[R] address some lintr warnings (#8609)

demo/kaggle-otto/otto_train_pred.R

@@ -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 <- rbind(train[, -ncol(train)], test)
 x <- as.matrix(x)
-x <- matrix(as.numeric(x),nrow(x),ncol(x))
+x <- matrix(as.numeric(x), nrow(x), ncol(x))
 trind <- 1:length(y)
-teind <- (nrow(train)+1):nrow(x)
+teind <- (nrow(train) + 1):nrow(x)
 
 # Set necessary parameter
 param <- list("objective" = "multi:softprob",
@@ -24,20 +24,25 @@ param <- list("objective" = "multi:softprob",
 
 # Run Cross Validation
 cv.nrounds <- 50
-bst.cv <- xgb.cv(param=param, data = x[trind,], label = y, 
-                nfold = 3, nrounds=cv.nrounds)
+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)
+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 <- 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))
-write.csv(pred,file='submission.csv', quote=FALSE,row.names=FALSE)
+pred <- format(pred, digits = 2, scientific = FALSE) # 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)

demo/kaggle-otto/understandingXGBoostModel.Rmd

@@ -31,7 +31,7 @@ require(methods)
 require(data.table)
 require(magrittr)
 train <- fread('data/train.csv', header = T, stringsAsFactors = FALSE)
-test <- fread('data/test.csv', header=TRUE, stringsAsFactors = FALSE)
+test <- fread('data/test.csv', header = TRUE, stringsAsFactors = FALSE)
 ```
 > `magrittr` and `data.table` are here to make the code cleaner and much more rapid.
 
@@ -42,13 +42,13 @@ Let's explore the dataset.
 dim(train)
 
 # Training content
-train[1:6,1:5, with =FALSE]
+train[1:6, 1:5, with = FALSE]
 
 # Test dataset dimensions
 dim(test)
 
 # Test content
-test[1:6,1:5, with =FALSE]
+test[1:6, 1:5, with = FALSE]
 ```
 > We only display the 6 first rows and 5 first columns for convenience
 
@@ -87,7 +87,7 @@ For that purpose, we will:
 ```{r classToIntegers}
 # Convert from classes to numbers
 y <- train[, nameLastCol, with = FALSE][[1]] %>%
-    gsub('Class_','',.) %>%
+    gsub('Class_', '', .) %>%
     as.integer %>%
     subtract(., 1)
 
@@ -98,14 +98,14 @@ y[1:5]
 We remove label column from training dataset, otherwise **XGBoost** would use it to guess the labels!
 
 ```{r deleteCols, results='hide'}
-train[, nameLastCol:=NULL, with = FALSE]
+train[, nameLastCol := NULL, with = FALSE]
 ```
 
 `data.table` is an awesome implementation of data.frame, unfortunately it is not a format supported natively by **XGBoost**. We need to convert both datasets (training and test) in `numeric` Matrix format.
 
 ```{r convertToNumericMatrix}
-trainMatrix <- train[,lapply(.SD,as.numeric)] %>% as.matrix
-testMatrix <- test[,lapply(.SD,as.numeric)] %>% as.matrix
+trainMatrix <- train[, lapply(.SD, as.numeric)] %>% as.matrix
+testMatrix <- test[, lapply(.SD, as.numeric)] %>% as.matrix
 ```
 
 Model training
@@ -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).
@@ -136,7 +136,7 @@ Finally, we are ready to train the real model!!!
 
 ```{r modelTraining}
 nrounds <- 50
-bst <- xgboost(param=param, data = trainMatrix, label = y, nrounds=nrounds)
+bst <- xgboost(param = param, data = trainMatrix, label = y, nrounds = nrounds)
 ```
 
 Model understanding
@@ -189,7 +189,7 @@ names <- dimnames(trainMatrix)[[2]]
 importance_matrix <- xgb.importance(names, model = bst)
 
 # Nice graph
-xgb.plot.importance(importance_matrix[1:10,])
+xgb.plot.importance(importance_matrix[1:10, ])
 ```
 
 > To make it understandable we first extract the column names from the `Matrix`.