diff --git "a/Week16_\341\204\207\341\205\251\341\206\250\341\204\211\341\205\263\341\206\270\341\204\200\341\205\252\341\204\214\341\205\246_\341\204\200\341\205\265\341\206\267\341\204\211\341\205\245\341\204\213\341\205\247\341\206\253.ipynb" "b/Week16_\341\204\207\341\205\251\341\206\250\341\204\211\341\205\263\341\206\270\341\204\200\341\205\252\341\204\214\341\205\246_\341\204\200\341\205\265\341\206\267\341\204\211\341\205\245\341\204\213\341\205\247\341\206\253.ipynb" new file mode 100644 index 0000000..2b0c171 --- /dev/null +++ "b/Week16_\341\204\207\341\205\251\341\206\250\341\204\211\341\205\263\341\206\270\341\204\200\341\205\252\341\204\214\341\205\246_\341\204\200\341\205\265\341\206\267\341\204\211\341\205\245\341\204\213\341\205\247\341\206\253.ipynb" @@ -0,0 +1,6148 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "cells": [ + { + "cell_type": "markdown", + "source": [ + "## **9.5 콘텐츠 기반 필터링 실습 -- TMDB 5000 데이터 세트**" + ], + "metadata": { + "id": "WSjMuEFnW4kZ" + } + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 219 + }, + "id": "Z1JP9HN_Utp0", + "outputId": "6223891b-8003-41e1-d8ba-0264698e48af" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Mounted at /content/drive\n", + "(4803, 20)\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " budget genres \\\n", + "0 237000000 [{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam... \n", + "\n", + " homepage id \\\n", + "0 http://www.avatarmovie.com/ 19995 \n", + "\n", + " keywords original_language \\\n", + "0 [{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":... en \n", + "\n", + " original_title overview \\\n", + "0 Avatar In the 22nd century, a paraplegic Marine is di... \n", + "\n", + " popularity production_companies \\\n", + "0 150.437577 [{\"name\": \"Ingenious Film Partners\", \"id\": 289... \n", + "\n", + " production_countries release_date revenue \\\n", + "0 [{\"iso_3166_1\": \"US\", \"name\": \"United States o... 2009-12-10 2787965087 \n", + "\n", + " runtime spoken_languages status \\\n", + "0 162.0 [{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso... Released \n", + "\n", + " tagline title vote_average vote_count \n", + "0 Enter the World of Pandora. Avatar 7.2 11800 " + ], + "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", + "
budgetgenreshomepageidkeywordsoriginal_languageoriginal_titleoverviewpopularityproduction_companiesproduction_countriesrelease_daterevenueruntimespoken_languagesstatustaglinetitlevote_averagevote_count
0237000000[{\"id\": 28, \"name\": \"Action\"}, {\"id\": 12, \"nam...http://www.avatarmovie.com/19995[{\"id\": 1463, \"name\": \"culture clash\"}, {\"id\":...enAvatarIn the 22nd century, a paraplegic Marine is di...150.437577[{\"name\": \"Ingenious Film Partners\", \"id\": 289...[{\"iso_3166_1\": \"US\", \"name\": \"United States o...2009-12-102787965087162.0[{\"iso_639_1\": \"en\", \"name\": \"English\"}, {\"iso...ReleasedEnter the World of Pandora.Avatar7.211800
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "movies", + "summary": "{\n \"name\": \"movies\",\n \"rows\": 4803,\n \"fields\": [\n {\n \"column\": \"budget\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 40722391,\n \"min\": 0,\n \"max\": 380000000,\n \"num_unique_values\": 436,\n \"samples\": [\n 439000,\n 68000000,\n 700000\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"genres\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 1175,\n \"samples\": [\n \"[{\\\"id\\\": 14, \\\"name\\\": \\\"Fantasy\\\"}, {\\\"id\\\": 12, \\\"name\\\": \\\"Adventure\\\"}, {\\\"id\\\": 16, \\\"name\\\": \\\"Animation\\\"}]\",\n \"[{\\\"id\\\": 28, \\\"name\\\": \\\"Action\\\"}, {\\\"id\\\": 35, \\\"name\\\": \\\"Comedy\\\"}, {\\\"id\\\": 80, \\\"name\\\": \\\"Crime\\\"}, {\\\"id\\\": 18, \\\"name\\\": \\\"Drama\\\"}]\",\n \"[{\\\"id\\\": 12, \\\"name\\\": \\\"Adventure\\\"}, {\\\"id\\\": 16, \\\"name\\\": \\\"Animation\\\"}, {\\\"id\\\": 10751, \\\"name\\\": \\\"Family\\\"}, {\\\"id\\\": 14, \\\"name\\\": \\\"Fantasy\\\"}, {\\\"id\\\": 878, \\\"name\\\": \\\"Science Fiction\\\"}]\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"homepage\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 1691,\n \"samples\": [\n \"https://www.warnerbros.com/running-scared\",\n \"http://www.51birchstreet.com/index.php\",\n \"http://movies2.foxjapan.com/glee/\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"id\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 88694,\n \"min\": 5,\n \"max\": 459488,\n \"num_unique_values\": 4803,\n \"samples\": [\n 8427,\n 13006,\n 18041\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"keywords\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 4222,\n \"samples\": [\n \"[{\\\"id\\\": 782, \\\"name\\\": \\\"assassin\\\"}, {\\\"id\\\": 1872, \\\"name\\\": \\\"loss of father\\\"}, {\\\"id\\\": 2908, \\\"name\\\": \\\"secret society\\\"}, {\\\"id\\\": 3045, \\\"name\\\": \\\"mission of murder\\\"}, {\\\"id\\\": 9748, \\\"name\\\": \\\"revenge\\\"}]\",\n \"[{\\\"id\\\": 2987, \\\"name\\\": \\\"gang war\\\"}, {\\\"id\\\": 4942, \\\"name\\\": \\\"victim of murder\\\"}, {\\\"id\\\": 5332, \\\"name\\\": \\\"greed\\\"}, {\\\"id\\\": 6062, \\\"name\\\": \\\"hostility\\\"}, {\\\"id\\\": 156212, \\\"name\\\": \\\"spaghetti western\\\"}]\",\n \"[{\\\"id\\\": 703, \\\"name\\\": \\\"detective\\\"}, {\\\"id\\\": 1299, \\\"name\\\": \\\"monster\\\"}, {\\\"id\\\": 6101, \\\"name\\\": \\\"engine\\\"}, {\\\"id\\\": 10988, \\\"name\\\": \\\"based on tv series\\\"}, {\\\"id\\\": 15162, \\\"name\\\": \\\"dog\\\"}]\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"original_language\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 37,\n \"samples\": [\n \"xx\",\n \"ta\",\n \"es\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"original_title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 4801,\n \"samples\": [\n \"I Spy\",\n \"Love Letters\",\n \"Sleepover\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"overview\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 4800,\n \"samples\": [\n \"When the Switchblade, the most sophisticated prototype stealth fighter created yet, is stolen from the U.S. government, one of the United States' top spies, Alex Scott, is called to action. What he doesn't expect is to get teamed up with a cocky civilian, World Class Boxing Champion Kelly Robinson, on a dangerous top secret espionage mission. Their assignment: using equal parts skill and humor, catch Arnold Gundars, one of the world's most successful arms dealers.\",\n \"When \\\"street smart\\\" rapper Christopher \\\"C-Note\\\" Hawkins (Big Boi) applies for a membership to all-white Carolina Pines Country Club, the establishment's proprietors are hardly ready to oblige him.\",\n \"As their first year of high school looms ahead, best friends Julie, Hannah, Yancy and Farrah have one last summer sleepover. Little do they know they're about to embark on the adventure of a lifetime. Desperate to shed their nerdy status, they take part in a night-long scavenger hunt that pits them against their popular archrivals. Everything under the sun goes on -- from taking Yancy's father's car to sneaking into nightclubs!