| [[ {SparkR} | R Documentation |
Return subsets of SparkDataFrame according to given conditions
## S4 method for signature 'SparkDataFrame,numericOrcharacter' x[[i]] ## S4 replacement method for signature 'SparkDataFrame,numericOrcharacter' x[[i]] <- value ## S4 method for signature 'SparkDataFrame' x[i, j, ..., drop = F] ## S4 method for signature 'SparkDataFrame' subset(x, subset, select, drop = F, ...) subset(x, ...)
x |
a SparkDataFrame. |
i,subset |
(Optional) a logical expression to filter on rows. For extract operator [[ and replacement operator [[<-, the indexing parameter for a single Column. |
value |
a Column or an atomic vector in the length of 1 as literal value, or |
j,select |
expression for the single Column or a list of columns to select from the SparkDataFrame. |
... |
currently not used. |
drop |
if TRUE, a Column will be returned if the resulting dataset has only one column. Otherwise, a SparkDataFrame will always be returned. |
A new SparkDataFrame containing only the rows that meet the condition with selected columns.
[[ since 1.4.0
[[<- since 2.1.1
[ since 1.4.0
subset since 1.5.0
Other SparkDataFrame functions: $,
$,SparkDataFrame-method, $<-,
$<-,SparkDataFrame-method,
select, select,
select,SparkDataFrame,Column-method,
select,SparkDataFrame,character-method,
select,SparkDataFrame,list-method;
SparkDataFrame-class; agg,
agg, agg,
agg,GroupedData-method,
agg,SparkDataFrame-method,
summarize, summarize,
summarize,
summarize,GroupedData-method,
summarize,SparkDataFrame-method;
arrange, arrange,
arrange,
arrange,SparkDataFrame,Column-method,
arrange,SparkDataFrame,character-method,
orderBy,SparkDataFrame,characterOrColumn-method;
as.data.frame,
as.data.frame,SparkDataFrame-method;
attach,
attach,SparkDataFrame-method;
cache, cache,
cache,SparkDataFrame-method;
coalesce, coalesce,
coalesce,
coalesce,Column-method,
coalesce,SparkDataFrame-method;
collect, collect,
collect,SparkDataFrame-method;
colnames, colnames,
colnames,SparkDataFrame-method,
colnames<-, colnames<-,
colnames<-,SparkDataFrame-method,
columns, columns,
columns,SparkDataFrame-method,
names,
names,SparkDataFrame-method,
names<-,
names<-,SparkDataFrame-method;
coltypes, coltypes,
coltypes,SparkDataFrame-method,
coltypes<-, coltypes<-,
coltypes<-,SparkDataFrame,character-method;
count,SparkDataFrame-method,
nrow, nrow,
nrow,SparkDataFrame-method;
createOrReplaceTempView,
createOrReplaceTempView,
createOrReplaceTempView,SparkDataFrame,character-method;
crossJoin,
crossJoin,SparkDataFrame,SparkDataFrame-method;
dapplyCollect, dapplyCollect,
dapplyCollect,SparkDataFrame,function-method;
dapply, dapply,
dapply,SparkDataFrame,function,structType-method;
describe, describe,
describe,
describe,SparkDataFrame,ANY-method,
describe,SparkDataFrame,character-method,
describe,SparkDataFrame-method,
summary, summary,
summary,SparkDataFrame-method;
dim,
dim,SparkDataFrame-method;
distinct, distinct,
distinct,SparkDataFrame-method,
unique,
unique,SparkDataFrame-method;
dropDuplicates,
dropDuplicates,
dropDuplicates,SparkDataFrame-method;
dropna, dropna,
dropna,SparkDataFrame-method,
fillna, fillna,
fillna,SparkDataFrame-method,
na.omit, na.omit,
na.omit,SparkDataFrame-method;
drop, drop,
drop, drop,ANY-method,
drop,SparkDataFrame-method;
dtypes, dtypes,
dtypes,SparkDataFrame-method;
except, except,
except,SparkDataFrame,SparkDataFrame-method;
explain, explain,
explain,SparkDataFrame-method;
filter, filter,
filter,SparkDataFrame,characterOrColumn-method,
where, where,
where,SparkDataFrame,characterOrColumn-method;
first, first,
first,
first,SparkDataFrame-method,
first,characterOrColumn-method;
gapplyCollect, gapplyCollect,
gapplyCollect,
gapplyCollect,GroupedData-method,
