diff --git "a/week16_\353\263\265\354\212\265\352\263\274\354\240\234_\353\205\270\355\230\204\354\204\240.ipynb" "b/week16_\353\263\265\354\212\265\352\263\274\354\240\234_\353\205\270\355\230\204\354\204\240.ipynb" new file mode 100644 index 0000000..9397f23 --- /dev/null +++ "b/week16_\353\263\265\354\212\265\352\263\274\354\240\234_\353\205\270\355\230\204\354\204\240.ipynb" @@ -0,0 +1,2931 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "ed2133b8", + "metadata": {}, + "source": [ + "### 9.5 컨텐츠 기반 필터링 실습: TMDB 5000 영화 데이터 세트" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "fc61e82c", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(4803, 20)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
budgetgenreshomepageidkeywordsoriginal_languageoriginal_titleoverviewpopularityproduction_companiesproduction_countriesrelease_daterevenueruntimespoken_languagesstatustaglinetitlevote_averagevote_count
0237000000[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"name\": \"Fantasy\"}, {...http://www.avatarmovie.com/19995[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\": 2964, \"name\": \"future\"}, {\"id\": 3386, \"name\": \"sp...enAvatarIn the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, ...150.437577[{\"name\": \"Ingenious Film Partners\", \"id\": 289}, {\"name\": \"Twentieth Century Fox Film Corporatio...[{\"iso_3166_1\": \"US\", \"name\": \"United States of America\"}, {\"iso_3166_1\": \"GB\", \"name\": \"United ...2009-12-102787965087162.0[{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso_639_1\": \"es\", \"name\": \"Espa\\u00f1ol\"}]ReleasedEnter the World of Pandora.Avatar7.211800
\n", + "
" + ], + "text/plain": [ + " budget \\\n", + "0 237000000 \n", + "\n", + " genres \\\n", + "0 [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"name\": \"Fantasy\"}, {... \n", + "\n", + " homepage id \\\n", + "0 http://www.avatarmovie.com/ 19995 \n", + "\n", + " keywords \\\n", + "0 [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\": 2964, \"name\": \"future\"}, {\"id\": 3386, \"name\": \"sp... \n", + "\n", + " original_language original_title \\\n", + "0 en Avatar \n", + "\n", + " overview \\\n", + "0 In the 22nd century, a paraplegic Marine is dispatched to the moon Pandora on a unique mission, ... \n", + "\n", + " popularity \\\n", + "0 150.437577 \n", + "\n", + " production_companies \\\n", + "0 [{\"name\": \"Ingenious Film Partners\", \"id\": 289}, {\"name\": \"Twentieth Century Fox Film Corporatio... \n", + "\n", + " production_countries \\\n", + "0 [{\"iso_3166_1\": \"US\", \"name\": \"United States of America\"}, {\"iso_3166_1\": \"GB\", \"name\": \"United ... \n", + "\n", + " release_date revenue runtime \\\n", + "0 2009-12-10 2787965087 162.0 \n", + "\n", + " spoken_languages \\\n", + "0 [{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso_639_1\": \"es\", \"name\": \"Espa\\u00f1ol\"}] \n", + "\n", + " status tagline title vote_average vote_count \n", + "0 Released Enter the World of Pandora. Avatar 7.2 11800 " + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import warnings; warnings.filterwarnings('ignore')\n", + "\n", + "movies =pd.read_csv('tmdb_5000_movies.csv')\n", + "print(movies.shape)\n", + "movies.head(1)" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "f2f81b96", + "metadata": {}, + "outputs": [], + "source": [ + "movies_df = movies[['id','title', 'genres', 'vote_average', 'vote_count',\n", + " 'popularity', 'keywords', 'overview']]" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "c27a51db", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
genreskeywords
0[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"name\": \"Fantasy\"}, {...[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\": 2964, \"name\": \"future\"}, {\"id\": 3386, \"name\": \"sp...
\n", + "
" + ], + "text/plain": [ + " genres \\\n", + "0 [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"name\": \"Adventure\"}, {\"id\": 14, \"name\": \"Fantasy\"}, {... \n", + "\n", + " keywords \n", + "0 [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\": 2964, \"name\": \"future\"}, {\"id\": 3386, \"name\": \"sp... " + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.set_option('max_colwidth', 100)\n", + "movies_df[['genres','keywords']][:1]" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "485ecdcc", + "metadata": {}, + "outputs": [], + "source": [ + "from ast import literal_eval\n", + "\n", + "# 문자열을 객체로 변환\n", + "movies_df['genres'] = movies_df['genres'].apply(literal_eval)\n", + "movies_df['keywords'] = movies_df['keywords'].apply(literal_eval)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "7fb257c1", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
genreskeywords
0[Action, Adventure, Fantasy, Science Fiction][culture clash, future, space war, space colony, society, space travel, futuristic, romance, spa...