\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"popularity\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 31.816649749537806,\n \"min\": 0.0,\n \"max\": 875.581305,\n \"num_unique_values\": 4802,\n \"samples\": [\n 13.267631,\n 0.010909,\n 5.842299\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"production_companies\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 3697,\n \"samples\": [\n \"[{\\\"name\\\": \\\"Paramount Pictures\\\", \\\"id\\\": 4}, {\\\"name\\\": \\\"Cherry Alley Productions\\\", \\\"id\\\": 2232}]\",\n \"[{\\\"name\\\": \\\"Twentieth Century Fox Film Corporation\\\", \\\"id\\\": 306}, {\\\"name\\\": \\\"Dune Entertainment\\\", \\\"id\\\": 444}, {\\\"name\\\": \\\"Regency Enterprises\\\", \\\"id\\\": 508}, {\\\"name\\\": \\\"Guy Walks into a Bar Productions\\\", \\\"id\\\": 2645}, {\\\"name\\\": \\\"Deep River Productions\\\", \\\"id\\\": 2646}, {\\\"name\\\": \\\"Friendly Films (II)\\\", \\\"id\\\": 81136}]\",\n \"[{\\\"name\\\": \\\"Twentieth Century Fox Film Corporation\\\", \\\"id\\\": 306}]\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"production_countries\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 469,\n \"samples\": [\n \"[{\\\"iso_3166_1\\\": \\\"ES\\\", \\\"name\\\": \\\"Spain\\\"}, {\\\"iso_3166_1\\\": \\\"GB\\\", \\\"name\\\": \\\"United Kingdom\\\"}, {\\\"iso_3166_1\\\": \\\"US\\\", \\\"name\\\": \\\"United States of America\\\"}, {\\\"iso_3166_1\\\": \\\"FR\\\", \\\"name\\\": \\\"France\\\"}]\",\n \"[{\\\"iso_3166_1\\\": \\\"US\\\", \\\"name\\\": \\\"United States of America\\\"}, {\\\"iso_3166_1\\\": \\\"CA\\\", \\\"name\\\": \\\"Canada\\\"}, {\\\"iso_3166_1\\\": \\\"DE\\\", \\\"name\\\": \\\"Germany\\\"}]\",\n \"[{\\\"iso_3166_1\\\": \\\"DE\\\", \\\"name\\\": \\\"Germany\\\"}, {\\\"iso_3166_1\\\": \\\"ES\\\", \\\"name\\\": \\\"Spain\\\"}, {\\\"iso_3166_1\\\": \\\"GB\\\", \\\"name\\\": \\\"United Kingdom\\\"}, {\\\"iso_3166_1\\\": \\\"US\\\", \\\"name\\\": \\\"United States of America\\\"}]\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"release_date\",\n \"properties\": {\n \"dtype\": \"object\",\n \"num_unique_values\": 3280,\n \"samples\": [\n \"1966-10-16\",\n \"1987-07-31\",\n \"1993-09-23\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"revenue\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 162857100,\n \"min\": 0,\n \"max\": 2787965087,\n \"num_unique_values\": 3297,\n \"samples\": [\n 11833696,\n 10462500,\n 17807569\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"runtime\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 22.611934588844207,\n \"min\": 0.0,\n \"max\": 338.0,\n \"num_unique_values\": 156,\n \"samples\": [\n 74.0,\n 85.0,\n 170.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"spoken_languages\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 544,\n \"samples\": [\n \"[{\\\"iso_639_1\\\": \\\"es\\\", \\\"name\\\": \\\"Espa\\\\u00f1ol\\\"}, {\\\"iso_639_1\\\": \\\"en\\\", \\\"name\\\": \\\"English\\\"}, {\\\"iso_639_1\\\": \\\"fr\\\", \\\"name\\\": \\\"Fran\\\\u00e7ais\\\"}, {\\\"iso_639_1\\\": \\\"hu\\\", \\\"name\\\": \\\"Magyar\\\"}]\",\n \"[{\\\"iso_639_1\\\": \\\"en\\\", \\\"name\\\": \\\"English\\\"}, {\\\"iso_639_1\\\": \\\"it\\\", \\\"name\\\": \\\"Italiano\\\"}, {\\\"iso_639_1\\\": \\\"pt\\\", \\\"name\\\": \\\"Portugu\\\\u00eas\\\"}]\",\n \"[{\\\"iso_639_1\\\": \\\"de\\\", \\\"name\\\": \\\"Deutsch\\\"}, {\\\"iso_639_1\\\": \\\"it\\\", \\\"name\\\": \\\"Italiano\\\"}, {\\\"iso_639_1\\\": \\\"la\\\", \\\"name\\\": \\\"Latin\\\"}, {\\\"iso_639_1\\\": \\\"pl\\\", \\\"name\\\": \\\"Polski\\\"}]\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"status\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Released\",\n \"Post Production\",\n \"Rumored\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"tagline\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 3944,\n \"samples\": [\n \"When you're 17, every day is war.\",\n \"An Unspeakable Horror. A Creative Genius. Captured For Eternity.\",\n \"May the schwartz be with you\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 4800,\n \"samples\": [\n \"I Spy\",\n \"Who's Your Caddy?\",\n \"Sleepover\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"vote_average\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.1946121628478925,\n \"min\": 0.0,\n \"max\": 10.0,\n \"num_unique_values\": 71,\n \"samples\": [\n 5.1,\n 7.2,\n 4.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"vote_count\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1234,\n \"min\": 0,\n \"max\": 13752,\n \"num_unique_values\": 1609,\n \"samples\": [\n 7604,\n 3428,\n 225\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 1 + } + ], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import warnings; warnings.filterwarnings('ignore')\n", + "\n", + "from google.colab import drive\n", + "drive.mount('/content/drive')\n", + "\n", + "movies =pd.read_csv('/content/drive/MyDrive/EuronData/tmdb_5000_movies.csv')\n", + "print(movies.shape)\n", + "movies.head(1)" + ] + }, + { + "cell_type": "code", + "source": [ + "movies_df = movies[['id','title', 'genres', 'vote_average', 'vote_count',\n", + " 'popularity', 'keywords', 'overview']]" + ], + "metadata": { + "id": "PUWd89RbXFiT" + }, + "execution_count": 2, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "pd.set_option('max_colwidth', 100)\n", + "movies_df[['genres','keywords']][:1]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 + }, + "id": "WWYzVMlaXFkE", + "outputId": "be1f3de8-f877-43e4-e398-0fc4034740d8" + }, + "execution_count": 3, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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... " + ], + "text/html": [ + "\n", + "
\n", + "
\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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"movies_df[['genres','keywords']][:1]\",\n \"rows\": 1,\n \"fields\": [\n {\n \"column\": \"genres\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 1,\n \"samples\": [\n \"[{\\\"id\\\": 28, \\\"name\\\": \\\"Action\\\"}, {\\\"id\\\": 12, \\\"name\\\": \\\"Adventure\\\"}, {\\\"id\\\": 14, \\\"name\\\": \\\"Fantasy\\\"}, {\\\"id\\\": 878, \\\"name\\\": \\\"Science Fiction\\\"}]\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"keywords\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 1,\n \"samples\": [\n \"[{\\\"id\\\": 1463, \\\"name\\\": \\\"culture clash\\\"}, {\\\"id\\\": 2964, \\\"name\\\": \\\"future\\\"}, {\\\"id\\\": 3386, \\\"name\\\": \\\"space war\\\"}, {\\\"id\\\": 3388, \\\"name\\\": \\\"space colony\\\"}, {\\\"id\\\": 3679, \\\"name\\\": \\\"society\\\"}, {\\\"id\\\": 3801, \\\"name\\\": \\\"space travel\\\"}, {\\\"id\\\": 9685, \\\"name\\\": \\\"futuristic\\\"}, {\\\"id\\\": 9840, \\\"name\\\": \\\"romance\\\"}, {\\\"id\\\": 9882, \\\"name\\\": \\\"space\\\"}, {\\\"id\\\": 9951, \\\"name\\\": \\\"alien\\\"}, {\\\"id\\\": 10148, \\\"name\\\": \\\"tribe\\\"}, {\\\"id\\\": 10158, \\\"name\\\": \\\"alien planet\\\"}, {\\\"id\\\": 10987, \\\"name\\\": \\\"cgi\\\"}, {\\\"id\\\": 11399, \\\"name\\\": \\\"marine\\\"}, {\\\"id\\\": 13065, \\\"name\\\": \\\"soldier\\\"}, {\\\"id\\\": 14643, \\\"name\\\": \\\"battle\\\"}, {\\\"id\\\": 14720, \\\"name\\\": \\\"love affair\\\"}, {\\\"id\\\": 165431, \\\"name\\\": \\\"anti war\\\"}, {\\\"id\\\": 193554, \\\"name\\\": \\\"power relations\\\"}, {\\\"id\\\": 206690, \\\"name\\\": \\\"mind and soul\\\"}, {\\\"id\\\": 209714, \\\"name\\\": \\\"3d\\\"}]\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 3 + } + ] + }, + { + "cell_type": "code", + "source": [ + "from ast import literal_eval\n", + "\n", + "movies_df['genres'] = movies_df['genres'].apply(literal_eval)\n", + "movies_df['keywords'] = movies_df['keywords'].apply(literal_eval)" + ], + "metadata": { + "id": "j635wiV5XFoe" + }, + "execution_count": 4, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "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]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 80 + }, + "id": "wbg8knAoXFrW", + "outputId": "208b8782-d32c-43d9-e399-fd08e2b2dbaa" + }, + "execution_count": 5, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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... " + ], + "text/html": [ + "\n", + "
\n", + "
