R语言 recommenderlab 包

时间：2021-11-17 23:23:14

recommend

li_volleyball

2016年3月20日

library(recommenderlab)
## Warning: package 'recommenderlab' was built under R version 3.2.4
## Loading required package: Matrix
## Loading required package: registry
## Loading required package: arules
##

## Attaching package: 'arules'
## The following objects are masked from 'package:base':

##

##     %in%, abbreviate, write
## Loading required package: proxy
##

## Attaching package: 'proxy'
## The following object is masked from 'package:Matrix':

##

##     as.matrix
## The following objects are masked from 'package:stats':

##

##     as.dist, dist
## The following object is masked from 'package:base':

##

##     as.matrix
library(ggplot2)

#

data(MovieLense)

dim(MovieLense)
## [1]  943 1664
MovieLense
## 943 x 1664 rating matrix of class 'realRatingMatrix' with 99392 ratings.
image(sample(MovieLense,500),main="Raw ratings")

R语言 recommenderlab 包

qplot(getRatings(MovieLense),binwidth=1,main="histogram of normalized ratings",xlab = "Ratings")

R语言 recommenderlab 包

summary(getRatings(MovieLense))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.

##    1.00    3.00    4.00    3.53    4.00    5.00
#normalized ratings

qplot(getRatings(normalize(MovieLense,method="Z-score")),main="hist of normalized ratings",xlab="rating")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

R语言 recommenderlab 包

summary(getRatings(normalize(MovieLense,method="Z-score")))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.

## -4.8520 -0.6466  0.1084  0.0000  0.7506  4.1280
qplot(rowCounts(MovieLense), binwidth=10, main="Movies rated on Average", xlab="# of users", ylab="# of movies rated")

R语言 recommenderlab 包

qplot(colMeans(MovieLense), binwidth=0.1, main="Mean ratings of Movies", xlab="Rating", ylab="# of movies")

R语言 recommenderlab 包

recommenderRegistry$get_entries(dataType="realRatingMatrix")
## $IBCF_realRatingMatrix

## Recommender method: IBCF

## Description: Recommender based on item-based collaborative filtering (real data).

## Parameters:

##    k method normalize normalize_sim_matrix alpha na_as_zero minRating

## 1 30 Cosine    center                FALSE   0.5      FALSE        NA

##

## $PCA_realRatingMatrix

## Recommender method: PCA

## Description: Recommender based on PCA approximation (real data).

## Parameters:

##   categories method normalize normalize_sim_matrix alpha na_as_zero

## 1         20 Cosine    center                FALSE   0.5      FALSE

##   minRating

## 1        NA

##

## $POPULAR_realRatingMatrix

## Recommender method: POPULAR

## Description: Recommender based on item popularity (real data).

## Parameters: None

##

## $RANDOM_realRatingMatrix

## Recommender method: RANDOM

## Description: Produce random recommendations (real ratings).

## Parameters: None

##

## $SVD_realRatingMatrix

## Recommender method: SVD

## Description: Recommender based on EM-based SVD approximation from package bcv (real data).

## Parameters:

##   approxRank maxiter normalize minRating

## 1         NA     100    center        NA

##

## $UBCF_realRatingMatrix

## Recommender method: UBCF

## Description: Recommender based on user-based collaborative filtering (real data).

## Parameters:

##   method nn sample normalize minRating

## 1 cosine 25  FALSE    center        NA
scheme <- evaluationScheme(MovieLense, method="split", train=0.9, k=1, given=10, goodRating=4)

scheme
## Evaluation scheme with 10 items given

## Method: 'split' with 1 run(s).

## Training set proportion: 0.900

## Good ratings: >=4.000000

## Data set: 943 x 1664 rating matrix of class 'realRatingMatrix' with 99392 ratings.
algorithms <- list(

  "random items" = list(name="RANDOM", param=list(normalize = "Z-score")),

  "popular items" = list(name="POPULAR", param=list(normalize = "Z-score")),

  "user-based CF" = list(name="UBCF", param=list(normalize = "Z-score", method="Cosine", nn=50, minRating=3)),

  "item-based CF" = list(name="IBCF", param=list(normalize = "Z-score", method="Cosine"))

)

# run algorithms, predict next n movies

results <- evaluate(scheme, algorithms, n=c(1, 3, 5, 10, 15, 20))
## RANDOM run fold/sample [model time/prediction time]

##   1  [0.02sec/1.25sec]

## POPULAR run fold/sample [model time/prediction time]

##   1  [0.16sec/0.21sec]

## UBCF run fold/sample [model time/prediction time]

##   1  [0.15sec/59.95sec]

## IBCF run fold/sample [model time/prediction time]

##   1  [506.98sec/0.89sec]
plot(results, annotate = 1:4, legend="topleft")

R语言 recommenderlab 包

# See precision / recall

plot(results, "prec/rec", annotate=3)

