mercedes.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sklearn.linear_model\n",
    "from sklearn.preprocessing import LabelEncoder, OneHotEncoder, OrdinalEncoder\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "#/generate\n",
    "# "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "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>ID</th>\n",
       "      <th>y</th>\n",
       "      <th>X0</th>\n",
       "      <th>X1</th>\n",
       "      <th>X2</th>\n",
       "      <th>X3</th>\n",
       "      <th>X4</th>\n",
       "      <th>X5</th>\n",
       "      <th>X6</th>\n",
       "      <th>X8</th>\n",
       "      <th>...</th>\n",
       "      <th>X375</th>\n",
       "      <th>X376</th>\n",
       "      <th>X377</th>\n",
       "      <th>X378</th>\n",
       "      <th>X379</th>\n",
       "      <th>X380</th>\n",
       "      <th>X382</th>\n",
       "      <th>X383</th>\n",
       "      <th>X384</th>\n",
       "      <th>X385</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>130.81</td>\n",
       "      <td>32</td>\n",
       "      <td>23</td>\n",
       "      <td>17</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>24</td>\n",
       "      <td>9</td>\n",
       "      <td>14</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6</td>\n",
       "      <td>88.53</td>\n",
       "      <td>32</td>\n",
       "      <td>21</td>\n",
       "      <td>19</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>28</td>\n",
       "      <td>11</td>\n",
       "      <td>14</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7</td>\n",
       "      <td>76.26</td>\n",
       "      <td>20</td>\n",
       "      <td>24</td>\n",
       "      <td>34</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>27</td>\n",
       "      <td>9</td>\n",
       "      <td>23</td>\n",
       "      <td>...</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",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>9</td>\n",
       "      <td>80.62</td>\n",
       "      <td>20</td>\n",
       "      <td>21</td>\n",
       "      <td>34</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>27</td>\n",
       "      <td>11</td>\n",
       "      <td>4</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>13</td>\n",
       "      <td>78.02</td>\n",
       "      <td>20</td>\n",
       "      <td>23</td>\n",
       "      <td>34</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>12</td>\n",
       "      <td>3</td>\n",
       "      <td>13</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 378 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   ID       y  X0  X1  X2  X3  X4  X5  X6  X8  ...  X375  X376  X377  X378  \\\n",
       "0   0  130.81  32  23  17   0   3  24   9  14  ...     0     0     1     0   \n",
       "1   6   88.53  32  21  19   4   3  28  11  14  ...     1     0     0     0   \n",
       "2   7   76.26  20  24  34   2   3  27   9  23  ...     0     0     0     0   \n",
       "3   9   80.62  20  21  34   5   3  27  11   4  ...     0     0     0     0   \n",
       "4  13   78.02  20  23  34   5   3  12   3  13  ...     0     0     0     0   \n",
       "\n",
       "   X379  X380  X382  X383  X384  X385  \n",
       "0     0     0     0     0     0     0  \n",
       "1     0     0     0     0     0     0  \n",
       "2     0     0     1     0     0     0  \n",
       "3     0     0     0     0     0     0  \n",
       "4     0     0     0     0     0     0  \n",
       "\n",
       "[5 rows x 378 columns]"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train_data = pd.read_csv('data/mercedes/train.csv')\n",
    "test_data = pd.read_csv('data/mercedes/test.csv')\n",
    "enc = LabelEncoder()\n",
    "#transforming categorical data into numbers. If this isn't working, I should try one-hot encoding instead of label encoding.\n",
    "for col_title in train_data:# not sure how to generalize this for no titles \n",
    "    if train_data[col_title].dtype==object:\n",
    "        train_data[col_title] = enc.fit_transform(train_data[col_title])\n",
    "train_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5935201743332184"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = sklearn.linear_model.LinearRegression()\n",
    "model.fit(X=train_data.drop(columns='y', axis=1), y=train_data['y'])\n",
    "model.score(X=train_data.drop(columns='y', axis=1), y=train_data['y'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-4.199308285163361e+28"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model = sklearn.linear_model.SGDRegressor(loss=\"squared_error\", max_iter = 100_000)\n",
    "model.fit(X=train_data.drop(columns='y', axis=1), y=train_data['y'])\n",
    "model.score(X=train_data.drop(columns='y', axis=1), y=train_data['y'])"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "6923796461e980e9bc73647c4512b3defb157e915c4c44698c323c8657921e8a"
  },
  "kernelspec": {
   "display_name": "Python 3.10.1 ('ml-hackathon': venv)",
   "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": "3.10.1"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}