.concat([fn(atomicspadl.add_names(actions)) for fn in yfns], axis=1)\n",
    "        labelstore.put(f\"game_{game.game_id}\", Y, format='table')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "socceraction",
   "language": "python",
   "name": "socceraction"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.1"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": true
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}