One_Hot_Encoder.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "One Hot Encoder",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "GJD1WjBEC3-8"
      },
      "source": [
        "import numpy as np \n",
        "import pandas as pd"
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IfuesynyC9dm"
      },
      "source": [
        "dataset = pd.read_csv(\"car-sales-extended.csv\")"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "fOyNO8ITDHJp",
        "outputId": "371b9a7b-89d5-48b2-cfbf-9f7e325cdf2f"
      },
      "source": [
        "dataset.head()"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Make</th>\n",
              "      <th>Colour</th>\n",
              "      <th>Odometer (KM)</th>\n",
              "      <th>Doors</th>\n",
              "      <th>Price</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Honda</td>\n",
              "      <td>White</td>\n",
              "      <td>35431</td>\n",
              "      <td>4</td>\n",
              "      <td>15323</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>BMW</td>\n",
              "      <td>Blue</td>\n",
              "      <td>192714</td>\n",
              "      <td>5</td>\n",
              "      <td>19943</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Honda</td>\n",
              "      <td>White</td>\n",
              "      <td>84714</td>\n",
              "      <td>4</td>\n",
              "      <td>28343</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Toyota</td>\n",
              "      <td>White</td>\n",
              "      <td>154365</td>\n",
              "      <td>4</td>\n",
              "      <td>13434</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Nissan</td>\n",
              "      <td>Blue</td>\n",
              "      <td>181577</td>\n",
              "      <td>3</td>\n",
              "      <td>14043</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "     Make Colour  Odometer (KM)  Doors  Price\n",
              "0   Honda  White          35431      4  15323\n",
              "1     BMW   Blue         192714      5  19943\n",
              "2   Honda  White          84714      4  28343\n",
              "3  Toyota  White         154365      4  13434\n",
              "4  Nissan   Blue         181577      3  14043"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "reAdFa7FDIRf",
        "outputId": "1f574816-b4f0-4ba9-dd30-75f3e41ba5be"
      },
      "source": [
        "dataset.info()"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 1000 entries, 0 to 999\n",
            "Data columns (total 5 columns):\n",
            " #   Column         Non-Null Count  Dtype \n",
            "---  ------         --------------  ----- \n",
            " 0   Make           1000 non-null   object\n",
            " 1   Colour         1000 non-null   object\n",
            " 2   Odometer (KM)  1000 non-null   int64 \n",
            " 3   Doors          1000 non-null   int64 \n",
            " 4   Price          1000 non-null   int64 \n",
            "dtypes: int64(3), object(2)\n",
            "memory usage: 39.2+ KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WgwGe0aJDKJw",
        "outputId": "689bf608-cf31-4d00-920a-a6cf837d1314"
      },
      "source": [
        "len(dataset)"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1000"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lTIyIK0JDWDz"
      },
      "source": [
        "x = dataset.drop(\"Price\", axis = 1)\n",
        "y = dataset[\"Price\"]"
      ],
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "s_LMfFEMNJs2"
      },
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "x_train, x_test, y_train, y_test = train_test_split(x,y,test_size=0.3)"
      ],
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 363
        },
        "id": "iqM6qeuwM73O",
        "outputId": "feb567f0-ef08-4e6c-b9af-15cf66c41cb6"
      },
      "source": [
        "from sklearn.ensemble import RandomForestRegressor\n",
        "\n",
        "model = RandomForestRegressor()\n",
        "model.fit(x_train,y_train) #error coming because the data type of x is object\n",
        "model.score(x_test,y_test)"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "error",
          "ename": "ValueError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-8-43624a44bebf>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mRandomForestRegressor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx_train\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my_train\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      5\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscore\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx_test\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0my_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/sklearn/ensemble/_forest.py\u001b[0m in \u001b[0;36mfit\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m    293\u001b[0m         \"\"\"\n\u001b[1;32m    294\u001b[0m         \u001b[0;31m# Validate or convert input data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 295\u001b[0;31m         \u001b[0mX\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcheck_array\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maccept_sparse\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"csc\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mDTYPE\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    