notebooks/classification_metrics.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/home/users/dmoreno2016/ATAT\n"
     ]
    }
   ],
   "source": [
    "%cd ../"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Classitication report metrics"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "These experiments consider MTA."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/users/dmoreno2016/miniconda3/envs/ATAT/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import glob\n",
    "import torch\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "from utils import get_pred_and_real, get_classification_report"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "path_root = 'results_paper'\n",
    "\n",
    "# Same order that in dataset.py \n",
    "classes = [ 'AGN', 'CART', 'Cepheid', 'Delta Scuti', 'Dwarf Novae', 'EB', 'ILOT',\n",
    "            'KN', 'M-dwarf Flare', 'PISN', 'RR Lyrae', 'SLSN', '91bg', 'Ia', 'Iax', 'Ib/c',\n",
    "            'II', 'SN-like/Other', 'TDE', 'uLens']\n",
    "\n",
    "# Order that we want\n",
    "labels_order = ['CART', 'Iax', '91bg', 'Ia', 'Ib/c', 'II', 'SN-like/Other', 'SLSN', \n",
    "                'PISN', 'TDE', 'ILOT', 'KN', 'M-dwarf Flare', 'uLens', 'Dwarf Novae', \n",
    "                'AGN', 'Delta Scuti', 'RR Lyrae', 'Cepheid', 'EB']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ATAT (LC + MD + Features)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "path_lc_md_feat_mta = 'lc_tab/Exp_cfg_-arch=lc_header_feat_mtime'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Num_folds: 5\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(20000, 20)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(20000, 20)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(20000, 20)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "test_proba_model, df_y_test = get_pred_and_real(path_root, path_lc_md_feat_mta, classes)\n",
    "\n",
    "num_folds = len(test_proba_model)\n",
    "print('Num_folds: {}'.format(num_folds))\n",
    "\n",
    "display(test_proba_model[0].shape)\n",
    "display(test_proba_model[1].shape)\n",
    "display(df_y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_keys(['f1-score', 'precision', 'recall'])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dict_mean_classes, dict_std_classes, report_metrics = get_classification_report(test_proba_model, df_y_test, num_folds)\n",
    "dict_mean_classes.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "#------------ PRECISION ------------#\n",
      "CART         :  75.3 + 2.52\n",
      "Iax          : 59.82 + 2.06\n",
      "91bg         : 88.76 + 2.18\n",
      "Ia           : 76.34 + 1.15\n",
      "Ib/c         : 50.01 + 3.76\n",
      "II           : 63.93 + 3.54\n",
      "SN-like/Other: 64.26 + 2.22\n",
      "SLSN         : 89.61 + 0.94\n",
      "PISN         : 95.94 + 0.43\n",
      "TDE          : 78.97 + 4.87\n",
      "ILOT         : 92.14 + 0.94\n",
      "KN           : 97.07 + 0.41\n",
      "M-dwarf Flare:  99.1 + 0.25\n",
      "uLens        :  86.8 + 1.72\n",
      "Dwarf Novae  : 86.16 + 1.81\n",
      "AGN          : 99.68 + 0.1 \n",
      "Delta Scuti  : 98.71 + 0.34\n",
      "RR Lyrae     : 99.52 + 0.19\n",
      "Cepheid      : 99.22 + 0.29\n",
      "EB           : 90.42 + 1.68\n",
      "#------------ RECALL ------------#\n",
      "CART         : 40.02 + 4.55\n",
      "Iax          : 65.14 + 5.43\n",
      "91bg         :  92.5 + 1.86\n",
      "Ia           : 81.38 + 1.68\n",
      "Ib/c         : 65.82 + 3.36\n",
      "II           : 66.44 + 2.79\n",
      "SN-like/Other: 60.54 + 2.88\n",
      "SLSN         : 95.42 + 0.44\n",
      "PISN         : 96.72 + 0.85\n",
      "TDE          : 92.54 + 1.0 \n",
      "ILOT         : 83.98 + 3.06\n",
      "KN           : 77.08 + 2.49\n",
      "M-dwarf Flare:  70.4 + 1.92\n",
      "uLens        : 95.64 + 0.66\n",
      "Dwarf Novae  : 92.04 + 0.94\n",
      "AGN          : 100.0 + 0.0 \n",
      "Delta Scuti  : 99.46 + 0.14\n",
      "RR Lyrae     :  99.1 + 0.19\n",
      "Cepheid      : 99.46 + 0.1 \n",
      "EB           : 99.62 + 0.1 \n",
      "#------------ F1-SCORE ------------#\n",
      "CART         : 52.02 + 3.31\n",
