{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2faa102c",
   "metadata": {},
   "source": [
    "\n",
    "The city is for Nominal Onehot Encoding.\n",
    "The Size is for Ordinla Encoding"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "46c96522",
   "metadata": {},
   "source": [
    "### Nominal OneHotEncoding "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 144,
   "id": "845be9a6",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 186,
   "id": "f40b286b",
   "metadata": {},
   "outputs": [],
   "source": [
    "d = {'sales': [100000, 222000, 10000000, 525000, 111111, 200000, 75000, 9000, 109000, 10000],\n",
    "    'city': ['Tampa', 'Tampa', 'Orlando', 'Jacksonville', 'Miami', 'Miami', 'Orlando', 'Jacksonville', 'Jacksonville', 'Orlando' ],\n",
    "    'size':['Small', 'Medium', 'Large', 'Medium', 'Medium', 'Large', 'Small', 'Small','Medium', 'Small'],\n",
    "    }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 187,
   "id": "19c6caf4",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 188,
   "id": "9108471a",
   "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>sales</th>\n",
       "      <th>city</th>\n",
       "      <th>size</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Small</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>222000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Large</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>525000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>111111</td>\n",
       "      <td>Miami</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sales          city    size\n",
       "0    100000         Tampa   Small\n",
       "1    222000         Tampa  Medium\n",
       "2  10000000       Orlando   Large\n",
       "3    525000  Jacksonville  Medium\n",
       "4    111111         Miami  Medium"
      ]
     },
     "execution_count": 188,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 189,
   "id": "bb9c6a80",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Tampa', 'Orlando', 'Jacksonville', 'Miami'], dtype=object)"
      ]
     },
     "execution_count": 189,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['city'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 190,
   "id": "d54b3754",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import OneHotEncoder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 191,
   "id": "b27a339f",
   "metadata": {},
   "outputs": [],
   "source": [
    "ohe = OneHotEncoder(handle_unknown = 'ignore', sparse=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d9a9dfb5",
   "metadata": {},
   "source": [
    "**In this code:**\n",
    "\n",
    "- handle_unknown='ignore' specifies that if unknown categories are encountered during transform, they should be ignored.\n",
    "- sparse=False specifies that the output should be a dense array rather than a sparse matrix."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 192,
   "id": "8a673202",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 0., 1.],\n",
       "       [0., 0., 0., 1.],\n",
       "       [0., 0., 1., 0.],\n",
       "       [1., 0., 0., 0.],\n",
       "       [0., 1., 0., 0.],\n",
       "       [0., 1., 0., 0.],\n",
       "       [0., 0., 1., 0.],\n",
       "       [1., 0., 0., 0.],\n",
       "       [1., 0., 0., 0.],\n",
       "       [0., 0., 1., 0.]])"
      ]
     },
     "execution_count": 192,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ohe_transform_city = ohe_city.fit_transform(df[['city']])\n",
    "# This fits the OneHotEncoder to the 'city' column of the DataFrame df and transforms it into a one-hot encoded representation.\n",
    "ohe_transform_city"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 193,
   "id": "17c4f8d1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['city_Jacksonville', 'city_Miami', 'city_Orlando', 'city_Tampa'],\n",
       "      dtype=object)"
      ]
     },
     "execution_count": 193,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "feature_names_city = ohe_city.get_feature_names_out(input_features=['city'])\n",
    "# This retrieves the feature names for the one-hot encoded 'city' column. It ensures that the column name is included in the feature names.\n",
    "feature_names_city"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 194,
   "id": "c1ad36cf",
   "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>city_Jacksonville</th>\n",
       "      <th>city_Miami</th>\n",
       "      <th>city_Orlando</th>\n",
       "      <th>city_Tampa</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   city_Jacksonville  city_Miami  city_Orlando  city_Tampa\n",
       "0                0.0         0.0           0.0         1.0\n",
       "1                0.0         0.0           0.0         1.0\n",
       "2                0.0         0.0           1.0         0.0\n",
       "3                1.0         0.0           0.0         0.0\n",
       "4                0.0         1.0           0.0         0.0\n",
       "5                0.0         1.0           0.0         0.0\n",
       "6                0.0         0.0           1.0         0.0\n",
       "7                1.0         0.0           0.0         0.0\n",
       "8                1.0         0.0           0.0         0.0\n",
       "9                0.0         0.0           1.0         0.0"
      ]
     },
     "execution_count": 194,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ohe_df_city = pd.DataFrame(ohe_transform_city, columns=feature_names_city)\n",
    "# This converts the transformed array of the one-hot encoded 'city' column into a pandas DataFrame using the feature names obtained earlier.\n",
    "ohe_df_city"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 195,
   "id": "e080cff1",
   "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>sales</th>\n",
       "      <th>size</th>\n",
       "      <th>city_Jacksonville</th>\n",
       "      <th>city_Miami</th>\n",
       "      <th>city_Orlando</th>\n",
       "      <th>city_Tampa</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100000</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>222000</td>\n",
       "      <td>Medium</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000000</td>\n",
       "      <td>Large</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>525000</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>111111</td>\n",
