{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "107dd047",
   "metadata": {},
   "source": [
    "# 시각화 자료: 데이터 전처리, 특징 공학, 타겟 정의, 모델 학습 슬라이드\n",
    "\n",
    "이 노트북은 신문과방송 기사 분석 프로젝트의 데이터 처리 및 모델 학습 과정을 시각화하는 코드를 포함합니다."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "bfa07fe7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "🇰🇷 사용 가능한 한글 폰트:\n",
      "  • C:\\Users\\korea\\AppData\\Local\\Microsoft\\Windows\\Fonts\\NanumSquareOTF_0.otf\n",
      "  • C:\\Windows\\Fonts\\HANDotumExt.ttf\n",
      "  • C:\\Windows\\Fonts\\HANBatang.ttf\n",
      "  • C:\\Windows\\Fonts\\malgunsl.ttf\n",
      "  • C:\\Windows\\Fonts\\HanSantteutDotum-Bold.ttf\n",
      "  • C:\\Windows\\Fonts\\HANBatangExtBB.ttf\n",
      "  • C:\\Users\\korea\\AppData\\Local\\Microsoft\\Windows\\Fonts\\NanumSquareOTF_acL.otf\n",
      "  • C:\\Windows\\Fonts\\gulim.ttc\n",
      "  • C:\\Users\\korea\\AppData\\Local\\Microsoft\\Windows\\Fonts\\NanumSquareOTF_acR.otf\n",
      "  • C:\\Windows\\Fonts\\batang.ttc\n"
     ]
    }
   ],
   "source": [
    "# 필요한 라이브러리 임포트 (메모리 절약을 위해 최소화)\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "sns.set_style(\"ticks\")\n",
    "from sklearn.preprocessing import LabelEncoder, OneHotEncoder\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from scipy.sparse import hstack\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "import matplotlib.font_manager as fm\n",
    "# konlpy는 필요할 때 import (메모리 절약)\n",
    "# from konlpy.tag import Okt\n",
    "# 시스템에 설치된 폰트 확인\n",
    "font_list = fm.findSystemFonts(fontpaths=None, fontext='ttf')\n",
    "korean_fonts = [font for font in font_list if any(keyword in font.lower() for keyword in ['malgun', 'nanum', 'gulim', 'batang', 'dotum', 'godic'])]\n",
    "plt.rcParams['font.family'] = 'Malgun Gothic'\n",
    "print(\"🇰🇷 사용 가능한 한글 폰트:\")\n",
    "for font in korean_fonts[:10]:  # 처음 10개만 출력\n",
    "    print(f\"  • {font}\")\n",
    "# 데이터 경로 설정\n",
    "data_dir = './data_csv'\n",
    "contents_path = f'{data_dir}/contents.csv'\n",
    "metrics_path = f'{data_dir}/article_metrics_monthly.csv'\n",
    "demographics_path = f'{data_dir}/demographics_merged.csv'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "29e1d716",
   "metadata": {},
   "source": [
    "## Slide 1: 데이터 전처리 및 통합\n",
    "### 데이터 준비: 원본 데이터의 통합 및 정제"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e4cbc6b2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "데이터 로딩 완료 (contents 제한):\n",
      "Contents: (1746, 7)\n",
      "Metrics: (45344, 5)\n",
      "Demographics: (1089504, 6)\n"
     ]
    }
   ],
   "source": [
    "# 1. 데이터 로딩 (메모리 절약을 위해 nrows 제한)\n",
    "contents = pd.read_csv(contents_path)  # 500개 행만 로드\n",
    "metrics = pd.read_csv(metrics_path)\n",
    "demographics = pd.read_csv(demographics_path)\n",
    "\n",
    "print(\"데이터 로딩 완료 (contents 제한):\")\n",
    "print(f\"Contents: {contents.shape}\")\n",
    "print(f\"Metrics: {metrics.shape}\")\n",
    "print(f\"Demographics: {demographics.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "903a7b37",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "메트릭 집계 완료:\n",
      "     article_id  views_total  comments_total  likes_total\n",
      "0  221763439722          135             0.0            0\n",
      "1  221766610231           84             0.0            0\n",
      "2  221770333278           11             0.0            0\n",
      "3  221770673553          120             0.0            0\n",