      "Iax          : 62.18 + 1.9 \n",
      "91bg         : 90.55 + 0.56\n",
      "Ia           : 78.76 + 0.74\n",
      "Ib/c         : 56.63 + 1.19\n",
      "II           : 65.03 + 1.32\n",
      "SN-like/Other: 62.27 + 1.5 \n",
      "SLSN         : 92.42 + 0.43\n",
      "PISN         : 96.32 + 0.37\n",
      "TDE          : 85.12 + 2.56\n",
      "ILOT         : 87.83 + 1.34\n",
      "KN           :  85.9 + 1.42\n",
      "M-dwarf Flare: 82.31 + 1.34\n",
      "uLens        : 90.99 + 0.74\n",
      "Dwarf Novae  : 88.99 + 0.89\n",
      "AGN          : 99.84 + 0.05\n",
      "Delta Scuti  : 99.08 + 0.12\n",
      "RR Lyrae     : 99.31 + 0.08\n",
      "Cepheid      : 99.34 + 0.12\n",
      "EB           : 94.79 + 0.91\n"
     ]
    }
   ],
   "source": [
    "max_label_length = max(len(label) for label in labels_order)\n",
    "max_value_length = max(max(len(f\"{dict_mean_classes[metric][label]}\") for label in labels_order) for metric in ['f1-score', 'precision', 'recall'])\n",
    "max_std_length = max(max(len(f\"{dict_std_classes[metric][label]}\") for label in labels_order) for metric in ['f1-score', 'precision', 'recall'])\n",
    "\n",
    "for metric in ['precision', 'recall', 'f1-score']:\n",
    "    print(f'#------------ {metric.upper()} ------------#')\n",
    "\n",
    "    for label in labels_order:\n",
    "        mean_val = f\"{dict_mean_classes[metric][label]:>{max_value_length}}\"\n",
    "        std_val = f\"{dict_std_classes[metric][label]:<{max_std_length}}\"\n",
    "        print(f'{label:<{max_label_length}}: {mean_val} + {std_val}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Macro avg (PRECISION): 84.59 + 0.33\n",
      "Macro avg (RECALL): 83.66 + 0.61\n",
      "Macro avg (F1-SCORE): 83.48 + 0.62\n"
     ]
    }
   ],
   "source": [
    "for metric in ['precision', 'recall', 'f1-score']:\n",
    "\n",
    "    list_mean_class = []\n",
    "    list_std_class = []\n",
    "    for i_fold in range(num_folds):\n",
    "        list_mean_class.append(report_metrics[i_fold]['macro avg'][metric] * 100)\n",
    "        list_std_class.append(report_metrics[i_fold]['macro avg'][metric] * 100)\n",
    "\n",
    "    list_mean_class = round(np.mean(list_mean_class), 2)\n",
    "    list_std_class = round(np.std(list_std_class), 2)\n",
    "\n",
    "    print('Macro avg ({}): {} + {}'.format(metric.upper(), list_mean_class, list_std_class))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ATAT (LC + MD)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "path_lc_md_mta = 'lc_tab/Exp_cfg_-arch=lc_header_mtime'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Num_folds: 5\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(20000, 20)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(20000, 20)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "(20000, 20)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "test_proba_model, df_y_test = get_pred_and_real(path_root, path_lc_md_mta, classes)\n",
    "\n",
    "num_folds = len(test_proba_model)\n",
    "print('Num_folds: {}'.format(num_folds))\n",
    "\n",
    "display(test_proba_model[0].shape)\n",
    "display(test_proba_model[1].shape)\n",
    "display(df_y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_keys(['f1-score', 'precision', 'recall'])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dict_mean_classes, dict_std_classes, report_metrics = get_classification_report(test_proba_model, df_y_test, num_folds)\n",
    "dict_mean_classes.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "#------------ PRECISION ------------#\n",
      "CART         : 72.81 + 2.95\n",
      "Iax          : 59.81 + 1.27\n",
      "91bg         : 89.42 + 0.43\n",
      "Ia           : 75.64 + 1.66\n",
      "Ib/c         : 53.81 + 3.09\n",
      "II           : 65.78 + 2.28\n",
      "SN-like/Other: 66.73 + 1.43\n",
      "SLSN         : 88.99 + 1.11\n",
      "PISN         : 93.08 + 1.09\n",
      "TDE          : 77.29 + 2.97\n",
      "ILOT         :  89.6 + 0.84\n",
      "KN           : 97.71 + 0.27\n",
      "M-dwarf Flare: 98.87 + 0.43\n",
      "uLens        : 85.78 + 1.8 \n",
      "Dwarf Novae  : 87.93 + 1.86\n",
      "AGN          : 99.78 + 0.04\n",
