如何在 R 中绘制/可视化 C50 决策树？
Posted
技术标签:
【中文标题】如何在 R 中绘制/可视化 C50 决策树？【英文标题】：How to plot/visualize a C50 decision tree in R? 【发布时间】：2014-02-11 22:53:37 【问题描述】：我正在使用 C50 决策树算法。我能够构建树并获得摘要，但无法弄清楚如何绘制或即树。
我的 C50 模型称为 credit_model
在其他决策树包中，我通常使用 plot(credit_model) 之类的东西。在 rpart 中是 rpart.plot(credit_model)。
C50 算法中的等价物是什么？
【问题讨论】：
目前（2015-08-07）C5.0有绘图功能 这在Visualizing C5.0 Decision Tree? 上有更多的主题，这里的所有答案无论如何都已经过时了，现在有一个绘图功能。 【参考方案1】：目前，没有内置的。我一直在为partykit 包（例如as.party）开发适配器，但还没有走多远。
最大
【讨论】：
它现在就在那里，对于新人来说......它绘制了树，但不是基于规则的模型......顺便说一句：cran.r-project.org/web/packages/C50/C50.pdf【参考方案2】：您可以使用以下例程，将决策树直接转换为 GraphViz 点语言（然后使用 GraphViz 绘制它 - 需要之前安装的 GraphViz (http://www.graphviz.org/)）。
编辑： 版本 2 包含在下文中，它能够处理多分支树（版本 1 可以处理只有两个拆分的树）。 2.2 版更正了缺失的初始化。
R 中的调用示例：
library(C50)
data(churn)
treeModel <- C5.0(x = churnTrain[, -20], y = churnTrain$churn)
C5.0.graphviz(treeModel, 'C:\\mydotfile.txt')
然后从操作系统（操作系统，例如 Windows 命令提示符）：
dot -Tpng 'C:\mydotfile.txt' > 'C:\mygraph.png'
然后您可以将 mygraph.png 文件作为 PNG（位图）打开并在您的应用程序中使用。
更多详情，请看原文：http://r-project-thanos.blogspot.de/2014/09/plot-c50-decision-trees-in-r.html
C5.0.graphviz <- function( C5.0.model, filename, fontname ='Arial',
col.draw ='black',col.font ='blue',col.conclusion ='lightpink',
col.question = 'grey78', shape.conclusion ='box3d',shape.question ='diamond',
bool.substitute = 'None', prefix=FALSE, vertical=TRUE )
library(cwhmisc)
library(stringr)
treeout <- C5.0.model$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
【讨论】：
如何让 graphviz 函数在 R 中可用？ 你没有让它可用。您可以从操作系统（Windows、Linux 等）调用 Graphviz 的 dot 命令。输入参数是上面介绍的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，在您的应用程序中使用（Word 等） 我收到一个错误dot: can't open 'mytree.txt' 知道为什么吗？【参考方案3】：
这是您正在寻找的功能：
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()
【讨论】：
以上是关于如何在 R 中绘制/可视化 C50 决策树？的主要内容，如果未能解决你的问题，请参考以下文章