我正在使用C50决策树算法。我能够构建树并得到摘要，但无法弄清楚如何绘制或可视化树。
我的C50模型名为credit_model
在其他决策树包中，我通常使用类似于plot（credit_model）的命令。在rpart中，是rpart.plot（credit_model）。
在C50算法中，相当于plot的命令是什么？
如何在R中绘制/可视化C50决策树？
9
- mpg
2
2目前（2015-08-07），C5.0具有绘图功能。 - user989762
这个问题更适合在[可视化C5.0决策树]讨论（http://stats.stackexchange.com/questions/198134/visualizing-c5-0-decision-tree），而且这里的所有回答都已经过时了，因为现在有了绘图函数。 - smci
3个回答
1
这是您正在寻找的函数：
C5.0.graphviz <- function( C5.0.model, filename, fontname ='Arial',col.draw ='black',
col.font ='blue',col.conclusion ='lightpink',col.question = 'grey78',
shape.conclusion ='box3d',shape.question ='diamond',
bool.substitute = 'None', prefix=FALSE, vertical=TRUE ) {
library(cwhmisc)
library(stringr)
treeout <- C5.0.model$output
treeout<- substr(treeout, cpos(treeout, 'Decision tree:', start=1)+14,nchar(treeout))
treeout<- substr(treeout, 1,cpos(treeout, 'Evaluation on training data', start=1)-2)
variables <- data.frame(matrix(nrow=500, ncol=4))
names(variables) <- c('SYMBOL','TOKEN', 'TYPE' , 'QUERY')
connectors <- data.frame(matrix(nrow=500, ncol=3))
names(connectors) <- c('TOKEN', 'START','END')
theStack <- data.frame(matrix(nrow=500, ncol=1))
names(theStack) <- c('ITEM')
theStackIndex <- 1
currentvar <- 1
currentcon <- 1
open_connection <- TRUE
previousindent <- -1
firstindent <- 4
substitutes <- data.frame(None=c('= 0','= 1'), yesno=c('no','yes'),
truefalse=c('false', 'true'),TF=c('F','T'))
dtreestring<-unlist( scan(text= treeout, sep='\n', what =list('character')))
for (linecount in c(1:length(dtreestring))) {
lineindent<-0
shortstring <- str_trim(dtreestring[linecount], side='left')
leadingspaces <- nchar(dtreestring[linecount]) - nchar(shortstring)
lineindent <- leadingspaces/4
dtreestring[linecount]<-str_trim(dtreestring[linecount], side='left')
while (!is.na(cpos(dtreestring[linecount], ': ', start=1)) ) {
lineindent<-lineindent + 1
dtreestring[linecount]<-substr(dtreestring[linecount],
ifelse(is.na(cpos(dtreestring[linecount], ': ', start=1)), 1,
cpos(dtreestring[linecount], ': ', start=1)+4),
nchar(dtreestring[linecount]) )
shortstring <- str_trim(dtreestring[linecount], side='left')
leadingspaces <- nchar(dtreestring[linecount]) - nchar(shortstring)
lineindent <- lineindent + leadingspaces/4
dtreestring[linecount]<-str_trim(dtreestring[linecount], side='left')
}
if (!is.na(cpos(dtreestring[linecount], ':...', start=1)))
lineindent<- lineindent + 1
dtreestring[linecount]<-substr(dtreestring[linecount],
ifelse(is.na(cpos(dtreestring[linecount], ':...', start=1)), 1,
cpos(dtreestring[linecount], ':...', start=1)+4),
nchar(dtreestring[linecount]) )
dtreestring[linecount]<-str_trim(dtreestring[linecount])
stringlist <- strsplit(dtreestring[linecount],'\\:')
stringpart <- strsplit(unlist(stringlist)[1],'\\s')
if (open_connection==TRUE) {
variables[currentvar,'TOKEN'] <- unlist(stringpart)[1]
variables[currentvar,'SYMBOL'] <- paste('node',as.character(currentvar), sep='')
variables[currentvar,'TYPE'] <- shape.question
variables[currentvar,'QUERY'] <- 1
theStack[theStackIndex,'ITEM']<-variables[currentvar,'SYMBOL']
theStack[theStackIndex,'INDENT'] <-firstindent
theStackIndex<-theStackIndex+1
currentvar <- currentvar + 1
if(currentvar>2) {
connectors[currentcon - 1,'END'] <- variables[currentvar - 1, 'SYMBOL']
}
}
connectors[currentcon,'TOKEN'] <- paste(unlist(stringpart)[2],unlist(stringpart)[3])