\n", + "
" + ], + "text/plain": [ + " genres \\\n", + "0 [Action, Adventure, Fantasy, Science Fiction] \n", + "\n", + " keywords \n", + "0 [culture clash, future, space war, space colony, society, space travel, futuristic, romance, spa... " + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 원하는 값만 추출하기 위해 람다식 사용\n", + "movies_df['genres'] = movies_df['genres'].apply(lambda x : [ y['name'] for y in x])\n", + "movies_df['keywords'] = movies_df['keywords'].apply(lambda x : [ y['name'] for y in x])\n", + "movies_df[['genres', 'keywords']][:1]" + ] + }, + { + "cell_type": "markdown", + "id": "3b1b8bb3", + "metadata": {}, + "source": [ + "#### 장르 콘텐츠 유사도 측정" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "0a6f06f1", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(4803, 276)\n" + ] + } + ], + "source": [ + "from sklearn.feature_extraction.text import CountVectorizer\n", + "\n", + "# CountVectorizer를 적용하기 위해 공백 문자로 word 단위가 구분되는 문자열로 변환\n", + "movies_df['genres_literal'] = movies_df['genres'].apply(lambda x : (' ').join(x))\n", + "count_vect = CountVectorizer(min_df=0.0, ngram_range=(1,2))\n", + "genre_mat = count_vect.fit_transform(movies_df['genres_literal'])\n", + "print(genre_mat.shape)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5b8b5107", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(4803, 4803)\n", + "[[1. 0.59628479 0.4472136 ... 0. 0. 0. ]\n", + " [0.59628479 1. 0.4 ... 0. 0. 0. ]]\n" + ] + } + ], + "source": [ + "from sklearn.metrics.pairwise import cosine_similarity\n", + "\n", + "# 코사인 유사도 계산\n", + "genre_sim = cosine_similarity(genre_mat, genre_mat)\n", + "print(genre_sim.shape)\n", + "print(genre_sim[:2])" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "bc7add2c", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[ 0 3494 813 ... 3038 3037 2401]]\n" + ] + } + ], + "source": [ + "genre_sim_sorted_ind = genre_sim.argsort()[:, ::-1]\n", + "print(genre_sim_sorted_ind[:1])" + ] + }, + { + "cell_type": "markdown", + "id": "729eb91e", + "metadata": {}, + "source": [ + "#### 장르 콘텐츠 필터링을 이용한 영화 추천" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "id": "513295b8", + "metadata": {}, + "outputs": [], + "source": [ + "def find_sim_movie(df, sorted_ind, title_name, top_n=10):\n", + " \n", + " # 인자로 입력된 movies_df 데이터프레임에서 'title' 컬럼이 입력된 title_name 값인 데이터 프레임 추출\n", + " title_movie = df[df['title'] == title_name]\n", + " \n", + " # title_named을 가진 데이터프레임의 index 객체를 ndarray로 반환하고 \n", + " # sorted_ind 인자로 입력된 genre_sim_sorted_ind 객체에서 유사도 순으로 top_n 개의 index 추출\n", + " title_index = title_movie.index.values\n", + " similar_indexes = sorted_ind[title_index, :(top_n)]\n", + " \n", + " # 추출된 top_n 인덱스들 출력: top_n 인덱스는 2차원 데이터\n", + " # 데이터프레임에서로 사용하기 위해서 1차원 배열로 변경\n", + " print(similar_indexes)\n", + " similar_indexes = similar_indexes.reshape(-1)\n", + " \n", + " return df.iloc[similar_indexes]" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "id": "5249b5b4", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[1370 4041 3337 1847 3378 4217 2839 281 588 3866]]\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
titlevote_average
1370216.5
4041This Is England7.4
3337The Godfather8.4
1847GoodFellas8.2
3378Auto Focus6.1
4217Kids6.8
2839Rounders6.9
281American Gangster7.4
588Wall Street: Money Never Sleeps5.8
3866City of God8.1
\n", + "
" + ], + "text/plain": [ + " title vote_average\n", + "1370 21 6.5\n", + "4041 This Is England 7.4\n", + "3337 The Godfather 8.4\n", + "1847 GoodFellas 8.2\n", + "3378 Auto Focus 6.1\n", + "4217 Kids 6.8\n", + "2839 Rounders 6.9\n", + "281 American Gangster 7.4\n", + "588 Wall Street: Money Never Sleeps 5.8\n", + "3866 City of God 8.1" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# '대부'와 장르별로 유사한 영화 열 개 추천\n", + "similar_movies = find_sim_movie(movies_df, genre_sim_sorted_ind, 'The Godfather',10)\n", + "similar_movies[['title', 'vote_average']]" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "id": "2734a7e4", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
titlevote_averagevote_count
3519Stiff Upper Lips10.01
4247Me You and Five Bucks10.02
4045Dancer, Texas Pop. 8110.01
4662Little Big Top10.01
3992Sardaarji9.52
2386One Man's Hero9.32
2970There Goes My Baby8.52
1881The Shawshank Redemption8.58205
2796The Prisoner of Zenda8.411
3337The Godfather8.45893
\n", + "
" + ], + "text/plain": [ + " title vote_average vote_count\n", + "3519 Stiff Upper Lips 10.0 1\n", + "4247 Me You and Five Bucks 10.0 2\n", + "4045 Dancer, Texas Pop. 81 10.0 1\n", + "4662 Little Big Top 10.0 1\n", + "3992 Sardaarji 9.5 2\n", + "2386 One Man's Hero 9.3 2\n", + "2970 There Goes My Baby 8.5 2\n", + "1881 The Shawshank Redemption 8.5 8205\n", + "2796 The Prisoner of Zenda 8.4 11\n", + "3337 The Godfather 8.4 5893" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 영화 평점에 따라 필터링해서 최종 추천\n", + "movies_df[['title','vote_average','vote_count']].sort_values('vote_average', ascending=False)[:10]" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "0dffc8d4", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "C: 6.092 m: 370.2\n" + ] + } + ], + "source": [ + "# 가중평점 방식\n", + "\n", + "C = movies_df['vote_average'].mean()\n", + "m = movies_df['vote_count'].quantile(0.6) # 상위 60% 영화\n", + "print('C:',round(C,3), 'm:',round(m,3))" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "bfe26f2f", + "metadata": {}, + "outputs": [], + "source": [ + "# 새로운 가중 평점으로 기존 평점 변경하는 함수 생성\n", + "percentile = 0.6\n", + "m = movies_df['vote_count'].quantile(percentile)\n", + "C = movies_df['vote_average'].mean()\n", + "\n", + "def weighted_vote_average(record):\n", + " v = record['vote_count']\n", + " R = record['vote_average']\n", + " \n", + " return ( (v/(v+m)) * R ) + ( (m/(m+v)) * C ) \n", + "\n", + "movies_df['weighted_vote'] = movies_df.apply(weighted_vote_average, axis=1) " + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "id": "16c0b332", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
