Created
April 6, 2012 05:24
-
-
Save truncs/2317226 to your computer and use it in GitHub Desktop.
Regression Tree using random samples
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Transform days spent to log(1 + x) | |
y1_data$DaysInHospital_Y2 <- log1p(y1_data$DaysInHospital_Y2) | |
# Divide the set, 80% for train and 20% for test | |
indexes <- sample(1:nrow(y1_data), size=0.2*nrow(y1_data)) | |
test <- y1_data[indexes,] | |
train <- y1_data[-indexes,] | |
# Remove unwanted features from both the sets | |
train <- subset(train, select=-c(MemberID_t, YEAR_t, DaysInHospital, trainset, DaysInHospital_Y3, age_05, PayDelay_max, PayDelay_min, PayDelay_stdev, LOS_max, LOS_min, | |
LOS_stdev, LOS_TOT_UNKNOWN, LOS_TOT_SUPRESSED, LOS_TOT_KNOWN, dsfs_max, dsfs_min, dsfs_range, dsfs_stdev, CharlsonIndexI_max, CharlsonIndexI_min, CharlsonIndexI_range, CharlsonIndexI_stdev,drugCount_max, drugCount_min, memberID_lc, YEAR_lc, labCount_max, labCount_min, labNull, drugNull)) | |
test <- subset(test, select=-c(MemberID_t, YEAR_t, DaysInHospital, trainset, DaysInHospital_Y2, DaysInHospital_Y3, age_05, PayDelay_max, PayDelay_min, PayDelay_stdev, LOS_max, LOS_min, | |
LOS_stdev, LOS_TOT_UNKNOWN, LOS_TOT_SUPRESSED, LOS_TOT_KNOWN, dsfs_max, dsfs_min, dsfs_range, dsfs_stdev, CharlsonIndexI_max, CharlsonIndexI_min, CharlsonIndexI_range, CharlsonIndexI_stdev,drugCount_max, drugCount_min, memberID_lc, YEAR_lc, labCount_max, labCount_min, labNull, drugNull)) | |
# Model a regression tree using the training data | |
tr <- tree(DaysInHospital_Y2 ~ ., train) | |
# Get the visual for the tree | |
plot(tr,type="uniform"); text(tr,pretty=0) | |
# Use the tree to predict the test set values and | |
# append the predicted values to the test set | |
result <- predict(tr, test, type="vector") | |
test$predicted <- result | |
# Calculate the RMSE without truncation | |
sqrt(mean((y1_data[indexes,]$DaysInHospital_Y2 - test$predicted)^2)) | |
# Truncate the values and then calculate the RMSE again | |
test$new_predicted <- log1p(trunc(exp(test$predicted) - 1)) | |
sqrt(mean((y1_data[indexes,]$DaysInHospital_Y2 - test$new_predicted)^2)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment