{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7d34f1af-07e7-4320-9cc8-085bc1848b2f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "from statistics import mean\n",
    "import os\n",
    "dataset_dir = os.path.abspath(os.path.join(os.getcwd(), '..', '..', 'financial_dataset'))\n",
    "sys.path.append(dataset_dir)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "99b69912-8c9e-49b5-abf1-229217ac5e5e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from load_test_data import get_labels_df, get_texts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "53b202a1-13c9-4ba0-9cba-bf6f207af9a1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "132 132\n",
      "92249.56060606061\n"
     ]
    }
   ],
   "source": [
    "labels_dir = dataset_dir + '/csvs/'\n",
    "df = get_labels_df(labels_dir)\n",
    "texts_dir = dataset_dir + '/txts/'\n",
    "texts = get_texts(texts_dir)\n",
    "print(len(df), len(texts))\n",
    "print(mean(list(map(len, texts))))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "b1f8d856-8204-4a42-ab73-3af2ff7a728e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Label\n",
       "SELL    53.8\n",
       "HOLD    28.0\n",
       "BUY     18.2\n",
       "Name: proportion, dtype: float64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Label.value_counts(normalize=True).round(3)s * 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "683fe2a9-6b9e-442b-a740-313482c96424",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}