Mutate
mutate.Rd
Return a new SparkDataFrame with the specified columns added or replaced.
Usage
mutate(.data, ...)
transform(`_data`, ...)
# S4 method for SparkDataFrame
mutate(.data, ...)
# S4 method for SparkDataFrame
transform(`_data`, ...)
Arguments
- .data
a SparkDataFrame.
- ...
additional column argument(s) each in the form name = col.
- _data
a SparkDataFrame.
See also
Other SparkDataFrame functions:
SparkDataFrame-class
,
agg()
,
alias()
,
arrange()
,
as.data.frame()
,
attach,SparkDataFrame-method
,
broadcast()
,
cache()
,
checkpoint()
,
coalesce()
,
collect()
,
colnames()
,
coltypes()
,
createOrReplaceTempView()
,
crossJoin()
,
cube()
,
dapplyCollect()
,
dapply()
,
describe()
,
dim()
,
distinct()
,
dropDuplicates()
,
dropna()
,
drop()
,
dtypes()
,
exceptAll()
,
except()
,
explain()
,
filter()
,
first()
,
gapplyCollect()
,
gapply()
,
getNumPartitions()
,
group_by()
,
head()
,
hint()
,
histogram()
,
insertInto()
,
intersectAll()
,
intersect()
,
isLocal()
,
isStreaming()
,
join()
,
limit()
,
localCheckpoint()
,
merge()
,
ncol()
,
nrow()
,
persist()
,
printSchema()
,
randomSplit()
,
rbind()
,
rename()
,
repartitionByRange()
,
repartition()
,
rollup()
,
sample()
,
saveAsTable()
,
schema()
,
selectExpr()
,
select()
,
showDF()
,
show()
,
storageLevel()
,
str()
,
subset()
,
summary()
,
take()
,
toJSON()
,
unionAll()
,
unionByName()
,
union()
,
unpersist()
,
unpivot()
,
withColumn()
,
withWatermark()
,
with()
,
write.df()
,
write.jdbc()
,
write.json()
,
write.orc()
,
write.parquet()
,
write.stream()
,
write.text()
Examples
if (FALSE) {
sparkR.session()
path <- "path/to/file.json"
df <- read.json(path)
newDF <- mutate(df, newCol = df$col1 * 5, newCol2 = df$col1 * 2)
names(newDF) # Will contain newCol, newCol2
newDF2 <- transform(df, newCol = df$col1 / 5, newCol2 = df$col1 * 2)
df <- createDataFrame(list(list("Andy", 30L), list("Justin", 19L)), c("name", "age"))
# Replace the "age" column
df1 <- mutate(df, age = df$age + 1L)
}