\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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"movies_df[['genres', 'keywords']][:1]\",\n \"rows\": 1,\n \"fields\": [\n {\n \"column\": \"genres\",\n \"properties\": {\n \"dtype\": \"object\",\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"keywords\",\n \"properties\": {\n \"dtype\": \"object\",\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 5 + } + ] + }, + { + "cell_type": "code", + "source": [ + "from sklearn.feature_extraction.text import CountVectorizer\n", + "\n", + "# CountVectorizer를 적용하기 위해 공백문자로 word 단위가 구분되는 문자열로 변환.\n", + "movies_df['genres_literal'] = movies_df['genres'].apply(lambda x : (' ').join(x))\n", + "count_vect = CountVectorizer(min_df=1, ngram_range=(1,2))\n", + "genre_mat = count_vect.fit_transform(movies_df['genres_literal'])\n", + "print(genre_mat.shape)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Si5l0QYOXFtK", + "outputId": "08e2d7a4-0eb2-4cd1-a94c-1370f446d7c3" + }, + "execution_count": 9, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "(4803, 276)\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "from sklearn.metrics.pairwise import cosine_similarity\n", + "\n", + "genre_sim = cosine_similarity(genre_mat, genre_mat)\n", + "print(genre_sim.shape)\n", + "print(genre_sim[:2])" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "S685NhMKXFvT", + "outputId": "0d26161d-f056-499b-c7de-d3ed1c0bfcd7" + }, + "execution_count": 10, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "(4803, 4803)\n", + "[[1. 0.59628479 0.4472136 ... 0. 0. 0. ]\n", + " [0.59628479 1. 0.4 ... 0. 0. 0. ]]\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "genre_sim_sorted_ind = genre_sim.argsort()[:, ::-1]\n", + "print(genre_sim_sorted_ind[:1])" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "5fxh6N1NXuYE", + "outputId": "06e2bbcd-38d5-4e71-b248-2c997c7e58a0" + }, + "execution_count": 11, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "[[ 0 46 3494 ... 3331 3333 2031]]\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "def find_sim_movie(df, sorted_ind, title_name, top_n=10):\n", + "\n", + " # 인자로 입력된 movies_df DataFrame에서 'title' 컬럼이 입력된 title_name 값인 DataFrame추출\n", + " title_movie = df[df['title'] == title_name]\n", + "\n", + " # title_named을 가진 DataFrame의 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 index들 출력. top_n index는 2차원 데이터 임.\n", + " #dataframe에서 index로 사용하기 위해서 1차원 array로 변경\n", + " print(similar_indexes)\n", + " similar_indexes = similar_indexes.reshape(-1)\n", + "\n", + " return df.iloc[similar_indexes]" + ], + "metadata": { + "id": "2ARQWP9YXuaM" + }, + "execution_count": 12, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "similar_movies = find_sim_movie(movies_df, genre_sim_sorted_ind, 'The Godfather',10)\n", + "similar_movies[['title', 'vote_average']]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 376 + }, + "id": "YoZDG0OBXuca", + "outputId": "9b36480d-afc0-4808-815a-7c9f89c11316" + }, + "execution_count": 13, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "[[1881 3378 3866 1370 1464 588 3887 3594 2839 892]]\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " title vote_average\n", + "1881 The Shawshank Redemption 8.5\n", + "3378 Auto Focus 6.1\n", + "3866 City of God 8.1\n", + "1370 21 6.5\n", + "1464 Black Water Transit 0.0\n", + "588 Wall Street: Money Never Sleeps 5.8\n", + "3887 Trainspotting 7.8\n", + "3594 Spring Breakers 5.0\n", + "2839 Rounders 6.9\n", + "892 Casino 7.8" + ], + "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", + "
titlevote_average
1881The Shawshank Redemption8.5
3378Auto Focus6.1
3866City of God8.1
1370216.5
1464Black Water Transit0.0
588Wall Street: Money Never Sleeps5.8
3887Trainspotting7.8
3594Spring Breakers5.0
2839Rounders6.9
892Casino7.8
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"similar_movies[['title', 'vote_average']]\",\n \"rows\": 10,\n \"fields\": [\n {\n \"column\": \"title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 10,\n \"samples\": [\n \"Rounders\",\n \"Auto Focus\",\n \"Wall Street: Money Never Sleeps\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"vote_average\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.4636242498490803,\n \"min\": 0.0,\n \"max\": 8.5,\n \"num_unique_values\": 9,\n \"samples\": [\n 5.0,\n 6.1,\n 5.8\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 13 + } + ] + }, + { + "cell_type": "code", + "source": [ + "movies_df[['title','vote_average','vote_count']].sort_values('vote_average', ascending=False)[:10]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 359 + }, + "id": "oZCUklPEXueH", + "outputId": "4056e20b-41fc-4b8c-ba83-49450ca15654" + }, + "execution_count": 14, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " title vote_average vote_count\n", + "4662 Little Big Top 10.0 1\n", + "3519 Stiff Upper Lips 10.0 1\n", + "4045 Dancer, Texas Pop. 81 10.0 1\n", + "4247 Me You and Five Bucks 10.0 2\n", + "3992 Sardaarji 9.5 2\n", + "2386 One Man's Hero 9.3 2\n", + "1881 The Shawshank Redemption 8.5 8205\n", + "2970 There Goes My Baby 8.5 2\n", + "3337 The Godfather 8.4 5893\n", + "2796 The Prisoner of Zenda 8.4 11" + ], + "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", + "
titlevote_averagevote_count
4662Little Big Top10.01
3519Stiff Upper Lips10.01
4045Dancer, Texas Pop. 8110.01
4247Me You and Five Bucks10.02
3992Sardaarji9.52
2386One Man's Hero9.32
1881The Shawshank Redemption8.58205
2970There Goes My Baby8.52
3337The Godfather8.45893
2796The Prisoner of Zenda8.411
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"movies_df[['title','vote_average','vote_count']]\",\n \"rows\": 10,\n \"fields\": [\n {\n \"column\": \"title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 10,\n \"samples\": [\n \"The Godfather\",\n \"Stiff Upper Lips\",\n \"One Man's Hero\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"vote_average\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.7366591251499343,\n \"min\": 8.4,\n \"max\": 10.0,\n \"num_unique_values\": 5,\n \"samples\": [\n 9.5,\n 8.4,\n 9.3\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"vote_count\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 3020,\n \"min\": 1,\n \"max\": 8205,\n \"num_unique_values\": 5,\n \"samples\": [\n 2,\n 11,\n 8205\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 14 + } + ] + }, + { + "cell_type": "code", + "source": [ + "C = movies_df['vote_average'].mean()\n", + "m = movies_df['vote_count'].quantile(0.6)\n", + "print('C:',round(C,3), 'm:',round(m,3))" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "jB76jZ1FXufw", + "outputId": "d03210de-63a8-4307-9ebd-80719bb440dd" + }, + "execution_count": 15, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "C: 6.092 m: 370.2\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "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)" + ], + "metadata": { + "id": "F134wuhmXuid" + }, + "execution_count": 16, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "movies_df[['title','vote_average','weighted_vote','vote_count']].sort_values('weighted_vote', ascending=False)[:10]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 359 + }, + "id": "8dQ99Ld4XukQ", + "outputId": "9cb5f073-4fd7-4f06-e429-f36573c9e6cf" + }, + "execution_count": 17, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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" + ], + "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", + "
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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"movies_df[['title','vote_average','weighted_vote','vote_count']]\",\n \"rows\": 10,\n \"fields\": [\n {\n \"column\": \"title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 10,\n \"samples\": [\n \"Spirited Away\",\n \"The Godfather\",\n \"Schindler's List\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"vote_average\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.08755950357709151,\n \"min\": 8.2,\n \"max\": 8.5,\n \"num_unique_values\": 4,\n \"samples\": [\n 8.4,\n 8.2,\n 8.5\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"weighted_vote\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.09696608479450805,\n \"min\": 8.07958629828635,\n \"max\": 8.39605162693645,\n \"num_unique_values\": 10,\n \"samples\": [\n 8.105867158639835,\n 8.263590802034972,\n 8.126068673669016\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"vote_count\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2866,\n \"min\": 3338,\n \"max\": 12002,\n \"num_unique_values\": 10,\n \"samples\": [\n 3840,\n 5893,\n 4329\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 17 + } + ] + }, + { + "cell_type": "code", + "source": [ + "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 index 추출\n", + " similar_indexes = sorted_ind[title_index, :(top_n*2)]\n", + " similar_indexes = similar_indexes.reshape(-1)\n", + "# 기준 영화 index는 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']]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 359 + }, + "id": "ER_Do16XYdOw", + "outputId": "f1788bab-827f-41d1-884b-50a0e48ba798" + }, + "execution_count": 18, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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", + "3887 Trainspotting 7.8 7.591009\n", + "883 Catch Me If You Can 7.7 7.557097\n", + "892 Casino 7.8 7.423040\n", + "4041 This Is England 7.4 6.739664\n", + "1149 American Hustle 6.8 6.717525" + ], + "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", + "
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
3887Trainspotting7.87.591009
883Catch Me If You Can7.77.557097
892Casino7.87.423040
4041This Is England7.46.739664
1149American Hustle6.86.717525
\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "summary": "{\n \"name\": \"similar_movies[['title', 'vote_average', 'weighted_vote']]\",\n \"rows\": 10,\n \"fields\": [\n {\n \"column\": \"title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 10,\n \"samples\": [\n \"This Is England\",\n \"The Godfather: Part II\",\n \"Trainspotting\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"vote_average\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.5006662228138289,\n \"min\": 6.8,\n \"max\": 8.5,\n \"num_unique_values\": 8,\n \"samples\": [\n 8.3,\n 7.7,\n 8.5\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"weighted_vote\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.5360110086094774,\n \"min\": 6.717525466229835,\n \"max\": 8.39605162693645,\n \"num_unique_values\": 10,\n \"samples\": [\n 6.739664363482589,\n 8.07958629828635,\n 7.591009490713154\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 18 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## **9.6 아이템 기반 최근접 이웃 협업 필터링 실습**" + ], + "metadata": { + "id": "OjzVQqRyYkVt" + } + }, + { + "cell_type": "code", + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "\n", + "movies = pd.read_csv('/content/drive/MyDrive/EuronData/ml-latest-small/movies.csv')\n", + "ratings = pd.read_csv('/content/drive/MyDrive/EuronData/ml-latest-small/ratings.csv')\n", + "print(movies.shape)\n", + "print(ratings.shape)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "RSslMSKTYdRm", + "outputId": "e656d388-9e19-4b40-e244-a185b219d54c" + }, + "execution_count": 19, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "(9742, 3)\n", + "(100836, 4)\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "ratings = ratings[['userId', 'movieId', 'rating']]\n", + "ratings_matrix = ratings.pivot_table('rating', index='userId', columns='movieId')\n", + "ratings_matrix.head(3)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 202 + }, + "id": "hX8HmhGmYdTq", + "outputId": "3b1c8b04-34cc-4fe4-be02-31ca49d169a5" + }, + "execution_count": 20, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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]" + ], + "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", + " \n", + " \n", + "
movieId12345678910...193565193567193571193573193579193581193583193585193587193609
userId
14.0NaN4.0NaNNaN4.0NaNNaNNaNNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
2NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
3NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN...NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN
\n", + "

3 rows × 9724 columns

\n", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "ratings_matrix" + } + }, + "metadata": {}, + "execution_count": 20 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# title 칼럼을 얻기 이해 movies와 조인\n", + "rating_movies = pd.merge(ratings, movies, on='movieId')\n", + "\n", + "# columns='title'로 title 칼럼으로 피벗 수행.\n", + "ratings_matrix = rating_movies.pivot_table('rating', index='userId', columns='title')\n", + "\n", + "# NaN 값을 모두 0 으로 변환\n", + "ratings_matrix = ratings_matrix.fillna(0)\n", + "ratings_matrix.head(3)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 341 + }, + "id": "48tkyyNoZ_-D", + "outputId": "99dcd7f9-026b-4cdf-9735-dbddb406df14" + }, + "execution_count": 21, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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]" + ], + "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", + " \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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "ratings_matrix" + } + }, + "metadata": {}, + "execution_count": 21 + } + ] + }, + { + "cell_type": "code", + "source": [ + "ratings_matrix_T = ratings_matrix.transpose()\n", + "ratings_matrix_T.head(3)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 202 + }, + "id": "bL2ltz42aAAw", + "outputId": "12e8b569-8afb-4ec3-e9b9-15845726c0c6" + }, + "execution_count": 22, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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]" + ], + "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", + " \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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "ratings_matrix_T" + } + }, + "metadata": {}, + "execution_count": 22 + } + ] + }, + { + "cell_type": "code", + "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 DataFrame으로 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)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 477 + }, + "id": "hH-dajHRaAD_", + "outputId": "76ed1d5a-1183-46e3-f5cd-0e1f92391250" + }, + "execution_count": 23, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "(9719, 9719)\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "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]" + ], + "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", + " \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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "item_sim_df" + } + }, + "metadata": {}, + "execution_count": 23 + } + ] + }, + { + "cell_type": "code", + "source": [ + "item_sim_df[\"Godfather, The (1972)\"].sort_values(ascending=False)[:6]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "id": "D-QQjTSUaAGb", + "outputId": "662a54eb-226b-4a70-cb85-0d8739257bcc" + }, + "execution_count": 24, + "outputs": [ + { + "output_type": "execute_result", + "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" + ], + "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", + "
Godfather, The (1972)
title
Godfather, The (1972)1.000000
Godfather: Part II, The (1974)0.821773
Goodfellas (1990)0.664841
One Flew Over the Cuckoo's Nest (1975)0.620536
Star Wars: Episode IV - A New Hope (1977)0.595317
Fargo (1996)0.588614
\n", + "

" + ] + }, + "metadata": {}, + "execution_count": 24 + } + ] + }, + { + "cell_type": "code", + "source": [ + "item_sim_df[\"Inception (2010)\"].sort_values(ascending=False)[1:6]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 269 + }, + "id": "CiBCp4CLaAJC", + "outputId": "244fc3c5-07fb-4408-cb9e-cfff917962a5" + }, + "execution_count": 25, + "outputs": [ + { + "output_type": "execute_result", + "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" + ], + "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", + "
Inception (2010)
title
Dark Knight, The (2008)0.727263
Inglourious Basterds (2009)0.646103
Shutter Island (2010)0.617736
Dark Knight Rises, The (2012)0.617504
Fight Club (1999)0.615417
\n", + "

