【R语言】词云图

Gonewind词云图

library(tm)

library(wordcloud)



article <- tolower(readLines('D:/RWorkPlace/第3章_类别比较型图表/gonewind.txt', warn = FALSE))

article <- Corpus(VectorSource(article))

# 去除标点

article <- tm_map(article, content_transformer(tolower))

article <- tm_map(article, removePunctuation)

article <- tm_map(article, removeNumbers)

article <- tm_map(article, removeWords, stopwords("en"))  # 去除英文停用词

article <- tm_map(article, stripWhitespace)

wordcloud(words = article, min.freq = 5, scale = c(3, 0.5), colors = brewer.pal(8, "Dark2"))

Sanguo1词云图

library(tm)

library(wordcloud)

library(jiebaR)



# 读取中文文本文件

text <- readLines("D:/RWorkPlace/第3章_类别比较型图表/sanguo1.txt", encoding = "UTF-8")

# 将文本合并为一个字符串

text <- paste(text, collapse = " ")

# 使用jiebaR分词

engine<-worker()

segmented_text <- segment(text,engine)

# 创建语料库

corpus <- Corpus(VectorSource(segmented_text))

# 进行文本预处理

corpus <- tm_map(corpus, removePunctuation)

corpus <- tm_map(corpus, removeNumbers)

corpus <- tm_map(corpus, stripWhitespace)

# 将Corpus对象转换为数据框

corpus_df <- data.frame(text = sapply(corpus, as.character))

# 创建词云图

wordcloud(words = corpus_df$text, min.freq = 50, scale = c(3, 0.5), colors = brewer.pal(8, "Dark2"))

NEWS词云图

library(tm)

library(wordcloud)



article <- tolower(readLines('D:/RWorkPlace/第3章_类别比较型图表/NEWS.txt', warn = FALSE))

article <- Corpus(VectorSource(article))

# 去除标点

article <- tm_map(article, content_transformer(tolower))

article <- tm_map(article, removePunctuation)

article <- tm_map(article, removeNumbers)

article <- tm_map(article, removeWords, stopwords("en"))  # 去除英文停用词

article <- tm_map(article, stripWhitespace)

wordcloud(words = article, min.freq = 10, scale = c(3, 0.5), colors = brewer.pal(8, "Dark2"))

全唐诗词云图

library(tm)

library(wordcloud)

library(RColorBrewer)

library(openxlsx)

library(jiebaR)



# 导入xlsx文件

file_path <- "D:/RWorkPlace/第3章_类别比较型图表/全唐诗.xlsx"

data <- read.xlsx(file_path, detectDates = TRUE)

# 合并多列文本为一个文本向量

text <- paste(data$poet, data$title, data$poem, sep = " ")

# 使用jiebaR分词

engine<-worker()

segmented_text <- segment(text,engine)

# 创建语料库

corpus <- Corpus(VectorSource(segmented_text))

# 进行文本预处理

corpus <- tm_map(corpus, removePunctuation)

corpus <- tm_map(corpus, removeNumbers)

corpus <- tm_map(corpus, stripWhitespace)

# 将Corpus对象转换为数据框

corpus_df <- data.frame(text = sapply(corpus, as.character))

# 创建词云图

wordcloud(words = corpus_df$text, min.freq = 70, scale = c(3, 0.5), colors = brewer.pal(8, "Dark2"))