# -*- coding: utf-8 -*-
import pandas as pd
import numpy as np
from math import sqrt
critics={'Lisa Rose': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.5,
'Just My Luck': 3.0, 'Superman Returns': 3.5, 'You, Me and Dupree': 2.5,
'The Night Listener': 3.0},
'Gene Seymour': {'Lady in the Water': 3.0, 'Snakes on a Plane': 3.5,
'Just My Luck': 1.5, 'Superman Returns': 5.0, 'The Night Listener': 3.0,
'You, Me and Dupree': 3.5},
'Michael Phillips': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.0,
'Superman Returns': 3.5, 'The Night Listener': 4.0},
'Claudia Puig': {'Snakes on a Plane': 3.5, 'Just My Luck': 3.0,
'The Night Listener': 4.5, 'Superman Returns': 4.0,
'You, Me and Dupree': 2.5},
'Mick LaSalle': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
'Just My Luck': 2.0, 'Superman Returns': 3.0, 'The Night Listener': 3.0,
'You, Me and Dupree': 2.0},
'Jack Matthews': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
'The Night Listener': 3.0, 'Superman Returns': 5.0, 'You, Me and Dupree': 3.5},
'Toby': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0,'Superman Returns':4.0}}
df_critics=pd.DataFrame(critics)
##欧氏距离
def sim_distance(prefs,person1,person2):
si={}
for item in prefs[person1]:
if item in prefs[person2]:
si[item]=1
if len(si)==0:
return 0
sum_of_squares=sum([pow(prefs[person1][item]-prefs[person2][item],2) for item in prefs[person1] if item in prefs[person2]])
return 1/(1+sqrt(sum_of_squares))
##numpy pandas 方法
def sim_distance2(prefs,person1,person2):
return 1/(1+np.linalg.norm(prefs[person1]-prefs[person2]))
##皮尔逊相关系数
def sim_pearson(prefs,p1,p2):
si={}
for item in prefs[p1]:
if item in prefs[p2]:
si[item]=1
n=len(si)
if n==0:
return 1
##对所有偏好求和
sum1=sum([prefs[p1][it] for it in si])
sum2=sum([prefs[p2][it] for it in si])
##求平方和
sum1Sq=sum([pow(prefs[p1][it]
扫一扫
7206
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
