인프런 커뮤니티 질문&답변

거친코딩님의 rating_matrix에선 943X1633이 나오는데 

제 코드 결과값에선 943X1643이 나옵니다 ㅠㅠ

#데이터 읽어오기(user, item, data)
base_src = 'drive/MyDrive/RecoSys/Data'
u_user_src = os.path.join(base_src,'u.user')
u_cols = ['user_id','age','sex','occupation','zip_code']
users = pd.read_csv(u_user_src,
                    sep='|',
                    names=u_cols,
                    encoding='latin-1')
u_item_src = os.path.join(base_src,'u.item')
i_cols = ['movie_id','title','release date','video release date',
          'IMDB URL','unknown','Action','Adventure','Animation',
          'Children\'s','Comedy','Crime','Documentary,','Drama','Fantasy',
          'FilmNoir','Horror','Musical','Mystery','Romance', 'Sci-Fi','Thriller','War','Western']
movies = pd.read_csv(u_item_src,
                     sep='|',
                     names=i_cols,
                     encoding='latin-1')
u_data_src = os.path.join(base_src,'u.data')
r_cols = ['user_id', 'movie_id','rating','timestamp']
ratings = pd.read_csv(u_data_src,
                      sep = '\t',
                      names = r_cols,
                      encoding='latin-1')
#ratings DataFrame에서 timestamp 제거
ratings = ratings.drop('timestamp',axis=1)
movies = movies[['movie_id','title']]

#데이터 train, test set 분리
from sklearn.model_selection import train_test_split
x = ratings.copy()
y = ratings['user_id']

x_train, x_test, y_train, y_test = train_test_split(x,y,
                                                    test_size = 0.25,
                                                    stratify=y) #stratify : 계층화추출(골고루 뽑히도록)
#정확도(RMSE)를 계산하는 함수
def RMSE(y_true, y_pred):
  return np.sqrt(np.mean((np.array(y_true) - np.array(y_pred))**2))
#모델별 RMSE를 계산하는 함수
def score(model):
  id_pairs = zip(x_test['user_id'],x_test['movie_id'])
  y_pred = np.array([model(user,movie) for (user,movie) in id_pairs])
  y_true = np.array(x_test['rating'])
  return RMSE(y_true,y_pred)

# best_seller 함수를 이용한 정확도 계산
train_mean = x_train.groupby(['movie_id'])['rating'].mean()
def best_seller(user_id,movie_id):
  try :
    rating = train_mean[movie_id]
  except : #해당 영화 데이터가 train data set에 없을때
    rating = 3.0
  return rating
score(best_seller)

#성별에 따른 예측값 계산
merged_ratings = pd.merge(x_train,users)
users = users.set_index('user_id')
g_mean = merged_ratings[['movie_id','sex','rating']].groupby(['movie_id','sex'])['rating'].mean()
#g_mean
rating_matrix = x_train.pivot(index='user_id',
                             columns='movie_id',
                             values='rating')
rating_matrix