usecols.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"train.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 401125 entries, 0 to 401124\n",
      "Columns: 53 entries, SalesID to Steering_Controls\n",
      "dtypes: float64(2), int64(6), object(45)\n",
      "memory usage: 815.8 MB\n"
     ]
    }
   ],
   "source": [
    "df.info(verbose=False, memory_usage=\"deep\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "53"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "40"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "req_cols = ['SalesID', 'SalePrice', 'MachineID', 'ModelID', 'datasource',\n",
    "       'auctioneerID', 'YearMade', 'MachineHoursCurrentMeter', 'UsageBand',\n",
    "       'saledate', 'fiModelDesc', 'fiBaseModel', 'fiSecondaryDesc',\n",
    "       'fiModelSeries', 'fiModelDescriptor', 'ProductSize',\n",
    "       'fiProductClassDesc', 'state', 'ProductGroup', 'ProductGroupDesc',\n",
    "       'Drive_System', 'Enclosure', 'Forks', 'Pad_Type', 'Ride_Control',\n",
    "       'Stick', 'Transmission', 'Turbocharged', 'Blade_Extension',\n",
    "       'Blade_Width', 'Enclosure_Type', 'Engine_Horsepower', 'Hydraulics',\n",
    "       'Pushblock', 'Ripper', 'Scarifier', 'Tip_Control', 'Tire_Size',\n",
    "       'Coupler', 'Coupler_System']\n",
    "len(req_cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"train.csv\", usecols=req_cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 401125 entries, 0 to 401124\n",
      "Columns: 40 entries, SalesID to Coupler_System\n",
      "dtypes: float64(2), int64(6), object(32)\n",
      "memory usage: 618.3 MB\n"
     ]
    }
   ],
   "source": [
    "df.info(verbose=False, memory_usage=\"deep\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}