gapplyCollect,SparkDataFrame-method;
gapply, gapply,
gapply,
gapply,GroupedData-method,
gapply,SparkDataFrame-method;
getNumPartitions,
getNumPartitions,SparkDataFrame-method;
groupBy, groupBy,
groupBy,SparkDataFrame-method,
group_by, group_by,
group_by,SparkDataFrame-method;
head,
head,SparkDataFrame-method;
histogram,
histogram,SparkDataFrame,characterOrColumn-method;
insertInto, insertInto,
insertInto,SparkDataFrame,character-method;
intersect, intersect,
intersect,SparkDataFrame,SparkDataFrame-method;
isLocal, isLocal,
isLocal,SparkDataFrame-method;
join,
join,SparkDataFrame,SparkDataFrame-method;
limit, limit,
limit,SparkDataFrame,numeric-method;
merge, merge,
merge,SparkDataFrame,SparkDataFrame-method;
mutate, mutate,
mutate,SparkDataFrame-method,
transform, transform,
transform,SparkDataFrame-method;
ncol,
ncol,SparkDataFrame-method;
persist, persist,
persist,SparkDataFrame,character-method;
printSchema, printSchema,
printSchema,SparkDataFrame-method;
randomSplit, randomSplit,
randomSplit,SparkDataFrame,numeric-method;
rbind, rbind,
rbind,SparkDataFrame-method;
registerTempTable,
registerTempTable,
registerTempTable,SparkDataFrame,character-method;
rename, rename,
rename,SparkDataFrame-method,
withColumnRenamed,
withColumnRenamed,
withColumnRenamed,SparkDataFrame,character,character-method;
repartition, repartition,
repartition,SparkDataFrame-method;
sample, sample,
sample,SparkDataFrame,logical,numeric-method,
sample_frac, sample_frac,
sample_frac,SparkDataFrame,logical,numeric-method;
saveAsParquetFile,
saveAsParquetFile,
saveAsParquetFile,SparkDataFrame,character-method,
write.parquet, write.parquet,
write.parquet,SparkDataFrame,character-method;
saveAsTable, saveAsTable,
saveAsTable,SparkDataFrame,character-method;
saveDF, saveDF,
saveDF,SparkDataFrame,character-method,
write.df, write.df,
write.df,
write.df,SparkDataFrame-method;
schema, schema,
schema,SparkDataFrame-method;
selectExpr, selectExpr,
selectExpr,SparkDataFrame,character-method;
showDF, showDF,
showDF,SparkDataFrame-method;
show, show,
show,Column-method,
show,GroupedData-method,
show,SparkDataFrame-method,
show,WindowSpec-method;
storageLevel,
storageLevel,SparkDataFrame-method;
str,
str,SparkDataFrame-method;
take, take,
take,SparkDataFrame,numeric-method;
union, union,
union,SparkDataFrame,SparkDataFrame-method,
unionAll, unionAll,
unionAll,SparkDataFrame,SparkDataFrame-method;
unpersist, unpersist,
unpersist,SparkDataFrame-method;
withColumn, withColumn,
withColumn,SparkDataFrame,character-method;
with,
with,SparkDataFrame-method;
write.jdbc, write.jdbc,
write.jdbc,SparkDataFrame,character,character-method;
write.json, write.json,
write.json,SparkDataFrame,character-method;
write.orc, write.orc,
write.orc,SparkDataFrame,character-method;
write.text, write.text,
write.text,SparkDataFrame,character-method
Other subsetting functions: $,
$,SparkDataFrame-method, $<-,
$<-,SparkDataFrame-method,
select, select,
select,SparkDataFrame,Column-method,
select,SparkDataFrame,character-method,
select,SparkDataFrame,list-method;
filter, filter,
filter,SparkDataFrame,characterOrColumn-method,
where, where,
where,SparkDataFrame,characterOrColumn-method
## Not run:
##D # Columns can be selected using [[ and [
##D df[[2]] == df[["age"]]
##D df[,2] == df[,"age"]
##D df[,c("name", "age")]
##D # Or to filter rows
##D df[df$age > 20,]
##D # SparkDataFrame can be subset on both rows and Columns
##D df[df$name == "Smith", c(1,2)]
##D df[df$age %in% c(19, 30), 1:2]
##D subset(df, df$age %in% c(19, 30), 1:2)
##D subset(df, df$age %in% c(19), select = c(1,2))
##D subset(df, select = c(1,2))
##D # Columns can be selected and set
##D df[["age"]] <- 23
##D df[[1]] <- df$age
##D df[[2]] <- NULL # drop column
## End(Not run)