      "Delta Scuti  : 92.34 + 0.71\n",
      "RR Lyrae     : 93.44 + 0.94\n",
      "Cepheid      : 96.04 + 0.81\n",
      "EB           : 87.01 + 0.23\n",
      "#------------ RECALL ------------#\n",
      "CART         : 40.26 + 3.77\n",
      "Iax          : 70.12 + 2.17\n",
      "91bg         : 92.44 + 1.11\n",
      "Ia           : 84.06 + 1.7 \n",
      "Ib/c         : 63.84 + 1.94\n",
      "II           : 65.16 + 1.04\n",
      "SN-like/Other: 62.88 + 2.36\n",
      "SLSN         : 95.36 + 0.28\n",
      "PISN         : 97.46 + 0.47\n",
      "TDE          :  92.7 + 0.73\n",
      "ILOT         : 85.86 + 2.82\n",
      "KN           : 71.56 + 2.58\n",
      "M-dwarf Flare: 67.56 + 1.23\n",
      "uLens        : 95.28 + 0.88\n",
      "Dwarf Novae  : 86.28 + 0.87\n",
      "AGN          : 100.0 + 0.0 \n",
      "Delta Scuti  : 94.96 + 0.44\n",
      "RR Lyrae     : 95.98 + 0.89\n",
      "Cepheid      : 97.92 + 0.25\n",
      "EB           : 98.76 + 0.29\n",
      "#------------ F1-SCORE ------------#\n",
      "CART         : 51.69 + 2.91\n",
      "Iax          : 64.54 + 1.19\n",
      "91bg         :  90.9 + 0.42\n",
      "Ia           :  79.6 + 0.62\n",
      "Ib/c         :  58.3 + 1.26\n",
      "II           : 65.45 + 1.33\n",
      "SN-like/Other: 64.73 + 1.68\n",
      "SLSN         : 92.06 + 0.47\n",
      "PISN         : 95.22 + 0.39\n",
      "TDE          : 84.26 + 1.63\n",
      "ILOT         : 87.65 + 1.1 \n",
      "KN           : 82.59 + 1.68\n",
      "M-dwarf Flare: 80.26 + 0.76\n",
      "uLens        : 90.26 + 0.77\n",
      "Dwarf Novae  : 87.08 + 0.72\n",
      "AGN          : 99.89 + 0.02\n",
      "Delta Scuti  : 93.63 + 0.32\n",
      "RR Lyrae     : 94.68 + 0.26\n",
      "Cepheid      : 96.97 + 0.43\n",
      "EB           : 92.52 + 0.11\n"
     ]
    }
   ],
   "source": [
    "max_label_length = max(len(label) for label in labels_order)\n",
    "max_value_length = max(max(len(f\"{dict_mean_classes[metric][label]}\") for label in labels_order) for metric in ['f1-score', 'precision', 'recall'])\n",
    "max_std_length = max(max(len(f\"{dict_std_classes[metric][label]}\") for label in labels_order) for metric in ['f1-score', 'precision', 'recall'])\n",
    "\n",
    "for metric in ['precision', 'recall', 'f1-score']:\n",
    "    print(f'#------------ {metric.upper()} ------------#')\n",
    "\n",
    "    for label in labels_order:\n",
    "        mean_val = f\"{dict_mean_classes[metric][label]:>{max_value_length}}\"\n",
    "        std_val = f\"{dict_std_classes[metric][label]:<{max_std_length}}\"\n",
    "        print(f'{label:<{max_label_length}}: {mean_val} + {std_val}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Macro avg (PRECISION): 83.59 + 0.41\n",
      "Macro avg (RECALL): 82.92 + 0.5\n",
      "Macro avg (F1-SCORE): 82.61 + 0.53\n"
     ]
    }
   ],
   "source": [
    "for metric in ['precision', 'recall', 'f1-score']:\n",
    "\n",
    "    list_mean_class = []\n",
    "    list_std_class = []\n",
    "    for i_fold in range(num_folds):\n",
    "        list_mean_class.append(report_metrics[i_fold]['macro avg'][metric] * 100)\n",
    "        list_std_class.append(report_metrics[i_fold]['macro avg'][metric] * 100)\n",
    "\n",
    "    list_mean_class = round(np.mean(list_mean_class), 2)\n",
    "    list_std_class = round(np.std(list_std_class), 2)\n",
    "\n",
    "    print('Macro avg ({}): {} + {}'.format(metric.upper(), list_mean_class, list_std_class))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "path_root = 'results_rf_paper/2048_days'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "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>AGN</th>\n",
       "      <th>Dwarf Novae</th>\n",
       "      <th>M-dwarf Flare</th>\n",
       "      <th>Cepheid</th>\n",
       "      <th>Delta Scuti</th>\n",
       "      <th>EB</th>\n",
       "      <th>RR Lyrae</th>\n",
       "      <th>91bg</th>\n",
       "      <th>CART</th>\n",
       "      <th>II</th>\n",
       "      <th>ILOT</th>\n",
       "      <th>Ia</th>\n",
       "      <th>Iax</th>\n",
       "      <th>Ib/c</th>\n",
       "      <th>KN</th>\n",
       "      <th>PISN</th>\n",