if (connectors[currentcon,'TOKEN']=='= 0')
connectors[currentcon,'TOKEN'] <- as.character(substitutes[1,bool.substitute])
if (connectors[currentcon,'TOKEN']=='= 1')
connectors[currentcon,'TOKEN'] <- as.character(substitutes[2,bool.substitute])
if (open_connection==TRUE) {
if (lineindent<previousindent) {
theStackIndex <- theStackIndex-(( previousindent- lineindent) +1 )
currentsymbol <-theStack[theStackIndex,'ITEM']
} else
currentsymbol <-variables[currentvar - 1,'SYMBOL']
} else {
currentsymbol <-theStack[theStackIndex-((previousindent -lineindent ) +1 ),'ITEM']
theStackIndex <- theStackIndex-(( previousindent- lineindent) )
}
connectors[currentcon, 'START'] <- currentsymbol
currentcon <- currentcon + 1
open_connection <- TRUE
if (length(unlist(stringlist))==2) {
stringpart2 <- strsplit(unlist(stringlist)[2],'\\s')
variables[currentvar,'TOKEN'] <- paste(ifelse((prefix==FALSE),'','Class'), unlist(stringpart2)[2])
variables[currentvar,'SYMBOL'] <- paste('node',as.character(currentvar), sep='')
variables[currentvar,'TYPE'] <- shape.conclusion
variables[currentvar,'QUERY'] <- 0
currentvar <- currentvar + 1
connectors[currentcon - 1,'END'] <- variables[currentvar - 1,'SYMBOL']
open_connection <- FALSE
}
previousindent<-lineindent
}
runningstring <- paste('digraph g {', 'graph ', sep='\n')
runningstring <- paste(runningstring, ' [rankdir="', sep='')
runningstring <- paste(runningstring, ifelse(vertical==TRUE,'TB','LR'), sep='' )
runningstring <- paste(runningstring, '"]', sep='')
for (lines in c(1:(currentvar-1))) {
runningline <- paste(variables[lines,'SYMBOL'], '[shape="')
runningline <- paste(runningline,variables[lines,'TYPE'], sep='' )
runningline <- paste(runningline,'" label ="', sep='' )
runningline <- paste(runningline,variables[lines,'TOKEN'], sep='' )
runningline <- paste(runningline,
'" style=filled fontcolor=', sep='')
runningline <- paste(runningline, col.font)
runningline <- paste(runningline,' color=' )
runningline <- paste(runningline, col.draw)
runningline <- paste(runningline,' fontname=')
runningline <- paste(runningline, fontname)
runningline <- paste(runningline,' fillcolor=')
runningline <- paste(runningline,
ifelse(variables[lines,'QUERY']== 0 ,col.conclusion,col.question))
runningline <- paste(runningline,'];')
runningstring <- paste(runningstring, runningline , sep='\n')
}
for (lines in c(1:(currentcon-1))) {
runningline <- paste (connectors[lines,'START'], '->')
runningline <- paste (runningline, connectors[lines,'END'])
runningline <- paste (runningline,'[label="')
runningline <- paste (runningline,connectors[lines,'TOKEN'], sep='')
runningline <- paste (runningline,'" fontname=', sep='')
runningline <- paste (runningline, fontname)
runningline <- paste (runningline,'];')
runningstring <- paste(runningstring, runningline , sep='\n')
}
runningstring <- paste(runningstring,'}')
cat(runningstring)
sink(filename, split=TRUE)
cat(runningstring)
sink()
}
- aliakbarian
1
您可以使用以下程序，直接将决策树转换为GraphViz点语言（然后使用GraphViz绘制它 - 需要先安装GraphViz http://www.graphviz.org/）。
< p > < em >编辑：此处包含版本2，能够处理多分支树（版本1仅能处理具有两个分裂的树）。 版本2.2更正了缺少的初始化。
你可以打开mygraph.png文件作为PNG（位图），并在应用程序中使用它。
如需更多详细信息，请参阅原始帖子：http://r-project-thanos.blogspot.de/2014/09/plot-c50-decision-trees-in-r.html
在R中调用示例：
library(C50)
data(churn)