       "      <td>Medium</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>200000</td>\n",
       "      <td>Large</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>75000</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>9000</td>\n",
       "      <td>Small</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>109000</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10000</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sales    size  city_Jacksonville  city_Miami  city_Orlando  city_Tampa\n",
       "0    100000   Small                0.0         0.0           0.0         1.0\n",
       "1    222000  Medium                0.0         0.0           0.0         1.0\n",
       "2  10000000   Large                0.0         0.0           1.0         0.0\n",
       "3    525000  Medium                1.0         0.0           0.0         0.0\n",
       "4    111111  Medium                0.0         1.0           0.0         0.0\n",
       "5    200000   Large                0.0         1.0           0.0         0.0\n",
       "6     75000   Small                0.0         0.0           1.0         0.0\n",
       "7      9000   Small                1.0         0.0           0.0         0.0\n",
       "8    109000  Medium                1.0         0.0           0.0         0.0\n",
       "9     10000   Small                0.0         0.0           1.0         0.0"
      ]
     },
     "execution_count": 195,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_encoded = pd.concat([df.drop(columns=['city']), ohe_df_city], axis=1)\n",
    "# This concatenates the original DataFrame df after dropping the 'city' column with the one-hot encoded 'city' DataFrame ohe_df_city, resulting in the final DataFrame df_encoded.\n",
    "df_encoded"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 196,
   "id": "7f6733a0",
   "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>sales</th>\n",
       "      <th>size</th>\n",
       "      <th>city_Jacksonville</th>\n",
       "      <th>city_Miami</th>\n",
       "      <th>city_Orlando</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100000</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>222000</td>\n",
       "      <td>Medium</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000000</td>\n",
       "      <td>Large</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>525000</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>111111</td>\n",
       "      <td>Medium</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>200000</td>\n",
       "      <td>Large</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>75000</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>9000</td>\n",
       "      <td>Small</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>109000</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10000</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sales    size  city_Jacksonville  city_Miami  city_Orlando\n",
       "0    100000   Small                0.0         0.0           0.0\n",
       "1    222000  Medium                0.0         0.0           0.0\n",
       "2  10000000   Large                0.0         0.0           1.0\n",
       "3    525000  Medium                1.0         0.0           0.0\n",
       "4    111111  Medium                0.0         1.0           0.0\n",
       "5    200000   Large                0.0         1.0           0.0\n",
       "6     75000   Small                0.0         0.0           1.0\n",
       "7      9000   Small                1.0         0.0           0.0\n",
       "8    109000  Medium                1.0         0.0           0.0\n",
       "9     10000   Small                0.0         0.0           1.0"
      ]
     },
     "execution_count": 196,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_encoded.drop('city_Tampa', axis=1)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eb4d721e",
   "metadata": {},
   "source": [
    "### OR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 197,
   "id": "b5f571d7",
   "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>sales</th>\n",
       "      <th>size</th>\n",
       "      <th>city_Jacksonville</th>\n",
       "      <th>city_Miami</th>\n",
       "      <th>city_Orlando</th>\n",
       "      <th>city_Tampa</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100000</td>\n",
       "      <td>Small</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>222000</td>\n",
       "      <td>Medium</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000000</td>\n",
       "      <td>Large</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>525000</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>111111</td>\n",
       "      <td>Medium</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>200000</td>\n",
       "      <td>Large</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>75000</td>\n",
       "      <td>Small</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>9000</td>\n",
       "      <td>Small</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>109000</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10000</td>\n",
       "      <td>Small</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sales    size  city_Jacksonville  city_Miami  city_Orlando  city_Tampa\n",
       "0    100000   Small                  0           0             0           1\n",
       "1    222000  Medium                  0           0             0           1\n",
       "2  10000000   Large                  0           0             1           0\n",
       "3    525000  Medium                  1           0             0           0\n",
       "4    111111  Medium                  0           1             0           0\n",
       "5    200000   Large                  0           1             0           0\n",
       "6     75000   Small                  0           0             1           0\n",
       "7      9000   Small                  1           0             0           0\n",
       "8    109000  Medium                  1           0             0           0\n",
       "9     10000   Small                  0           0             1           0"
      ]
     },
     "execution_count": 197,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_encoded = pd.get_dummies(df, columns=['city'])\n",
    "df_encoded\n",
    "\n",
