Question

我需要通过使用其他评论家排名的加权平均值来获得维多利亚推荐的前5部电影。我只能在Excel中完成它，但我需要翻译成R. 获取值的公式为：

维多利亚的平均值+（Σ（其他评论家评分 - 其他评论家平均评分）*皮尔森相关性）/Σ绝对加权皮尔逊值-1（维多利亚）

更好地说明对于电影The.Matrix来说，结果应该是

John vote = 4

John Average = 3,0714

John pearson cor = 0,27709796

公式=（4-3,07）* 0,27709796 / 6,9280（绝对加权值之和）

（如何在R ???中创建此公式）如果我能解决这个问题，也许我可以做其余的

在为每个人做这个之后你会增加3,1538（Victoria's Avg），这应该会产生 3,791701302

我需要为Victorias没有看过的所有电影做这些，这些应该是结果

3.7917013044215, 'The Matrix'
3.50776533175371, 'Forrest Gump'  
3.33118834864677, 'The Sixth Sense'
3.11491825315719, 'Shakespeare in Love'
2.9124513228665, 'Blade Runner'

以下是Excel上的Matrix版本：

到目前为止，这是我的代码：

cr2<-t(cr[,2:21]) 
colnames(cr2)<-cr[,1] 
cr2<-as.data.frame(cr2)    
cr$Mean <- rowMeans(cr[,2:20], na.rm = TRUE)
cr$Pearson <- cor(cr2[,1:20], cr2[15], use = "pairwise.complete.obs")
cr$PearsonABS <- abs(cor(cr2[,1:20], cr2[15], use = "pairwise.complete.obs"))
x <- sum(cr$PearsonABS) - 1

我是以一种非常废话的方式（手动）

g <- cr[15,22]

#Forrest Gump
fg = cr[,4] - cr[, 22]
fga = fg * cr[,23]
fgb = fga / x 
fgc = sum(fgb, na.rm = TRUE) + g
print(fgc)

#The Shawshank Redemption
sr = cr[,5] - cr[, 22]
sra = sr * cr[,23]
srb = sra / x 
src = sum(srb, na.rm = TRUE) + g
print(src)

#Saving Private Ryan
sp = cr[,9] - cr[, 22]
spa = sp * cr[,23]
spb = spa / x 
spc = sum(spb, na.rm = TRUE) + g
print(spc)

#Shakespeare in Love
sl = cr[,12] - cr[, 22]
sla = sl * cr[,23]
slb = sla / x 
slc = sum(slb, na.rm = TRUE) + g
print(slc)

#Blade Runner
br = cr[,15] - cr[, 22]
bra = br * cr[,23]
brb = bra / x 
brc = sum(brb, na.rm = TRUE) + g
print(brc)

#The Matrix
tm = cr[,17] - cr[, 22]
tma = tm * cr[,23]
tmb = tma / x 
tmc = sum(tmb, na.rm = TRUE) + g
print(tmc)

#The Sixth Sense
ts = cr[,19] - cr[, 22]
tsa = ts * cr[,23]
tsb = tsa / x 
tsc = sum(tsb, na.rm = TRUE) + g
print(tsc)

my_list <- c(fgc, src, spc, slc, brc, tmc, tsc)
head(sort(my_list, decreasing=TRUE), 5)