296\u001b[0m         \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcheck_array\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maccept_sparse\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'csc'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mensure_2d\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    297\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0msample_weight\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36mcheck_array\u001b[0;34m(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)\u001b[0m\n\u001b[1;32m    529\u001b[0m                     \u001b[0marray\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0marray\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcasting\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"unsafe\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    530\u001b[0m                 \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 531\u001b[0;31m                     \u001b[0marray\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0morder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0morder\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    532\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mComplexWarning\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    533\u001b[0m                 raise ValueError(\"Complex data not supported\\n\"\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/numpy/core/_asarray.py\u001b[0m in \u001b[0;36masarray\u001b[0;34m(a, dtype, order)\u001b[0m\n\u001b[1;32m     81\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     82\u001b[0m     \"\"\"\n\u001b[0;32m---> 83\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0morder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0morder\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     85\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m__array__\u001b[0;34m(self, dtype)\u001b[0m\n\u001b[1;32m   1779\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1780\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__array__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndarray\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1781\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_values\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1782\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1783\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__array_wrap__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.7/dist-packages/numpy/core/_asarray.py\u001b[0m in \u001b[0;36masarray\u001b[0;34m(a, dtype, order)\u001b[0m\n\u001b[1;32m     81\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     82\u001b[0m     \"\"\"\n\u001b[0;32m---> 83\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0morder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0morder\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     85\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mValueError\u001b[0m: could not convert string to float: 'Nissan'"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "C1R0teoMDxFU",
        "outputId": "c09d5a18-afd0-459f-bcdc-f3a4dbce1ff9"
      },
      "source": [
        "#converting the data into numbers\n",
        "\n",
        "from sklearn.preprocessing import OneHotEncoder\n",
        "from sklearn.compose import ColumnTransformer\n",
        "\n",
        "one_hot = OneHotEncoder()\n",
        "categorical_features = [\"Make\", \"Colour\",\"Doors\"]\n",
        "transformer = ColumnTransformer([(\"one_hot\", one_hot, categorical_features)],remainder=\"passthrough\")\n",
        "\n",
        "transformed_x = transformer.fit_transform(x)\n",
        "transformed_x"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.00000e+00, 1.00000e+00, 0.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 3.54310e+04],\n",
              "       [1.00000e+00, 0.00000e+00, 0.00000e+00, ..., 0.00000e+00,\n",
              "        1.00000e+00, 1.92714e+05],\n",
              "       [0.00000e+00, 1.00000e+00, 0.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 8.47140e+04],\n",
              "       ...,\n",
              "       [0.00000e+00, 0.00000e+00, 1.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 6.66040e+04],\n",
              "       [0.00000e+00, 1.00000e+00, 0.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 2.15883e+05],\n",
              "       [0.00000e+00, 0.00000e+00, 0.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 2.48360e+05]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2dNSiSuKHpCg",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "outputId": "9fe4084a-ff4b-4cb5-e00c-2290c3172764"
      },
      "source": [
        "x"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Make</th>\n",
              "      <th>Colour</th>\n",
              "      <th>Odometer (KM)</th>\n",
              "      <th>Doors</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Honda</td>\n",
              "      <td>White</td>\n",
              "      <td>35431</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>BMW</td>\n",
              "      <td>Blue</td>\n",
              "      <td>192714</td>\n",
              "      <td>5</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Honda</td>\n",