    "# This is straight forward"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d90b7716",
   "metadata": {},
   "source": [
    "### Nominal OneHotEncoding "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 211,
   "id": "2036e719",
   "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>sales</th>\n",
       "      <th>city</th>\n",
       "      <th>size</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Small</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>222000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Large</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>525000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>111111</td>\n",
       "      <td>Miami</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>200000</td>\n",
       "      <td>Miami</td>\n",
       "      <td>Large</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>75000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Small</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>9000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Small</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>109000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Small</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sales          city    size\n",
       "0    100000         Tampa   Small\n",
       "1    222000         Tampa  Medium\n",
       "2  10000000       Orlando   Large\n",
       "3    525000  Jacksonville  Medium\n",
       "4    111111         Miami  Medium\n",
       "5    200000         Miami   Large\n",
       "6     75000       Orlando   Small\n",
       "7      9000  Jacksonville   Small\n",
       "8    109000  Jacksonville  Medium\n",
       "9     10000       Orlando   Small"
      ]
     },
     "execution_count": 211,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 212,
   "id": "3f3be309",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Small', 'Medium', 'Large'], dtype=object)"
      ]
     },
     "execution_count": 212,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['size'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 213,
   "id": "97911261",
   "metadata": {},
   "outputs": [],
   "source": [
    "sizes = ['Small', 'Medium', 'Large']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 214,
   "id": "5e523950",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import OrdinalEncoder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 219,
   "id": "16c1fbd2",
   "metadata": {},
   "outputs": [],
   "source": [
    "enc = OrdinalEncoder(categories = [sizes])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 221,
   "id": "9a79444b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0.],\n",
       "       [1.],\n",
       "       [2.],\n",
       "       [1.],\n",
       "       [1.],\n",
       "       [2.],\n",
       "       [0.],\n",
       "       [0.],\n",
       "       [1.],\n",
       "       [0.]])"
      ]
     },
     "execution_count": 221,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "enc.fit_transform(df[['size']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 217,
   "id": "f8005068",
   "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>sales</th>\n",
       "      <th>city</th>\n",
       "      <th>size</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Small</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>222000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Large</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>525000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>111111</td>\n",
       "      <td>Miami</td>\n",
       "      <td>Medium</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sales          city    size\n",
       "0    100000         Tampa   Small\n",
       "1    222000         Tampa  Medium\n",
       "2  10000000       Orlando   Large\n",
       "3    525000  Jacksonville  Medium\n",
       "4    111111         Miami  Medium"
      ]
     },
     "execution_count": 217,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 222,
   "id": "6974c92e",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['size '] = enc.fit_transform(df[['size']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 224,
   "id": "e8b3424f",
   "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>sales</th>\n",
       "      <th>city</th>\n",
       "      <th>size</th>\n",
       "      <th>size</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>222000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Large</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>525000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>111111</td>\n",
       "      <td>Miami</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>200000</td>\n",
       "      <td>Miami</td>\n",
       "      <td>Large</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>75000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>9000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>109000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sales          city    size  size \n",
       "0    100000         Tampa   Small    0.0\n",
       "1    222000         Tampa  Medium    1.0\n",
       "2  10000000       Orlando   Large    2.0\n",
       "3    525000  Jacksonville  Medium    1.0\n",
       "4    111111         Miami  Medium    1.0\n",
       "5    200000         Miami   Large    2.0\n",
       "6     75000       Orlando   Small    0.0\n",
       "7      9000  Jacksonville   Small    0.0\n",
       "8    109000  Jacksonville  Medium    1.0\n",
       "9     10000       Orlando   Small    0.0"
      ]
     },
     "execution_count": 224,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d62227bf",
   "metadata": {},
   "source": [
    "#####  To now convert the Nominal Data- City"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 206,
   "id": "b92b0bbe",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_encoded = pd.get_dummies(df[['city']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 225,
   "id": "ac8359f6",
   "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>city_Jacksonville</th>\n",
       "      <th>city_Miami</th>\n",
       "      <th>city_Orlando</th>\n",
       "      <th>city_Tampa</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   city_Jacksonville  city_Miami  city_Orlando  city_Tampa\n",
       "0                  0           0             0           1\n",