R语言 recommenderlab 包

summary(results)
##               Length Class             Mode

## random items  1      evaluationResults S4

## popular items 1      evaluationResults S4

## user-based CF 1      evaluationResults S4

## item-based CF 1      evaluationResults S4
print(results)
## List of evaluation results for 4 recommenders:

## Evaluation results for 1 folds/samples using method 'RANDOM'.

## Evaluation results for 1 folds/samples using method 'POPULAR'.

## Evaluation results for 1 folds/samples using method 'UBCF'.

## Evaluation results for 1 folds/samples using method 'IBCF'.
library(plyr)

result1<-ldply(avg(results))

head(result1)
##            .id         TP         FP       FN       TN  precision

## 1 random items 0.02105263  0.9789474 59.09474 1593.905 0.02105263

## 2 random items 0.09473684  2.9052632 59.02105 1591.979 0.03157895

## 3 random items 0.20000000  4.8000000 58.91579 1590.084 0.04000000

## 4 random items 0.36842105  9.6315789 58.74737 1585.253 0.03684211

## 5 random items 0.63157895 14.3684211 58.48421 1580.516 0.04210526

## 6 random items 0.82105263 19.1789474 58.29474 1575.705 0.04105263

##         recall          TPR          FPR

## 1 0.0001625365 0.0001625365 0.0006139374

## 2 0.0017415933 0.0017415933 0.0018211266

## 3 0.0028771009 0.0028771009 0.0030075810

## 4 0.0091514632 0.0091514632 0.0060388289

## 5 0.0131256428 0.0131256428 0.0090061881

## 6 0.0171367235 0.0171367235 0.0120237980
result1[,1]<-paste(result1[,1],c(1, 3, 5, 10, 15, 20))

temp_result1<-result1[,c(1,6,7)]

f<-function(p,r){

  return(2*p*r)/(p+r)

}

result1_f<-cbind(result1,f=f(temp_result1[,2],temp_result1[,3]))

head(result1_f)
##               .id         TP         FP       FN       TN  precision

## 1  random items 1 0.02105263  0.9789474 59.09474 1593.905 0.02105263

## 2  random items 3 0.09473684  2.9052632 59.02105 1591.979 0.03157895

## 3  random items 5 0.20000000  4.8000000 58.91579 1590.084 0.04000000

## 4 random items 10 0.36842105  9.6315789 58.74737 1585.253 0.03684211

## 5 random items 15 0.63157895 14.3684211 58.48421 1580.516 0.04210526

## 6 random items 20 0.82105263 19.1789474 58.29474 1575.705 0.04105263

##         recall          TPR          FPR            f

## 1 0.0001625365 0.0001625365 0.0006139374 6.843643e-06

## 2 0.0017415933 0.0017415933 0.0018211266 1.099954e-04

## 3 0.0028771009 0.0028771009 0.0030075810 2.301681e-04

## 4 0.0091514632 0.0091514632 0.0060388289 6.743183e-04

## 5 0.0131256428 0.0131256428 0.0090061881 1.105317e-03

## 6 0.0171367235 0.0171367235 0.0120237980 1.407015e-03
head(result1_f[order(-result1_f$f),])
##                 .id       TP        FP       FN       TN precision

## 18 user-based CF 20 7.231579 11.894737 51.88421 1582.989 0.3819792

## 17 user-based CF 15 5.968421  8.473684 53.14737 1586.411 0.4158444

## 16 user-based CF 10 4.463158  5.263158 54.65263 1589.621 0.4603343

## 12 popular items 20 6.726316 13.273684 52.38947 1581.611 0.3363158

## 11 popular items 15 5.273684  9.726316 53.84211 1585.158 0.3515789

## 15  user-based CF 5 2.600000  2.315789 56.51579 1592.568 0.5287234

##        recall        TPR         FPR          f

## 18 0.17582028 0.17582028 0.007392742 0.13431937

## 17 0.15055639 0.15055639 0.005262247 0.12521608

## 16 0.11854595 0.11854595 0.003264888 0.10914154

## 12 0.13805753 0.13805753 0.008238022 0.09286185

## 11 0.11359184 0.11359184 0.006035319 0.07987300

## 15 0.07230233 0.07230233 0.001433397 0.07645587
#带入模型

moive_re<-Recommender(MovieLense,method="UBCF")

moives_pr<-predict(moive_re,MovieLense,n=20)

class(moives_pr)
## [1] "topNList"