      "4  221771937661          171             0.0            0\n"
     ]
    }
   ],
   "source": [
    "# 2. 핵심 지표 집계\n",
    "metrics_agg = (\n",
    "    metrics.groupby(\"article_id\")[[\"views_total\", \"comments\", \"likes\"]]\n",
    "    .sum()\n",
    "    .reset_index()\n",
    "    .rename(columns={\n",
    "        \"views_total\": \"views_total\",\n",
    "        \"comments\": \"comments_total\",\n",
    "        \"likes\": \"likes_total\",\n",
    "    })\n",
    ")\n",
    "print(\"메트릭 집계 완료:\")\n",
    "print(metrics_agg.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "e5b69c6b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "주요 청중 생성 완료:\n",
      "     article_id primary_age_group\n",
      "0  221763439722             30-34\n",
      "1  221766610231             25-29\n",
      "2  221770333278              0-12\n",
      "3  221770673553             25-29\n",
      "4  221771937661             19-24\n"
     ]
    }
   ],
   "source": [
    "# 3. 타겟 변수 생성 (1)\n",
    "filtered_demo = demographics[demographics[\"age_group\"] != \"전체\"].copy()\n",
    "idx = filtered_demo.groupby(\"article_id\")[\"views\"].idxmax()\n",
    "primary_audience = (\n",
    "    filtered_demo.loc[idx, [\"article_id\", \"age_group\"]]\n",
    "    .rename(columns={\"age_group\": \"primary_age_group\"})\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "print(\"주요 청중 생성 완료:\")\n",
    "print(primary_audience.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "e1603051",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "마스터 데이터프레임 생성 완료:\n",
      "     article_id category                                              title  \\\n",
      "0  221763439722    커버스토리  언론과 독자 : 기자에게 언론 신뢰를 묻다…기자 87% “내 기사 신뢰해”… 언론 ...   \n",
      "1  221766610231    커버스토리            [2019 언론인 조사] 언론 자유도 급반등…지상파 3사 체감 두드러져   \n",
      "2  221770333278     빅카인즈      [뉴스 빅데이터로 본 ‘새해 소망’]  새해 소망 기사에 담긴 우리 사회의 시대상   \n",
      "3  221770673553    커버스토리        [2019 신문산업 실태조사] 신문사 늘었지만 매출 제자리…구독 수익 집중해야   \n",
      "4  221771937661    커버스토리   [독자에게 언론 신뢰를 묻다]시민 60% “한국 언론, 정치·경제권력으로부터 독립해야”   \n",
      "\n",
      "                                             content                date  \\\n",
      "0  독자가 서슴없이 쓰는 ‘기레기’라는 표현에 정작 기자들은 어떤 생각을 가지고 있을까...    2020. 1. 8. 8:30   \n",
      "1  언론인이 현장에서 느끼는 언론의 자유와 직업 만족도는 어떻게 변화했을까. 국민의 미...  2020. 1. 10. 13:01   \n",
      "2  해마다 맞는 연말연시, 사람들은 어떤 희망을 품고 새해를 계획할까. 개인의 소망을 ...   2020. 1. 14. 8:40   \n",
      "3  침체 위기에 직면한 한국의 언론 산업은 지난 한 해동안 얼마나 많은 부침이 있었을까...  2020. 1. 14. 10:00   \n",
      "4  오늘 당신이 선택한 뉴스는 무엇이며, 그 뉴스는 믿을만했는가? ‘언론을 신뢰하는가’...  2020. 1. 15. 10:00   \n",
      "\n",
      "                                                 tag  \\\n",
      "0  #언론,#신문과방송,#신문기자,#방송기자,#기자,#기레기,#기사,#이슈,#신뢰도,#...   \n",
      "1  #신문과방송,#한국언론진흥재단,#언론인,#설문조사,#기자,#기자되는법,#만족도,#기...   \n",
      "2  #대한민국,#키워드,#2020,#새해,#경제,#남북관계,#대통령,#새해소망,#한국언...   \n",
      "3  #신문과방송,#한국언론진흥재단,#언론,#언론인,#기자,#신문,#종이신문,#구독자,#신문사   \n",
      "4  #한군언론진흥재단,#신문과방송,#독자,#신문,#기레기,#기자,#방송,#신뢰도,#언론...   \n",
      "\n",
      "                                    source_url  views_total  comments_total  \\\n",
      "0  https://blog.naver.com/kpfjra_/221763439722        135.0             0.0   \n",
      "1  https://blog.naver.com/kpfjra_/221766610231         84.0             0.0   \n",
      "2  https://blog.naver.com/kpfjra_/221770333278         11.0             0.0   \n",
