k-NNの精度が間違っています

私はk-NNを初めて使用しているため、UCI MLリポジトリのタイタニックデータセットで学ぶことをお勧めします。k-NNの精度が間違っています

私は精度（accs）に基づいて最良のkパラメータを選択する部分に到達しました。しかし、私がRstudioの演習を複製すると、k = 1が得られます。答えはk = 73とする。どこで私は間違えましたか？

#load dataset 
titanic_train<-read.csv("https://kaggle2.blob.core.windows.net/competitions-data/kaggle/3136/train.csv?sv=2015-12-11&sr=b&sig=coHTg7HQb86RdaxfD2f9SiN492A4XLIDDRKVxLvw8Ys%3D&se=2017-03-19T10%3A26%3A52Z&sp=r") 

# Omit NAs 
titanic_train<-na.omit(titanic_train[,c("Survived", "Pclass", "Age", "Sex")]) 
library(class) 
library(dplyr) 

set.seed(1) 
n <- nrow(titanic_train) 
shuffled <- titanic_train[sample(n), ] 

# Split the data : train and test 
train_indices <- 1:round(0.7 * n) 
train <- shuffled[train_indices, ] 
test_indices <- (round(0.7 * n) + 1):n 
test <- shuffled[test_indices, ] 

# Store the Survived column of train and test in train_labels and test_labels 
train_labels<-train$Survived 
test_labels<-test$Survived 

# Copy train and test to knn_train and knn_test 
train$Sex = as.numeric(factor(train$Sex)) 
train <- train %>% mutate(Sex=ifelse(Sex==2, 1,0)) 
train$Survived=factor(train$Survived) 
summary(train$Sex) 
knn_train<-train 
knn_train$Age<-round(knn_train$Age,7) 

test$Sex = as.numeric(factor(test$Sex)) 
test <- test %>% mutate(Sex=ifelse(Sex==2, 1,0)) 
test$Survived=factor(test$Survived) 
summary(test$Sex) 
knn_test<-test 

# Drop Survived column for knn_train and knn_test 
knn_train$Survived<-NULL 
knn_test$Survived<-NULL 

# Normalize Pclass 
min_class <- min(knn_train$Pclass) 
max_class <- max(knn_train$Pclass) 
knn_train$Pclass <- (knn_train$Pclass - min_class)/(max_class - min_class) 
knn_test$Pclass <- (knn_test$Pclass - min_class)/(max_class - min_class) 

# Normalize Age 
min_age <- min(knn_train$Age) 
max_age <- max(knn_train$Age) 
knn_train$Age <- (knn_train$Age-min_age)/(max_age-min_age) 
knn_test$Age <- (knn_test$Age-min_age)/(max_age-min_age) 
summary(train) 

# Set random seed. 
set.seed(1) 

# define range and accs 
range <- 1:round(0.2 * nrow(knn_train)) 
accs <- rep(0, length(range)) 

for (k in range) { 
    pred <- knn(knn_train, knn_test, train_labels, k = k) 
    pred<-factor(pred, levels=c(1,0)) 
    test_labels<-factor(test_labels, levels=c(1,0)) 
    conf <- table(test_labels, pred) 
    accs[k] <- sum(diag(conf))/sum(conf) 
} 

# Plot the accuracies. 
plot(range, accs, xlab = "k") 

# Calculate the best k 
which.max(accs) 
accs[which.max(accs)]

出典

2017-03-19 Saiful Safuan