# 加载rJava、Rwordseg库

library(rJava);

library(Rwordseg);

library(RColorBrewer);

# == 读入数据

lecture=read.csv("G:\\test.txt",sep=",",header=TRUE,fileEncoding="UTF-8");

# 查看前几行，看是否有字符编码问题

head(lecture);

# 获取数据集长度

n=length(lecture[,1]);

print(n)  

# == 文本预处理

res=lecture[lecture!=" "];

#剔除URL

res=gsub(pattern="http:[a-zA-Z\\/\\.0-9]+","",res);

#剔除特殊词

res=gsub(pattern="[我|你|的|了|是|和|阳|创业|宁阳]","",res);       

# == 分词+频数统计

words=unlist(lapply(X=res, FUN=segmentCN));

word=lapply(X=words, FUN=strsplit, " ");

v=table(unlist(word));

# 降序排序

v=rev(sort(v));

d=data.frame(word=names(v), freq=v);

# 过滤掉1个字和词频小于100的记录

d=subset(d, nchar(as.character(d$word))>1 & d$freq>=10)  

require(wordcloud)

library(RColorBrewer);

dd = head(d, 50)

op = par(bg = "lightyellow")      #背景为亮黄色

rainbowLevels = rainbow((dd$freq)/(max(dd$freq) - 10))      #不知道什么意义，删除后图形无太大变化

text(family = "Kai")

wordcloud(d$word, d$freq, scale=c(5,0.5),  random.order=FALSE, colors=brewer.pal(8, "Dark2"),use.r.layout=FALSE) #

par(op)