Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[R] resolve assignment_linter warnings (#8599)

Browse Source
This commit is contained in:
James Lamb
2022-12-16 11:22:41 -06:00
committed by GitHub
parent f6effa1734
commit 53e6e32718
8 changed files with 43 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
demo/kaggle-otto/otto_train_pred.R
View File

@@ -1,20 +1,20 @@
require(xgboost)
require(methods)
train = read.csv('data/train.csv',header=TRUE,stringsAsFactors = FALSE)
test = read.csv('data/test.csv',header=TRUE,stringsAsFactors = FALSE)
train = train[,-1]
test = test[,-1]
train <- read.csv('data/train.csv',header=TRUE,stringsAsFactors = FALSE)
test <- read.csv('data/test.csv',header=TRUE,stringsAsFactors = FALSE)
train <- train[,-1]
test <- test[,-1]
y = train[,ncol(train)]
y = gsub('Class_','',y)
y = as.integer(y)-1 # xgboost take features in [0,numOfClass)
y <- train[,ncol(train)]
y <- gsub('Class_','',y)
y <- as.integer(y)-1 # xgboost take features in [0,numOfClass)
x = rbind(train[,-ncol(train)],test)
x = as.matrix(x)
x = matrix(as.numeric(x),nrow(x),ncol(x))
trind = 1:length(y)
teind = (nrow(train)+1):nrow(x)
x <- rbind(train[,-ncol(train)],test)
x <- as.matrix(x)
x <- matrix(as.numeric(x),nrow(x),ncol(x))
trind <- 1:length(y)
teind <- (nrow(train)+1):nrow(x)
# Set necessary parameter
param <- list("objective" = "multi:softprob",
@@ -23,21 +23,21 @@ param <- list("objective" = "multi:softprob",
"nthread" = 8)
# Run Cross Validation
cv.nrounds = 50
bst.cv = xgb.cv(param=param, data = x[trind,], label = y,
cv.nrounds <- 50
bst.cv <- xgb.cv(param=param, data = x[trind,], label = y,
nfold = 3, nrounds=cv.nrounds)
# Train the model
nrounds = 50
bst = xgboost(param=param, data = x[trind,], label = y, nrounds=nrounds)
nrounds <- 50
bst <- xgboost(param=param, data = x[trind,], label = y, nrounds=nrounds)
# Make prediction
pred = predict(bst,x[teind,])
pred = matrix(pred,9,length(pred)/9)
pred = t(pred)
pred <- predict(bst,x[teind,])
pred <- matrix(pred,9,length(pred)/9)
pred <- t(pred)
# Output submission
pred = format(pred, digits=2,scientific=F) # shrink the size of submission
pred = data.frame(1:nrow(pred),pred)
names(pred) = c('id', paste0('Class_',1:9))
pred <- format(pred, digits=2,scientific=F) # shrink the size of submission
pred <- data.frame(1:nrow(pred),pred)
names(pred) <- c('id', paste0('Class_',1:9))
write.csv(pred,file='submission.csv', quote=FALSE,row.names=FALSE)

6
demo/kaggle-otto/understandingXGBoostModel.Rmd
View File

@@ -127,7 +127,7 @@ param <- list("objective" = "multi:softprob",
cv.nrounds <- 5
cv.nfold <- 3
bst.cv = xgb.cv(param=param, data = trainMatrix, label = y,
bst.cv <- xgb.cv(param=param, data = trainMatrix, label = y,
nfold = cv.nfold, nrounds = cv.nrounds)
```
> As we can see the error rate is low on the test dataset (for a 5mn trained model).
@@ -135,8 +135,8 @@ bst.cv = xgb.cv(param=param, data = trainMatrix, label = y,
Finally, we are ready to train the real model!!!
```{r modelTraining}
nrounds = 50
bst = xgboost(param=param, data = trainMatrix, label = y, nrounds=nrounds)
nrounds <- 50
bst <- xgboost(param=param, data = trainMatrix, label = y, nrounds=nrounds)
```
Model understanding