使用 K-fold 交叉验证 KNN

Question

当使用KNN预测价格时，如何使用K-fold进行交叉验证？ 我当前要预测的代码是

library("tidyverse")
library("FNN")
library("forecast")
library("caret")
library("stats")


houses=read_csv("data.csv")
houses = subset(houses, price < 1000001)
houses = subset(houses, price >99999)
houses = subset(houses, price != 0)


houses =houses %>%
  select(-street,-city, -statezip,-country)


houses = houses %>%
  mutate(date = as.Date(houses$date)) %>%
  mutate(date = format(date, format="%Y"))

houses = houses %>%
  mutate(date = as.numeric(houses$date)) %>%
  mutate(yr_built = as.numeric(houses$yr_built)) %>%
  mutate(age_when_listed = date - yr_built)

houses = houses %>%
  mutate(age_when_listed = (houses$date - houses$yr_built))


houses= houses %>%
  mutate(renovated = ifelse(yr_renovated > 0, 1,0))



b1= mean(houses$bedrooms)
b2=sd(houses$bedrooms)

c1= mean(houses$bathrooms)
c2=sd(houses$bathrooms)

e1= mean(houses$sqft_lot)
e2=sd(houses$sqft_lot)

f1= mean(houses$floors)
f2=sd(houses$floors)

g1= mean(houses$view)
g2=sd(houses$view)

h1=mean(houses$waterfront)
h2=sd(houses$waterfront)

i1= mean(houses$condition)
i2=sd(houses$condition)

j1= mean(houses$sqft_above)
j2=sd(houses$sqft_above)

k1= mean(houses$sqft_basement)
k2=sd(houses$sqft_basement)

l1= mean(houses$age_when_listed)
l2=sd(houses$age_when_listed)

m1=mean(houses$yr_renovated)
m2=sd(houses$yr_renovated)


houses = houses %>%
  mutate(bedrooms_norm = (bedrooms-b1)/b2,bathrooms_norm = (bathrooms-c1)/c2,
         sqft_lot_norm = (sqft_lot-e1)/e2,floors_norm = (floors-f1)/f2,
         view_norm = (view-g1)/g2, condition_norm = (condition-i1)/i2,
         sqft_above_norm = (sqft_above-j1)/j2, sqft_basement_norm = (sqft_basement-k1)/k2,
         age_when_listed_norm = (age_when_listed-l1)/l2, waterfront_norm=(waterfront-h1)/h2,
         yr_renovated_norm=(yr_renovated-m1)/m2)

houses_input_norm = houses %>%
  select(bedrooms_norm, bathrooms_norm, 
         sqft_lot_norm, floors_norm, view_norm,condition_norm, sqft_above_norm,
         sqft_basement_norm, age_when_listed_norm, waterfront_norm, yr_renovated_norm)

#New sample observation
newdata= as_tibble(list(bedrooms=4,bathrooms=3, sqft_lot=2000,floors=2, waterfront= 0,
                        view=2, condition=3,sqft_above = 3000,sqft_basement=0,age_when_listed=20, yr_renovated=0))

newdata = newdata %>%
  mutate(bedrooms_norm = (bedrooms-b1)/b2,bathrooms_norm = (bathrooms-c1)/c2,
         sqft_lot_norm = (sqft_lot-e1)/e2,floors_norm = (floors-f1)/f2,
         view_norm = (view-g1)/g2, condition_norm = (condition-i1)/i2,
         sqft_above_norm = (sqft_above-j1)/j2, sqft_basement_norm = (sqft_basement-k1)/k2,
         age_when_listed_norm = (age_when_listed-l1)/l2,waterfront_norm=(waterfront-h1)/h2,
         yr_renovated_norm=(yr_renovated-m1)/m2)


newdata_input_norm = newdata %>%
  select(bedrooms_norm, bathrooms_norm, 
         sqft_lot_norm, floors_norm, view_norm,
         condition_norm, sqft_above_norm, sqft_basement_norm, 
         age_when_listed_norm,waterfront_norm, yr_renovated_norm)

houses_output= houses$price

然后交叉验证我使用了此代码（基于教科书示例）这仅用于交叉验证线性回归问题还是对于 K-NN 也准确？

set.seed(30)

houses = houses%>%
  tibble::rowid_to_column("ID")

temp =as_tibble()

houses = houses %>%
  mutate(fold = sample(1:10, 4202, replace = TRUE))