       "      <th>SLSN</th>\n",
       "      <th>SN-like/Other</th>\n",
       "      <th>TDE</th>\n",
       "      <th>uLens</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SNID</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>63769469_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66380842_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64815643_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>52486614_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34971786_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               AGN  Dwarf Novae  M-dwarf Flare  Cepheid  Delta Scuti   EB  \\\n",
       "SNID                                                                        \n",
       "63769469_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "66380842_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "64815643_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "52486614_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "34971786_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "\n",
       "               RR Lyrae  91bg  CART   II  ILOT   Ia  Iax  Ib/c   KN  PISN  \\\n",
       "SNID                                                                        \n",
       "63769469_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "66380842_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "64815643_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "52486614_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "34971786_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "\n",
       "               SLSN  SN-like/Other  TDE  uLens  \n",
       "SNID                                            \n",
       "63769469_2048   0.0            0.0  0.0    0.0  \n",
       "66380842_2048   0.0            0.0  0.0    0.0  \n",
       "64815643_2048   0.0            0.0  0.0    0.0  \n",
       "52486614_2048   0.0            0.0  0.0    0.0  \n",
       "34971786_2048   0.0            0.0  0.0    0.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>AGN</th>\n",
       "      <th>Dwarf Novae</th>\n",
       "      <th>M-dwarf Flare</th>\n",
       "      <th>Cepheid</th>\n",
       "      <th>Delta Scuti</th>\n",
       "      <th>EB</th>\n",
       "      <th>RR Lyrae</th>\n",
       "      <th>91bg</th>\n",
       "      <th>CART</th>\n",
       "      <th>II</th>\n",
       "      <th>ILOT</th>\n",
       "      <th>Ia</th>\n",
       "      <th>Iax</th>\n",
       "      <th>Ib/c</th>\n",
       "      <th>KN</th>\n",
       "      <th>PISN</th>\n",
       "      <th>SLSN</th>\n",
       "      <th>SN-like/Other</th>\n",
       "      <th>TDE</th>\n",
       "      <th>uLens</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SNID</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>63769469_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66380842_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64815643_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>52486614_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34971786_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               AGN  Dwarf Novae  M-dwarf Flare  Cepheid  Delta Scuti   EB  \\\n",
       "SNID                                                                        \n",
       "63769469_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "66380842_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "64815643_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "52486614_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "34971786_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "\n",
       "               RR Lyrae  91bg  CART   II  ILOT   Ia  Iax  Ib/c   KN  PISN  \\\n",
       "SNID                                                                        \n",
       "63769469_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "66380842_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "64815643_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "52486614_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "34971786_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "\n",
       "               SLSN  SN-like/Other  TDE  uLens  \n",
       "SNID                                            \n",
