blocks|key|202946|text|R具有在一个窗口中绘制多个绘图的功能。如果软件包不支持一个窗口中的多个绘图，您可以使用R的标准仪器来解决问题。其他方法:使用此脚本的Example+of+several+ROCs文章：An+example+of+ROC+curves+plotting+with+ROCR|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|202947|entityMap|0|LINK|mutability|MUTABLE|url|https://github.com/chupvl/R_scripts|1|http://www.r-bloggers.com/an-example-of-roc-curves-plotting-with-rocr/^0|1U|N|0|2K|17|1|0^^$0|@$1|2|3|4|5|6|7|N|8|@]|9|@$A|O|B|P|1|Q]|$A|R|B|S|1|T]]|C|$]]|$1|D|3|-4|5|6|7|U|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]|L|$5|G|H|I|C|$J|M]]]]

R has functions for draw several plots in one window. And if package doesn't support several plots in one window,you can solve problem with standard instruments of R. Other way: <a href="https://github.com/chupvl/R_scripts" rel="nofollow">Example of several ROCs</a> 
Article with this script:<a href="http://www.r-bloggers.com/an-example-of-roc-curves-plotting-with-rocr/" rel="nofollow">An example of ROC curves plotting with ROCR</a>

blocks|key|3048763|text|您的lines-approach的问题在于，对于ROCR包中定义的performance类的对象，没有通用的S4行函数。但是您可以像使用额外的add+=+TRUE参数一样使用通用的plot函数。例如，这部分来自?plot.performance的示例页面：|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|3048764|library(ROCR)
data(ROCR.simple)
pred+<-+prediction(+ROCR.simple$predictions,+ROCR.simple$labels+)
pred2+<-+prediction(abs(ROCR.simple$predictions+%2B+
++++++++++++++++++++++++rnorm(length(ROCR.simple$predictions),+0,+0.1)),+
++++++++ROCR.simple$labels)
perf+<-+performance(+pred,+"tpr",+"fpr"+)
perf2+<-+performance(pred2,+"tpr",+"fpr")
plot(+perf,+colorize+=+TRUE)
plot(perf2,+add+=+TRUE,+colorize+=+TRUE)|code-block|syntax|javascript|3048765|或者，您可以将所有预测存储在一个矩阵中，然后在一个矩阵中完成所有后续步骤：|3048766|preds+<-+cbind(p1+=+ROCR.simple$predictions,+
++++++++++++++++p2+=+abs(ROCR.simple$predictions+%2B+
++++++++++++++++rnorm(length(ROCR.simple$predictions),+0,+0.1)))

pred.mat+<-+prediction(preds,+labels+=+matrix(ROCR.simple$labels,+
++++++++++++++++nrow+=+length(ROCR.simple$labels),+ncol+=+2)+)

perf.mat+<-+performance(pred.mat,+"tpr",+"fpr")
plot(perf.mat,+colorize+=+TRUE)|3048767|顺便说一句，如果你因为某些原因真的想用lines来绘制连续的ROC曲线，你必须得做点什么。如下所示：|3048768|plot(perf)+
lines(perf2@x.values[[1]],+perf2@y.values[[1]],+col+=+2)|3048769|entityMap^0|2|5|O|4|X|B|1I|2|1Z|A|2X|H|0|0|0|0|J|5|0|0^^$0|@$1|2|3|4|5|6|7|U|8|@$9|V|A|W|B|C]|$9|X|A|Y|B|C]|$9|Z|A|10|B|C]|$9|11|A|12|B|C]|$9|13|A|14|B|C]|$9|15|A|16|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|17|8|@]|D|@]|E|$I|J]]|$1|K|3|L|5|6|7|18|8|@]|D|@]|E|$]]|$1|M|3|N|5|H|7|19|8|@]|D|@]|E|$I|J]]|$1|O|3|P|5|6|7|1A|8|@$9|1B|A|1C|B|C]]|D|@]|E|$]]|$1|Q|3|R|5|H|7|1D|8|@]|D|@]|E|$I|J]]|$1|S|3|-4|5|6|7|1E|8|@]|D|@]|E|$]]]|T|$]]