      "3  https://blog.naver.com/kpfjra_/221770673553        120.0             0.0   \n",
      "4  https://blog.naver.com/kpfjra_/221771937661        171.0             0.0   \n",
      "\n",
      "   likes_total primary_age_group  \n",
      "0          0.0             30-34  \n",
      "1          0.0             25-29  \n",
      "2          0.0              0-12  \n",
      "3          0.0             25-29  \n",
      "4          0.0             19-24  \n"
     ]
    }
   ],
   "source": [
    "# 4. 데이터 병합\n",
    "df_master = contents.merge(metrics_agg, on=\"article_id\", how=\"left\")\n",
    "df_master = df_master.merge(primary_audience, on=\"article_id\", how=\"left\")\n",
    "df_master[[\"views_total\", \"comments_total\", \"likes_total\"]] = df_master[\n",
    "    [\"views_total\", \"comments_total\", \"likes_total\"]\n",
    "].fillna(0)\n",
    "\n",
    "# 샘플링 제거 (nrows로 이미 제한됨)\n",
    "\n",
    "print(\"마스터 데이터프레임 생성 완료:\")\n",
    "print(df_master.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "d799187e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x800 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Slide 1 시각화: 데이터 흐름 다이어그램\n",
    "fig, ax = plt.subplots(figsize=(12, 8))\n",
    "ax.axis('off')\n",
    "\n",
    "# CSV 파일\n",
    "ax.text(0.1, 0.8, 'contents.csv\\n(기사 콘텐츠)', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"lightblue\"))\n",
    "ax.text(0.1, 0.6, 'article_metrics_monthly.csv\\n(월별 성과)', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"lightgreen\"))\n",
    "ax.text(0.1, 0.4, 'demographics_merged.csv\\n(연령대 조회수)', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"lightcoral\"))\n",
    "\n",
    "# 화살표\n",
    "ax.arrow(0.25, 0.8, 0.2, 0, head_width=0.02, head_length=0.05, fc='k', ec='k')\n",
    "ax.arrow(0.25, 0.6, 0.2, 0.1, head_width=0.02, head_length=0.05, fc='k', ec='k')\n",
    "ax.arrow(0.25, 0.4, 0.2, -0.1, head_width=0.02, head_length=0.05, fc='k', ec='k')\n",
    "\n",
    "# 처리 단계\n",
    "ax.text(0.5, 0.9, '집계\\n(메트릭 합산)', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"yellow\"))\n",
    "ax.text(0.5, 0.7, '주요 청중 추출', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"yellow\"))\n",
    "ax.text(0.5, 0.5, '병합\\n(Left Join)', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"yellow\"))\n",
    "\n",
    "# 화살표\n",
    "ax.arrow(0.65, 0.9, 0.15, 0, head_width=0.02, head_length=0.05, fc='k', ec='k')\n",
    "ax.arrow(0.65, 0.7, 0.15, 0, head_width=0.02, head_length=0.05, fc='k', ec='k')\n",
    "ax.arrow(0.65, 0.5, 0.15, 0, head_width=0.02, head_length=0.05, fc='k', ec='k')\n",
    "\n",
    "# 최종 결과\n",
    "ax.text(0.85, 0.7, 'df_master\\n(마스터 데이터프레임)', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.5\", facecolor=\"orange\"))\n",
    "\n",
    "plt.title('Slide 1: 데이터 전처리 및 통합 흐름')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7d4f5164",
   "metadata": {},
   "source": [
    "## Slide 2: 특징 공학 (Feature Engineering)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "5be55793",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "텍스트 특징 행렬 크기: (1746, 33564)\n"
     ]
    }
   ],
   "source": [
    "# 5. 텍스트 특징 처리 (메모리 절약을 위해 max_features 줄임)\n",
    "text_series = (df_master[\"title\"].fillna(\"\") + \" \" + df_master[\"content\"].fillna(\"\")).str.strip()\n",
    "from konlpy.tag import Okt\n",
    "def okt_tokenizer(text):\n",
    "    okt = Okt()\n",
    "    if not text.strip():\n",
    "        return []\n",
