caret: แนะนำวิธีใช้แพ็กเกจ machine learning ที่ทรงพลังในภาษา R — ตัวอย่างการทำนายราคาบ้านใน BostonHousing dataset

# Install mlbench
install.packages("mlbench")

# Load mlbench
library(caret)
library(mlbench)

# Load BostonHousing
data("BostonHousing")

# Preview
head(BostonHousing)

     crim zn indus chas   nox    rm  age    dis rad tax ptratio      b lstat medv
1 0.00632 18  2.31    0 0.538 6.575 65.2 4.0900   1 296    15.3 396.90  4.98 24.0
2 0.02731  0  7.07    0 0.469 6.421 78.9 4.9671   2 242    17.8 396.90  9.14 21.6
3 0.02729  0  7.07    0 0.469 7.185 61.1 4.9671   2 242    17.8 392.83  4.03 34.7
4 0.03237  0  2.18    0 0.458 6.998 45.8 6.0622   3 222    18.7 394.63  2.94 33.4
5 0.06905  0  2.18    0 0.458 7.147 54.2 6.0622   3 222    18.7 396.90  5.33 36.2
6 0.02985  0  2.18    0 0.458 6.430 58.7 6.0622   3 222    18.7 394.12  5.21 28.7

# View the structure
str(BostonHousing)

'data.frame':	506 obs. of  14 variables:
 $ crim   : num  0.00632 0.02731 0.02729 0.03237 0.06905 ...
 $ zn     : num  18 0 0 0 0 0 12.5 12.5 12.5 12.5 ...
 $ indus  : num  2.31 7.07 7.07 2.18 2.18 2.18 7.87 7.87 7.87 7.87 ...
 $ chas   : Factor w/ 2 levels "0","1": 1 1 1 1 1 1 1 1 1 1 ...
 $ nox    : num  0.538 0.469 0.469 0.458 0.458 0.458 0.524 0.524 0.524 0.524 ...
 $ rm     : num  6.58 6.42 7.18 7 7.15 ...
 $ age    : num  65.2 78.9 61.1 45.8 54.2 58.7 66.6 96.1 100 85.9 ...
 $ dis    : num  4.09 4.97 4.97 6.06 6.06 ...
 $ rad    : num  1 2 2 3 3 3 5 5 5 5 ...
 $ tax    : num  296 242 242 222 222 222 311 311 311 311 ...
 $ ptratio: num  15.3 17.8 17.8 18.7 18.7 18.7 15.2 15.2 15.2 15.2 ...
 $ b      : num  397 397 393 395 397 ...
 $ lstat  : num  4.98 9.14 4.03 2.94 5.33 ...
 $ medv   : num  24 21.6 34.7 33.4 36.2 28.7 22.9 27.1 16.5 18.9 ...

# Set seed for reproducibility
set.seed(888)

# Get train index
train_index <- createDataPartition(BostonHousing$medv, # Specify the outcome
                                   p = 0.7, # Set aside 70% for training set
                                   list = FALSE) # Return as matrix

# Create training set
bt_train <- BostonHousing[train_index, ]

# Create test set
bt_test <- BostonHousing[-train_index, ]

# Check the results
cat("Rows in training set:", nrow(bt_train), "\\n")
cat("Rows in test set:", nrow(bt_test))

Rows in training set: 356
Rows in test set: 150

# Learn preprocessing on training set
ppc <- preProcess(bt_train[, -14], # Select all predictors
                  method = c("center", "scale"))  # Centre and scale

# Apply preprocessing to training set
bt_train_processed <- predict(ppc,
                              bt_train[, -14])

# Combine the preprocessed training set with outcome
bt_train_processed <- cbind(bt_train_processed,
                            medv = bt_train$medv)

# Apply preprocessing to test set
bt_test_processed <- predict(ppc,
                             bt_test[, -14])

# Combine the preprocessed test set with outcome
bt_test_processed <- cbind(bt_test_processed,
                            medv = bt_test$medv)

# Define training control:
# use k-fold cross-validation where k = 5
trc <- trainControl(method = "cv",
                    number = 5)

# Define grid:
# set k as odd numbers between 3 and 13
grid <- data.frame(k = seq(from = 3,
                           to = 13,
                           by = 2))

# Train the model
knn_model <- train(medv ~ ., # Specify the formula
                   data = bt_train_processed, # Use training set
                   method = "kknn", # Use knn engine
                   trControl = trc, # Specify training control
                   tuneGrid = grid) # Use grid to tune the model

# Print the model
knn_model

k-Nearest Neighbors 

356 samples
 13 predictor

No pre-processing
Resampling: Cross-Validated (5 fold) 
Summary of sample sizes: 284, 286, 286, 284, 284 
Resampling results across tuning parameters:

  k   RMSE      Rsquared   MAE     
   3  4.357333  0.7770080  2.840630
   5  4.438162  0.7760085  2.849984
   7  4.607954  0.7610468  2.941034
   9  4.683062  0.7577702  2.972661
  11  4.771317  0.7508908  3.043617
  13  4.815444  0.7524266  3.053415

RMSE was used to select the optimal model using the smallest value.
The final value used for the model was k = 3.

# Make predictions
predictions <- predict(knn_model,
                       newdata = bt_test_processed)

# Calculate MAE
mae <- MAE(predictions,
           bt_test_processed$medv)

# Calculate RMSE
rmse <- RMSE(predictions,
             bt_test_processed$medv)

# Calculate R squared
r2 <- R2(predictions,
         bt_test_processed$medv)

# Combine the results
results <- data.frame(Model = "KNN",
                      MAE = round(mae, 2),
                      RMSE = round(rmse, 2),
                      R_Squared = round(r2, 2))

# Print the results
results

  Model  MAE RMSE R_Squared
1   KNN 2.67 3.74      0.86