{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.append('../scripts')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import hydra\n",
    "from hydra import compose, initialize\n",
    "\n",
    "hydra.core.global_hydra.GlobalHydra.instance().clear()\n",
    "initialize(config_path=Path('..'), job_name='foo', version_base='1.1')\n",
    "config = compose(config_name='experiment.yaml')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dataset import load_data\n",
    "\n",
    "base_path = Path('..')\n",
    "train_df, val_df, test_df = load_data(base_path / config.data.cnf_tsv_path, base_path / config.data.controls_tsv_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_df = pd.concat([train_df, val_df, test_df])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5336, 1201, 1159, 7696)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(train_df), len(val_df), len(test_df), len(all_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2715, 590, 543, 3848)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Ellipses\n",
    "(~train_df.controls).sum(), (~val_df.controls).sum(), (~test_df.controls).sum(), (~all_df.controls).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2621, 611, 616, 3848)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Controls\n",
    "(train_df.controls).sum(), (val_df.controls).sum(), (test_df.controls).sum(), (all_df.controls).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:ellipses]",
   "language": "python",
   "name": "conda-env-ellipses-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  },
  "vscode": {
   "interpreter": {
    "hash": "8f7616dd95153615ba76d82383ee4b763d06514f4c395e85d9efff1c9a575639"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}