Question

在zomato文件夹中，有4个csv（孟加拉，中文，意大利语和panjabi）文件。我正在使用基于lexicom的情绪分析将这些文件与正词和负词文本文件进行比较。一切工作正常，我也非常完美地获得了a，c，e，g的值。但是当涉及到绘图时，它给了我这个错误

不知道如何自动为列表类型的对象选择比例。默认为连续。错误：geom_bar需要以下美感：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复制的示例来很好地回答，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也是列表。您需要将它们转换为数字，然后将其求和

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"))

错误：geom_bar需要以下美感：y

1 个答案: