数据来源:http://www.grouplens.org/node/73
一、 导入python库
import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from matplotlib.font_manager import FontProperties
二、数据整理
1.通过pandas读取数据
pd.options.display.max_rows=10 #分块读取,让展示内容少一点
unames = list(str.split('UserID::Gender::Age::Occupation::Zip-code',"::"))
users = pd.read_table(r'D:\360极速浏览器下载\ml-1m\users.dat', sep='::', header=None, names=unames)
rnames = list(str.split('UserID::MovieID::Rating::Timestamp','::'))
ratings=pd.read_table(r'D:\360极速浏览器下载\ml-1m\ratings.dat',sep='::',header=None, names=rnames)
mnames