The problem with your <code>lines</code>-approach is that there is no generic <code>S4</code> lines function for an object of class <code>performance</code> defined in the <code>ROCR</code> package. But you can use the generic plot function as you did with an additional <code>add = TRUE</code> argument. For example this is partly from the example page of <code>?plot.performance</code>: 

<pre><code>library(ROCR)
data(ROCR.simple)
pred &lt;- prediction( ROCR.simple$predictions, ROCR.simple$labels )
pred2 &lt;- prediction(abs(ROCR.simple$predictions + 
 rnorm(length(ROCR.simple$predictions), 0, 0.1)), 
 ROCR.simple$labels)
perf &lt;- performance( pred, "tpr", "fpr" )
perf2 &lt;- performance(pred2, "tpr", "fpr")
plot( perf, colorize = TRUE)
plot(perf2, add = TRUE, colorize = TRUE)
</code></pre>

OR, you can store all your predictions in a matrix and do all the subsequent steps in one: 

<pre><code>preds &lt;- cbind(p1 = ROCR.simple$predictions, 
 p2 = abs(ROCR.simple$predictions + 
 rnorm(length(ROCR.simple$predictions), 0, 0.1)))

pred.mat &lt;- prediction(preds, labels = matrix(ROCR.simple$labels, 
 nrow = length(ROCR.simple$labels), ncol = 2) )

perf.mat &lt;- performance(pred.mat, "tpr", "fpr")
plot(perf.mat, colorize = TRUE)
</code></pre>

Btw, if you for some reason really wanted to use <code>lines</code> to plot consecutive ROC curves you would have to do sth. like this:

<pre><code>plot(perf) 
lines(perf2@x.values[[1]], perf2@y.values[[1]], col = 2)
</code></pre>

blocks|key|202957|text|回显@adibender，并添加注释:该示例没有涵盖如何使用第二种方法(一次绘制所有曲线)为每条曲线设置单独的颜色。在这种情况下，将col作为列表传递：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|202958|library(ROCR)
data(ROCR.hiv)
x+++<-+prediction(ROCR.hiv$hiv.nn$predictions,+ROCR.hiv$hiv.nn$labels)
ROC+<-+performance(x,+"tpr",+"fpr")
plot(ROC,+col+=+as.list(1:10))|code-block|syntax|javascript|202959|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

Echoing @adibender, and adding a comment: the example doesn't cover how to set separate colors for each individual curve using the second (plot all at once) approach. In this case, pass col as a list:

<pre><code>library(ROCR)
data(ROCR.hiv)
x &lt;- prediction(ROCR.hiv$hiv.nn$predictions, ROCR.hiv$hiv.nn$labels)
ROC &lt;- performance(x, "tpr", "fpr")
plot(ROC, col = as.list(1:10))
</code></pre>

Is it possible to plot the roc curve for diffrent classifiers in the same plot using the ROCR package? I've tried:
<pre><code>&gt;plot(perf.neuralNet, colorize=TRUE)
&gt;lines(perf.randomForest)
</code></pre>
But I get:
<blockquote>
Error en as.double(y) :
cannot coerce type 'S4' to vector of type 'double'
</blockquote>
Thank you!

Multiple ROC curves in one plot ROCR

是否可以使用ROCR包在同一图中绘制不同分类器的roc曲线？我试过了：>plot(perf.neuralNet, colorize=TRUE)>lines(perf.randomForest)但我得到了：错误en as.double(y)：无法将类型'S4‘强制为类型'double’的向量谢谢!

问一块岩层中的多条ROC曲线
EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问一块岩层中的多条ROC曲线EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问一块岩层中的多条ROC曲线
EN