## attr(,"package")

## [1] "recommenderlab"
print(as(moives_pr,"list"))
## [[1]]

##  [1] "Glory (1989)"

##  [2] "Schindler's List (1993)"

##  [3] "Casablanca (1942)"

##  [4] "Close Shave, A (1995)"

##  [5] "Dr. Strangelove or: How I Learned to Stop Worrying and Love the Bomb (1963)"

##  [6] "Leaving Las Vegas (1995)"

##  [7] "One Flew Over the Cuckoo's Nest (1975)"

##  [8] "Rear Window (1954)"

##  [9] "Heathers (1989)"

## [10] "L.A. Confidential (1997)"

## [11] "City of Lost Children, The (1995)"

## [12] "Butch Cassidy and the Sundance Kid (1969)"

## [13] "Titanic (1997)"

## [14] "Lawrence of Arabia (1962)"

## [15] "Shine (1996)"

## [16] "Stand by Me (1986)"

## [17] "Gandhi (1982)"

## [18] "To Kill a Mockingbird (1962)"

## [19] "In the Name of the Father (1993)"

## [20] "Harold and Maude (1971)"

##

## [[2]]

##  [1] "Boot, Das (1981)"

##  [2] "Dead Man Walking (1995)"

##  [3] "Lone Star (1996)"

##  [4] "Return of the Jedi (1983)"

##  [5] "Celluloid Closet, The (1995)"

##  [6] "Casablanca (1942)"

##  [7] "Citizen Kane (1941)"

##  [8] "Godfather: Part II, The (1974)"

##  [9] "2001: A Space Odyssey (1968)"

## [10] "When We Were Kings (1996)"

## [11] "Diva (1981)"

## [12] "Close Shave, A (1995)"

## [13] "Tango Lesson, The (1997)"

## [14] "Beautiful Thing (1996)"

## [15] "Empire Strikes Back, The (1980)"

## [16] "Mrs. Dalloway (1997)"

## [17] "Butch Cassidy and the Sundance Kid (1969)"

## [18] "My Fair Lady (1964)"

## [19] "Bonnie and Clyde (1967)"

## [20] "Annie Hall (1977)"

##

## [[3]]

##  [1] "Mrs. Brown (Her Majesty, Mrs. Brown) (1997)"

##  [2] "Star Wars (1977)"

##  [3] "Pulp Fiction (1994)"

##  [4] "English Patient, The (1996)"

##  [5] "Full Monty, The (1997)"

##  [6] "Lone Star (1996)"

##  [7] "Titanic (1997)"

##  [8] "Sweet Hereafter, The (1997)"

##  [9] "In the Company of Men (1997)"

## [10] "Willy Wonka and the Chocolate Factory (1971)"

## [11] "In & Out (1997)"

## [12] "Vertigo (1958)"

## [13] "As Good As It Gets (1997)"

## [14] "Apt Pupil (1998)"

## [15] "Dazed and Confused (1993)"

## [16] "Ice Storm, The (1997)"

## [17] "This Is Spinal Tap (1984)"

## [18] "Trainspotting (1996)"

## [19] "Heat (1995)"

## [20] "Fargo (1996)"

##

## [[4]]

##  [1] "Titanic (1997)"               "English Patient, The (1996)"

##  [3] "L.A. Confidential (1997)"     "Game, The (1997)"

##  [5] "Good Will Hunting (1997)"     "Kiss the Girls (1997)"

##  [7] "Full Monty, The (1997)"       "Usual Suspects, The (1995)"

##  [9] "Rosewood (1997)"              "Boogie Nights (1997)"

## [11] "Raise the Red * (1991)" "Pulp Fiction (1994)"

## [13] "Toy Story (1995)"             "Love Jones (1997)"

## [15] "Eve's Bayou (1997)"           "Edge, The (1997)"

## [17] "Sting, The (1973)"            "Some Like It Hot (1959)"

## [19] "Strictly Ballroom (1992)"     "Soul Food (1997)"

##

## [[5]]

##  [1] "Terminator 2: Judgment Day (1991)"

##  [2] "Terminator, The (1984)"

##  [3] "Usual Suspects, The (1995)"

##  [4] "Contact (1997)"

##  [5] "Braveheart (1995)"

##  [6] "Casablanca (1942)"

##  [7] "Twelve Monkeys (1995)"

##  [8] "Godfather, The (1972)"

##  [9] "Shawshank Redemption, The (1994)"

## [10] "Raising Arizona (1987)"

## [11] "Amadeus (1984)"

## [12] "Nikita (La Femme Nikita) (1990)"

## [13] "Reservoir Dogs (1992)"

## [14] "Citizen Kane (1941)"

## [15] "Dr. Strangelove or: How I Learned to Stop Worrying and Love the Bomb (1963)"

## [16] "Schindler's List (1993)"

## [17] "Titanic (1997)"

## [18] "Leaving Las Vegas (1995)"

## [19] "North by Northwest (1959)"

## [20] "Army of Darkness (1993)"

R语言 recommenderlab 包的更多相关文章

  1. R语言-神经网络包RSNNS

    code{white-space: pre;} pre:not([class]) { background-color: white; }if (window.hljs && docu ...