titlevote_averageweighted_votevote_count
1881The Shawshank Redemption8.58.3960528205
3337The Godfather8.48.2635915893
662Fight Club8.38.2164559413
3232Pulp Fiction8.38.2071028428
65The Dark Knight8.28.13693012002
1818Schindler's List8.38.1260694329
3865Whiplash8.38.1232484254
809Forrest Gump8.28.1059547927
2294Spirited Away8.38.1058673840
2731The Godfather: Part II8.38.0795863338
\n", + "
" + ], + "text/plain": [ + " title vote_average weighted_vote vote_count\n", + "1881 The Shawshank Redemption 8.5 8.396052 8205\n", + "3337 The Godfather 8.4 8.263591 5893\n", + "662 Fight Club 8.3 8.216455 9413\n", + "3232 Pulp Fiction 8.3 8.207102 8428\n", + "65 The Dark Knight 8.2 8.136930 12002\n", + "1818 Schindler's List 8.3 8.126069 4329\n", + "3865 Whiplash 8.3 8.123248 4254\n", + "809 Forrest Gump 8.2 8.105954 7927\n", + "2294 Spirited Away 8.3 8.105867 3840\n", + "2731 The Godfather: Part II 8.3 8.079586 3338" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "movies_df[['title','vote_average','weighted_vote','vote_count']].sort_values('weighted_vote',\n", + " ascending=False)[:10]\n" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "id": "9f6971c8", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
titlevote_averageweighted_vote
1881The Shawshank Redemption8.58.396052
2731The Godfather: Part II8.38.079586
1847GoodFellas8.27.976937
3866City of God8.17.759693
1663Once Upon a Time in America8.27.657811
892Casino7.87.423040
281American Gangster7.47.141396
4041This Is England7.46.739664
1149American Hustle6.86.717525
1243Mean Streets7.26.626569
\n", + "
" + ], + "text/plain": [ + " title vote_average weighted_vote\n", + "1881 The Shawshank Redemption 8.5 8.396052\n", + "2731 The Godfather: Part II 8.3 8.079586\n", + "1847 GoodFellas 8.2 7.976937\n", + "3866 City of God 8.1 7.759693\n", + "1663 Once Upon a Time in America 8.2 7.657811\n", + "892 Casino 7.8 7.423040\n", + "281 American Gangster 7.4 7.141396\n", + "4041 This Is England 7.4 6.739664\n", + "1149 American Hustle 6.8 6.717525\n", + "1243 Mean Streets 7.2 6.626569" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 장르 유사성 높은 영화를 후보군으로 선정하고 weighted_vote 높은 영화 추천하는 방식으로 변경\n", + "\n", + "def find_sim_movie(df, sorted_ind, title_name, top_n=10):\n", + " title_movie = df[df['title'] == title_name]\n", + " title_index = title_movie.index.values\n", + " \n", + " # top_n의 2배에 해당하는 쟝르 유사성이 높은 인덱스 추출 \n", + " similar_indexes = sorted_ind[title_index, :(top_n*2)]\n", + " similar_indexes = similar_indexes.reshape(-1)\n", + "# 기준 영화 인덱스는 제외\n", + " similar_indexes = similar_indexes[similar_indexes != title_index]\n", + " \n", + " # top_n의 2배에 해당하는 후보군에서 weighted_vote 높은 순으로 top_n 만큼 추출 \n", + " return df.iloc[similar_indexes].sort_values('weighted_vote', ascending=False)[:top_n]\n", + "\n", + "similar_movies = find_sim_movie(movies_df, genre_sim_sorted_ind, 'The Godfather',10)\n", + "similar_movies[['title', 'vote_average', 'weighted_vote']]" + ] + }, + { + "cell_type": "markdown", + "id": "6d503732", + "metadata": {}, + "source": [ + "### 9.6 아이템 기반 인접 이웃 협업 필터링 실습" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "id": "7b8dfa24", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(9742, 3)\n", + "(100836, 4)\n" + ] + } + ], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "\n", + "movies = pd.read_csv('movies.csv')\n", + "ratings = pd.read_csv('ratings.csv')\n", + "print(movies.shape)\n", + "print(ratings.shape)" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "id": "e4c7e9fe", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
movieId12345678910...193565193567193571193573193579193581193583193585193587193609
userId
14.0NaN4.0NaNNaN4.0NaNNaNNaNNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
3NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "

3 rows × 9724 columns

\n", + "
" + ], + "text/plain": [ + "movieId 1 2 3 4 5 6 7 8 \\\n", + "userId \n", + "1 4.0 NaN 4.0 NaN NaN 4.0 NaN NaN \n", + "2 NaN NaN NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN NaN NaN NaN NaN \n", + "\n", + "movieId 9 10 ... 193565 193567 193571 193573 193579 193581 \\\n", + "userId ... \n", + "1 NaN NaN ... NaN NaN NaN NaN NaN NaN \n", + "2 NaN NaN ... NaN NaN NaN NaN NaN NaN \n", + "3 NaN NaN ... NaN NaN NaN NaN NaN NaN \n", + "\n", + "movieId 193583 193585 193587 193609 \n", + "userId \n", + "1 NaN NaN NaN NaN \n", + "2 NaN NaN NaN NaN \n", + "3 NaN NaN NaN NaN \n", + "\n", + "[3 rows x 9724 columns]" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 사용자를 로우로, 영화를 칼럼으로 구성한 데이터셋으로 변경\n", + "ratings = ratings[['userId', 'movieId', 'rating']]\n", + "ratings_matrix = ratings.pivot_table('rating', index='userId', columns='movieId')\n", + "ratings_matrix.head(3)" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "36ef7a0a", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
title'71 (2014)'Hellboy': The Seeds of Creation (2004)'Round Midnight (1986)'Salem's Lot (2004)'Til There Was You (1997)'Tis the Season for Love (2015)'burbs, The (1989)'night Mother (1986)(500) Days of Summer (2009)*batteries not included (1987)...Zulu (2013)[REC] (2007)[REC]² (2009)[REC]³ 3 Génesis (2012)anohana: The Flower We Saw That Day - The Movie (2013)eXistenZ (1999)xXx (2002)xXx: State of the Union (2005)¡Three Amigos! (1986)À nous la liberté (Freedom for Us) (1931)