这是dput（）

dput(cr)
structure(list(User = structure(c(8L, 10L, 2L, 17L, 11L, 1L, 
18L, 9L, 7L, 5L, 3L, 14L, 13L, 4L, 20L, 6L, 16L, 12L, 15L, 19L
), .Label = c("Ana", "Anton", "Bernard", "Carles", "Chris", "Ivan", 
"Jim", "John", "Marc", "Maria", "Martina", "Nadia", "Nerea", 
"Nuria", "Oriol", "Rachel", "Roger", "Sergi", "Valery", "Victoria"
), class = "factor"), Star.Wars.IV...A.New.Hope = c(1L, 5L, NA, 
NA, 4L, 2L, NA, 4L, 5L, 4L, 2L, 3L, 2L, 3L, 4L, NA, NA, 4L, 5L, 
1L), Star.Wars.VI...Return.of.the.Jedi = c(5L, 3L, NA, 3L, 3L, 
4L, NA, NA, 1L, 2L, 1L, 5L, 3L, NA, 4L, NA, NA, 5L, 1L, 2L), 
    Forrest.Gump = c(2L, NA, NA, NA, 4L, 4L, 3L, NA, NA, NA, 
    5L, 2L, NA, 3L, NA, 1L, NA, 1L, NA, 2L), The.Shawshank.Redemption = c(NA, 
    2L, 5L, NA, 1L, 4L, 1L, NA, 4L, 5L, NA, NA, 5L, NA, NA, NA, 
    NA, 5L, NA, 4L), The.Silence.of.the.Lambs = c(4L, 4L, 2L, 
    NA, 4L, NA, 1L, 3L, 2L, 3L, NA, 2L, 4L, 2L, 5L, 3L, 4L, 1L, 
    NA, 5L), Gladiator = c(4L, 2L, NA, 1L, 1L, NA, 4L, 2L, 4L, 
    NA, 5L, NA, NA, NA, 5L, 2L, NA, 1L, 4L, NA), Toy.Story = c(2L, 
    1L, 4L, 2L, NA, 3L, NA, 2L, 4L, 4L, 5L, 2L, 4L, 3L, 2L, NA, 
    2L, 4L, 2L, 2L), Saving.Private.Ryan = c(2L, NA, NA, 3L, 
    4L, 1L, 5L, NA, 4L, 3L, NA, NA, 5L, NA, NA, 2L, NA, NA, 1L, 
    3L), Pulp.Fiction = c(NA, NA, NA, 4L, NA, 4L, 2L, 3L, NA, 
    4L, NA, 1L, NA, NA, 3L, NA, 2L, 5L, 3L, 2L), Stand.by.Me = c(3L, 
    4L, 1L, NA, 1L, 4L, NA, NA, 1L, NA, NA, NA, NA, 4L, 5L, 1L, 
    NA, NA, 3L, 2L), Shakespeare.in.Love = c(2L, 3L, NA, NA, 
    5L, 5L, 1L, NA, 2L, NA, NA, 3L, NA, NA, NA, 5L, 2L, NA, 3L, 
    1L), Total.Recall = c(NA, 2L, 1L, 4L, 1L, 2L, NA, 2L, 3L, 
    NA, 3L, NA, 2L, 1L, 1L, NA, NA, NA, 1L, NA), Independence.Day = c(5L, 
    2L, 4L, 1L, NA, 4L, NA, 3L, 1L, 2L, 2L, 3L, 4L, 2L, 3L, NA, 
    NA, NA, NA, NA), Blade.Runner = c(2L, NA, 4L, 3L, 4L, NA, 
    3L, 2L, NA, NA, NA, NA, NA, 2L, NA, NA, NA, 4L, NA, 5L), 
    Groundhog.Day = c(NA, 2L, 1L, 5L, NA, 1L, NA, 4L, 5L, NA, 
    NA, 2L, 3L, 3L, 2L, 5L, NA, NA, NA, 5L), The.Matrix = c(4L, 
    NA, 1L, NA, 3L, NA, 1L, NA, NA, 2L, 1L, 5L, NA, 5L, NA, 2L, 
    4L, NA, 2L, 4L), Schindler.s.List = c(2L, 5L, 2L, 5L, 5L, 
    NA, NA, 1L, NA, 5L, NA, NA, NA, 1L, 3L, 2L, NA, 2L, NA, 3L
    ), The.Sixth.Sense = c(5L, 1L, 3L, 1L, 5L, 3L, NA, 3L, NA, 
    1L, 2L, NA, NA, NA, NA, 4L, NA, 1L, NA, 5L), Raiders.of.the.Lost.Ark = c(NA, 
