{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "d12d28db-72c9-4f6d-a081-fc7ebb381759",
   "metadata": {},
   "outputs": [],
   "source": [
    "# take log of a single column\n",
    "\n",
    "# other things to try: removing outliers etc.\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.preprocessing import FunctionTransformer\n",
    "from sklearn.compose import ColumnTransformer\n",
    "from sklearn.pipeline import Pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f52e13ea-f7dd-492c-9602-87cc321e6e2b",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = pd.DataFrame({\n",
    "    \"A\": [1, 2, 3, 4],\n",
    "    \"B\": [1, 2, 4, 8]\n",
    "})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "518aaccc-b290-4f69-8794-191bdf0eb4cc",
   "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>A</th>\n",
       "      <th>B</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   A  B\n",
       "0  1  1\n",
       "1  2  2\n",
       "2  3  4\n",
       "3  4  8"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1683e44c-6ce2-4d50-a270-c85b6076e986",
   "metadata": {},
   "outputs": [],
   "source": [
    "log_transformer = FunctionTransformer(\n",
    "    np.log,   # safer than log (handles zeros)\n",
    "    validate=False\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4f8de888-7939-4a88-8a7c-bfc21d4470a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "preprocessor = ColumnTransformer(\n",
    "    transformers=[\n",
    "        (\"B\", log_transformer, [\"B\"])\n",
    "    ],\n",
    "    remainder=\"passthrough\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "395e65e6-a7e2-4e5a-9867-8f36bc463708",
   "metadata": {},
   "outputs": [],
   "source": [
    "pipeline = Pipeline([\n",
    "    (\"preprocess\", preprocessor)\n",
    "])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "aa44f214-0be3-442f-a9db-5a5234f510cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_transformed = preprocessor.fit_transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "9f375dfc-c44a-47c7-813d-bd4024d1e527",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[0.         1.        ]\n",
      " [0.69314718 2.        ]\n",
      " [1.38629436 3.        ]\n",
      " [2.07944154 4.        ]]\n"
     ]
    }
   ],
   "source": [
    "print(X_transformed)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "be4135a7-26ed-410d-aaed-7b24ab5b643a",
   "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": "3.12.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}