Refactor: Removed output from .ipynb files

nbstripout을 사용하여 ipynb파일의 출력을 제거
CSID-DGU · Aug 23, 2024 · 23e8bfb · 23e8bfb
1 parent e36f8ed
commit 23e8bfb
Show file tree

Hide file tree

Showing 3 changed files with 20 additions and 617 deletions.
diff --git a/.gitattribute b/.gitattribute
@@ -0,0 +1,3 @@
+*.ipynb filter=nbstripout
+*.zpln filter=nbstripout
+*.ipynb diff=ipynb
diff --git a/src/_non-module/junhofile.ipynb b/src/_non-module/junhofile.ipynb
@@ -2,23 +2,10 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "35cb5d7175402951",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-08-05T07:41:46.951888Z",
-     "start_time": "2024-08-05T07:41:46.794476Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "File loaded.\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "id": "0",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "# 기존 데이터를 분석하는 코드\n",
     "import pandas as pd\n",
@@ -44,7 +31,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "edf5915269299a02",
+   "id": "1",
    "metadata": {},
    "source": [
     "### 기존 csv파일 전처리 및 답변 분리 ###"
@@ -53,7 +40,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "460c01a6ab106916",
+   "id": "2",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -107,31 +94,18 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e0fdcefa731ca245",
+   "id": "3",
    "metadata": {},
    "source": [
     "### 분리한 답변에서 유의미한 데이터 추출"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "5a556fcb5938297f",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-07-24T07:41:26.350426Z",
-     "start_time": "2024-07-24T07:41:26.304026Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "파일이 성공적으로 저장되었습니다. C:\\Users\\A\\Desktop\\repo\\PM4_JS\\src\\_non-module\\..\\..\\public\\AI_bokji_result_final_filtered.csv\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "id": "4",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "final_df = pd.read_csv(result_csv_path, encoding='euc-kr')\n",
     "\n",
@@ -150,45 +124,18 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7076096ec8d88224",
+   "id": "5",
    "metadata": {},
    "source": [
     "### 이전답변을 반영하여 답변 데이터만을 저장 ###"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "caf0d1f2897f1483",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-08-05T07:39:33.242907Z",
-     "start_time": "2024-08-05T07:39:33.148235Z"
-    }
-   },
-   "outputs": [
-    {
-     "ename": "KeyError",
-     "evalue": "1",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "File \u001b[1;32mc:\\Users\\A\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\pandas\\core\\indexes\\base.py:3361\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m   3360\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m-> 3361\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcasted_key\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   3362\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n",
-      "File \u001b[1;32mc:\\Users\\A\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\pandas\\_libs\\index.pyx:76\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
-      "File \u001b[1;32mc:\\Users\\A\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\pandas\\_libs\\index.pyx:108\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n",
-      "File \u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi:5198\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
-      "File \u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi:5206\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n",
-      "\u001b[1;31mKeyError\u001b[0m: 1",
-      "\nThe above exception was the direct cause of the following exception:\n",
-      "\u001b[1;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
-      "Cell \u001b[1;32mIn[4], line 3\u001b[0m\n\u001b[0;32m      1\u001b[0m answers \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mDataFrame(columns\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mQuestion\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAnswer\u001b[39m\u001b[38;5;124m\"\u001b[39m])\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(\u001b[38;5;241m1\u001b[39m, \u001b[38;5;28mlen\u001b[39m(df)):\n\u001b[1;32m----> 3\u001b[0m     current \u001b[38;5;241m=\u001b[39m \u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\n\u001b[0;32m      4\u001b[0m     before \u001b[38;5;241m=\u001b[39m df[i\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n\u001b[0;32m      5\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m current[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mVOC_SDRC_DCD\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mRX\u001b[39m\u001b[38;5;124m'\u001b[39m\\\n\u001b[0;32m      6\u001b[0m         \u001b[38;5;129;01mand\u001b[39;00m before[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mVOC_SDRC_DCD\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mTX\u001b[39m\u001b[38;5;124m'\u001b[39m\\\n\u001b[0;32m      7\u001b[0m         \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(current[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mSTT_TRNF_RSLT_CN\u001b[39m\u001b[38;5;124m'\u001b[39m]) \u001b[38;5;241m>\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m5\u001b[39m:\n",
-      "File \u001b[1;32mc:\\Users\\A\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\pandas\\core\\frame.py:3458\u001b[0m, in \u001b[0;36mDataFrame.__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m   3456\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns\u001b[38;5;241m.\u001b[39mnlevels \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m   3457\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_getitem_multilevel(key)\n\u001b[1;32m-> 3458\u001b[0m indexer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcolumns\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   3459\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_integer(indexer):\n\u001b[0;32m   3460\u001b[0m     indexer \u001b[38;5;241m=\u001b[39m [indexer]\n",
-      "File \u001b[1;32mc:\\Users\\A\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\pandas\\core\\indexes\\base.py:3363\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m   3361\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_engine\u001b[38;5;241m.\u001b[39mget_loc(casted_key)\n\u001b[0;32m   3362\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[1;32m-> 3363\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01merr\u001b[39;00m\n\u001b[0;32m   3365\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_scalar(key) \u001b[38;5;129;01mand\u001b[39;00m isna(key) \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhasnans:\n\u001b[0;32m   3366\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key)\n",
-      "\u001b[1;31mKeyError\u001b[0m: 1"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "id": "6",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "answers = pd.DataFrame(columns=[\"Question\", \"Answer\"])\n",
     "for i in range(1, len(df)):\n",
@@ -208,7 +155,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "433d6d14c8d463b",
+   "id": "7",
    "metadata": {},
    "outputs": [],
    "source": []