{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5d8abefd",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install kaggle\n",
    "!pip install pandas\n",
    "!pip install seaborn\n",
    "!pip install opendatasets --upgrade\n",
    "import opendatasets as od\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5911d036",
   "metadata": {},
   "outputs": [],
   "source": [
    "cd ~/.kaggle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8d07bb31",
   "metadata": {},
   "outputs": [],
   "source": [
    "!kaggle datasets download -d shree1992/housedata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9c04f525",
   "metadata": {},
   "outputs": [],
   "source": [
    "!unzip -o housedata.zip"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b407a064",
   "metadata": {},
   "outputs": [],
   "source": [
    "!wc -l data.csv\n",
    "data = pd.read_csv('data.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "17d29b04",
   "metadata": {},
   "outputs": [],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5fa21ef9",
   "metadata": {},
   "outputs": [],
   "source": [
    "!head -n -1 data.csv | shuf > data.csv.shuf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "baa9b34e",
   "metadata": {},
   "outputs": [],
   "source": [
    "!head -n 460 data.csv.shuf > data.csv.test\n",
    "!head -n 920 data.csv.shuf | tail -n 460 > data.csv.dev\n",
    "!tail -n +920 data.csv.shuf > data.csv.train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "30b520c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "!rm data.csv.shuf\n",
    "!wc -l data.csv*"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b7652c69",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_test = pd.read_csv('data.csv.test')\n",
    "data_dev = pd.read_csv('data.csv.dev')\n",
    "data_train = pd.read_csv('data.csv.train')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c4670def",
   "metadata": {},
   "outputs": [],
   "source": [
    "data.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b18d32a1",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_train.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6b8d6568",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_dev.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "dd366750",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_test.describe(include='all')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2801c205",
   "metadata": {},
   "outputs": [],
   "source": [
    "grep -P \"^$\" -n data.csv"
   ]
  }
 ],
 "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": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}