" + ] + }, + "metadata": {}, + "execution_count": 25 + } + ] + }, + { + "cell_type": "code", + "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" + ], + "metadata": { + "id": "CQ_3unwUaALb" + }, + "execution_count": 26, + "outputs": [] + }, + { + "cell_type": "code", + "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)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 341 + }, + "id": "-kP9EacoYdX4", + "outputId": "559ffabb-bcde-4b1e-d2e3-0e9acfc3c789" + }, + "execution_count": 27, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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]" + ], + "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", + " \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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "ratings_pred_matrix" + } + }, + "metadata": {}, + "execution_count": 27 + } + ] + }, + { + "cell_type": "code", + "source": [ + "from sklearn.metrics import mean_squared_error\n", + "\n", + "# 사용자가 평점을 부여한 영화에 대해서만 예측 성능 평가 MSE 를 구함.\n", + "def get_mse(pred, actual):\n", + " # Ignore nonzero terms.\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 ))" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "HaUjBk43XF0J", + "outputId": "7dcd83c7-dc28-44fd-a053-21c5866d21a5" + }, + "execution_count": 28, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "아이템 기반 모든 인접 이웃 MSE: 9.895354759094706\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "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 Loop 수행.\n", + " for col in range(ratings_arr.shape[1]):\n", + " # 유사도 행렬에서 유사도가 큰 순으로 n개 데이터 행렬의 index 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" + ], + "metadata": { + "id": "AL6_EsLFa5Ly" + }, + "execution_count": 29, + "outputs": [] + }, + { + "cell_type": "code", + "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)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "feqq90iia5RK", + "outputId": "f9193e98-ce8e-4f44-e4ef-24c44d4498b7" + }, + "execution_count": 30, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/tmp/ipython-input-29-2394360531.py:11: DeprecationWarning: Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)\n", + " pred[row, col] = item_sim_arr[col, :][top_n_items].dot(ratings_arr[row, :][top_n_items].T)\n" + ] + }, + { + "output_type": "stream", + "name": "stdout", + "text": [ + "아이템 기반 인접 TOP-20 이웃 MSE: 3.694409449382562\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "user_rating_id = ratings_matrix.loc[9, :]\n", + "user_rating_id[ user_rating_id > 0].sort_values(ascending=False)[:10]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 424 + }, + "id": "23Fg406qa5VG", + "outputId": "e537b055-2236-49c1-a934-7275a31d09ec" + }, + "execution_count": 31, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "title\n", + "Adaptation (2002) 5.0\n", + "Austin Powers in Goldmember (2002) 5.0\n", + "Back to the Future (1985) 5.0\n", + "Citizen Kane (1941) 5.0\n", + "Lord of the Rings: The Fellowship of the Ring, The (2001) 5.0\n", + "Lord of the Rings: The Two Towers, The (2002) 5.0\n", + "Producers, The (1968) 5.0\n", + "Raiders of the Lost Ark (Indiana Jones and the Raiders of the Lost Ark) (1981) 5.0\n", + "Elling (2001) 4.0\n", + "King of Comedy, The (1983) 4.0\n", + "Name: 9, dtype: float64" + ], + "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", + "
9
title
Adaptation (2002)5.0
Austin Powers in Goldmember (2002)5.0
Back to the Future (1985)5.0
Citizen Kane (1941)5.0
Lord of the Rings: The Fellowship of the Ring, The (2001)5.0
Lord of the Rings: The Two Towers, The (2002)5.0
Producers, The (1968)5.0
Raiders of the Lost Ark (Indiana Jones and the Raiders of the Lost Ark) (1981)5.0
Elling (2001)4.0
King of Comedy, The (1983)4.0
\n", + "

" + ] + }, + "metadata": {}, + "execution_count": 31 + } + ] + }, + { + "cell_type": "code", + "source": [ + "def get_unseen_movies(ratings_matrix, userId):\n", + " # userId로 입력받은 사용자의 모든 영화정보 추출하여 Series로 반환함.\n", + " # 반환된 user_rating 은 영화명(title)을 index로 가지는 Series 객체임.\n", + " user_rating = ratings_matrix.loc[userId,:]\n", + "\n", + " # user_rating이 0보다 크면 기존에 관람한 영화임. 대상 index를 추출하여 list 객체로 만듬\n", + " already_seen = user_rating[ user_rating > 0].index.tolist()\n", + "\n", + " # 모든 영화명을 list 객체로 만듬.\n", + " movies_list = ratings_matrix.columns.tolist()\n", + "\n", + " # list comprehension으로 already_seen에 해당하는 movie는 movies_list에서 제외함.\n", + " unseen_list = [ movie for movie in movies_list if movie not in already_seen]\n", + "\n", + " return unseen_list" + ], + "metadata": { + "id": "K8AkRRp8a5Yk" + }, + "execution_count": 32, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "def recomm_movie_by_userid(pred_df, userId, unseen_list, top_n=10):\n", + " # 예측 평점 DataFrame에서 사용자id index와 unseen_list로 들어온 영화명 컬럼을 추출하여\n", + " # 가장 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 데이타를 DataFrame으로 생성.\n", + "recomm_movies = pd.DataFrame(data=recomm_movies.values,index=recomm_movies.index,columns=['pred_score'])\n", + "recomm_movies" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 390 + }, + "id": "QKPMUOxea5b8", + "outputId": "d6dc5912-66f2-447b-ae8e-aeff9b778eac" + }, + "execution_count": 33, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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" + ], + "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", + "
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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + " \n", + " \n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "recomm_movies", + "summary": "{\n \"name\": \"recomm_movies\",\n \"rows\": 10,\n \"fields\": [\n {\n \"column\": \"title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 10,\n \"samples\": [\n \"Pirates of the Caribbean: The Curse of the Black Pearl (2003)\",\n \"Spider-Man (2002)\",\n \"Harry Potter and the Sorcerer's Stone (a.k.a. Harry Potter and the Philosopher's Stone) (2001)\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"pred_score\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.06614432811511851,\n \"min\": 0.6767108283499336,\n \"max\": 0.8662018746933645,\n \"num_unique_values\": 10,\n \"samples\": [\n 0.6895905595608812,\n 0.8578535950426878,\n 0.7651586070058114\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 33 + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## **9.7 행렬 분해를 이용한 잠재 요인 협업 필터링 실습**" + ], + "metadata": { + "id": "g-F-u3PGbo5_" + } + }, + { + "cell_type": "code", + "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", + " # 두개의 분해된 행렬 P와 Q.T의 내적 곱으로 예측 R 행렬 생성\n", + " full_pred_matrix = np.dot(P, Q.T)\n", + "\n", + " # 실제 R 행렬에서 널이 아닌 값의 위치 인덱스 추출하여 실제 R 행렬과 예측 행렬의 RMSE 추출\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" + ], + "metadata": { + "id": "MY2kI8aka5fS" + }, + "execution_count": 37, + "outputs": [] + }, + { + "cell_type": "code", + "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 정규분포를 가진 랜덤한 값으로 입력합니다.\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 > 0 인 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", + " # SGD기법으로 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", + " # Regularization을 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" + ], + "metadata": { + "id": "hx1MGUGda5kQ" + }, + "execution_count": 34, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "\n", + "movies = pd.read_csv('/content/drive/MyDrive/EuronData/ml-latest-small/movies.csv')\n", + "ratings = pd.read_csv('/content/drive/MyDrive/EuronData/ml-latest-small/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 movies 와 조인 수행\n", + "rating_movies = pd.merge(ratings, movies, on='movieId')\n", + "\n", + "# columns='title' 로 title 컬럼으로 pivot 수행.\n", + "ratings_matrix = rating_movies.pivot_table('rating', index='userId', columns='title')" + ], + "metadata": { + "id": "S3t1GJ9ra5qE" + }, + "execution_count": 35, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "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)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Hby-fB-fczVT", + "outputId": "09c17b2f-0e92-4cd1-afc0-be17f18910c5" + }, + "execution_count": 38, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "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 : 0.2068545530233154\n", + "### iteration step : 80 rmse : 0.19413418783028685\n", + "### iteration step : 90 rmse : 0.18470082002720406\n", + "### iteration step : 100 rmse : 0.17742927527209104\n", + "### iteration step : 110 rmse : 0.1716522696470749\n", + "### iteration step : 120 rmse : 0.16695181946871726\n", + "### iteration step : 130 rmse : 0.16305292191997542\n", + "### iteration step : 140 rmse : 0.15976691929679646\n", + "### iteration step : 150 rmse : 0.1569598699945732\n", + "### iteration step : 160 rmse : 0.15453398186715425\n", + "### iteration step : 170 rmse : 0.15241618551077643\n", + "### iteration step : 180 rmse : 0.1505508073962831\n", + "### iteration step : 190 rmse : 0.1488947091323209\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "ratings_pred_matrix = pd.DataFrame(data=pred_matrix, index= ratings_matrix.index, columns = ratings_matrix.columns)\n", + "ratings_pred_matrix.head(3)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 341 + }, + "id": "iwoG1CH0czbW", + "outputId": "f5f797cb-87c4-4f01-98c4-97132a41709a" + }, + "execution_count": 39, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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]" + ], + "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", + " \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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "ratings_pred_matrix" + } + }, + "metadata": {}, + "execution_count": 39 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# 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 데이타를 DataFrame으로 생성.\n", + "recomm_movies = pd.DataFrame(data=recomm_movies.values,index=recomm_movies.index,columns=['pred_score'])\n", + "recomm_movies" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 390 + }, + "id": "_RGN-MqDczgK", + "outputId": "346b7d6c-eeef-4e1e-8a0d-4f320b068e08" + }, + "execution_count": 40, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "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" + ], + "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", + "