    "    return [word for word, tag in okt.pos(text, stem=True) if tag in ['Noun', 'Verb']]\n",
    "\n",
    "vectorizer = TfidfVectorizer(\n",
    "    tokenizer=okt_tokenizer,\n",
    "    lowercase=False,\n",
    ")\n",
    "X_text = vectorizer.fit_transform(text_series)\n",
    "print(f\"텍스트 특징 행렬 크기: {X_text.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "56c7b337",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "카테고리 특징 행렬 크기: (1746, 24)\n"
     ]
    }
   ],
   "source": [
    "# 6. 카테고리 특징 처리\n",
    "category_series = df_master[\"category\"].fillna(\"미분류\")\n",
    "onehot_encoder = OneHotEncoder(handle_unknown=\"ignore\", sparse_output=True)\n",
    "X_cat = onehot_encoder.fit_transform(category_series.to_frame())\n",
    "print(f\"카테고리 특징 행렬 크기: {X_cat.shape}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "607c2514",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "결합된 특징 행렬 크기: (1746, 33588)\n"
     ]
    }
   ],
   "source": [
    "# 7. 최종 특징 결합\n",
    "X_combined = hstack([X_text, X_cat]).tocsr()\n",
    "print(f\"결합된 특징 행렬 크기: {X_combined.shape}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5636bc2d",
   "metadata": {},
   "source": [
    "## Slide 3: 타겟 변수 정의 및 데이터 필터링"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "88ffab68",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "유효 샘플 수: 1746\n",
      "연령대 클래스: ['0-12' '13-18' '19-24' '25-29' '30-34' '35-39' '40-44' '45-49' '50-54'\n",
      " '55-59' '60-']\n"
     ]
    }
   ],
   "source": [
    "# 8. 타겟 변수 정의 및 데이터 필터링\n",
    "y_views = np.log1p(df_master[\"views_total\"].astype(np.float32))\n",
    "y_age = df_master[\"primary_age_group\"]\n",
    "\n",
    "valid_mask = y_age.notna().to_numpy()\n",
    "X_combined_valid = X_combined[valid_mask]\n",
    "y_views_valid = y_views[valid_mask]\n",
    "y_age_valid = y_age[valid_mask].astype(str)\n",
    "\n",
    "label_encoder = LabelEncoder()\n",
    "y_age_encoded = label_encoder.fit_transform(y_age_valid)\n",
    "\n",
    "print(f\"유효 샘플 수: {valid_mask.sum()}\")\n",
    "print(f\"연령대 클래스: {label_encoder.classes_}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "0000f91a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 2100x900 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "# --- 2. 색상 팔레트 정의 (세련된 민트) ---\n",
    "primary_mint = \"#40c0a0\" # 포인트가 되는 선명한 민트\n",
    "secondary_mint = \"#d0f2e9\" # 히스토그램 배경색 (연한 민트)\n",
    "base_gray = \"#444444\" # 텍스트 및 라벨 (진한 회색)\n",
    "kde_color = \"#1a9075\" # KDE 라인 (진한 민트/청록)\n",
    "grid_color = \"#e0e0e0\" # 그리드 (연한 회색)\n",
    "from scipy.stats import skew\n",
    "# --- 4. 시각화 ---\n",
    "fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(14, 6), dpi=150)\n",
    "\n",
    "# --- 플롯 1: 원본 분포 ---\n",
    "sns.histplot(df_master[\"views_total\"], bins=50, ax=ax1,\n",
    "             color=secondary_mint, # 연한 민트 배경\n",
    "             edgecolor=primary_mint, # 선명한 민트 테두리\n",
    "             alpha=0.7)\n",
    "# KDE(밀도 곡선)는 따로 그려서 강조\n",
    "sns.kdeplot(df_master[\"views_total\"], ax=ax1, color=kde_color, linewidth=2.5)\n",
    "\n",
    "ax1.set_title('원본 데이터 분포 (변환 전)', fontsize=16, color=base_gray, pad=15, weight='bold')\n",
    "ax1.set_xlabel('총 조회수', fontsize=14, color=base_gray)\n",
    "ax1.set_ylabel('빈도', fontsize=14, color=base_gray)\n",
    "ax1.set_xlim(0, df_master[\"views_total\"].quantile(0.98)) # 상위 2% 극단치 제외\n",
    "ax1.tick_params(axis='both', colors=base_gray) # 축 눈금 색상\n",
    "\n",