userId
10.00.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.04.00.0
20.00.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
30.00.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
\n", + "

3 rows × 9719 columns

\n", + "
" + ], + "text/plain": [ + "title '71 (2014) 'Hellboy': The Seeds of Creation (2004) \\\n", + "userId \n", + "1 0.0 0.0 \n", + "2 0.0 0.0 \n", + "3 0.0 0.0 \n", + "\n", + "title 'Round Midnight (1986) 'Salem's Lot (2004) \\\n", + "userId \n", + "1 0.0 0.0 \n", + "2 0.0 0.0 \n", + "3 0.0 0.0 \n", + "\n", + "title 'Til There Was You (1997) 'Tis the Season for Love (2015) \\\n", + "userId \n", + "1 0.0 0.0 \n", + "2 0.0 0.0 \n", + "3 0.0 0.0 \n", + "\n", + "title 'burbs, The (1989) 'night Mother (1986) (500) Days of Summer (2009) \\\n", + "userId \n", + "1 0.0 0.0 0.0 \n", + "2 0.0 0.0 0.0 \n", + "3 0.0 0.0 0.0 \n", + "\n", + "title *batteries not included (1987) ... Zulu (2013) [REC] (2007) \\\n", + "userId ... \n", + "1 0.0 ... 0.0 0.0 \n", + "2 0.0 ... 0.0 0.0 \n", + "3 0.0 ... 0.0 0.0 \n", + "\n", + "title [REC]² (2009) [REC]³ 3 Génesis (2012) \\\n", + "userId \n", + "1 0.0 0.0 \n", + "2 0.0 0.0 \n", + "3 0.0 0.0 \n", + "\n", + "title anohana: The Flower We Saw That Day - The Movie (2013) \\\n", + "userId \n", + "1 0.0 \n", + "2 0.0 \n", + "3 0.0 \n", + "\n", + "title eXistenZ (1999) xXx (2002) xXx: State of the Union (2005) \\\n", + "userId \n", + "1 0.0 0.0 0.0 \n", + "2 0.0 0.0 0.0 \n", + "3 0.0 0.0 0.0 \n", + "\n", + "title ¡Three Amigos! (1986) À nous la liberté (Freedom for Us) (1931) \n", + "userId \n", + "1 4.0 0.0 \n", + "2 0.0 0.0 \n", + "3 0.0 0.0 \n", + "\n", + "[3 rows x 9719 columns]" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# title 컬럼을 얻기 이해 movies와 조인 \n", + "rating_movies = pd.merge(ratings, movies, on='movieId')\n", + "\n", + "# columns='title' 로 title 칼럼으로 피벗 \n", + "ratings_matrix = rating_movies.pivot_table('rating', index='userId', columns='title')\n", + "\n", + "# NaN 값을 모두 0으로 변환\n", + "ratings_matrix = ratings_matrix.fillna(0)\n", + "ratings_matrix.head(3)" + ] + }, + { + "cell_type": "markdown", + "id": "51bccda9", + "metadata": {}, + "source": [ + "#### 영화 간 유사도 산출" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "id": "9767a1eb", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
userId12345678910...601602603604605606607608609610
title
'71 (2014)0.00.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.04.0
'Hellboy': The Seeds of Creation (2004)0.00.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
'Round Midnight (1986)0.00.00.00.00.00.00.00.00.00.0...0.00.00.00.00.00.00.00.00.00.0
\n", + "

3 rows × 610 columns

\n", + "
" + ], + "text/plain": [ + "userId 1 2 3 4 5 6 7 \\\n", + "title \n", + "'71 (2014) 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n", + "'Round Midnight (1986) 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n", + "\n", + "userId 8 9 10 ... 601 602 603 \\\n", + "title ... \n", + "'71 (2014) 0.0 0.0 0.0 ... 0.0 0.0 0.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 0.0 0.0 ... 0.0 0.0 0.0 \n", + "'Round Midnight (1986) 0.0 0.0 0.0 ... 0.0 0.0 0.0 \n", + "\n", + "userId 604 605 606 607 608 609 610 \n", + "title \n", + "'71 (2014) 0.0 0.0 0.0 0.0 0.0 0.0 4.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n", + "'Round Midnight (1986) 0.0 0.0 0.0 0.0 0.0 0.0 0.0 \n", + "\n", + "[3 rows x 610 columns]" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ratings_matrix_T = ratings_matrix.transpose()\n", + "ratings_matrix_T.head(3)" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "id": "76687495", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "(9719, 9719)\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
title'71 (2014)'Hellboy': The Seeds of Creation (2004)'Round Midnight (1986)'Salem's Lot (2004)'Til There Was You (1997)'Tis the Season for Love (2015)'burbs, The (1989)'night Mother (1986)(500) Days of Summer (2009)*batteries not included (1987)...Zulu (2013)[REC] (2007)[REC]² (2009)[REC]³ 3 Génesis (2012)anohana: The Flower We Saw That Day - The Movie (2013)eXistenZ (1999)xXx (2002)xXx: State of the Union (2005)¡Three Amigos! (1986)À nous la liberté (Freedom for Us) (1931)
title
'71 (2014)1.00.0000000.0000000.00.00.00.0000000.00.1416530.0...0.00.3420550.5433050.7071070.00.00.1394310.3273270.00.0
'Hellboy': The Seeds of Creation (2004)0.01.0000000.7071070.00.00.00.0000000.00.0000000.0...0.00.0000000.0000000.0000000.00.00.0000000.0000000.00.0
'Round Midnight (1986)0.00.7071071.0000000.00.00.00.1767770.00.0000000.0...0.00.0000000.0000000.0000000.00.00.0000000.0000000.00.0
\n", + "

3 rows × 9719 columns

\n", + "
" + ], + "text/plain": [ + "title '71 (2014) \\\n", + "title \n", + "'71 (2014) 1.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 \n", + "'Round Midnight (1986) 0.0 \n", + "\n", + "title 'Hellboy': The Seeds of Creation (2004) \\\n", + "title \n", + "'71 (2014) 0.000000 \n", + "'Hellboy': The Seeds of Creation (2004) 1.000000 \n", + "'Round Midnight (1986) 0.707107 \n", + "\n", + "title 'Round Midnight (1986) \\\n", + "title \n", + "'71 (2014) 0.000000 \n", + "'Hellboy': The Seeds of Creation (2004) 0.707107 \n", + "'Round Midnight (1986) 1.000000 \n", + "\n", + "title 'Salem's Lot (2004) \\\n", + "title \n", + "'71 (2014) 0.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 \n", + "'Round Midnight (1986) 0.0 \n", + "\n", + "title 'Til There Was You (1997) \\\n", + "title \n", + "'71 (2014) 0.