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", + "
\n", + "
\n", + "\n", + "
\n", + " \n", + "\n", + " \n", + "\n", + " \n", + "
\n", + "\n", + "\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + " \n", + "
\n", + "\n", + "
\n", + " \n", + " \n", + " \n", + "
\n", + "\n", + "
\n", + "
\n" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "dataframe", + "variable_name": "recomm_movies", + "summary": "{\n \"name\": \"recomm_movies\",\n \"rows\": 10,\n \"fields\": [\n {\n \"column\": \"title\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 10,\n \"samples\": [\n \"Big Lebowski, The (1998)\",\n \"South Park: Bigger, Longer and Uncut (1999)\",\n \"Gattaca (1997)\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"pred_score\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.21272885538651393,\n \"min\": 4.989601238872484,\n \"max\": 5.704612469838172,\n \"num_unique_values\": 10,\n \"samples\": [\n 5.0386897288205725,\n 5.451100205772531,\n 5.183178550884765\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" + } + }, + "metadata": {}, + "execution_count": 40 + } + ] + } + ] +} \ No newline at end of file diff --git "a/Week16_\341\204\213\341\205\250\341\204\211\341\205\263\341\206\270\341\204\200\341\205\252\341\204\214\341\205\246_\341\204\200\341\205\265\341\206\267\341\204\211\341\205\245\341\204\213\341\205\247\341\206\253.ipynb" "b/Week16_\341\204\213\341\205\250\341\204\211\341\205\263\341\206\270\341\204\200\341\205\252\341\204\214\341\205\246_\341\204\200\341\205\265\341\206\267\341\204\211\341\205\245\341\204\213\341\205\247\341\206\253.ipynb" new file mode 100644 index 0000000..80b4edb --- /dev/null +++ "b/Week16_\341\204\213\341\205\250\341\204\211\341\205\263\341\206\270\341\204\200\341\205\252\341\204\214\341\205\246_\341\204\200\341\205\265\341\206\267\341\204\211\341\205\245\341\204\213\341\205\247\341\206\253.ipynb" @@ -0,0 +1,897 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "cells": [ + { + "cell_type": "markdown", + "source": [ + "## **9.4 확률적 경사하강법을 이용한 행렬분해**" + ], + "metadata": { + "id": "XVpQsZt1ZzFK" + } + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "id": "n29zZflu6eco" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "\n", + "# 원본 행렬 R 생성, 분해 행렬 P와 Q 초기화, 잠재요인 차원 K는 3 설정.\n", + "R = np.array([[4, np.nan, np.nan, 2, np.nan ],\n", + " [np.nan, 5, np.nan, 3, 1 ],\n", + " [np.nan, np.nan, 3, 4, 4 ],\n", + " [5, 2, 1, 2, np.nan ]])\n", + "num_users, num_items = R.shape\n", + "K=3\n", + "\n", + "# P와 Q 행렬의 크기를 지정하고 정규 분포를 가진 임의의 값으로 입력합니다.\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))" + ] + }, + { + "cell_type": "code", + "source": [ + "from sklearn.metrics import mean_squared_error\n", + "\n", + "def get_rmse(R, P, Q, non_zeros):\n", + " error = 0\n", + " # 두개의 분해된 행렬 P와 Q.T의 내적으로 예측 R 행렬 생성\n", + " full_pred_matrix = np.dot(P, Q.T)\n", + "\n", + " # 실제 R 행렬에서 널이 아닌 값의 위치 인덱스 추출하여 실제 R 행렬과 예측 행렬의 RMSE 추출\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", + " full_pred_matrix_non_zeros = full_pred_matrix[x_non_zero_ind, y_non_zero_ind]\n", + " mse = mean_squared_error(R_non_zeros, full_pred_matrix_non_zeros)\n", + " rmse = np.sqrt(mse)\n", + "\n", + " return rmse" + ], + "metadata": { + "id": "HCeaIAnlYoyE" + }, + "execution_count": 3, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "# R > 0 인 행 위치, 열 위치, 값을 non_zeros 리스트에 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", + "steps=1000\n", + "learning_rate=0.01\n", + "r_lambda=0.01\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", + " # Regularization을 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 % 50) == 0 :\n", + " print(\"### iteration step : \", step,\" rmse : \", rmse)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "Hunsa_qDYpGK", + "outputId": "51e912f7-be9a-474f-e530-4df6aa96736c" + }, + "execution_count": 4, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "### iteration step : 0 rmse : 3.2388050277987723\n", + "### iteration step : 50 rmse : 0.4876723101369648\n", + "### iteration step : 100 rmse : 0.1564340384819247\n", + "### iteration step : 150 rmse : 0.07455141311978046\n", + "### iteration step : 200 rmse : 0.04325226798579314\n", + "### iteration step : 250 rmse : 0.029248328780878973\n", + "### iteration step : 300 rmse : 0.022621116143829466\n", + "### iteration step : 350 rmse : 0.019493636196525135\n", + "### iteration step : 400 rmse : 0.018022719092132704\n", + "### iteration step : 450 rmse : 0.01731968595344266\n", + "### iteration step : 500 rmse : 0.016973657887570753\n", + "### iteration step : 550 rmse : 0.016796804595895633\n", + "### iteration step : 600 rmse : 0.01670132290188466\n", + "### iteration step : 650 rmse : 0.01664473691247669\n", + "### iteration step : 700 rmse : 0.016605910068210026\n", + "### iteration step : 750 rmse : 0.016574200475705\n", + "### iteration step : 800 rmse : 0.01654431582921597\n", + "### iteration step : 850 rmse : 0.01651375177473524\n", + "### iteration step : 900 rmse : 0.01648146573819501\n", + "### iteration step : 950 rmse : 0.016447171683479155\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "pred_matrix = np.dot(P, Q.T)\n", + "print('예측 행렬:\\n', np.round(pred_matrix, 3))" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "w5lHOo9qYpIW", + "outputId": "ce6307b0-57be-4263-b97a-14c00961e5a0" + }, + "execution_count": 5, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "예측 행렬:\n", + " [[3.991 0.897 1.306 2.002 1.663]\n", + " [6.696 4.978 0.979 2.981 1.003]\n", + " [6.677 0.391 2.987 3.977 3.986]\n", + " [4.968 2.005 1.006 2.017 1.14 ]]\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## **9.8 파이썬 추천 시스템 패키지 -- Surprise**" + ], + "metadata": { + "id": "vvakSXz7aLii" + } + }, + { + "cell_type": "code", + "source": [ + "!pip install scikit-surprise\n", + "\n", + "import surprise\n", + "print(surprise.__version__)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "EtnpP5ibYpKc", + "outputId": "ed6c1d37-0339-4eee-adc7-ef4e0d8cd139" + }, + "execution_count": 1, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Requirement already satisfied: scikit-surprise in /usr/local/lib/python3.11/dist-packages (1.1.4)\n", + "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from scikit-surprise) (1.5.1)\n", + "Requirement already satisfied: numpy>=1.19.5 in /usr/local/lib/python3.11/dist-packages (from scikit-surprise) (1.26.4)\n", + "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.11/dist-packages (from scikit-surprise) (1.15.3)\n", + "1.1.4\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "!pip uninstall -y numpy\n", + "\n", + "!pip install numpy==1.26.4" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 337 + }, + "id": "jLIxnIFceGTp", + "outputId": "def66ac6-da67-4ec9-db25-aec054ad214e" + }, + "execution_count": 7, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Found existing installation: numpy 2.0.2\n", + "Uninstalling numpy-2.0.2:\n", + " Successfully uninstalled numpy-2.0.2\n", + "Collecting numpy==1.26.4\n", + " Downloading numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (61 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.0/61.0 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hDownloading numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.3 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.3/18.3 MB\u001b[0m \u001b[31m89.