错误：geom_bar 需要以下缺失的美学：y

Question

在 zomato 文件夹中有 4 个 csv（bengoli、chinese、italian 和 panjabi）文件。我正在使用基于词典的情感分析将这些文件与正面和负面的单词文本文件进行比较。一切都运行良好，我也非常完美地获得了 a、c、e、g 的值。但是当涉及到情节时，它给了我这个错误

不知道如何为列表类型的对象自动选择比例。默认为连续。 错误：geom_bar 需要以下缺失的美学：y

 library(stringr)
    library(ggplot2)
    library(tm)


     src <- DirSource("./Data/foodwise/zomato")
        docs <- Corpus(src)
        docs <- tm_map(docs, removePunctuation)
        docs <- tm_map(docs,content_transformer(tolower))
        docs <- tm_map(docs, removeNumbers)
        docs <- tm_map(docs, removeWords,stopwords("english"))
        docs <- tm_map(docs, stripWhitespace)
        docs <- tm_map(docs, stemDocument)
        writeCorpus(docs, path="./Data")

texts <- readLines("./Data/zomato bengoli.csv.txt")
        opinion.lexicon.pos <- scan('./Data/positive-word.txt', what='character', comment.char = ';')
        opinion.lexicon.neg <- scan('./Data/negative-word.txt', what='character', comment.char = ';')
        jj <- str_split(texts, pattern="\\s+")
        a <- lapply(jj,function(x){sum(!is.na(match(x,opinion.lexicon.pos)))})
        texts1 <- readLines("./Data/zomato chinese.csv.txt")
        jj <- str_split(texts1, pattern="\\s+")
        c <- lapply(jj,function(x){sum(!is.na(match(x,opinion.lexicon.pos)))})

        texts2 <- readLines("./Data/zomato Italian.csv.txt")
        jj <- str_split(texts2, pattern="\\s+")
        e <- lapply(jj,function(x){sum(!is.na(match(x,opinion.lexicon.pos)))})

        texts3 <- readLines("./Data/zomato panjabi.csv.txt")
        jj <- str_split(texts3, pattern="\\s+")
        g <- lapply(jj,function(x){sum(!is.na(match(x,opinion.lexicon.pos)))})
        x <-c("Bengoli", "Chinese", "Italian", "Panjabi")
        y <- c(a, c ,e, g)
        data <- data.frame(x, y)
        ggplot(data, aes(x, y)) + geom_bar(stat = "identity",aes(fill = x)) + xlab("Cuisines") + ylab("Total count") + ggtitle("")+ scale_fill_manual("Cuisines", values = c("Italian" = "lightpink", "Panjabi" = "lightblue", "Chinese" = "darkgrey", "Bengoli"="lightgreen"))

Answer 1

如前所述，我们确实需要一个可重复的示例来做好回答工作，但我会根据我认为您的要求进行尝试

您的主要问题是您a、c、e 和g 都是列表，所以y 也是一个列表。您需要将它们转换为数字，然后求和，如果您想要总数

jj <- list("Bengoli","English", "Bengoli")
g <- lapply(jj,function(i){sum(!is.na(match(i,"Bengoli")))})
# this is a list:
g

g2 <- sum(unlist(g))
# Now it is a number which you can supply to ggplot
g2

x <-c("Bengoli", "Chinese", "Italian", "Panjabi")
y <- c(g2,4,3,6)

data <- data.frame(x, y)
ggplot(data, aes(x, y)) + 
  geom_bar(stat = "identity",aes(fill = x)) + 
  xlab("Cuisines") + 
  ylab("Total count") + 
  scale_fill_manual("Cuisines",
                    values = c("Italian" = "lightpink",
                               "Panjabi" = "lightblue", 
                               "Chinese" = "darkgrey", 
                               "Bengoli"="lightgreen"))