    "# 왜도(Skewness) 값 계산 및 표기\n",
    "original_skew = skew(df_master[\"views_total\"])\n",
    "ax1.text(0.95, 0.90, f'왜도: {original_skew:.2f}', # Skewness -> 왜도\n",
    "         transform=ax1.transAxes, ha='right', fontsize=12,\n",
    "         color=base_gray, bbox=dict(facecolor='white', alpha=0.5, boxstyle='round,pad=0.3'))\n",
    "\n",
    "# --- 플롯 2: 로그 변환 후 분포 ---\n",
    "sns.histplot(y_views, bins=50, ax=ax2,\n",
    "             color=secondary_mint, # 동일한 색상 적용\n",
    "             edgecolor=primary_mint,\n",
    "             alpha=0.7)\n",
    "# KDE(밀도 곡선)\n",
    "sns.kdeplot(y_views, ax=ax2, color=kde_color, linewidth=2.5)\n",
    "\n",
    "ax2.set_title('로그 변환 분포 (log(1+Views))', fontsize=16, color=base_gray, pad=15, weight='bold')\n",
    "ax2.set_xlabel('로그 변환된 조회수', fontsize=14, color=base_gray)\n",
    "ax2.set_ylabel('빈도', fontsize=14, color=base_gray)\n",
    "ax2.tick_params(axis='both', colors=base_gray) # 축 눈금 색상\n",
    "\n",
    "# 왜도(Skewness) 값 계산 및 표기\n",
    "log_skew = skew(y_views)\n",
    "ax2.text(0.95, 0.90, f'왜도: {log_skew:.2f}', # Skewness -> 왜도\n",
    "         transform=ax2.transAxes, ha='right', fontsize=12,\n",
    "         color=base_gray, bbox=dict(facecolor='white', alpha=0.5, boxstyle='round,pad=0.3'))\n",
    "\n",
    "\n",
    "# --- 5. 최종 스타일링 ---\n",
    "for ax in [ax1, ax2]:\n",
    "    # 그리드: Y축에만 연하게 표시\n",
    "    ax.grid(True, linestyle='--', alpha=0.5, color=grid_color, axis='y')\n",
    "    # 스파인(테두리) 제거: 위쪽, 오른쪽 테두리 제거\n",
    "    sns.despine(ax=ax, top=True, right=True)\n",
    "    # X, Y축 선 색상 변경 (연하게)\n",
    "    ax.spines['bottom'].set_color(grid_color)\n",
    "    ax.spines['left'].set_color(grid_color)\n",
    "    \n",
    "# 전체 제목\n",
    "plt.suptitle('조회수 분포 비교 (원본 vs 로그 변환)', \n",
    "             fontsize=20, weight='bold', color=base_gray, y=1.05)\n",
    "\n",
    "plt.tight_layout() # 레이아웃 자동 조정\n",
    "plt.show()\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "203265c8",
   "metadata": {},
   "source": [
    "## Slide 4: 모델 학습 및 추론 과정"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c0b0125b",
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Found input variables with inconsistent numbers of samples: [1746, 350, 1746]",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[28], line 4\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;66;03m# 9. 데이터 분할\u001b[39;00m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01msklearn\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodel_selection\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;28;01mimport\u001b[39;00m train_test_split\n\u001b[1;32m----> 4\u001b[0m X_train, X_valid, y_views_train, y_views_valid, y_age_train, y_age_valid \u001b[38;5;241m=\u001b[39m \u001b[43mtrain_test_split\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m      5\u001b[0m \u001b[43m    \u001b[49m\u001b[43mX_combined_valid\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_views_valid\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_age_encoded\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m      6\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtest_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.2\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m      7\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrandom_state\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m42\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m      