treeModel <- C5.0(x = churnTrain[, -20], y = churnTrain$churn)
C5.0.graphviz(treeModel, 'C:\\mydotfile.txt')
然后从操作系统（OS，例如Windows命令提示符）开始：
dot -Tpng 'C:\mydotfile.txt' > 'C:\mygraph.png'
你可以打开mygraph.png文件作为PNG（位图），并在应用程序中使用它。
如需更多详细信息，请参阅原始帖子：http://r-project-thanos.blogspot.de/2014/09/plot-c50-decision-trees-in-r.html
C5.0.graphviz <- function( C5.0.model, filename, fontname ='Arial',
col.draw ='black',col.font ='blue',col.conclusion ='lightpink',
col.question = 'grey78', shape.conclusion ='box3d',shape.question ='diamond',
bool.substitute = 'None', prefix=FALSE, vertical=TRUE ) {
library(cwhmisc)
library(stringr)
treeout <- C5.0.model$output
treeout<- substr(treeout, cpos(treeout, 'Decision tree:', start=1)+14,nchar(treeout))
treeout<- substr(treeout, 1,cpos(treeout, 'Evaluation on training data', start=1)-2)
variables <- data.frame(matrix(nrow=500, ncol=4))
names(variables) <- c('SYMBOL','TOKEN', 'TYPE' , 'QUERY')
connectors <- data.frame(matrix(nrow=500, ncol=3))
names(connectors) <- c('TOKEN', 'START','END')
theStack <- data.frame(matrix(nrow=500, ncol=1))
names(theStack) <- c('ITEM')
theStackIndex <- 1
currentvar <- 1
currentcon <- 1
open_connection <- TRUE
previousindent <- -1
firstindent <- 4
substitutes <- data.frame(None=c('= 0','= 1'), yesno=c('no','yes'),
truefalse=c('false', 'true'),TF=c('F','T'))
dtreestring<-unlist( scan(text= treeout, sep='\n', what =list('character')))
for (linecount in c(1:length(dtreestring))) {
lineindent<-0
shortstring <- str_trim(dtreestring[linecount], side='left')
leadingspaces <- nchar(dtreestring[linecount]) - nchar(shortstring)
lineindent <- leadingspaces/4
dtreestring[linecount]<-str_trim(dtreestring[linecount], side='left')
while (!is.na(cpos(dtreestring[linecount], ': ', start=1)) ) {
lineindent<-lineindent + 1
dtreestring[linecount]<-substr(dtreestring[linecount],
ifelse(is.na(cpos(dtreestring[linecount], ': ', start=1)), 1,
cpos(dtreestring[linecount], ': ', start=1)+4),
nchar(dtreestring[linecount]) )
shortstring <- str_trim(dtreestring[linecount], side='left')
leadingspaces <- nchar(dtreestring[linecount]) - nchar(shortstring)
lineindent <- lineindent + leadingspaces/4
dtreestring[linecount]<-str_trim(dtreestring[linecount], side='left')
}
if (!is.na(cpos(dtreestring[linecount], ':...', start=1)))
lineindent<- lineindent + 1
dtreestring[linecount]<-substr(dtreestring[linecount],
ifelse(is.na(cpos(dtreestring[linecount], ':...', start=1)), 1,
cpos(dtreestring[linecount], ':...', start=1)+4),
nchar(dtreestring[linecount]) )
dtreestring[linecount]<-str_trim(dtreestring[linecount])
stringlist <- strsplit(dtreestring[linecount],'\\:')
stringpart <- strsplit(unlist(stringlist)[1],'\\s')
if (open_connection==TRUE) {
variables[currentvar,'TOKEN'] <- unlist(stringpart)[1]
variables[currentvar,'SYMBOL'] <- paste('node',as.character(currentvar), sep='')
variables[currentvar,'TYPE'] <- shape.question
variables[currentvar,'QUERY'] <- 1
theStack[theStackIndex,'ITEM']<-variables[currentvar,'SYMBOL']
theStack[theStackIndex,'INDENT'] <-firstindent
theStackIndex<-theStackIndex+1
currentvar <- currentvar + 1
if(currentvar>2) {
connectors[currentcon - 1,'END'] <- variables[currentvar - 1, 'SYMBOL']
}
}
connectors[currentcon,'TOKEN'] <- paste(unlist(stringpart)[2],unlist(stringpart)[3])
if (connectors[currentcon,'TOKEN']=='= 0')