       "63769469_2048   0.0            0.0  0.0    0.0  \n",
       "66380842_2048   0.0            0.0  0.0    0.0  \n",
       "64815643_2048   0.0            0.0  0.0    0.0  \n",
       "52486614_2048   0.0            0.0  0.0    0.0  \n",
       "34971786_2048   0.0            0.0  0.0    0.0  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(20000, 20)\n"
     ]
    }
   ],
   "source": [
    "test_proba_model = []\n",
    "num_folds = 5\n",
    "\n",
    "for i_fold in range(num_folds):\n",
    "    test_proba_model.append(pd.read_parquet('./{}/test_predictions_proba_model_{}.parquet'.format(path_root, i_fold)))\n",
    "\n",
    "    for idx_row in range(test_proba_model[i_fold].shape[0]):\n",
    "        idx_col = test_proba_model[i_fold].iloc[idx_row].argmax()\n",
    "        test_proba_model[i_fold].iloc[idx_row][idx_col] = 1\n",
    "\n",
    "    test_proba_model[i_fold][test_proba_model[i_fold] != 1] = 0\n",
    "\n",
    "display(test_proba_model[0].head())\n",
    "display(test_proba_model[1].head())\n",
    "print(test_proba_model[0].shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "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>AGN</th>\n",
       "      <th>Dwarf Novae</th>\n",
       "      <th>M-dwarf Flare</th>\n",
       "      <th>Cepheid</th>\n",
       "      <th>Delta Scuti</th>\n",
       "      <th>EB</th>\n",
       "      <th>RR Lyrae</th>\n",
       "      <th>91bg</th>\n",
       "      <th>CART</th>\n",
       "      <th>II</th>\n",
       "      <th>ILOT</th>\n",
       "      <th>Ia</th>\n",
       "      <th>Iax</th>\n",
       "      <th>Ib/c</th>\n",
       "      <th>KN</th>\n",
       "      <th>PISN</th>\n",
       "      <th>SLSN</th>\n",
       "      <th>SN-like/Other</th>\n",
       "      <th>TDE</th>\n",
       "      <th>uLens</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SNID</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>63769469_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>66380842_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64815643_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>52486614_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34971786_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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",
       "      <td>...</td>\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",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34694580_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>42840389_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28545440_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19549596_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>52428273_2048</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>20000 rows × 20 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               AGN  Dwarf Novae  M-dwarf Flare  Cepheid  Delta Scuti   EB  \\\n",
       "SNID                                                                        \n",
       "63769469_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "66380842_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "64815643_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "52486614_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "34971786_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "...            ...          ...            ...      ...          ...  ...   \n",
       "34694580_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "42840389_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "28545440_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "19549596_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "52428273_2048  0.0          0.0            0.0      0.0          0.0  0.0   \n",
       "\n",
       "               RR Lyrae  91bg  CART   II  ILOT   Ia  Iax  Ib/c   KN  PISN  \\\n",
       "SNID                                                                        \n",
       "63769469_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "66380842_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "64815643_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "52486614_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "34971786_2048       0.0   1.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "...                 ...   ...   ...  ...   ...  ...  ...   ...  ...   ...   \n",