K=10
for(obs_num in 1:K)
{  
  train = houses %>%
    filter(ID != obs_num)
  
  validation= houses%>%
    filter(ID ==obs_num)
  
  train.mlr = lm(price~bedrooms + bathrooms + sqft_lot+floors+
                   view+ condition+sqft_above+ sqft_basement+ age_when_listed+
                 yr_renovated+ waterfront, train)
  
  validation = validation%>%
    mutate(price_prediction = predict(train.mlr, validation))
  
  am= accuracy(validation$price_prediction, validation$price)
  
  temp= temp %>%
    bind_rows(as_tibble(list(run=obs_num, RSME = am[2], MAPE= am[5])))
  print(paste("iteration", obs_num, "completed"), sep =" ")
  
}

temp %>%
  summarise(mean_MAPE = mean(MAPE), sd_MAPE = sd(MAPE))

temp %>%
  summarise(mean_RSME = mean(RSME), sd_RSME = sd(RSME))

此代码是否准确地使用 K-fold 进行交叉验证，还是我需要更改它，它当前输出错误级别，但不确定它们是否正确

Answer 1

目前对我来说看起来不太合适。在交叉验证循环中，您将根据 ID 变量分配给 train 和 validation 表。我认为如果您将其更改为基于您的 fold 变量，那么它应该可以正常工作。

例如，

K=10
for(obs_num in 1:K)
{  
  train = houses %>%
    filter(fold != obs_num)
  
  validation = houses%>%
    filter(fold == obs_num)
  
  train.mlr = lm(price~bedrooms + bathrooms + sqft_lot+floors+
                   view+ condition+sqft_above+ sqft_basement+ age_when_listed+
                 yr_renovated+ waterfront, train)
  
  validation = validation%>%
    mutate(price_prediction = predict(train.mlr, validation))
  
  am= accuracy(validation$price_prediction, validation$price)
  
  temp= temp %>%
    bind_rows(as_tibble(list(run=obs_num, RSME = am[2], MAPE= am[5])))
  print(paste("iteration", obs_num, "completed"), sep =" ")
  
}

针对不同的模型类型调整这样的交叉验证循环通常相当容易。要检查的是 predict() 函数仍然以相同的方式工作。 predict 是使用大多数模型类型进行预测的包装器 - 有时它需要额外的输入参数，有时输出采用不同的格式。

您的 KNN 模型稍微复杂一些，因为 FNN 包没有内置简单的 predict 函数。它必须看起来像这样：

K=10
for(obs_num in 1:K)
{  
  train = houses %>%
    filter(fold != obs_num) 
  
  # Select your predictors, and convert to a matrix. 
  train.matrix = train %>%
    select(bedrooms,bathrooms,sqft_lot,floors,
               view,condition,sqft_above,sqft_basement,age_when_listed,
             yr_renovated,waterfront) %>% as.matrix()
  
  validation = houses%>%
    filter(fold == obs_num)
  
  # Select your predictors, and convert to a matrix. 
  validation.matrix = validation %>%
    select(bedrooms,bathrooms,sqft_lot,floors,
               view,condition,sqft_above,sqft_basement,age_when_listed,
             yr_renovated,waterfront) %>% as.matrix()
  
  # Here k is set to 3, but you can set it to something else
  train.knn = FNN::knn(train.matrix, validation.matrix, train$price, k=3)
  
  validation = validation %>%
    mutate(price_prediction = train.knn[1:nrow(validation)])
  
  am= accuracy(validation$price_prediction, validation$price)
  
  temp= temp %>%
    bind_rows(as_tibble(list(run=obs_num, RSME = am[2], MAPE= am[5])))
  print(paste("iteration", obs_num, "completed"), sep =" ")
  
}

当然，如果不查看您的数据，很难判断这是否有效。您能否提供数据样本，或者使用 R 中可用数据集的可重现示例？使用上面的代码，您必须确保 train.matrix 和 validation.matrix 的格式完全匹配。另请注意，FNN 仅适用于数字数据 - 如果您有任何分类预测变量，则必须首先对它们进行单热编码。