    3L, 1L, 1L, NA, NA, 5L, 5L, NA, NA, 1L, NA, 5L, NA, 3L, 3L, 
    NA, 2L, NA, 3L), Babe = c(NA, NA, 3L, 2L, NA, 2L, 2L, NA, 
    5L, NA, 4L, 2L, NA, NA, 1L, 4L, NA, 5L, NA, NA), Mean = c(3.07142857142857, 
    2.78571428571429, 2.46153846153846, 2.69230769230769, 3.21428571428571, 
    3.07142857142857, 2.54545454545455, 2.83333333333333, 3.15384615384615, 
    3.18181818181818, 2.81818181818182, 2.72727272727273, 3.7, 
    2.63636363636364, 3.15384615384615, 2.83333333333333, 2.8, 
    3.07692307692308, 2.5, 3.0625), Pearson = structure(c(0.277097961607667, 
    0.492592183071889, -0.184664098655286, -0.306988756155365, 
    0.047716527859489, 0.597614304667197, 0.0363696483726654, 
    0.0793422835603058, -0.444514447822542, -0.344265186329548, 
    -0.186499664263607, 0.365148371670111, 0.205737799949456, 
    0.427324672683063, 1, -0.732776720760177, 0.944911182523068, 
    -0.587378478571482, 0.578979445733232, -0.0881134221062802
    ), .Dim = c(20L, 1L), .Dimnames = list(c("John", "Maria", 
    "Anton", "Roger", "Martina", "Ana", "Sergi", "Marc", "Jim", 
    "Chris", "Bernard", "Nuria", "Nerea", "Carles", "Victoria", 
    "Ivan", "Rachel", "Nadia", "Oriol", "Valery"), "Victoria")), 
    PearsonABS = structure(c(0.277097961607667, 0.492592183071889, 
    0.184664098655286, 0.306988756155365, 0.047716527859489, 
    0.597614304667197, 0.0363696483726654, 0.0793422835603058, 
    0.444514447822542, 0.344265186329548, 0.186499664263607, 
    0.365148371670111, 0.205737799949456, 0.427324672683063, 
    1, 0.732776720760177, 0.944911182523068, 0.587378478571482, 
    0.578979445733232, 0.0881134221062802), .Dim = c(20L, 1L), .Dimnames = list(
        c("John", "Maria", "Anton", "Roger", "Martina", "Ana", 
        "Sergi", "Marc", "Jim", "Chris", "Bernard", "Nuria", 
        "Nerea", "Carles", "Victoria", "Ivan", "Rachel", "Nadia", 
        "Oriol", "Valery"), "Victoria"))), .Names = c("User", 
"Star.Wars.IV...A.New.Hope", "Star.Wars.VI...Return.of.the.Jedi", 
"Forrest.Gump", "The.Shawshank.Redemption", "The.Silence.of.the.Lambs", 
"Gladiator", "Toy.Story", "Saving.Private.Ryan", "Pulp.Fiction", 
"Stand.by.Me", "Shakespeare.in.Love", "Total.Recall", "Independence.Day", 
"Blade.Runner", "Groundhog.Day", "The.Matrix", "Schindler.s.List", 
"The.Sixth.Sense", "Raiders.of.the.Lost.Ark", "Babe", "Mean", 
"Pearson", "PearsonABS"), row.names = c(NA, -20L), class = "data.frame")

