Chapter 4 | 추천시스템¶

# ! apt-get update
# ! apt-get install g++ openjdk-8-jdk 
# ! pip3  install  nltk konlpy matplotlib gensim 

# ! apt-get install fonts-nanum-eco
# ! apt-get install fontconfig
# ! fc-cache -fv
# ! cp /usr/share/fonts/truetype/nanum/Nanum* /usr/local/lib/python3.6/dist-packages/matplotlib/mpl-data/fonts/ttf/
# ! rm -rf /content/.cache/matplotlib/*

import pandas as pd
movies = pd.read_csv('../data/movies_metadata.csv', usecols=['original_title', 'overview', 'title'], low_memory=False)
movies = movies.dropna(axis=0)
print(movies.shape)

movie_plot_li = movies['overview']
movie_info_li = movies['title']
movies.head(3)

from nltk.stem import WordNetLemmatizer
from nltk.tokenize import RegexpTokenizer

class LemmaTokenizer(object):
    def __init__(self):
        self.wnl       = WordNetLemmatizer()
        self.tokenizer = RegexpTokenizer('(?u)[A-z]+')
    
    def __call__(self, doc):  # 클래스 호출시 마다 실행(Tf-idf Vector 호출)
        return([self.wnl.lemmatize(t) for t in self.tokenizer.tokenize(doc)])

# 사이킷런에 위에서 정의한 토크나이저를 입력으로 넣습니다.
from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer   = TfidfVectorizer(min_df=3, tokenizer=LemmaTokenizer(), 
                               stop_words='english')
X            = vectorizer.fit_transform(movie_plot_li[:10000]) # 메모리 오류로 갯수를 제한
vocabluary   = vectorizer.get_feature_names()

# 비슷한 영화 추천하는 Cosin 유사모델 만들기
from sklearn.metrics.pairwise import cosine_similarity
movie_sim = cosine_similarity(X)
print(movie_sim.shape)
movie_sim

# 특정 영화와 유사한 영화목록 출력하기
def similar_recommend_by_movie_id(movielens_id, rank=8):
    movie_index    = movielens_id - 1
    similar_movies = sorted(list(enumerate(movie_sim[movie_index])), key=lambda x:x[1], reverse=True)
    print("----- {} : 관람객 추천영화 -------".format(movie_info_li[similar_movies[0][0]]))
    for no, movie_idx in enumerate(similar_movies[1:rank]):
        print('추천영화 {}순위 : {}'.format(no, movie_info_li[movie_idx[0]]))

similar_recommend_by_movie_id(1, rank=20)