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 \n", + "'Round Midnight (1986) 0.0 \n", + "\n", + "title 'Tis the Season for Love (2015) \\\n", + "title \n", + "'71 (2014) 0.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 \n", + "'Round Midnight (1986) 0.0 \n", + "\n", + "title 'burbs, The (1989) \\\n", + "title \n", + "'71 (2014) 0.000000 \n", + "'Hellboy': The Seeds of Creation (2004) 0.000000 \n", + "'Round Midnight (1986) 0.176777 \n", + "\n", + "title 'night Mother (1986) \\\n", + "title \n", + "'71 (2014) 0.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 \n", + "'Round Midnight (1986) 0.0 \n", + "\n", + "title (500) Days of Summer (2009) \\\n", + "title \n", + "'71 (2014) 0.141653 \n", + "'Hellboy': The Seeds of Creation (2004) 0.000000 \n", + "'Round Midnight (1986) 0.000000 \n", + "\n", + "title *batteries not included (1987) ... \\\n", + "title ... \n", + "'71 (2014) 0.0 ... \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 ... \n", + "'Round Midnight (1986) 0.0 ... \n", + "\n", + "title Zulu (2013) [REC] (2007) \\\n", + "title \n", + "'71 (2014) 0.0 0.342055 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 0.000000 \n", + "'Round Midnight (1986) 0.0 0.000000 \n", + "\n", + "title [REC]² (2009) \\\n", + "title \n", + "'71 (2014) 0.543305 \n", + "'Hellboy': The Seeds of Creation (2004) 0.000000 \n", + "'Round Midnight (1986) 0.000000 \n", + "\n", + "title [REC]³ 3 Génesis (2012) \\\n", + "title \n", + "'71 (2014) 0.707107 \n", + "'Hellboy': The Seeds of Creation (2004) 0.000000 \n", + "'Round Midnight (1986) 0.000000 \n", + "\n", + "title anohana: The Flower We Saw That Day - The Movie (2013) \\\n", + "title \n", + "'71 (2014) 0.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 \n", + "'Round Midnight (1986) 0.0 \n", + "\n", + "title eXistenZ (1999) xXx (2002) \\\n", + "title \n", + "'71 (2014) 0.0 0.139431 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 0.000000 \n", + "'Round Midnight (1986) 0.0 0.000000 \n", + "\n", + "title xXx: State of the Union (2005) \\\n", + "title \n", + "'71 (2014) 0.327327 \n", + "'Hellboy': The Seeds of Creation (2004) 0.000000 \n", + "'Round Midnight (1986) 0.000000 \n", + "\n", + "title ¡Three Amigos! (1986) \\\n", + "title \n", + "'71 (2014) 0.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 \n", + "'Round Midnight (1986) 0.0 \n", + "\n", + "title À nous la liberté (Freedom for Us) (1931) \n", + "title \n", + "'71 (2014) 0.0 \n", + "'Hellboy': The Seeds of Creation (2004) 0.0 \n", + "'Round Midnight (1986) 0.0 \n", + "\n", + "[3 rows x 9719 columns]" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.metrics.pairwise import cosine_similarity\n", + "\n", + "item_sim = cosine_similarity(ratings_matrix_T, ratings_matrix_T)\n", + "\n", + "# cosine_similarity() 로 반환된 넘파이 행렬을 영화명을 매핑하여 데이터프레임으로 변환\n", + "item_sim_df = pd.DataFrame(data=item_sim, index=ratings_matrix.columns,\n", + " columns=ratings_matrix.columns)\n", + "print(item_sim_df.shape)\n", + "item_sim_df.head(3)" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "id": "4031501a", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "title\n", + "Godfather, The (1972) 1.000000\n", + "Godfather: Part II, The (1974) 0.821773\n", + "Goodfellas (1990) 0.664841\n", + "One Flew Over the Cuckoo's Nest (1975) 0.620536\n", + "Star Wars: Episode IV - A New Hope (1977) 0.595317\n", + "Fargo (1996) 0.588614\n", + "Name: Godfather, The (1972), dtype: float64" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "item_sim_df[\"Godfather, The (1972)\"].sort_values(ascending=False)[:6]" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "id": "7cd43c35", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "title\n", + "Dark Knight, The (2008) 0.727263\n", + "Inglourious Basterds (2009) 0.646103\n", + "Shutter Island (2010) 0.617736\n", + "Dark Knight Rises, The (2012) 0.617504\n", + "Fight Club (1999) 0.615417\n", + "Name: Inception (2010), dtype: float64" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 인셉션과 유사도 높은 영화\n", + "item_sim_df[\"Inception (2010)\"].sort_values(ascending=False)[1:6]" + ] + }, + { + "cell_type": "markdown", + "id": "1fe099e6", + "metadata": {}, + "source": [ + "#### 아이템 기반 최근접 이웃 협업 필터링으로 개인화된 영화 추천" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "id": "f672d6e6", + "metadata": {}, + "outputs": [], + "source": [ + "def predict_rating(ratings_arr, item_sim_arr ):\n", + " ratings_pred = ratings_arr.dot(item_sim_arr)/ np.array([np.abs(item_sim_arr).sum(axis=1)])\n", + " return ratings_pred" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "id": "3ddffe8f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
title'71 (2014)'Hellboy': The Seeds of Creation (2004)'Round Midnight (1986)'Salem's Lot (2004)'Til There Was You (1997)'Tis the Season for Love (2015)'burbs, The (1989)'night Mother (1986)(500) Days of Summer (2009)*batteries not included (1987)...Zulu (2013)[REC] (2007)[REC]² (2009)[REC]³ 3 Génesis (2012)anohana: The Flower We Saw That Day - The Movie (2013)eXistenZ (1999)xXx (2002)xXx: State of the Union (2005)¡Three Amigos! (1986)À nous la liberté (Freedom for Us) (1931)
userId
10.0703450.5778550.3216960.2270550.2069580.1946150.2498830.1025420.1570840.178197...0.1136080.1817380.1339620.1285740.0061790.2120700.1929210.1360240.2929550.720347
20.0182600.0427440.0188610.0000000.0000000.0359950.0134130.0023140.0322130.014863...0.0156400.0208550.0201190.0157450.0499830.0148760.0216160.0245280.0175630.000000
30.0118840.0302790.0644370.0037620.0037490.0027220.0146250.0020850.0056660.006272...0.0069230.0116650.0118000.0122250.0000000.0081940.0070170.0092290.0104200.084501
\n", + "

3 rows × 9719 columns