8\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstratify\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43my_age_encoded\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m      9\u001b[0m \u001b[43m)\u001b[49m\n\u001b[0;32m     10\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m훈련 세트 크기: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mX_train\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, 검증 세트 크기: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mX_valid\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
      "File \u001b[1;32mc:\\Users\\korea\\Desktop\\dacon_broadcast_paper\\.venv\\lib\\site-packages\\sklearn\\utils\\_param_validation.py:218\u001b[0m, in \u001b[0;36mvalidate_params.<locals>.decorator.<locals>.wrapper\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    212\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m    213\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[0;32m    214\u001b[0m         skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[0;32m    215\u001b[0m             prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[0;32m    216\u001b[0m         )\n\u001b[0;32m    217\u001b[0m     ):\n\u001b[1;32m--> 218\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m    219\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m InvalidParameterError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    220\u001b[0m     \u001b[38;5;66;03m# When the function is just a wrapper around an estimator, we allow\u001b[39;00m\n\u001b[0;32m    221\u001b[0m     \u001b[38;5;66;03m# the function to delegate validation to the estimator, but we replace\u001b[39;00m\n\u001b[0;32m    222\u001b[0m     \u001b[38;5;66;03m# the name of the estimator by the name of the function in the error\u001b[39;00m\n\u001b[0;32m    223\u001b[0m     \u001b[38;5;66;03m# message to avoid confusion.\u001b[39;00m\n\u001b[0;32m    224\u001b[0m     msg \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msub(\n\u001b[0;32m    225\u001b[0m         \u001b[38;5;124mr\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparameter of \u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124mw+ must be\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m    226\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparameter of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfunc\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__qualname__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m must be\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m    227\u001b[0m         \u001b[38;5;28mstr\u001b[39m(e),\n\u001b[0;32m    228\u001b[0m     )\n",
      "File \u001b[1;32mc:\\Users\\korea\\Desktop\\dacon_broadcast_paper\\.venv\\lib\\site-packages\\sklearn\\model_selection\\_split.py:2916\u001b[0m, in \u001b[0;36mtrain_test_split\u001b[1;34m(test_size, train_size, random_state, shuffle, stratify, *arrays)\u001b[0m\n\u001b[0;32m   2913\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m n_arrays \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[0;32m   2914\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAt least one array required as input\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m-> 2916\u001b[0m arrays \u001b[38;5;241m=\u001b[39m \u001b[43mindexable\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43marrays\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   2918\u001b[0m n_samples \u001b[38;5;241m=\u001b[39m _num_samples(arrays[\u001b[38;5;241m0\u001b[39m])\n\u001b[0;32m   2919\u001b[0m n_train, n_test \u001b[38;5;241m=\u001b[39m _validate_shuffle_split(\n\u001b[0;32m   2920\u001b[0m     n_samples, test_size, train_size, default_test_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.25\u001b[39m\n\u001b[0;32m   2921\u001b[0m )\n",
