如何计算除MNIST以外的较大数据集以及R Studio中的简单编码是什么

Question

我尝试在R Studio中运行编码，但无法产生准确性结果。您能否帮助我使用RBM方法来预测R Studio中较大数据集中的准确性的示例？我的预期输出：1但是，下面的编码在使用RBM方法预测数据集的准确性方面存在一些错误。

install.packages("devtools")
# Load devtools library(devtools)
# install RBM install_github("TimoMatzen/RBM")
# load RBM library(RBM)
Wednesdaydataset <- read.csv('C:\Users\FSKKP\Desktop\R iqa\dataset20181220T065754Z-001\dataset\Wednesday-workingHours.pcap_ISCX.csv') 
Wednesdaydataset
class(Wednesdaydataset) 
str(Wednesdaydataset) 
Wednesdaydataset <-as.matrix(Wednesdaydataset) 
Wednesdaydataset <-cbind(Wednesdaydataset) 
class(Wednesdaydataset)
str(Wednesdaydataset)
view(Wednesdaydataset) 
set.seed(1234)
ind<-sample(2,nrow(Wednesdaydataset),replace = TRUE,prob=c(0.7,0.30))
train.data<-Wednesdaydataset [ind==1,] 
test.data<-Wednesdaydataset [ind==2,]
# First get the train data from train.data 
train <- train.data$Active.Min
# Then fit the model
 modelRBM <- RBM(x = train, n.iter = 1000, n.hidden = 100, size.minibatch = 10)
# First get the train labels of test.data 
test <- test.data$Active.Min
# This time we add the labels as the y argument
modelClassRBM <- RBM(x = train, y = test, n.iter = 1000, n.hidden = 100, size.minibatch = 10)
# First get the test labels of test.data 
test <- test.data$Active.Min
# Give our ClassRBM model as input
PredictRBM(test = test, labels = test, model = modelClassRBM)

Answer 1

您只需总结对角线并将其分配总和：

# Some lables (like your outputs from RBM)
lab_true <- c("a", "a", "a", "b", "c")
lab_pred <- c("a", "b", "c", "b", "a")
# Making them into a confusion matrix
confusion_matrix <- table(lab_true, lab_pred)
# Calculating overall precision
overall_precision <- sum(diag(confusion_matrix))/sum(confusion_matrix)