connectors[currentcon,'TOKEN'] <- as.character(substitutes[1,bool.substitute])
if (connectors[currentcon,'TOKEN']=='= 1')
connectors[currentcon,'TOKEN'] <- as.character(substitutes[2,bool.substitute])
if (open_connection==TRUE) {
if (lineindent<previousindent) {
theStackIndex <- theStackIndex-(( previousindent- lineindent) +1 )
currentsymbol <-theStack[theStackIndex,'ITEM']
} else
currentsymbol <-variables[currentvar - 1,'SYMBOL']
} else {
currentsymbol <-theStack[theStackIndex-((previousindent -lineindent ) +1 ),'ITEM']
theStackIndex <- theStackIndex-(( previousindent- lineindent) )
}
connectors[currentcon, 'START'] <- currentsymbol
currentcon <- currentcon + 1
open_connection <- TRUE
if (length(unlist(stringlist))==2) {
stringpart2 <- strsplit(unlist(stringlist)[2],'\\s')
variables[currentvar,'TOKEN'] <- paste(ifelse((prefix==FALSE),'','Class'), unlist(stringpart2)[2])
variables[currentvar,'SYMBOL'] <- paste('node',as.character(currentvar), sep='')
variables[currentvar,'TYPE'] <- shape.conclusion
variables[currentvar,'QUERY'] <- 0
currentvar <- currentvar + 1
connectors[currentcon - 1,'END'] <- variables[currentvar - 1,'SYMBOL']
open_connection <- FALSE
}
previousindent<-lineindent
}
runningstring <- paste('digraph g {', 'graph ', sep='\n')
runningstring <- paste(runningstring, ' [rankdir="', sep='')
runningstring <- paste(runningstring, ifelse(vertical==TRUE,'TB','LR'), sep='' )
runningstring <- paste(runningstring, '"]', sep='')
for (lines in c(1:(currentvar-1))) {
runningline <- paste(variables[lines,'SYMBOL'], '[shape="')
runningline <- paste(runningline,variables[lines,'TYPE'], sep='' )
runningline <- paste(runningline,'" label ="', sep='' )
runningline <- paste(runningline,variables[lines,'TOKEN'], sep='' )
runningline <- paste(runningline,
'" style=filled fontcolor=', sep='')
runningline <- paste(runningline, col.font)
runningline <- paste(runningline,' color=' )
runningline <- paste(runningline, col.draw)
runningline <- paste(runningline,' fontname=')
runningline <- paste(runningline, fontname)
runningline <- paste(runningline,' fillcolor=')
runningline <- paste(runningline,
ifelse(variables[lines,'QUERY']== 0 ,col.conclusion,col.question))
runningline <- paste(runningline,'];')
runningstring <- paste(runningstring, runningline , sep='\n')
}
for (lines in c(1:(currentcon-1))) {
runningline <- paste (connectors[lines,'START'], '->')
runningline <- paste (runningline, connectors[lines,'END'])
runningline <- paste (runningline,'[label="')
runningline <- paste (runningline,connectors[lines,'TOKEN'], sep='')
runningline <- paste (runningline,'" fontname=', sep='')
runningline <- paste (runningline, fontname)
runningline <- paste (runningline,'];')
runningstring <- paste(runningstring, runningline , sep='\n')
}
runningstring <- paste(runningstring,'}')
cat(runningstring)
sink(filename, split=TRUE)
cat(runningstring)
sink()
}
灭霸
- Thanos
3
你如何在R中使用graphviz函数？ - Cybernetic
你不需要使其可用。你可以从操作系统（Windows、Linux等）中调用Graphviz的dot命令。输入参数是由上面介绍的C5.0.graphviz函数生成的文本文件，dot命令的输出文件将是图形文件，可用于你的应用程序（Word等）。 - Thanos
我遇到了一个错误
dot: can't open 'mytree.txt'，你有什么想法为什么会出现这个错误？ - Furqan Hashim1
目前还没有内置的内容。我一直在为partykit包（例如as.party）工作适配器，但并没有取得太大进展。
Max
- topepo
1
2现在已经有了，对于新来的人...它绘制树形图而不是基于规则的模型...顺便说一下：https://cran.r-project.org/web/packages/C50/C50.pdf - slushy
网页内容由stack overflow 提供, 点击上面的可以查看英文原文，
原文链接
原文链接