\n", + "
" + ], + "text/plain": [ + "title '71 (2014) 'Hellboy': The Seeds of Creation (2004) \\\n", + "userId \n", + "1 0.070345 0.577855 \n", + "2 0.018260 0.042744 \n", + "3 0.011884 0.030279 \n", + "\n", + "title 'Round Midnight (1986) 'Salem's Lot (2004) \\\n", + "userId \n", + "1 0.321696 0.227055 \n", + "2 0.018861 0.000000 \n", + "3 0.064437 0.003762 \n", + "\n", + "title 'Til There Was You (1997) 'Tis the Season for Love (2015) \\\n", + "userId \n", + "1 0.206958 0.194615 \n", + "2 0.000000 0.035995 \n", + "3 0.003749 0.002722 \n", + "\n", + "title 'burbs, The (1989) 'night Mother (1986) (500) Days of Summer (2009) \\\n", + "userId \n", + "1 0.249883 0.102542 0.157084 \n", + "2 0.013413 0.002314 0.032213 \n", + "3 0.014625 0.002085 0.005666 \n", + "\n", + "title *batteries not included (1987) ... Zulu (2013) [REC] (2007) \\\n", + "userId ... \n", + "1 0.178197 ... 0.113608 0.181738 \n", + "2 0.014863 ... 0.015640 0.020855 \n", + "3 0.006272 ... 0.006923 0.011665 \n", + "\n", + "title [REC]² (2009) [REC]³ 3 Génesis (2012) \\\n", + "userId \n", + "1 0.133962 0.128574 \n", + "2 0.020119 0.015745 \n", + "3 0.011800 0.012225 \n", + "\n", + "title anohana: The Flower We Saw That Day - The Movie (2013) \\\n", + "userId \n", + "1 0.006179 \n", + "2 0.049983 \n", + "3 0.000000 \n", + "\n", + "title eXistenZ (1999) xXx (2002) xXx: State of the Union (2005) \\\n", + "userId \n", + "1 0.212070 0.192921 0.136024 \n", + "2 0.014876 0.021616 0.024528 \n", + "3 0.008194 0.007017 0.009229 \n", + "\n", + "title ¡Three Amigos! (1986) À nous la liberté (Freedom for Us) (1931) \n", + "userId \n", + "1 0.292955 0.720347 \n", + "2 0.017563 0.000000 \n", + "3 0.010420 0.084501 \n", + "\n", + "[3 rows x 9719 columns]" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "ratings_pred = predict_rating(ratings_matrix.values , item_sim_df.values)\n", + "ratings_pred_matrix = pd.DataFrame(data=ratings_pred, index= ratings_matrix.index,\n", + " columns = ratings_matrix.columns)\n", + "ratings_pred_matrix.head(3)" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "id": "5d4f025a", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "아이템 기반 모든 인접 이웃 MSE: 9.895354759094706\n" + ] + } + ], + "source": [ + "from sklearn.metrics import mean_squared_error\n", + "\n", + "# 사용자가 평점을 부여한 영화에 대해서만 예측 성능 평가 MSE 구하기\n", + "def get_mse(pred, actual):\n", + " # 평점 있는 실제 영화만 추출\n", + " pred = pred[actual.nonzero()].flatten()\n", + " actual = actual[actual.nonzero()].flatten()\n", + " return mean_squared_error(pred, actual)\n", + "\n", + "print('아이템 기반 모든 인접 이웃 MSE: ', get_mse(ratings_pred, ratings_matrix.values ))\n" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "id": "9645c7f2", + "metadata": {}, + "outputs": [], + "source": [ + "# 특정 영화와 가장 비슷한 유사도 갖는 영화에 대해서만 유사도 벡터 적용하는 함수로 변경\n", + "# 이유: 많은 영화의 유사도 벡터 이용하다 보니 평점 예측 떨어짐\n", + "\n", + "def predict_rating_topsim(ratings_arr, item_sim_arr, n=20):\n", + " # 사용자-아이템 평점 행렬 크기만큼 0으로 채운 예측 행렬 초기화\n", + " pred = np.zeros(ratings_arr.shape)\n", + "\n", + " # 사용자-아이템 평점 행렬의 열 크기만큼 루프 수행\n", + " for col in range(ratings_arr.shape[1]):\n", + " # 유사도 행렬에서 유사도가 큰 순으로 n개 데이터 행렬의 인덱스 반환\n", + " top_n_items = [np.argsort(item_sim_arr[:, col])[:-n-1:-1]]\n", + " # 개인화된 예측 평점을 계산\n", + " for row in range(ratings_arr.shape[0]):\n", + " pred[row, col] = item_sim_arr[col, :][top_n_items].dot(ratings_arr[row, :][top_n_items].T) \n", + " pred[row, col] /= np.sum(np.abs(item_sim_arr[col, :][top_n_items])) \n", + " return pred" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "id": "b6264beb", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "아이템 기반 인접 TOP-20 이웃 MSE: 3.694999233129397\n" + ] + } + ], + "source": [ + "ratings_pred = predict_rating_topsim(ratings_matrix.values , item_sim_df.values, n=20)\n", + "print('아이템 기반 인접 TOP-20 이웃 MSE: ', get_mse(ratings_pred, ratings_matrix.values ))\n", + "\n", + "\n", + "# 계산된 예측 평점 데이터는 DataFrame으로 재생성\n", + "ratings_pred_matrix = pd.DataFrame(data=ratings_pred, index= ratings_matrix.index,\n", + " columns = ratings_matrix.columns)" + ] + }, + { + "cell_type": "markdown", + "id": "336eb74e", + "metadata": {}, + "source": [ + "MSE 9.89에서 3.69로 향상됨. " + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "id": "6ce7b140", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "title\n", + "Adaptation (2002) 5.0\n", + "Citizen Kane (1941) 5.0\n", + "Raiders of the Lost Ark (Indiana Jones and the Raiders of the Lost Ark) (1981) 5.0\n", + "Producers, The (1968) 5.0\n", + "Lord of the Rings: The Two Towers, The (2002) 5.0\n", + "Lord of the Rings: The Fellowship of the Ring, The (2001) 5.0\n", + "Back to the Future (1985) 5.0\n", + "Austin Powers in Goldmember (2002) 5.0\n", + "Minority Report (2002) 4.0\n", + "Witness (1985) 4.0\n", + "Name: 9, dtype: float64" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 특정 사용자에 대해 영화 추천하기 (userid 9)\n", + "user_rating_id = ratings_matrix.loc[9, :]\n", + "user_rating_id[ user_rating_id > 0].sort_values(ascending=False)[:10]" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "id": "fad49387", + "metadata": {}, + "outputs": [], + "source": [ + "# 아이템 기반 협업 필터링 적용\n", + "# 이미 평점 준 영화 제외하도록 평점 안 준 영화 리스트 객체로 반환하는 함수 생성\n", + "\n", + "def get_unseen_movies(ratings_matrix, userId):\n", + " # userId로 입력받은 사용자의 모든 영화정보 추출하여 시리즈로 반환\n", + " # 반환된 user_rating: 영화명(title)을 인덱스로 가지는 시리즈 객체\n", + " user_rating = ratings_matrix.loc[userId,:]\n", + " \n", + " # user_rating이 0보다 크면 기존에 관람한 영화. 대상 인덱스 추출하여 리스트 객체로 만듦.\n", + " already_seen = user_rating[ user_rating > 0].index.tolist()\n", + " \n", + " # 모든 영화명을 리스트 객체로 만듦. \n", + " movies_list = ratings_matrix.columns.tolist()\n", + " \n", + " # list comprehension으로 already_seen에 해당하는 movie는 movies_list에서 제외\n", + " unseen_list = [ movie for movie in movies_list if movie not in already_seen]\n", + " \n", + " return unseen_list" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "id": "20050a05", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