  2. R语言-Knitr包的详细使用说明

    R语言-Knitr包的详细使用说明 by 扬眉剑 来自数盟[总舵] 群:321311420 1.相关资料 1:自动化报告-谢益辉 https://github.com/yihui/r-ninja/bl ...

  3. R语言dplyr包初探

    昨天学了一下R语言dplyr包,处理数据框还是很好用的.记录一下免得我忘记了... 先写一篇入门的,以后有空再写一篇详细的用法. #dplyr learning library(dplyr) #fil ...

  4. R语言 ggplot2包

    R语言  ggplot2包的学习   分析数据要做的第一件事情,就是观察它.对于每个变量,哪些值是最常见的?值域是大是小?是否有异常观测? ggplot2图形之基本语法: ggplot2的核心理念是将 ...

  5. R语言扩展包dplyr——数据清洗和整理

    R语言扩展包dplyr——数据清洗和整理 标签: 数据R语言数据清洗数据整理 2015-01-22 18:04 7357人阅读 评论(0) 收藏 举报  分类: R Programming(11)  ...

  6. 安装R语言的包的方法

    安装R语言的包的方法: 1. 在线安装 在R的控制台,输入类似install.packages("TSA")  # 安装 TSA install.packages("TS ...

  7. Bagging&lpar;R语言实现&rpar;—包外错误率，多样性测度

    1.      Bagging Bagging即套袋法,其算法过程如下: 从原始样本集中抽取训练集.每轮从原始样本集中使用Bootstraping的方法抽取n个训练样本(在训练集中,有些样本可能被多次 ...

  8. R语言扩展包dplyr笔记

    引言 2014年刚到, 就在 Feedly 订阅里看到 RStudio Blog 介绍 dplyr 包已发布 (Introducing dplyr), 此包将原本 plyr 包中的 ddply() 等 ...

  9. R语言 arules包 apriori&lpar;&rpar;函数中文帮助文档&lpar;中英文对照&rpar;

    apriori(arules) apriori()所属R语言包:arules                                         Mining Associations w ...

随机推荐

  1. VBS基础篇 - 队列

    VBS中的队列需要使用System.Collections.Queue '建立队列 Dim Que : Set Que = CreateObject("System.Collections. ...

  2. 你需要知道的九大排序算法【Python实现】之基数排序

    八.基数排序 基本思想:基数排序(radix sort)属于"分配式排序"(distribution sort),又称"桶子法"(bucket sort)或bi ...

  3. Intent MIME 打开各种类型的文件

    使用 public class MainActivity extends ListActivity {     public static final String path = Environmen ...

  4. Java内部类——局部内部类

    局部内部类,即放在“{块中}”,局部内部类,不能被成员修饰符static修饰,且内部类的成员也不能是static. 内部类中访问局部变量“{块中}”,需要将局部变量声明为final. 可以直接访问外部 ...

  5. 了解OutOfMemoryError异常 - 深入Java虚拟机读后总结

    JVM中的异常发生 Java虚拟机规范中除了程序计数器外,其他几个运行时区域都有发生OutOfMemoryError异常的可能. 本章笔记通过代码来验证Java虚拟机规范中描述的各个运行时区域存储的内 ...

  6. c语言一&comma;二数组

    一.PTA实验作业 题目1:7-4 简化的插入排序 1. 本题PTA提交列表 2. 设计思路 1.定义整形变量N,temp,i. 2.输入N 3.通过for(i=1;i<=N;i++)的循环语句 ...

  7. Codeforces 863 简要题解

    文章目录 A题 B题 C题 D题 E题 F题 G题 传送门 简要题解?因为最后一题太毒不想写了所以其实是部分题解... A题 传送门 题意简述:给你一个数,问你能不能通过加前导000使其成为一个回文数 ...

  8. 收藏 —— 教你阅读Python开源项目

    https://zhuanlan.zhihu.com/p/22275595?refer=python-cn

  9. 关于miniconda的安装，配置以及包批量安装和使用

    由于时间很晚了.就不写废话了. conda官方文档地址:http://conda.pydata.org/docs/ 一切其实都可以从miniconda的文档找到,这里只纪录自己操作的时候遇到的值得一说 ...

  10. 面试真题-----hashMap原理

    HashMap详解   JDK1.8对HashMap底层的实现进行了优化,例如引入红黑树的数据结构和扩容的优化等 简介 Java为数据结构中的映射定义了一个接口java.util.Map HashMa ...

相关文章