数据导论实验一

from lenskit.datasets import ML100K
from lenskit import batch, topn, util
from lenskit import crossfold as xf
from lenskit.algorithms import Recommender, als, item_knn as knn
from lenskit import topn
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
ratings = pd.read_csv("F://ml-latest-small//ratings.csv")
ratings = ratings.rename(columns={'userId': 'user', 'movieId': 'item'})
print(ratings.shape)
ratings.head()

movies = pd.read_csv('F://ml-latest-small//movies.csv')
movies = movies.rename(columns={'movieId': 'items'})
print(movies.shape)
print('\n'+ movies.head().to_string())

movie_ratings = ratings.groupby('item')['rating'].agg(['mean', 'count']) \
    .rename(columns = {'mean' : 'rating_mean', 'count' : 'rating_count'})
movie_ratings['items'] = movie_ratings.index
movie_ratings.head()

movie_ratings = pd.merge(movie_ratings, movies, on = 'items')
print(movie_ratings.head().to_string())