       "1                  0           0             0           1\n",
       "2                  0           0             1           0\n",
       "3                  1           0             0           0\n",
       "4                  0           1             0           0\n",
       "5                  0           1             0           0\n",
       "6                  0           0             1           0\n",
       "7                  1           0             0           0\n",
       "8                  1           0             0           0\n",
       "9                  0           0             1           0"
      ]
     },
     "execution_count": 225,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_encoded"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 226,
   "id": "cf7ab28f",
   "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>sales</th>\n",
       "      <th>city</th>\n",
       "      <th>size</th>\n",
       "      <th>size</th>\n",
       "      <th>city_Jacksonville</th>\n",
       "      <th>city_Miami</th>\n",
       "      <th>city_Orlando</th>\n",
       "      <th>city_Tampa</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>222000</td>\n",
       "      <td>Tampa</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Large</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>525000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>111111</td>\n",
       "      <td>Miami</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>200000</td>\n",
       "      <td>Miami</td>\n",
       "      <td>Large</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>75000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>9000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>109000</td>\n",
       "      <td>Jacksonville</td>\n",
       "      <td>Medium</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10000</td>\n",
       "      <td>Orlando</td>\n",
       "      <td>Small</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sales          city    size  size   city_Jacksonville  city_Miami  \\\n",
       "0    100000         Tampa   Small    0.0                  0           0   \n",
       "1    222000         Tampa  Medium    1.0                  0           0   \n",
       "2  10000000       Orlando   Large    2.0                  0           0   \n",
       "3    525000  Jacksonville  Medium    1.0                  1           0   \n",
       "4    111111         Miami  Medium    1.0                  0           1   \n",
       "5    200000         Miami   Large    2.0                  0           1   \n",
       "6     75000       Orlando   Small    0.0                  0           0   \n",
       "7      9000  Jacksonville   Small    0.0                  1           0   \n",
       "8    109000  Jacksonville  Medium    1.0                  1           0   \n",
       "9     10000       Orlando   Small    0.0                  0           0   \n",
       "\n",
       "   city_Orlando  city_Tampa  \n",
       "0             0           1  \n",
       "1             0           1  \n",
       "2             1           0  \n",
       "3             0           0  \n",
       "4             0           0  \n",
       "5             0           0  \n",
       "6             1           0  \n",
       "7             0           0  \n",
       "8             0           0  \n",
       "9             1           0  "
      ]
     },
     "execution_count": 226,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_df = pd.concat([df, df_encoded], axis=1)\n",
    "final_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 232,
   "id": "d1c30211",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Select columns of type 'object' (string)\n",
    "string_size_columns = final_df.select_dtypes(include=['object']).columns\n",
    "\n",
    "# Drop the column containing string values, all string values\n",
    "final_df = final_df.drop(columns=string_size_columns)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 233,
   "id": "a0713ee4",
   "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>sales</th>\n",
       "      <th>size</th>\n",
       "      <th>city_Jacksonville</th>\n",
       "      <th>city_Miami</th>\n",
       "      <th>city_Orlando</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>100000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>222000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>10000000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>525000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>111111</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>200000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>75000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>9000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>109000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      sales  size   city_Jacksonville  city_Miami  city_Orlando\n",
       "0    100000    0.0                  0           0             0\n",
       "1    222000    1.0                  0           0             0\n",
       "2  10000000    2.0                  0           0             1\n",
       "3    525000    1.0                  1           0             0\n",
       "4    111111    1.0                  0           1             0\n",
       "5    200000    2.0                  0           1             0\n",
       "6     75000    0.0                  0           0             1\n",
       "7      9000    0.0                  1           0             0\n",
       "8    109000    1.0                  1           0             0\n",
       "9     10000    0.0                  0           0             1"
      ]
     },
     "execution_count": 233,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "final_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "233ca643",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6b7aa33b",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2a8b5324",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6b0e9551",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fd22a693",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "133dd589",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5af006ca",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4881a786",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6bd66716",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}