我希望我能够解释清楚。有人能帮助我吗？

Answer 1

好的，我希望你能遵循这个，我会尽力给出足够的解释。目标是编写一个功能，可以结束您的手动计算，并使其易于运行多次。

整理

首先，我们希望使数据整洁，因此更容易使用。这意味着使每列成为可变的，因此不会在多列中具有胶片评级。见more about tidy data here。我们将使用tidyverse包来执行此操作。

使用select删除mean和pearson列。我们希望能够根据我们正在查看的用户对它们进行不同的计算，并将它们奇怪地存储在dput列表中。
使用gather获取所有电影专栏，并将电影名称放入一列，将评级放入另一列。
将User重命名为小写以保持一致性
使用group_by和mutate为每个用户制定平均评分。 na.rm = TRUE表示mean在计算时会忽略所有NA值。

看起来像这样。看到数据现在整齐，只有四列。

library(tidyverse)
library(magrittr)
tidy_cr <- cr %>%
  select(-Mean, -Pearson, -PearsonABS) %>%
  gather("film", "rating", -User) %>%
  rename(user = User) %>%
  group_by(user) %>%
  mutate(mean = mean(rating, na.rm = TRUE)) %>%
  ungroup()
# A tibble: 400 x 4
   user    film                      rating  mean
   <fct>   <chr>                      <int> <dbl>
 1 John    Star.Wars.IV...A.New.Hope      1  3.07
 2 Maria   Star.Wars.IV...A.New.Hope      5  2.79
 3 Anton   Star.Wars.IV...A.New.Hope     NA  2.46
 4 Roger   Star.Wars.IV...A.New.Hope     NA  2.69
 5 Martina Star.Wars.IV...A.New.Hope      4  3.21
 6 Ana     Star.Wars.IV...A.New.Hope      2  3.07
 7 Sergi   Star.Wars.IV...A.New.Hope     NA  2.55
 8 Marc    Star.Wars.IV...A.New.Hope      4  2.83
 9 Jim     Star.Wars.IV...A.New.Hope      5  3.15
10 Chris   Star.Wars.IV...A.New.Hope      4  3.18
# ... with 390 more rows

维多利亚州的例子

这是一个循序渐进的过程，以维多利亚为例向您展示每个阶段的输出。首先，我们想知道维多利亚没有看过哪部电影。我们通过filter在user列和NA评级中包含维多利亚的行，然后提取film列来执行此操作。

v_films_not_seen <- tidy_cr %>%
  filter(user == "Victoria" & is.na(rating)) %>%
  extract2("film")
[1] "Forrest.Gump"             "The.Shawshank.Redemption" "Saving.Private.Ryan"     
[4] "Shakespeare.in.Love"      "Blade.Runner"             "The.Matrix"              
[7] "The.Sixth.Sense"

然后，我们想要提取维多利亚的评级，以便我们可以计算相关系数和她的特定均值。我们再次减少维多利亚的行，现在撤出rating列。

v_persons_ratings <- tidy_cr %>%
  filter(user == "Victoria") %>%
  extract2("rating")
 [1]  4  4 NA NA  5  5  2 NA  3  5 NA  1  3 NA  2 NA  3 NA  3  1

现在我们要计算相关性。我们首先是group_by用户，因此这个计算将按用户完成。然后，我们使用mutate和cor来计算每个用户评分和维多利亚评级之间的相关性，我们在最后一步保存为v_persons_ratings。选项use = "complete.obs"意味着相关性仅查看两个用户对电影进行评级的观察结果。然后我们使用abs来获得相关系数的绝对值。

v_correlations <- tidy_cr %>%
  group_by(user) %>%
  mutate(
    pearson = cor(rating, v_persons_ratings, use = "complete.obs"),
    pearson_abs = abs(pearson)
  ) %>%
  ungroup()
# A tibble: 400 x 6
   user    film                      rating  mean pearson pearson_abs
   <fct>   <chr>                      <int> <dbl>   <dbl>       <dbl>
 1 John    Star.Wars.IV...A.New.Hope      1  3.07  0.277       0.277 
 2 Maria   Star.Wars.IV...A.New.Hope      5  2.79  0.493       0.493 
 3 Anton   Star.Wars.IV...A.New.Hope     NA  2.46 -0.185       0.185 
 4 Roger   Star.Wars.IV...A.New.Hope     NA  2.69 -0.307       0.307 
 5 Martina Star.Wars.IV...A.New.Hope      4  3.21  0.0477      0.0477
 6 Ana     Star.Wars.IV...A.New.Hope      2  3.07  0.598       0.598 
 7 Sergi   Star.Wars.IV...A.New.Hope     NA  2.55  0.0364      0.0364
 8 Marc    Star.Wars.IV...A.New.Hope      4  2.83  0.0793      0.0793
 9 Jim     Star.Wars.IV...A.New.Hope      5  3.15 -0.445       0.445 
10 Chris   Star.Wars.IV...A.New.Hope      4  3.18 -0.344       0.344 
# ... with 390 more rows