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hInstalling collected packages: numpy\n", + "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", + "thinc 8.3.6 requires numpy<3.0.0,>=2.0.0, but you have numpy 1.26.4 which is incompatible.\u001b[0m\u001b[31m\n", + "\u001b[0mSuccessfully installed numpy-1.26.4\n" + ] + }, + { + "output_type": "display_data", + "data": { + "application/vnd.colab-display-data+json": { + "pip_warning": { + "packages": [ + "numpy" + ] + }, + "id": "877691c0bf694162b3604fd39caab693" + } + }, + "metadata": {} + } + ] + }, + { + "cell_type": "code", + "source": [ + "from surprise import SVD\n", + "from surprise import Dataset\n", + "from surprise import accuracy\n", + "from surprise.model_selection import train_test_split" + ], + "metadata": { + "id": "l82DEukjYpQO" + }, + "execution_count": 3, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "data = Dataset.load_builtin('ml-100k')\n", + "# 수행 시마다 동일하게 데이터를 분할하기 위해 random_state 값 부여\n", + "trainset, testset = train_test_split(data, test_size=.25, random_state=0)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "nSec7kS3YpXS", + "outputId": "7b2095fa-1826-4f21-8b02-9e199602acc6" + }, + "execution_count": 4, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Dataset ml-100k could not be found. Do you want to download it? [Y/n] Y\n", + "Trying to download dataset from https://files.grouplens.org/datasets/movielens/ml-100k.zip...\n", + "Done! Dataset ml-100k has been saved to /root/.surprise_data/ml-100k\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "algo = SVD(random_state=0)\n", + "algo.fit(trainset)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "dJ_URy4NemoY", + "outputId": "50799af3-3998-4b81-af27-6882e93c266b" + }, + "execution_count": 5, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "" + ] + }, + "metadata": {}, + "execution_count": 5 + } + ] + }, + { + "cell_type": "code", + "source": [ + "predictions = algo.test( testset )\n", + "print('prediction type :',type(predictions), ' size:',len(predictions))\n", + "print('prediction 결과의 최초 5개 추출')\n", + "predictions[:5]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "uL1QYvZIemqt", + "outputId": "20faaf33-ce0b-4fe9-ff4a-1d44020f617e" + }, + "execution_count": 6, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "prediction type : size: 25000\n", + "prediction 결과의 최초 5개 추출\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[Prediction(uid='120', iid='282', r_ui=4.0, est=3.5114147666251547, details={'was_impossible': False}),\n", + " Prediction(uid='882', iid='291', r_ui=4.0, est=3.573872419581491, details={'was_impossible': False}),\n", + " Prediction(uid='535', iid='507', r_ui=5.0, est=4.033583485472447, details={'was_impossible': False}),\n", + " Prediction(uid='697', iid='244', r_ui=5.0, est=3.8463639495936905, details={'was_impossible': False}),\n", + " Prediction(uid='751', iid='385', r_ui=4.0, est=3.1807542478219157, details={'was_impossible': False})]" + ] + }, + "metadata": {}, + "execution_count": 6 + } + ] + }, + { + "cell_type": "code", + "source": [ + "[ (pred.uid, pred.iid, pred.est) for pred in predictions[:3] ]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "tZ0js334emtP", + "outputId": "4c327268-b519-48f2-f694-a2858950e93b" + }, + "execution_count": 7, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "[('120', '282', 3.5114147666251547),\n", + " ('882', '291', 3.573872419581491),\n", + " ('535', '507', 4.033583485472447)]" + ] + }, + "metadata": {}, + "execution_count": 7 + } + ] + }, + { + "cell_type": "code", + "source": [ + "# 사용자 아이디, 아이템 아이디는 문자열로 입력해야 함.\n", + "uid = str(196)\n", + "iid = str(302)\n", + "pred = algo.predict(uid, iid)\n", + "print(pred)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "5ZjyHlJeemvI", + "outputId": "6ab5271f-3853-4b1b-9a0a-00cfae81b05d" + }, + "execution_count": 8, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "user: 196 item: 302 r_ui = None est = 4.49 {'was_impossible': False}\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "accuracy.rmse(predictions)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "SX_ywdr7fBqC", + "outputId": "19d964ee-ec1a-4b43-b3f7-f8d6c7501922" + }, + "execution_count": 9, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "RMSE: 0.9467\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "0.9466860806937948" + ] + }, + "metadata": {}, + "execution_count": 9 + } + ] + }, + { + "cell_type": "code", + "source": [ + "import pandas as pd\n", + "\n", + "from google.colab import drive\n", + "drive.mount('/content/drive')\n", + "\n", + "ratings = pd.read_csv('/content/drive/MyDrive/EuronData/ml-latest-small/ratings.csv')\n", + "# ratings_noh.csv 파일로 unload 시 index 와 header를 모두 제거한 새로운 파일 생성.\n", + "ratings.to_csv('/content/drive/MyDrive/EuronData/ml-latest-small/ratings_noh.csv', index=False, header=False)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "YJ6zKg9vfBt5", + "outputId": "22edf420-0a04-4e33-f13d-4870a84ce74f" + }, + "execution_count": 10, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "from surprise import Reader\n", + "\n", + "reader = Reader(line_format='user item rating timestamp', sep=',', rating_scale=(0.5, 5))\n", + "data=Dataset.load_from_file('/content/drive/MyDrive/EuronData/ml-latest-small/ratings_noh.csv',reader=reader)" + ], + "metadata": { + "id": "NseIa_z3fBv7" + }, + "execution_count": 12, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "trainset, testset = train_test_split(data, test_size=.25, random_state=0)\n", + "\n", + "# 수행시마다 동일한 결과 도출을 위해 random_state 설정\n", + "algo = SVD(n_factors=50, random_state=0)\n", + "\n", + "# 학습 데이터 세트로 학습 후 테스트 데이터 세트로 평점 예측 후 RMSE 평가\n", + "algo.fit(trainset)\n", + "predictions = algo.test( testset )\n", + "accuracy.rmse(predictions)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "a1vxm1pvfByD", + "outputId": "24ba6f7d-4e3b-419e-e767-c58664e6aaea" + }, + "execution_count": 13, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "RMSE: 0.8682\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "0.8681952927143516" + ] + }, + "metadata": {}, + "execution_count": 13 + } + ] + }, + { + "cell_type": "code", + "source": [ + "import pandas as pd\n", + "from surprise import Reader, Dataset\n", + "\n", + "ratings = pd.read_csv('/content/drive/MyDrive/EuronData/ml-latest-small/ratings.csv')\n", + "reader = Reader(rating_scale=(0.5, 5.0))\n", + "\n", + "# ratings DataFrame 에서 컬럼은 사용자 아이디, 아이템 아이디, 평점 순서를 지켜야 합니다.\n", + "data = Dataset.load_from_df(ratings[['userId', 'movieId', 'rating']], reader)\n", + "trainset, testset = train_test_split(data, test_size=.25, random_state=0)\n", + "\n", + "algo = SVD(n_factors=50, random_state=0)\n", + "algo.fit(trainset)\n", + "predictions = algo.test( testset )\n", + "accuracy.rmse(predictions)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "NaFJS0affB0Y", + "outputId": "5d4f7c51-7824-4ff1-ed6b-8ef15ab4b28d" + }, + "execution_count": 15, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "RMSE: 0.8682\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "0.8681952927143516" + ] + }, + "metadata": {}, + "execution_count": 15 + } + ] + }, + { + "cell_type": "code", + "source": [ + "from surprise.model_selection import cross_validate\n", + "\n", + "# 판다스 DataFrame에서 Surprise 데이터 세트로 데이터 로딩\n", + "ratings = pd.read_csv('/content/drive/MyDrive/EuronData/ml-latest-small/ratings.csv') # reading data in pandas df\n", + "reader = Reader(rating_scale=(0.5, 5.0))\n", + "data = Dataset.load_from_df(ratings[['userId', 'movieId', 'rating']], reader)\n", + "\n", + "algo = SVD(random_state=0)\n", + "cross_validate(algo, data, measures=['RMSE', 'MAE'], cv=5, verbose=True)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "5AQRJcBcfB2t", + "outputId": "4cfa12ee-0d9e-4ce0-df47-201670d5ee73" + }, + "execution_count": 17, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Evaluating RMSE, MAE of algorithm SVD on 5 split(s).