              "      <td>White</td>\n",
              "      <td>84714</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Toyota</td>\n",
              "      <td>White</td>\n",
              "      <td>154365</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Nissan</td>\n",
              "      <td>Blue</td>\n",
              "      <td>181577</td>\n",
              "      <td>3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>995</th>\n",
              "      <td>Toyota</td>\n",
              "      <td>Black</td>\n",
              "      <td>35820</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>996</th>\n",
              "      <td>Nissan</td>\n",
              "      <td>White</td>\n",
              "      <td>155144</td>\n",
              "      <td>3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>997</th>\n",
              "      <td>Nissan</td>\n",
              "      <td>Blue</td>\n",
              "      <td>66604</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>998</th>\n",
              "      <td>Honda</td>\n",
              "      <td>White</td>\n",
              "      <td>215883</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>999</th>\n",
              "      <td>Toyota</td>\n",
              "      <td>Blue</td>\n",
              "      <td>248360</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1000 rows × 4 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "       Make Colour  Odometer (KM)  Doors\n",
              "0     Honda  White          35431      4\n",
              "1       BMW   Blue         192714      5\n",
              "2     Honda  White          84714      4\n",
              "3    Toyota  White         154365      4\n",
              "4    Nissan   Blue         181577      3\n",
              "..      ...    ...            ...    ...\n",
              "995  Toyota  Black          35820      4\n",
              "996  Nissan  White         155144      3\n",
              "997  Nissan   Blue          66604      4\n",
              "998   Honda  White         215883      4\n",
              "999  Toyota   Blue         248360      4\n",
              "\n",
              "[1000 rows x 4 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DpKUOL7IJbTK",
        "outputId": "8990874f-ba5f-4ed0-990c-409e36f07049"
      },
      "source": [
        "transformed_x"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[0.00000e+00, 1.00000e+00, 0.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 3.54310e+04],\n",
              "       [1.00000e+00, 0.00000e+00, 0.00000e+00, ..., 0.00000e+00,\n",
              "        1.00000e+00, 1.92714e+05],\n",
              "       [0.00000e+00, 1.00000e+00, 0.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 8.47140e+04],\n",
              "       ...,\n",
              "       [0.00000e+00, 0.00000e+00, 1.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 6.66040e+04],\n",
              "       [0.00000e+00, 1.00000e+00, 0.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 2.15883e+05],\n",
              "       [0.00000e+00, 0.00000e+00, 0.00000e+00, ..., 1.00000e+00,\n",
              "        0.00000e+00, 2.48360e+05]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 423
        },
        "id": "8QRZh2mfJj5l",
        "outputId": "0aedd8a9-57b8-452b-f235-496d9256c7c5"
      },
      "source": [
        "pd.DataFrame(transformed_x)"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>0</th>\n",
              "      <th>1</th>\n",
              "      <th>2</th>\n",
              "      <th>3</th>\n",
              "      <th>4</th>\n",
              "      <th>5</th>\n",
              "      <th>6</th>\n",
              "      <th>7</th>\n",
              "      <th>8</th>\n",
              "      <th>9</th>\n",
              "      <th>10</th>\n",
              "      <th>11</th>\n",
              "      <th>12</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>35431.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>192714.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>84714.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>154365.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>181577.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>995</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>35820.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>996</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>155144.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>997</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>66604.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>998</th>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>215883.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>999</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>248360.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1000 rows × 13 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "      0    1    2    3    4    5    6    7    8    9    10   11        12\n",
              "0    0.0  1.0  0.0  0.0  0.0  0.0  0.0  0.0  1.0  0.0  1.0  0.0   35431.0\n",
              "1    1.0  0.0  0.0  0.0  0.0  1.0  0.0  0.0  0.0  0.0  0.0  1.0  192714.0\n",
              "2    0.0  1.0  0.0  0.0  0.0  0.0  0.0  0.0  1.0  0.0  1.0  0.0   84714.0\n",
