Plot confusion matrix in R using ggplot

Question

I have two confusion matrices with calculated values as true positive (tp), false positives (fp), true negatives(tn) and false negatives (fn), corresponding to two different

Answer 1

It is a very old question, still it seems there is a quite straight forward solution to that using ggplot2 which hasn't been mentioned.

Hope it might be helpful to someone:

cm <- confusionMatrix(factor(y.pred), factor(y.test), dnn = c("Prediction", "Reference"))

ggplot(as.data.frame(cm$table), aes(Prediction,sort(Reference,decreasing = T), fill= Freq)) +
        geom_tile() + geom_text(aes(label=Freq)) +
        scale_fill_gradient(low="white", high="#009194") +
        labs(x = "Reference",y = "Prediction") +
        scale_x_discrete(labels=c("Class_1","Class_2","Class_3","Class_4")) +
        scale_y_discrete(labels=c("Class_4","Class_3","Class_2","Class_1"))

Answer 2

Old question, but I wrote this function which I think makes a prettier answer. Results in a divergent color palette (or whatever you want, but default is divergent):

prettyConfused<-function(Actual,Predict,colors=c("white","red4","dodgerblue3"),text.scl=5){
  actual = as.data.frame(table(Actual))
  names(actual) = c("Actual","ActualFreq")

  #build confusion matrix
  confusion = as.data.frame(table(Actual, Predict))
  names(confusion) = c("Actual","Predicted","Freq")

  #calculate percentage of test cases based on actual frequency

  confusion = merge(confusion, actual, by=c('Actual','Actual'))
  confusion$Percent = confusion$Freq/confusion$ActualFreq*100
  confusion$ColorScale<-confusion$Percent*-1
  confusion[which(confusion$Actual==confusion$Predicted),]$ColorScale<-confusion[which(confusion$Actual==confusion$Predicted),]$ColorScale*-1
  confusion$Label<-paste(round(confusion$Percent,0),"%, n=",confusion$Freq,sep="")
  tile <- ggplot() +
    geom_tile(aes(x=Actual, y=Predicted,fill=ColorScale),data=confusion, color="black",size=0.1) +
    labs(x="Actual",y="Predicted")

  tile = tile +
        geom_text(aes(x=Actual,y=Predicted, label=Label),data=confusion, size=text.scl, colour="black") +
        scale_fill_gradient2(low=colors[2],high=colors[3],mid=colors[1],midpoint = 0,guide='none')
}

Answer 3

This could be a good start

library(ggplot2)
ggplot(data =  dframe, mapping = aes(x = label, y = method)) +
  geom_tile(aes(fill = value), colour = "white") +
  geom_text(aes(label = sprintf("%1.0f",value)), vjust = 1) +
  scale_fill_gradient(low = "white", high = "steelblue")

Edited

TClass <- factor(c(0, 0, 1, 1))
PClass <- factor(c(0, 1, 0, 1))
Y      <- c(2816, 248, 34, 235)
df <- data.frame(TClass, PClass, Y)

library(ggplot2)
ggplot(data =  df, mapping = aes(x = TClass, y = PClass)) +
  geom_tile(aes(fill = Y), colour = "white") +
  geom_text(aes(label = sprintf("%1.0f", Y)), vjust = 1) +
  scale_fill_gradient(low = "blue", high = "red") +
  theme_bw() + theme(legend.position = "none")

Answer 4

Here's another ggplot2 based option; first the data (from caret):

library(caret)

# data/code from "2 class example" example courtesy of ?caret::confusionMatrix

lvs <- c("normal", "abnormal")
truth <- factor(rep(lvs, times = c(86, 258)),
                levels = rev(lvs))
pred <- factor(
  c(
    rep(lvs, times = c(54, 32)),
    rep(lvs, times = c(27, 231))),
  levels = rev(lvs))

confusionMatrix(pred, truth)

And to construct the plots (substitute your own matrix below as needed when setting up "table"):

library(ggplot2)
library(dplyr)

table <- data.frame(confusionMatrix(pred, truth)$table)

plotTable <- table %>%
  mutate(goodbad = ifelse(table$Prediction == table$Reference, "good", "bad")) %>%
  group_by(Reference) %>%
  mutate(prop = Freq/sum(Freq))

# fill alpha relative to sensitivity/specificity by proportional outcomes within reference groups (see dplyr code above as well as original confusion matrix for comparison)
ggplot(data = plotTable, mapping = aes(x = Reference, y = Prediction, fill = goodbad, alpha = prop)) +
  geom_tile() +
  geom_text(aes(label = Freq), vjust = .5, fontface  = "bold", alpha = 1) +
  scale_fill_manual(values = c(good = "green", bad = "red")) +
  theme_bw() +
  xlim(rev(levels(table$Reference)))

# note: for simple alpha shading by frequency across the table at large, simply use "alpha = Freq" in place of "alpha = prop" when setting up the ggplot call above, e.g.,
ggplot(data = plotTable, mapping = aes(x = Reference, y = Prediction, fill = goodbad, alpha = Freq)) +
  geom_tile() +
  geom_text(aes(label = Freq), vjust = .5, fontface  = "bold", alpha = 1) +
  scale_fill_manual(values = c(good = "green", bad = "red")) +
  theme_bw() +
  xlim(rev(levels(table$Reference)))

Answer 5

A slightly more modular solution based on MYaseen208's answer. Might be more effective for large datasets / multinomial classification:

confusion_matrix <- as.data.frame(table(predicted_class, actual_class))

ggplot(data = confusion_matrix
       mapping = aes(x = predicted_class,
                     y = Var2)) +
  geom_tile(aes(fill = Freq)) +
  geom_text(aes(label = sprintf("%1.0f", Freq)), vjust = 1) +
  scale_fill_gradient(low = "blue",
                      high = "red",
                      trans = "log") # if your results aren't quite as clear as the above example