Quickstarter code for using PCA.

sklearn_pca_quickstarter.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pipeline(steps=[('standardscaler', StandardScaler()), ('pca', PCA())])\n"
     ]
    },
    {
     "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>주성분_개수</th>\n",
       "      <th>설명력</th>\n",
       "      <th>누적설명력</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0.729624</td>\n",
       "      <td>0.729624</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0.228508</td>\n",
       "      <td>0.958132</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>0.036689</td>\n",
       "      <td>0.994821</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>0.005179</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   주성분_개수       설명력     누적설명력\n",
       "0       0  0.729624  0.729624\n",
       "1       1  0.228508  0.958132\n",
       "2       2  0.036689  0.994821\n",
       "3       3  0.005179  1.000000"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# PCA 사용법\n",
    "\n",
    "from sklearn.decomposition import PCA\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.pipeline import make_pipeline\n",
    "import seaborn as sns\n",
    "import pandas as pd\n",
    "\n",
    "df = sns.load_dataset(\"iris\")\n",
    "df = df.drop(columns=\"species\")\n",
    "\n",
    "scaler = StandardScaler()\n",
    "pca = PCA()\n",
    "pipeline = make_pipeline(scaler, pca)\n",
    "print(pipeline)\n",
    "\n",
    "pipeline.fit(df)\n",
    "\n",
    "pca_result = (\n",
    "    pd.DataFrame()\n",
    "    .assign(주성분_개수=range(pca.n_components_))\n",
    "    .assign(설명력=pca.explained_variance_ratio_)\n",
    "    .assign(누적설명력=pca.explained_variance_ratio_.cumsum()) # 누적설명력이 0.99이면, 위에서부터 해당 주성분을 모두 사용하면 데이터의 99%를 설명할 수 있다는 뜻임.\n",
    ")\n",
    "\n",
    "pca_result"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.10.9"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}