1

できれば混乱行列()関数を使用して混同行列を作成しようとしていますが、次のエラーが発生します: sort.list(y) のエラー: 'x' は 'sort.list' のアトミックである必要があります' を呼び出しましたか?リストを並べ替えますか？

table() 関数も使用してみましたが、同じエラーが発生しました。

以下は私のコード全体です：

#install load libraries
install.packages('MASS')
install.packages('tree')
install.packages("e1071")
install.packages("caret")
library('MASS')
library('tree')
library('e1071')
library('caret')
set.seed(1985)

#GET DATA
training <- read.csv("C:/Users/anaim/data_minig_project/pml-training.csv",header=TRUE, sep=",", na.strings="NA", dec=".", strip.white=TRUE)
training_df <- data.frame(training,stringsAsFactors=FALSE)
nrow(training_df)
ncol(training_df)

#create train & test set splits
inTrain <- createDataPartition(y=training_df$classe, p=0.75, list=FALSE)
training_data <- training_df[inTrain,]
testing_data<- training_df[-inTrain,]

#FEATURE SELECTION & DATA CLEANING
#one can see numbers of features is quite large with 160 columns, therefore we will refer to the studies such as paper #1 to start and reduce the number of features

#subset based on features mentioned studies 
training_data_subset <- subset(training_data, select=c("avg_roll_belt","var_roll_belt","var_total_accel_belt","amplitude_roll_belt","max_roll_belt","var_roll_belt",
                                                       "var_accel_arm","magnet_arm_x","magnet_arm_y","magnet_arm_z","accel_dumbbell_y","accel_dumbbell_z","magnet_dumbbell_x","gyros_dumbbell_x",
                                                       "gyros_dumbbell_y","gyros_dumbbell_z","pitch_forearm","gyros_forearm_x","gyros_forearm_y","classe"))

#subset based on features mentioned studies 
testing_data_subset <- subset(testing_data, select=c("avg_roll_belt","var_roll_belt","var_total_accel_belt","amplitude_roll_belt","max_roll_belt","var_roll_belt",
                                                     "var_accel_arm","magnet_arm_x","magnet_arm_y","magnet_arm_z","accel_dumbbell_y","accel_dumbbell_z","magnet_dumbbell_x","gyros_dumbbell_x",
                                                     "gyros_dumbbell_y","gyros_dumbbell_z","pitch_forearm","gyros_forearm_x","gyros_forearm_y","classe"))


#all NAs to 0
testing_data_subset[is.na(testing_data_subset)] <- 0
training_data_subset[is.na(training_data_subset)] <- 0

#load library(e1071) before using skewness() 
#load library(e1071) befortraining_datae using skewness() 
#investigate skewness
# Interpretation of skewness - http://www.tc3.edu/instruct/sbrown/stat/shape.htm#SkewnessCompute

skewness_result <- apply(training_data_subset[, sapply(training_data_subset, is.numeric)], 2, skewness)

skewness_df <- data.frame(skewness_result)

#remove highly skewed columns
remove <- c("var_roll_belt","var_total_accel_belt","amplitude_roll_belt","var_roll_belt","var_roll_belt.1","magnet_dumbbell_x")
training_data_subset <- training_data_subset[, !(colnames(training_data_subset) %in% remove), drop=FALSE] 
testing_data_subset <- testing_data_subset[, !(colnames(testing_data_subset) %in% remove), drop=FALSE] 

#valid columns were removed 
ncol(training_data_subset)
ncol(testing_data_subset)

#BUILD MODEL

#1)decision tree

exercise.model <- tree(formula = classe ~ ., data = training_data_subset)
summary(exercise.model)

plot(exercise.model)
text(exercise.model ,pretty =0)

#MODEL EVALUATION
exercise.prediction <- predict(exercise.model,newdata = testing_data_subset, type="tree")

**#THIS IS WERE I GET THE ERROR** 
confusionMatrix(exercise.prediction,testing_data_subset[['classe']])
confusionMatrix(exercise.prediction,testing_data_subset$classe)

**# I also tried table() just to get raw True (positive + True Negatives / Total) values but I got the same error**  

table(exercise.prediction, testing_data_subset[['classe']])
table(exercise.prediction,testing_data_subset$classe)

混乱マトリックス（）を使用して混乱マトリックスを作成する際の助けをいただければ幸いです。

ありがとう

4

1 に答える 1

1

tree() 関数は、決定木を構築するための R の基本関数ですが、confusionMatrix() は CARET パッケージの一部であるため、tree() の出力は、何らかの理由で、confusionMatrix() と互換性がありませんでした。tree() を Than に置き換えると exercise.model <- train(classe ~ ., preProcess = c("center", "scale", "BoxCox", "pca"), data =training_data_subset ,method ="rpart");、confusionMatrix() および table() 関数が機能するようになりました。

于 2015-08-13T20:06:47.660 に答える