最后，我们使用filter和%in%运算符缩小到包含维多利亚未见过的影片的行。这次我们group_by拍摄，所以计算是按照电影进行的。然后，我们使用summarise使用您在问题中列出的公式计算推荐得分，并添加维多利亚的平均值。最后，我们使用arrange和desc按降序排序。

v_recommendations <- v_correlations %>%
  filter(film %in% v_films_not_seen) %>%
  group_by(film) %>%
  summarise(
    score = sum((rating - mean) * pearson, na.rm = TRUE) / (sum(pearson_abs) - 1)) %>%
  mutate(score = score + mean(v_persons_ratings, na.rm = TRUE)) %>%
  arrange(desc(score))
# A tibble: 7 x 2
  film                     score
  <chr>                    <dbl>
1 The.Matrix                3.79
2 Forrest.Gump              3.51
3 The.Sixth.Sense           3.33
4 Shakespeare.in.Love       3.11
5 Blade.Runner              2.91
6 Saving.Private.Ryan       2.89
7 The.Shawshank.Redemption  2.81

功能

呼！现在我们可以将上面的代码放到一个函数中，用通用的代替上面的所有v_个对象，并提供tbl，person和n作为参数。 tbl是电影，用户，评分和用户平均评分的数据，person是我们想要推荐的人，n是我们想要的推荐数量。此代码与上面的代码基本相同，只是我在末尾添加了head(n)以仅返回推荐表的n行。

top_recs <- function(tbl, person, n){
  films_not_seen <- tbl %>%
    filter(user == person & is.na(rating)) %>%
    extract2("film")
  persons_ratings <- tbl %>%
    filter(user == person) %>%
    extract2("rating")
  correlations <- tbl %>%
    group_by(user) %>%
    mutate(
      pearson = cor(rating, persons_ratings, use = "complete.obs"),
      pearson_abs = abs(pearson)
    ) %>%
    ungroup()
  recommendations <- correlations %>%
    filter(film %in% films_not_seen) %>%
    group_by(film) %>%
    summarise(
      score = sum((rating - mean) * pearson, na.rm = TRUE) / (sum(pearson_abs) - 1)) %>%
    mutate(score = score + mean(persons_ratings, na.rm = TRUE)) %>%
    arrange(desc(score)) %>%
    head(n)
}

我们可以再次测试维多利亚的功能，看看它是否有效：

top_recs(tidy_cr, "Victoria", 5) %>% print()
# A tibble: 5 x 2
  film                score
  <chr>               <dbl>
1 The.Matrix           3.79
2 Forrest.Gump         3.51
3 The.Sixth.Sense      3.33
4 Shakespeare.in.Love  3.11
5 Blade.Runner         2.91

但我们现在也可以获得任何用户的建议，例如Bernard的8条建议：

top_recs(tidy_cr, "Bernard", 8) %>% print()
# A tibble: 8 x 2
  film                     score
  <chr>                    <dbl>
1 The.Shawshank.Redemption  3.23
2 Pulp.Fiction              3.17
3 Schindler.s.List          3.11
4 Blade.Runner              2.97
5 Saving.Private.Ryan       2.94
6 Shakespeare.in.Love       2.74
7 Groundhog.Day             2.72
8 Stand.by.Me               2.60

备注

这实际上是一个有趣的练习，你是否可以找出你想要的工具并相应地构建工作流程。我认为这种方法的强大之处在于我们现在可以为任何用户提供建议。也许更重要的是，此代码（我认为）中的任何内容都不依赖于这些特定用户或电影或评级。如果您有更多数据，可以将它们添加到tidy_cr的底部，该功能仍然有效。如果您更改了评分公式，则只需编辑几行即可更新它。

我希望您可以逐步完成这项工作，并详细了解如何在R中编写自己的函数！其他后续步骤可能是错误检查，如果您要求提供更多建议，或者如果您键入用户名不在数据库中，则显示信息。我认为这可能是令人生畏的，但?是你在R中最好的朋友，检查功能的选项是什么。我绝对不知道所有这一切都在我头顶！

协同过滤 - R.

1 个答案:

整理

维多利亚州的例子

功能

备注