      "File \u001b[1;32mc:\\Users\\korea\\Desktop\\dacon_broadcast_paper\\.venv\\lib\\site-packages\\sklearn\\utils\\validation.py:530\u001b[0m, in \u001b[0;36mindexable\u001b[1;34m(*iterables)\u001b[0m\n\u001b[0;32m    500\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Make arrays indexable for cross-validation.\u001b[39;00m\n\u001b[0;32m    501\u001b[0m \n\u001b[0;32m    502\u001b[0m \u001b[38;5;124;03mChecks consistent length, passes through None, and ensures that everything\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    526\u001b[0m \u001b[38;5;124;03m[[1, 2, 3], array([2, 3, 4]), None, <...Sparse...dtype 'int64'...shape (3, 1)>]\u001b[39;00m\n\u001b[0;32m    527\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    529\u001b[0m result \u001b[38;5;241m=\u001b[39m [_make_indexable(X) \u001b[38;5;28;01mfor\u001b[39;00m X \u001b[38;5;129;01min\u001b[39;00m iterables]\n\u001b[1;32m--> 530\u001b[0m \u001b[43mcheck_consistent_length\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mresult\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    531\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n",
      "File \u001b[1;32mc:\\Users\\korea\\Desktop\\dacon_broadcast_paper\\.venv\\lib\\site-packages\\sklearn\\utils\\validation.py:473\u001b[0m, in \u001b[0;36mcheck_consistent_length\u001b[1;34m(*arrays)\u001b[0m\n\u001b[0;32m    471\u001b[0m lengths \u001b[38;5;241m=\u001b[39m [_num_samples(X) \u001b[38;5;28;01mfor\u001b[39;00m X \u001b[38;5;129;01min\u001b[39;00m arrays \u001b[38;5;28;01mif\u001b[39;00m X \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m]\n\u001b[0;32m    472\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mset\u001b[39m(lengths)) \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m--> 473\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m    474\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFound input variables with inconsistent numbers of samples: \u001b[39m\u001b[38;5;132;01m%r\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m    475\u001b[0m         \u001b[38;5;241m%\u001b[39m [\u001b[38;5;28mint\u001b[39m(l) \u001b[38;5;28;01mfor\u001b[39;00m l \u001b[38;5;129;01min\u001b[39;00m lengths]\n\u001b[0;32m    476\u001b[0m     )\n",
      "\u001b[1;31mValueError\u001b[0m: Found input variables with inconsistent numbers of samples: [1746, 350, 1746]"
     ]
    }
   ],
   "source": [
    "# 9. 데이터 분할\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_valid, y_views_train, y_views_valid, y_age_train, y_age_valid = train_test_split(\n",
    "    X_combined_valid, y_views_valid, y_age_encoded,\n",
    "    test_size=0.2,\n",
    "    random_state=42,\n",
    "    stratify=y_age_encoded,\n",
    ")\n",
    "print(f\"훈련 세트 크기: {X_train.shape[0]}, 검증 세트 크기: {X_valid.shape[0]}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9f6cf943",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# 10. 하이퍼파라미터 튜닝 (모의 데이터로 시각화)\n",
    "# 실제 튜닝은 시간이 오래 걸리므로 모의 데이터를 사용해 그래프 생성\n",
    "trials = list(range(1, 51))\n",
    "rmse_values = [np.random.uniform(0.5, 1.5) - 0.01 * i for i in range(50)]  # 점진적 개선 모의\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.plot(trials, rmse_values, marker='o', linestyle='-', color='blue')\n",