\n", + "\n", + " Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Mean Std \n", + "RMSE (testset) 0.8778 0.8697 0.8688 0.8826 0.8646 0.8727 0.0065 \n", + "MAE (testset) 0.6764 0.6672 0.6694 0.6764 0.6660 0.6711 0.0045 \n", + "Fit time 2.41 1.38 1.74 1.35 1.47 1.67 0.40 \n", + "Test time 0.17 0.32 0.09 0.27 0.13 0.20 0.08 \n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "{'test_rmse': array([0.87781408, 0.86972885, 0.86881851, 0.88259044, 0.86455604]),\n", + " 'test_mae': array([0.67644946, 0.66721403, 0.66935152, 0.67643556, 0.6659921 ]),\n", + " 'fit_time': (2.4129509925842285,\n", + " 1.3790216445922852,\n", + " 1.7405798435211182,\n", + " 1.3522956371307373,\n", + " 1.4670145511627197),\n", + " 'test_time': (0.17442965507507324,\n", + " 0.31662940979003906,\n", + " 0.09467887878417969,\n", + " 0.27152299880981445,\n", + " 0.12813067436218262)}" + ] + }, + "metadata": {}, + "execution_count": 17 + } + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "id": "qoqwlsJBbcpX", + "outputId": "8e2f90ff-a0c8-44c8-e47d-81c33284f864", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "0.8763574308838056\n", + "{'n_epochs': 20, 'n_factors': 50}\n" + ] + } + ], + "source": [ + "from surprise.model_selection import GridSearchCV\n", + "\n", + "# 최적화할 파라미터를 딕셔너리 형태로 지정.\n", + "param_grid = {'n_epochs': [20, 40, 60], 'n_factors': [50, 100, 200] }\n", + "\n", + "# CV를 3개 폴드 세트로 지정, 성능 평가는 rmse, mse로 수행하도록 GridSearchCV 구성\n", + "gs = GridSearchCV(SVD, param_grid, measures=['rmse', 'mae'], cv=3)\n", + "gs.fit(data)\n", + "\n", + "# 최고 RMSE Evaluation 점수와 그때의 하이퍼 파라미터\n", + "print(gs.best_score['rmse'])\n", + "print(gs.best_params['rmse'])" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "scrolled": true, + "id": "cT64RqRObcpY", + "collapsed": true + }, + "outputs": [], + "source": [ + "# 다음 코드는 train_test_split( )으로 분리되지 않는 데이터 세트에 fit( )을 호출해 오류가 발생합니다.\n", + "data = Dataset.load_from_df(ratings[['userId', 'movieId', 'rating']], reader)\n", + "algo = SVD(n_factors=50, random_state=0)\n", + "algo.fit(data)\n", + "\n", + "-> TrainSet 클래스 객체로 변환하지 않으면 fit()을 통해 학습할 수가 없음" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "id": "Kk_bx3BRbcpY" + }, + "outputs": [], + "source": [ + "from surprise.dataset import DatasetAutoFolds\n", + "\n", + "reader = Reader(line_format='user item rating timestamp', sep=',', rating_scale=(0.5, 5))\n", + "# DatasetAutoFolds 클래스를 ratings_noh.csv 파일 기반으로 생성.\n", + "data_folds = DatasetAutoFolds(ratings_file='/content/drive/MyDrive/EuronData/ml-latest-small/ratings_noh.csv', reader=reader)\n", + "\n", + "#전체 데이터를 학습데이터로 생성함.\n", + "trainset = data_folds.build_full_trainset()" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "id": "X2mvTwzfbcpY", + "outputId": "1edfd17d-380e-4d33-edd1-c75767dcc05f", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "" + ] + }, + "metadata": {}, + "execution_count": 24 + } + ], + "source": [ + "algo = SVD(n_epochs=20, n_factors=50, random_state=0)\n", + "algo.fit(trainset)" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "id": "b1Q8sXfrbcpZ", + "outputId": "c6ef5bdc-30b8-4b99-92c2-d037b7298eec", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "사용자 아이디 9는 영화 아이디 42의 평점 없음\n", + " movieId title genres\n", + "38 42 Dead Presidents (1995) Action|Crime|Drama\n" + ] + } + ], + "source": [ + "# 영화에 대한 상세 속성 정보 DataFrame로딩\n", + "movies = pd.read_csv('/content/drive/MyDrive/EuronData/ml-latest-small/movies.csv')\n", + "\n", + "# userId=9 의 movieId 데이터 추출하여 movieId=42 데이터가 있는지 확인.\n", + "movieIds = ratings[ratings['userId']==9]['movieId']\n", + "if movieIds[movieIds==42].count() == 0:\n", + " print('사용자 아이디 9는 영화 아이디 42의 평점 없음')\n", + "\n", + "print(movies[movies['movieId']==42])" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": { + "id": "EVpvWdpcbcpZ", + "outputId": "dd396825-46a0-4373-f994-f7e7575c49ce", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "user: 9 item: 42 r_ui = None est = 3.13 {'was_impossible': False}\n" + ] + } + ], + "source": [ + "uid = str(9)\n", + "iid = str(42)\n", + "\n", + "pred = algo.predict(uid, iid, verbose=True)" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "id": "4wp3dcgabcpZ", + "outputId": "0ecd4c26-20d5-4467-fd55-6fe6fdf6d0f1", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "평점 매긴 영화수: 46 추천대상 영화수: 9696 전체 영화수: 9742\n" + ] + } + ], + "source": [ + "def get_unseen_surprise(ratings, movies, userId):\n", + " #입력값으로 들어온 userId에 해당하는 사용자가 평점을 매긴 모든 영화를 리스트로 생성\n", + " seen_movies = ratings[ratings['userId']== userId]['movieId'].tolist()\n", + "\n", + " # 모든 영화들의 movieId를 리스트로 생성.\n", + " total_movies = movies['movieId'].tolist()\n", + "\n", + " # 모든 영화들의 movieId중 이미 평점을 매긴 영화의 movieId를 제외하여 리스트로 생성\n", + " unseen_movies= [movie for movie in total_movies if movie not in seen_movies]\n", + " print('평점 매긴 영화수:',len(seen_movies), '추천대상 영화수:',len(unseen_movies), \\\n", + " '전체 영화수:',len(total_movies))\n", + "\n", + " return unseen_movies\n", + "\n", + "unseen_movies = get_unseen_surprise(ratings, movies, 9)" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "id": "Cs-6orCcbcpZ", + "outputId": "0f14852d-3487-40bc-8e11-135dfd0e3c65", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "평점 매긴 영화수: 46 추천대상 영화수: 9696 전체 영화수: 9742\n", + "##### Top-10 추천 영화 리스트 #####\n", + "Usual Suspects, The (1995) : 4.306302135700814\n", + "Star Wars: Episode IV - A New Hope (1977) : 4.281663842987387\n", + "Pulp Fiction (1994) : 4.278152632122759\n", + "Silence of the Lambs, The (1991) : 4.226073566460876\n", + "Godfather, The (1972) : 4.1918097904381995\n", + "Streetcar Named Desire, A (1951) : 4.154746591122657\n", + "Star Wars: Episode V - The Empire Strikes Back (1980) : 4.122016128534504\n", + "Star Wars: Episode VI - Return of the Jedi (1983) : 4.108009609093436\n", + "Goodfellas (1990) : 4.083464936588478\n", + "Glory (1989) : 4.07887165526957\n" + ] + } + ], + "source": [ + "def recomm_movie_by_surprise(algo, userId, unseen_movies, top_n=10):\n", + " # 알고리즘 객체의 predict() 메서드를 평점이 없는 영화에 반복 수행한 후 결과를 list 객체로 저장\n", + " predictions = [algo.predict(str(userId), str(movieId)) for movieId in unseen_movies]\n", + "\n", + " # predictions list 객체는 surprise의 Predictions 객체를 원소로 가지고 있음.\n", + " # [Prediction(uid='9', iid='1', est=3.69), Prediction(uid='9', iid='2', est=2.98),,,,]\n", + " # 이를 est 값으로 정렬하기 위해서 아래의 sortkey_est 함수를 정의함.\n", + " # sortkey_est 함수는 list 객체의 sort() 함수의 키 값으로 사용되어 정렬 수행.\n", + " def sortkey_est(pred):\n", + " return pred.est\n", + "\n", + " # sortkey_est( ) 반환값의 내림 차순으로 정렬 수행하고 top_n개의 최상위 값 추출.\n", + " predictions.sort(key=sortkey_est, reverse=True)\n", + " top_predictions= predictions[:top_n]\n", + "\n", + " # top_n으로 추출된 영화의 정보 추출. 영화 아이디, 추천 예상 평점, 제목 추출\n", + " top_movie_ids = [ int(pred.iid) for pred in top_predictions]\n", + " top_movie_rating = [ pred.est for pred in top_predictions]\n", + " top_movie_titles = movies[movies.movieId.isin(top_movie_ids)]['title']\n", + " top_movie_preds = [ (id, title, rating) for id, title, rating in zip(top_movie_ids, top_movie_titles, top_movie_rating)]\n", + "\n", + " return top_movie_preds\n", + "\n", + "unseen_movies = get_unseen_surprise(ratings, movies, 9)\n", + "top_movie_preds = recomm_movie_by_surprise(algo, 9, unseen_movies, top_n=10)\n", + "print('##### Top-10 추천 영화 리스트 #####')\n", + "\n", + "for top_movie in top_movie_preds:\n", + " print(top_movie[1], \":\", top_movie[2])" + ] + } + ] +} \ No newline at end of file diff --git "a/Week16_\341\204\213\341\205\250\341\204\211\341\205\263\341\206\270\341\204\200\341\205\252\341\204\214\341\205\246_\341\204\200\341\205\265\341\206\267\341\204\211\341\205\245\341\204\213\341\205\247\341\206\253.pdf" "b/Week16_\341\204\213\341\205\250\341\204\211\341\205\263\341\206\270\341\204\200\341\205\252\341\204\214\341\205\246_\341\204\200\341\205\265\341\206\267\341\204\211\341\205\245\341\204\213\341\205\247\341\206\253.pdf" new file mode 100644 index 0000000..c00ae19 Binary files /dev/null and "b/Week16_\341\204\213\341\205\250\341\204\211\341\205\263\341\206\270\341\204\200\341\205\252\341\204\214\341\205\246_\341\204\200\341\205\265\341\206\267\341\204\211\341\205\245\341\204\213\341\205\247\341\206\253.pdf" differ