python pandas 实战 电影评分处理

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import json
from pandas import DataFrame, Series


unames = ['user_id', 'gender', 'age', 'occupation', 'zip']
#用read_table方式读取数据，给出分隔和names
users = pd.read_table('ch02/movielens/users.dat', sep='::', header=None, names=unames)

rnames = ['user_id', 'movie_id', 'rating', 'timestamp']
ratings = pd.read_table('ch02/movielens/ratings.dat', sep='::', header=None, names=rnames)


mnames = ['movie_id', 'title', 'genres']
movies = pd.read_table('ch02/movielens/movies.dat', sep='::', header=None, names=mnames)

#合并
data = pd.merge(pd.merge(ratings, users), movies)

#透视表
mean_ratings = data.pivot_table('rating', index='title', columns='gender', aggfunc='mean')

ratings_by_title = data.groupby('title').size()
#得到活跃的电影
active_titles = ratings_by_title.index[ratings_by_title >= 250]

mean_ratings = mean_ratings.loc[active_titles]
#女性评分最高排序
top_female_ratings = mean_ratings.sort_index(by='F', ascending=False)

mean_ratings['diff'] = mean_ratings['M'] - mean_ratings['F']
#按照差异来排序
sorted_by_diff = mean_ratings.sort_index(by='diff')