update

code/Ensemble/power_ensemble.ipynb

@@ -0,0 +1,68 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "343ee127-66d1-48cd-a207-3f5ddba915cc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['/opt/ml/code/output/pjh_0.7312_0.7911.csv', '/opt/ml/code/output/output6_19_17_30.csv', '/opt/ml/code/output/hk_auc8285_acc7554.csv', '/opt/ml/code/output/output_7975.csv']\n"
+     ]
+    }
+   ],
+   "source": [
+    "# 평균\n",
+    "from glob import glob\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "plt.style.use('fivethirtyeight')\n",
+    "\n",
+    "%matplotlib inline\n",
+    "\n",
+    "output_path = \"/opt/ml/code/output/cross_validation/output.csv\"\n",
+    "csv_file_path_list = glob(\"/opt/ml/code/output/*.csv\")\n",
+    "print(csv_file_path_list)\n",
+    "\n",
+    "POWER = 1/4\n",
+    "\n",
+    "# concat result dataframe\n",
+    "result = pd.read_csv(csv_file_path_list[0])[\"prediction\"]\n",
+    "result = result ** POWER\n",
+    "for csv_file_path in csv_file_path_list[1:]:\n",
+    "    temp_result = pd.read_csv(csv_file_path)[\"prediction\"]\n",
+    "    temp_result = temp_result ** POWER\n",
+    "    result = pd.concat([result, temp_result], axis=1)\n",
+    "\n",
+    "# mean result dataframe\n",
+    "result = pd.DataFrame(result.mean(axis=1)).reset_index().rename(columns = {0:\"prediction\", \"index\":\"id\"})\n",
+    "result.to_csv(output_path, index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.7.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}