              "3    0.0  0.0  0.0  1.0  0.0  0.0  0.0  0.0  1.0  0.0  1.0  0.0  154365.0\n",
              "4    0.0  0.0  1.0  0.0  0.0  1.0  0.0  0.0  0.0  1.0  0.0  0.0  181577.0\n",
              "..   ...  ...  ...  ...  ...  ...  ...  ...  ...  ...  ...  ...       ...\n",
              "995  0.0  0.0  0.0  1.0  1.0  0.0  0.0  0.0  0.0  0.0  1.0  0.0   35820.0\n",
              "996  0.0  0.0  1.0  0.0  0.0  0.0  0.0  0.0  1.0  1.0  0.0  0.0  155144.0\n",
              "997  0.0  0.0  1.0  0.0  0.0  1.0  0.0  0.0  0.0  0.0  1.0  0.0   66604.0\n",
              "998  0.0  1.0  0.0  0.0  0.0  0.0  0.0  0.0  1.0  0.0  1.0  0.0  215883.0\n",
              "999  0.0  0.0  0.0  1.0  0.0  1.0  0.0  0.0  0.0  0.0  1.0  0.0  248360.0\n",
              "\n",
              "[1000 rows x 13 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bcgMgq9OJ1M8"
      },
      "source": [
        "#another way "
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 443
        },
        "id": "aCR9o0HhLtC9",
        "outputId": "62dac5dc-181e-481b-db56-ebac4bcb9c84"
      },
      "source": [
        "dummies = pd.get_dummies(dataset[[\"Make\",\"Colour\",\"Doors\"]])\n",
        "\n",
        "dummies"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "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>Doors</th>\n",
              "      <th>Make_BMW</th>\n",
              "      <th>Make_Honda</th>\n",
              "      <th>Make_Nissan</th>\n",
              "      <th>Make_Toyota</th>\n",
              "      <th>Colour_Black</th>\n",
              "      <th>Colour_Blue</th>\n",
              "      <th>Colour_Green</th>\n",
              "      <th>Colour_Red</th>\n",
              "      <th>Colour_White</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>4</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>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>5</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>4</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>3</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>995</th>\n",
              "      <td>4</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>996</th>\n",
              "      <td>3</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>997</th>\n",
              "      <td>4</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>998</th>\n",
              "      <td>4</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>999</th>\n",
              "      <td>4</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1000 rows × 10 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "     Doors  Make_BMW  Make_Honda  ...  Colour_Green  Colour_Red  Colour_White\n",
              "0        4         0           1  ...             0           0             1\n",
              "1        5         1           0  ...             0           0             0\n",
              "2        4         0           1  ...             0           0             1\n",
              "3        4         0           0  ...             0           0             1\n",
              "4        3         0           0  ...             0           0             0\n",
              "..     ...       ...         ...  ...           ...         ...           ...\n",
              "995      4         0           0  ...             0           0             0\n",
              "996      3         0           0  ...             0           0             1\n",
              "997      4         0           0  ...             0           0             0\n",
              "998      4         0           1  ...             0           0             1\n",
              "999      4         0           0  ...             0           0             0\n",
              "\n",
              "[1000 rows x 10 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CChUBNqXL6Sv"
      },
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "x_train, x_test, y_train, y_test = train_test_split(transformed_x,y,test_size=0.3)"
      ],
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xUQ4ZI5DMWmP",
        "outputId": "3c506910-d51e-4980-d18f-b8b77ff223d0"
      },
      "source": [
        "from sklearn.ensemble import RandomForestRegressor\n",
        "\n",
        "model = RandomForestRegressor()\n",
        "model.fit(x_train,y_train)"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "RandomForestRegressor(bootstrap=True, ccp_alpha=0.0, criterion='mse',\n",
              "                      max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
              "                      max_samples=None, min_impurity_decrease=0.0,\n",
              "                      min_impurity_split=None, min_samples_leaf=1,\n",
              "                      min_samples_split=2, min_weight_fraction_leaf=0.0,\n",
              "                      n_estimators=100, n_jobs=None, oob_score=False,\n",
              "                      random_state=None, verbose=0, warm_start=False)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cc0FkMUpMt1p",
        "outputId": "8941b818-7c60-4082-dbd6-e54795d42e74"
      },
      "source": [
        "model.score(x_test,y_test)"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.2716338422765433"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 17
        }
      ]
    }
  ]
}