       "34694580_2048       0.0   0.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "42840389_2048       0.0   0.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "28545440_2048       0.0   0.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "19549596_2048       0.0   0.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "52428273_2048       0.0   0.0   0.0  0.0   0.0  0.0  0.0   0.0  0.0   0.0   \n",
       "\n",
       "               SLSN  SN-like/Other  TDE  uLens  \n",
       "SNID                                            \n",
       "63769469_2048   0.0            0.0  0.0    0.0  \n",
       "66380842_2048   0.0            0.0  0.0    0.0  \n",
       "64815643_2048   0.0            0.0  0.0    0.0  \n",
       "52486614_2048   0.0            0.0  0.0    0.0  \n",
       "34971786_2048   0.0            0.0  0.0    0.0  \n",
       "...             ...            ...  ...    ...  \n",
       "34694580_2048   0.0            0.0  0.0    1.0  \n",
       "42840389_2048   0.0            0.0  0.0    1.0  \n",
       "28545440_2048   0.0            0.0  0.0    1.0  \n",
       "19549596_2048   0.0            0.0  0.0    1.0  \n",
       "52428273_2048   0.0            0.0  0.0    1.0  \n",
       "\n",
       "[20000 rows x 20 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_set = pd.read_parquet('./data_partition_paper/partitions.parquet')\n",
    "test_set = test_set[test_set.partition == 'test'].drop(['partition'], axis=1)\n",
    "test_set['SNID'] = test_set['SNID'].apply(lambda row: row+'_2048')\n",
    "test_set = test_set.set_index('SNID')\n",
    "test_set = pd.get_dummies(test_set.label, dtype=float)\n",
    "test_set = test_set[test_proba_model[0].columns]\n",
    "test_set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_keys(['f1-score', 'precision', 'recall'])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dict_mean_classes, dict_std_classes, report_metrics = get_classification_report(test_proba_model, test_set, num_folds)\n",
    "dict_mean_classes.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'f1-score': {'AGN': 97.59,\n",
       "  'Dwarf Novae': 80.63,\n",
       "  'M-dwarf Flare': 86.52,\n",
       "  'Cepheid': 95.64,\n",
       "  'Delta Scuti': 94.69,\n",
       "  'EB': 95.46,\n",
       "  'RR Lyrae': 95.09,\n",
       "  '91bg': 82.01,\n",
       "  'CART': 57.62,\n",
       "  'II': 52.12,\n",
       "  'ILOT': 84.08,\n",
       "  'Ia': 68.17,\n",
       "  'Iax': 56.76,\n",
       "  'Ib/c': 47.06,\n",
       "  'KN': 88.51,\n",
       "  'PISN': 90.82,\n",
       "  'SLSN': 90.17,\n",
       "  'SN-like/Other': 56.45,\n",
       "  'TDE': 79.88,\n",
       "  'uLens': 89.28},\n",
       " 'precision': {'AGN': 95.38,\n",
       "  'Dwarf Novae': 78.51,\n",
       "  'M-dwarf Flare': 95.02,\n",
       "  'Cepheid': 92.57,\n",
       "  'Delta Scuti': 90.8,\n",
       "  'EB': 93.48,\n",
       "  'RR Lyrae': 91.61,\n",
       "  '91bg': 75.2,\n",
       "  'CART': 59.16,\n",
       "  'II': 66.84,\n",
       "  'ILOT': 76.31,\n",
       "  'Ia': 61.35,\n",
       "  'Iax': 57.61,\n",
       "  'Ib/c': 57.98,\n",
       "  'KN': 86.78,\n",
       "  'PISN': 85.58,\n",
       "  'SLSN': 90.29,\n",
       "  'SN-like/Other': 59.02,\n",
       "  'TDE': 83.2,\n",
       "  'uLens': 96.91},\n",
       " 'recall': {'AGN': 99.9,\n",
       "  'Dwarf Novae': 82.86,\n",
       "  'M-dwarf Flare': 79.42,\n",
       "  'Cepheid': 98.92,\n",
       "  'Delta Scuti': 98.92,\n",
       "  'EB': 97.52,\n",
       "  'RR Lyrae': 98.86,\n",
       "  '91bg': 90.18,\n",
       "  'CART': 56.16,\n",
       "  'II': 42.72,\n",
       "  'ILOT': 93.62,\n",
       "  'Ia': 76.7,\n",
       "  'Iax': 55.94,\n",
       "  'Ib/c': 39.6,\n",
       "  'KN': 90.32,\n",
       "  'PISN': 96.74,\n",
       "  'SLSN': 90.04,\n",
       "  'SN-like/Other': 54.1,\n",
       "  'TDE': 76.82,\n",
       "  'uLens': 82.76}}"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dict_mean_classes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "#------------ PRECISION ------------#\n",