    "plt.title('Optuna 최적화 과정 (RMSE)')\n",
    "plt.xlabel('Trial 번호')\n",
    "plt.ylabel('RMSE')\n",
    "plt.grid(True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ef7fd333",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "모델 학습 완료\n"
     ]
    }
   ],
   "source": [
    "# 11. 최종 모델 학습 (메모리 절약을 위해 n_estimators 줄임)\n",
    "from xgboost import XGBRegressor, XGBClassifier\n",
    "\n",
    "view_model = XGBRegressor(objective=\"reg:squarederror\", n_estimators=20, random_state=42)  # 50에서 20으로 줄임\n",
    "view_model.fit(X_train, y_views_train)\n",
    "\n",
    "age_model = XGBClassifier(objective=\"multi:softprob\", num_class=len(label_encoder.classes_), n_estimators=20, random_state=42)  # 50에서 20으로 줄임\n",
    "age_model.fit(X_train, y_age_train)\n",
    "\n",
    "print(\"모델 학습 완료\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f1f793c9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "예측 조회수: 44\n",
      "예측 연령대: 0-12\n"
     ]
    }
   ],
   "source": [
    "# 12. 결과물 저장 및 추론\n",
    "import joblib\n",
    "\n",
    "# 저장 (실제로는 파일로 저장)\n",
    "artifacts = {\n",
    "    \"vectorizer\": vectorizer,\n",
    "    \"onehot_encoder\": onehot_encoder,\n",
    "    \"label_encoder\": label_encoder,\n",
    "    \"view_model\": view_model,\n",
    "    \"age_model\": age_model,\n",
    "}\n",
    "# joblib.dump(artifacts, 'models.pkl')  # 실제 저장 시 주석 해제\n",
    "\n",
    "# 추론 예시\n",
    "sample_text = \"새로운 기사 제목 새로운 기사 내용\"\n",
    "sample_category = \"정치\"\n",
    "sample_text_vec = vectorizer.transform([sample_text])\n",
    "sample_cat_vec = onehot_encoder.transform([[sample_category]])\n",
    "sample_combined = hstack([sample_text_vec, sample_cat_vec])\n",
    "\n",
    "pred_views_log = view_model.predict(sample_combined)\n",
    "pred_views = np.expm1(pred_views_log)\n",
    "pred_age_encoded = age_model.predict(sample_combined)\n",
    "pred_age = label_encoder.inverse_transform(pred_age_encoded)\n",
    "\n",
    "print(f\"예측 조회수: {pred_views[0]:.0f}\")\n",
    "print(f\"예측 연령대: {pred_age[0]}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "810ca9fe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Slide 4 시각화: 추론 순서도\n",
    "fig, ax = plt.subplots(figsize=(10, 6))\n",
    "ax.axis('off')\n",
    "\n",
    "# 순서도\n",
    "ax.text(0.5, 0.9, '새 기사 입력', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"lightblue\"), fontsize=12)\n",
    "ax.arrow(0.5, 0.85, 0, -0.1, head_width=0.02, head_length=0.03, fc='k', ec='k')\n",
    "ax.text(0.5, 0.7, '전처리\\n(TF-IDF + One-Hot)', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"yellow\"), fontsize=12)\n",
    "ax.arrow(0.5, 0.65, 0, -0.1, head_width=0.02, head_length=0.03, fc='k', ec='k')\n",
    "ax.text(0.5, 0.5, '모델 예측\\n(XGB Regressor + Classifier)', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"orange\"), fontsize=12)\n",
    "ax.arrow(0.5, 0.45, 0, -0.1, head_width=0.02, head_length=0.03, fc='k', ec='k')\n",
    "ax.text(0.5, 0.3, '예측 결과\\n(조회수 + 연령대)', ha='center', va='center', bbox=dict(boxstyle=\"round,pad=0.3\", facecolor=\"green\"), fontsize=12)\n",
    "\n",
    "plt.title('Slide 4: 추론 과정 순서도')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3e5262e5",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".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": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}