dealing with redundant feature.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Dropping redundant features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# dask operation\n",
    "dask_df = dask_df.drop('state_po', axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>year</th>\n",
       "      <th>state</th>\n",
       "      <th>county</th>\n",
       "      <th>FIPS</th>\n",
       "      <th>office</th>\n",
       "      <th>candidate</th>\n",
       "      <th>party</th>\n",
       "      <th>candidatevotes</th>\n",
       "      <th>totalvotes</th>\n",
       "      <th>version</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2016.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Autauga</td>\n",
       "      <td>1001.0</td>\n",
       "      <td>President</td>\n",
       "      <td>Hillary Clinton</td>\n",
       "      <td>democrat</td>\n",
       "      <td>5936.0</td>\n",
       "      <td>24973.0</td>\n",
       "      <td>20190722.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2016.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Autauga</td>\n",
       "      <td>1001.0</td>\n",
       "      <td>President</td>\n",
       "      <td>Donald Trump</td>\n",
       "      <td>republican</td>\n",
       "      <td>18172.0</td>\n",
       "      <td>24973.0</td>\n",
       "      <td>20190722.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2016.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Autauga</td>\n",
       "      <td>1001.0</td>\n",
       "      <td>President</td>\n",
       "      <td>Other</td>\n",
       "      <td>NaN</td>\n",
       "      <td>865.0</td>\n",
       "      <td>24973.0</td>\n",
       "      <td>20190722.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2016.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Baldwin</td>\n",
       "      <td>1003.0</td>\n",
       "      <td>President</td>\n",
       "      <td>Hillary Clinton</td>\n",
       "      <td>democrat</td>\n",
       "      <td>18458.0</td>\n",
       "      <td>95215.0</td>\n",
       "      <td>20190722.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2016.0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Baldwin</td>\n",
       "      <td>1003.0</td>\n",
       "      <td>President</td>\n",
       "      <td>Donald Trump</td>\n",
       "      <td>republican</td>\n",
       "      <td>72883.0</td>\n",
       "      <td>95215.0</td>\n",
       "      <td>20190722.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     year    state   county  ...  candidatevotes totalvotes     version\n",
       "0  2016.0  Alabama  Autauga  ...          5936.0    24973.0  20190722.0\n",
       "1  2016.0  Alabama  Autauga  ...         18172.0    24973.0  20190722.0\n",
       "2  2016.0  Alabama  Autauga  ...           865.0    24973.0  20190722.0\n",
       "3  2016.0  Alabama  Baldwin  ...         18458.0    95215.0  20190722.0\n",
       "4  2016.0  Alabama  Baldwin  ...         72883.0    95215.0  20190722.0\n",
       "\n",
       "[5 rows x 10 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dask_df.head()"
   ]
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}