      "CART         : 59.16 + 0.38\n",
      "Iax          : 57.61 + 0.51\n",
      "91bg         :  75.2 + 0.4 \n",
      "Ia           : 61.35 + 0.36\n",
      "Ib/c         : 57.98 + 0.31\n",
      "II           : 66.84 + 0.63\n",
      "SN-like/Other: 59.02 + 0.46\n",
      "SLSN         : 90.29 + 0.12\n",
      "PISN         : 85.58 + 0.1 \n",
      "TDE          :  83.2 + 0.41\n",
      "ILOT         : 76.31 + 0.27\n",
      "KN           : 86.78 + 0.25\n",
      "M-dwarf Flare: 95.02 + 0.28\n",
      "uLens        : 96.91 + 0.43\n",
      "Dwarf Novae  : 78.51 + 0.23\n",
      "AGN          : 95.38 + 0.38\n",
      "Delta Scuti  :  90.8 + 0.3 \n",
      "RR Lyrae     : 91.61 + 0.38\n",
      "Cepheid      : 92.57 + 0.49\n",
      "EB           : 93.48 + 0.3 \n",
      "#------------ RECALL ------------#\n",
      "CART         : 56.16 + 0.57\n",
      "Iax          : 55.94 + 0.6 \n",
      "91bg         : 90.18 + 0.23\n",
      "Ia           :  76.7 + 0.24\n",
      "Ib/c         :  39.6 + 0.35\n",
      "II           : 42.72 + 0.5 \n",
      "SN-like/Other:  54.1 + 0.75\n",
      "SLSN         : 90.04 + 0.12\n",
      "PISN         : 96.74 + 0.08\n",
      "TDE          : 76.82 + 0.28\n",
      "ILOT         : 93.62 + 0.22\n",
      "KN           : 90.32 + 0.13\n",
      "M-dwarf Flare: 79.42 + 0.32\n",
      "uLens        : 82.76 + 0.2 \n",
      "Dwarf Novae  : 82.86 + 0.29\n",
      "AGN          :  99.9 + 0.06\n",
      "Delta Scuti  : 98.92 + 0.04\n",
      "RR Lyrae     : 98.86 + 0.12\n",
      "Cepheid      : 98.92 + 0.07\n",
      "EB           : 97.52 + 0.07\n",
      "#------------ F1-SCORE ------------#\n",
      "CART         : 57.62 + 0.46\n",
      "Iax          : 56.76 + 0.55\n",
      "91bg         : 82.01 + 0.19\n",
      "Ia           : 68.17 + 0.31\n",
      "Ib/c         : 47.06 + 0.16\n",
      "II           : 52.12 + 0.5 \n",
      "SN-like/Other: 56.45 + 0.6 \n",
      "SLSN         : 90.17 + 0.07\n",
      "PISN         : 90.82 + 0.04\n",
      "TDE          : 79.88 + 0.18\n",
      "ILOT         : 84.08 + 0.21\n",
      "KN           : 88.51 + 0.14\n",
      "M-dwarf Flare: 86.52 + 0.27\n",
      "uLens        : 89.28 + 0.28\n",
      "Dwarf Novae  : 80.63 + 0.24\n",
      "AGN          : 97.59 + 0.17\n",
      "Delta Scuti  : 94.69 + 0.17\n",
      "RR Lyrae     : 95.09 + 0.22\n",
      "Cepheid      : 95.64 + 0.26\n",
      "EB           : 95.46 + 0.17\n"
     ]
    }
   ],
   "source": [
    "max_label_length = max(len(label) for label in labels_order)\n",
    "max_value_length = max(max(len(f\"{dict_mean_classes[metric][label]}\") for label in labels_order) for metric in ['f1-score', 'precision', 'recall'])\n",
    "max_std_length = max(max(len(f\"{dict_std_classes[metric][label]}\") for label in labels_order) for metric in ['f1-score', 'precision', 'recall'])\n",
    "\n",
    "for metric in ['precision', 'recall', 'f1-score']:\n",
    "    print(f'#------------ {metric.upper()} ------------#')\n",
    "\n",
    "    for label in labels_order:\n",
    "        mean_val = f\"{dict_mean_classes[metric][label]:>{max_value_length}}\"\n",
    "        std_val = f\"{dict_std_classes[metric][label]:<{max_std_length}}\"\n",
    "        print(f'{label:<{max_label_length}}: {mean_val} + {std_val}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Macro avg (PRECISION): 79.68 + 0.08\n",
      "Macro avg (RECALL): 80.1 + 0.07\n",
      "Macro avg (F1-SCORE): 79.43 + 0.08\n"
     ]
    }
   ],
   "source": [
    "for metric in ['precision', 'recall', 'f1-score']:\n",
    "\n",
    "    list_mean_class = []\n",
    "    list_std_class = []\n",
    "    for i_fold in range(num_folds):\n",
    "        list_mean_class.append(report_metrics[i_fold]['macro avg'][metric] * 100)\n",
    "        list_std_class.append(report_metrics[i_fold]['macro avg'][metric] * 100)\n",
    "\n",
    "    list_mean_class = round(np.mean(list_mean_class), 2)\n",
    "    list_std_class = round(np.std(list_std_class), 2)\n",
    "\n",
    "    print('Macro avg ({}): {} + {}'.format(metric.upper(), list_mean_class, list_std_class))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.10.13"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}