$ {SparkR} | R Documentation |
Selects a set of columns with names or Column expressions.
## S4 method for signature 'DataFrame' x$name ## S4 replacement method for signature 'DataFrame' x$name <- value ## S4 method for signature 'DataFrame,character' select(x, col, ...) ## S4 method for signature 'DataFrame,Column' select(x, col, ...) ## S4 method for signature 'DataFrame,list' select(x, col) select(x, col, ...) selectExpr(x, expr, ...)
x |
A DataFrame |
col |
A list of columns or single Column or name |
A new DataFrame with selected columns
Other DataFrame functions: DataFrame-class
,
dataFrame
, groupedData
;
[
, [
, [[
,
subset
; agg
,
agg
,
count,GroupedData-method
,
summarize
, summarize
;
arrange
, arrange
,
arrange
, orderBy
,
orderBy
; as.data.frame
,
as.data.frame,DataFrame-method
;
attach
,
attach,DataFrame-method
;
cache
; collect
;
colnames
, colnames
,
colnames<-
, colnames<-
,
columns
, names
,
names<-
; coltypes
,
coltypes
, coltypes<-
,
coltypes<-
; columns
,
dtypes
, printSchema
,
schema
, schema
;
count
, nrow
;
describe
, describe
,
describe
, summary
,
summary
,
summary,PipelineModel-method
;
dim
; distinct
,
unique
; dropna
,
dropna
, fillna
,
fillna
, na.omit
,
na.omit
; dtypes
;
except
, except
;
explain
, explain
;
filter
, filter
,
where
, where
;
first
, first
;
groupBy
, groupBy
,
group_by
, group_by
;
head
; insertInto
,
insertInto
; intersect
,
intersect
; isLocal
,
isLocal
; join
;
limit
, limit
;
merge
, merge
;
mutate
, mutate
,
transform
; ncol
;
persist
; printSchema
;
rbind
, rbind
,
unionAll
, unionAll
;
registerTempTable
,
registerTempTable
; rename
,
rename
, withColumnRenamed
,
withColumnRenamed
;
repartition
; sample
,
sample
, sample_frac
,
sample_frac
;
saveAsParquetFile
,
saveAsParquetFile
,
write.parquet
, write.parquet
;
saveAsTable
, saveAsTable
;
saveDF
, saveDF
,
write.df
, write.df
;
selectExpr
; showDF
,
showDF
; show
,
show
,
show,GroupedData-method
;
take
; transform
,
withColumn
, withColumn
;
unpersist
; write.json
,
write.json
Other DataFrame functions: DataFrame-class
,
dataFrame
, groupedData
;
[
, [
, [[
,
subset
; agg
,
agg
,
count,GroupedData-method
,
summarize
, summarize
;
arrange
, arrange
,
arrange
, orderBy
,
orderBy
; as.data.frame
,
as.data.frame,DataFrame-method
;
attach
,
attach,DataFrame-method
;
cache
; collect
;
colnames
, colnames
,
colnames<-
, colnames<-
,
columns
, names
,
names<-
; coltypes
,
coltypes
, coltypes<-
,
coltypes<-
; columns
,
dtypes
, printSchema
,
schema
, schema
;
count
, nrow
;
describe
, describe
,
describe
, summary
,
summary
,
summary,PipelineModel-method
;
dim
; distinct
,
unique
; dropna
,
dropna
, fillna
,
fillna
, na.omit
,
na.omit
; dtypes
;
except
, except
;
explain
, explain
;
filter
, filter
,
where
, where
;
first
, first
;
groupBy
, groupBy
,
group_by
, group_by
;
head
; insertInto
,
insertInto
; intersect
,
intersect
; isLocal
,
isLocal
; join
;
limit
, limit
;
merge
, merge
;
mutate
, mutate
,
transform
; ncol
;
persist
; printSchema
;
rbind
, rbind
,
unionAll
, unionAll
;
registerTempTable
,
registerTempTable
; rename
,
rename
, withColumnRenamed
,
withColumnRenamed
;
repartition
; sample
,
sample
, sample_frac
,
sample_frac
;
saveAsParquetFile
,
saveAsParquetFile
,
write.parquet
, write.parquet
;
saveAsTable
, saveAsTable
;
saveDF
, saveDF
,
write.df
, write.df
;
selectExpr
; showDF
,
showDF
; show
,
show
,
show,GroupedData-method
;
take
; transform
,
withColumn
, withColumn
;
unpersist
; write.json
,
write.json
Other DataFrame functions: DataFrame-class
,
dataFrame
, groupedData
;
[
, [
, [[
,
subset
; agg
,
agg
,
count,GroupedData-method
,
summarize
, summarize
;
arrange
, arrange
,
arrange
, orderBy
,
orderBy
; as.data.frame
,
as.data.frame,DataFrame-method
;
attach
,
attach,DataFrame-method
;
cache
; collect
;
colnames
, colnames
,
colnames<-
, colnames<-
,
columns
, names
,
names<-
; coltypes
,
coltypes
, coltypes<-
,
coltypes<-
; columns
,
dtypes
, printSchema
,
schema
, schema
;
count
, nrow
;
describe
, describe
,
describe
, summary
,
summary
,
summary,PipelineModel-method
;
dim
; distinct
,
unique
; dropna
,
dropna
, fillna
,
fillna
, na.omit
,
na.omit
; dtypes
;
except
, except
;
explain
, explain
;
filter
, filter
,
where
, where
;
first
, first
;
groupBy
, groupBy
,
group_by
, group_by
;
head
; insertInto
,
insertInto
; intersect
,
intersect
; isLocal
,
isLocal
; join
;
limit
, limit
;
merge
, merge
;
mutate
, mutate
,
transform
; ncol
;
persist
; printSchema
;
rbind
, rbind
,
unionAll
, unionAll
;
registerTempTable
,
registerTempTable
; rename
,
rename
, withColumnRenamed
,
withColumnRenamed
;
repartition
; sample
,
sample
, sample_frac
,
sample_frac
;
saveAsParquetFile
,
saveAsParquetFile
,
write.parquet
, write.parquet
;
saveAsTable
, saveAsTable
;
saveDF
, saveDF
,
write.df
, write.df
;
selectExpr
; showDF
,
showDF
; show
,
show
,
show,GroupedData-method
;
take
; transform
,
withColumn
, withColumn
;
unpersist
; write.json
,
write.json
Other subsetting functions: [
,
[
, [[
, subset
;
filter
, filter
,
where
, where
## Not run:
##D select(df, "*")
##D select(df, "col1", "col2")
##D select(df, df$name, df$age + 1)
##D select(df, c("col1", "col2"))
##D select(df, list(df$name, df$age + 1))
##D # Similar to R data frames columns can also be selected using `$`
##D df[,df$age]
## End(Not run)