pred_score
title
Shrek (2001)0.866202
Spider-Man (2002)0.857854
Last Samurai, The (2003)0.817473
Indiana Jones and the Temple of Doom (1984)0.816626
Matrix Reloaded, The (2003)0.800990
Harry Potter and the Sorcerer's Stone (a.k.a. Harry Potter and the Philosopher's Stone) (2001)0.765159
Gladiator (2000)0.740956
Matrix, The (1999)0.732693
Pirates of the Caribbean: The Curse of the Black Pearl (2003)0.689591
Lord of the Rings: The Return of the King, The (2003)0.676711
\n", + "
" + ], + "text/plain": [ + " pred_score\n", + "title \n", + "Shrek (2001) 0.866202\n", + "Spider-Man (2002) 0.857854\n", + "Last Samurai, The (2003) 0.817473\n", + "Indiana Jones and the Temple of Doom (1984) 0.816626\n", + "Matrix Reloaded, The (2003) 0.800990\n", + "Harry Potter and the Sorcerer's Stone (a.k.a. Harry Potter and the Philosopher's Stone) (2001) 0.765159\n", + "Gladiator (2000) 0.740956\n", + "Matrix, The (1999) 0.732693\n", + "Pirates of the Caribbean: The Curse of the Black Pearl (2003) 0.689591\n", + "Lord of the Rings: The Return of the King, The (2003) 0.676711" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "def recomm_movie_by_userid(pred_df, userId, unseen_list, top_n=10):\n", + " # 예측 평점 데이터프레임에서 사용자 id 인덱스와 unseen_list로 들어온 영화명 칼럼 추출\n", + " # 예측 평점이 높은 순으로 정렬함\n", + " recomm_movies = pred_df.loc[userId, unseen_list].sort_values(ascending=False)[:top_n]\n", + " return recomm_movies\n", + " \n", + "# 사용자가 관람하지 않는 영화명 추출 \n", + "unseen_list = get_unseen_movies(ratings_matrix, 9)\n", + "\n", + "# 아이템 기반의 인접 이웃 협업 필터링으로 영화 추천 \n", + "recomm_movies = recomm_movie_by_userid(ratings_pred_matrix, 9, unseen_list, top_n=10)\n", + "\n", + "# 평점 데이터를 데이터프레임으로 생성\n", + "recomm_movies = pd.DataFrame(data=recomm_movies.values,index=recomm_movies.index,columns=['pred_score'])\n", + "recomm_movies" + ] + }, + { + "cell_type": "markdown", + "id": "379a4369", + "metadata": {}, + "source": [ + "### 9.7 행렬 분해를 이용한 잠재 요인 협업 필터링 실습" + ] + }, + { + "cell_type": "markdown", + "id": "021b01c4", + "metadata": {}, + "source": [ + "9.4절에서 사용한 코드 활용 but 행렬 분해 로직 부분을 함수로 생성 " + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "id": "c49df58d", + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "from sklearn.metrics import mean_squared_error\n", + "\n", + "def get_rmse(R, P, Q, non_zeros):\n", + " error = 0\n", + " full_pred_matrix = np.dot(P, Q.T)\n", + " \n", + " x_non_zero_ind = [non_zero[0] for non_zero in non_zeros]\n", + " y_non_zero_ind = [non_zero[1] for non_zero in non_zeros]\n", + " R_non_zeros = R[x_non_zero_ind, y_non_zero_ind]\n", + " \n", + " full_pred_matrix_non_zeros = full_pred_matrix[x_non_zero_ind, y_non_zero_ind]\n", + " \n", + " mse = mean_squared_error(R_non_zeros, full_pred_matrix_non_zeros)\n", + " rmse = np.sqrt(mse)\n", + " \n", + " return rmse" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "id": "8c6b83d5", + "metadata": {}, + "outputs": [], + "source": [ + "def matrix_factorization(R, K, steps=200, learning_rate=0.01, r_lambda = 0.01):\n", + " num_users, num_items = R.shape\n", + " # P와 Q 매트릭스의 크기를 지정하고 정규 분포를 가진 랜덤한 값으로 입력합\n", + " np.random.seed(1)\n", + " P = np.random.normal(scale=1./K, size=(num_users, K))\n", + " Q = np.random.normal(scale=1./K, size=(num_items, K))\n", + " \n", + " # R>0인 행 위치, 열 위치, 값을 non_zeros 리스트 객체에 저장 \n", + " non_zeros = [ (i, j, R[i,j]) for i in range(num_users) for j in range(num_items) if R[i,j] > 0 ]\n", + " \n", + " # SGD 기법으로 P와 Q 매트릭스를 계속 업데이트\n", + " for step in range(steps):\n", + " for i, j, r in non_zeros:\n", + " # 실제 값과 예측 값의 차이인 오류 값 구함\n", + " eij = r - np.dot(P[i, :], Q[j, :].T)\n", + " # 정규화 반영한 SGD 업데이트 공식 적용\n", + " P[i,:] = P[i,:] + learning_rate*(eij * Q[j, :] - r_lambda*P[i,:])\n", + " Q[j,:] = Q[j,:] + learning_rate*(eij * P[i, :] - r_lambda*Q[j,:])\n", + " \n", + " rmse = get_rmse(R, P, Q, non_zeros)\n", + " if (step % 10) == 0 :\n", + " print(\"### iteration step : \", step,\" rmse : \", rmse)\n", + " \n", + " return P, Q" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "id": "c40bb303", + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "\n", + "movies = pd.read_csv('movies.csv')\n", + "ratings = pd.read_csv('ratings.csv')\n", + "ratings = ratings[['userId', 'movieId', 'rating']]\n", + "ratings_matrix = ratings.pivot_table('rating', index='userId', columns='movieId')\n", + "\n", + "# title 컬럼을 얻기 이해 movies와 조인 수행\n", + "rating_movies = pd.merge(ratings, movies, on='movieId')\n", + "\n", + "# columns='title'로 title 칼럼으로 피봇 수행\n", + "ratings_matrix = rating_movies.pivot_table('rating', index='userId', columns='title')\n" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "id": "59390917", + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "### iteration step : 0 rmse : 2.9023619751336867\n", + "### iteration step : 10 rmse : 0.7335768591017927\n", + "### iteration step : 20 rmse : 0.5115539026853442\n", + "### iteration step : 30 rmse : 0.37261628282537446\n", + "### iteration step : 40 rmse : 0.2960818299181014\n", + "### iteration step : 50 rmse : 0.2520353192341642\n", + "### iteration step : 60 rmse : 0.22487503275269854\n", + "### iteration step : 70 rmse : 0.20685455302331537\n", + "### iteration step : 80 rmse : 0.19413418783028688\n", + "### iteration step : 90 rmse : 0.18470082002720403\n", + "### iteration step : 100 rmse : 0.17742927527209104\n", + "### iteration step : 110 rmse : 0.1716522696470749\n", + "### iteration step : 120 rmse : 0.16695181946871723\n", + "### iteration step : 130 rmse : 0.16305292191997542\n", + "### iteration step : 140 rmse : 0.1597669192967964\n", + "### iteration step : 150 rmse : 0.15695986999457318\n", + "### iteration step : 160 rmse : 0.1545339818671543\n", + "### iteration step : 170 rmse : 0.1524161855107764\n", + "### iteration step : 180 rmse : 0.15055080739628304\n", + "### iteration step : 190 rmse : 0.1488947091323209\n" + ] + } + ], + "source": [ + "# 사용자-아이템 평점 행렬 분해\n", + "P, Q = matrix_factorization(ratings_matrix.values, K=50, steps=200, learning_rate=0.01, r_lambda = 0.01)\n", + "pred_matrix = np.dot(P, Q.T)" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "id": "f9e662b0", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
title'71 (2014)'Hellboy': The Seeds of Creation (2004)'Round Midnight (1986)'Salem's Lot (2004)'Til There Was You (1997)'Tis the Season for Love (2015)'burbs, The (1989)'night Mother (1986)(500) Days of Summer (2009)*batteries not included (1987)...Zulu (2013)[REC] (2007)[REC]² (2009)[REC]³ 3 Génesis (2012)anohana: The Flower We Saw That Day - The Movie (2013)eXistenZ (1999)xXx (2002)xXx: State of the Union (2005)¡Three Amigos! (1986)À nous la liberté (Freedom for Us) (1931)
userId
13.0550844.0920183.5641304.5021673.9812151.2716943.6032742.3332665.0917493.972454...1.4026084.2083823.7059572.7205142.7873313.4750763.2534582.1610874.0104950.859474
23.1701193.6579923.3087074.1665214.3118901.2754694.2379721.9003663.3928593.647421...0.9738113.5282643.3615322.6725352.4044564.2327892.9116021.6345764.1357350.725684
32.3070731.6588531.4435382.2088592.2294860.7807601.9970430.9249082.9707002.551446...0.5203541.7094942.2815961.7828331.6351731.3232762.8875801.0426182.2938900.396941
\n", + "

3 rows × 9719 columns

\n", + "
" + ], + "text/plain": [ + "title '71 (2014) 'Hellboy': The Seeds of Creation (2004) \\\n", + "userId \n", + "1 3.055084 4.092018 \n", + "2 3.170119 3.657992 \n", + "3 2.307073 1.658853 \n", + "\n", + "title 'Round Midnight (1986) 'Salem's Lot (2004) \\\n", + "userId \n", + "1 3.564130 4.502167 \n", + "2 3.308707 4.166521 \n", + "3 1.443538 2.208859 \n", + "\n", + "title 'Til There Was You (1997) 'Tis the Season for Love (2015) \\\n", + "userId \n", + "1 3.981215 1.271694 \n", + "2 4.311890 1.275469 \n", + "3 2.229486 0.780760 \n", + "\n", + "title 'burbs, The (1989) 'night Mother (1986) (500) Days of Summer (2009) \\\n", + "userId \n", + "1 3.603274 2.333266 5.091749 \n", + "2 4.237972 1.900366 3.392859 \n", + "3 1.997043 0.924908 2.970700 \n", + "\n", + "title *batteries not included (1987) ... Zulu (2013) [REC] (2007) \\\n", + "userId ... \n", + "1 3.972454 ... 1.402608 4.208382 \n", + "2 3.647421 ... 0.973811 3.528264 \n", + "3 2.551446 ... 0.520354 1.709494 \n", + "\n", + "title [REC]² (2009) [REC]³ 3 Génesis (2012) \\\n", + "userId \n", + "1 3.705957 2.720514 \n", + "2 3.361532 2.672535 \n", + "3 2.281596 1.782833 \n", + "\n", + "title anohana: The Flower We Saw That Day - The Movie (2013) \\\n", + "userId \n", + "1 2.787331 \n", + "2 2.404456 \n", + "3 1.635173 \n", + "\n", + "title eXistenZ (1999) xXx (2002) xXx: State of the Union (2005) \\\n", + "userId \n", + "1 3.475076 3.253458 2.161087 \n", + "2 4.232789 2.911602 1.634576 \n", + "3 1.323276 2.887580 1.042618 \n", + "\n", + "title ¡Three Amigos! (1986) À nous la liberté (Freedom for Us) (1931) \n", + "userId \n", + "1 4.010495 0.859474 \n", + "2 4.135735 0.725684 \n", + "3 2.293890 0.396941 \n", + "\n", + "[3 rows x 9719 columns]" + ] + }, + "execution_count": 43, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "\n", + "# 영화 타이틀을 칼럼명으로 가지는 데이터프레임으로 변경\n", + "ratings_pred_matrix = pd.DataFrame(data=pred_matrix, index= ratings_matrix.index,\n", + " columns = ratings_matrix.columns)\n", + "\n", + "ratings_pred_matrix.head(3)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "a9ec9e7c", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
pred_score
title
Rear Window (1954)5.704612
South Park: Bigger, Longer and Uncut (1999)5.451100
Rounders (1998)5.298393
Blade Runner (1982)5.244951
Roger & Me (1989)5.191962
Gattaca (1997)5.183179
Ben-Hur (1959)5.130463
Rosencrantz and Guildenstern Are Dead (1990)5.087375
Big Lebowski, The (1998)5.038690
Star Wars: Episode V - The Empire Strikes Back (1980)4.989601
\n", + "
" + ], + "text/plain": [ + " pred_score\n", + "title \n", + "Rear Window (1954) 5.704612\n", + "South Park: Bigger, Longer and Uncut (1999) 5.451100\n", + "Rounders (1998) 5.298393\n", + "Blade Runner (1982) 5.244951\n", + "Roger & Me (1989) 5.191962\n", + "Gattaca (1997) 5.183179\n", + "Ben-Hur (1959) 5.130463\n", + "Rosencrantz and Guildenstern Are Dead (1990) 5.087375\n", + "Big Lebowski, The (1998) 5.038690\n", + "Star Wars: Episode V - The Empire Strikes Back (1980) 4.989601" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 사용자가 관람하지 않은 영화명 추출\n", + "unseen_list = get_unseen_movies(ratings_matrix, 9)\n", + "\n", + "# 잠재 요인 협업 필터링으로 영화 추천\n", + "recomm_movies = recomm_movie_by_userid(ratings_pred_matrix, 9, unseen_list, top_n=10)\n", + "\n", + "# 평점 데이터를 데이터프레임으로 생성\n", + "recomm_movies = pd.DataFrame(data=recomm_movies.values,index=recomm_movies.index,columns=['pred_score'])\n", + "recomm_movies" + ] + } + ], + "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": "3.13.5" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +}