merge {SparkR} | R Documentation |
Merges two data frames
## S4 method for signature 'SparkDataFrame,SparkDataFrame' merge(x, y, by = intersect(names(x), names(y)), by.x = by, by.y = by, all = FALSE, all.x = all, all.y = all, sort = TRUE, suffixes = c("_x", "_y"), ...) merge(x, y, ...)
x |
the first data frame to be joined |
y |
the second data frame to be joined |
by |
a character vector specifying the join columns. If by is not
specified, the common column names in |
by.x |
a character vector specifying the joining columns for x. |
by.y |
a character vector specifying the joining columns for y. |
all.x |
a boolean value indicating whether all the rows in x should be including in the join |
all.y |
a boolean value indicating whether all the rows in y should be including in the join |
sort |
a logical argument indicating whether the resulting columns should be sorted |
If all.x and all.y are set to FALSE, a natural join will be returned. If all.x is set to TRUE and all.y is set to FALSE, a left outer join will be returned. If all.x is set to FALSE and all.y is set to TRUE, a right outer join will be returned. If all.x and all.y are set to TRUE, a full outer join will be returned.
Other SparkDataFrame functions: $
,
$<-
, select
,
select
,
select,SparkDataFrame,Column-method
,
select,SparkDataFrame,list-method
,
selectExpr
;
SparkDataFrame-class
,
dataFrame
; [
,
[[
, subset
;
agg
, agg
,
count,GroupedData-method
,
summarize
, summarize
;
arrange
, arrange
,
arrange
, orderBy
,
orderBy
, orderBy
,
orderBy
; as.data.frame
,
as.data.frame,SparkDataFrame-method
;
attach
,
attach,SparkDataFrame-method
;
cache
; collect
;
colnames
, colnames
,
colnames<-
, colnames<-
,
columns
, names
,
names<-
; coltypes
,
coltypes
, coltypes<-
,
coltypes<-
; columns
,
dtypes
, printSchema
,
schema
, schema
;
count
, nrow
;
dapply
, dapply
,
dapplyCollect
, dapplyCollect
;
describe
, describe
,
describe
, summary
,
summary
,
summary,AFTSurvivalRegressionModel-method
,
summary,GeneralizedLinearRegressionModel-method
,
summary,KMeansModel-method
,
summary,NaiveBayesModel-method
;
dim
; distinct
,
unique
; dropDuplicates
,
dropDuplicates
; dropna
,
dropna
, fillna
,
fillna
, na.omit
,
na.omit
; drop
,
drop
; dtypes
;
except
, except
;
explain
, explain
;
filter
, filter
,
where
, where
;
first
, first
;
groupBy
, groupBy
,
group_by
, group_by
;
head
; histogram
;
insertInto
, insertInto
;
intersect
, intersect
;
isLocal
, isLocal
;
join
; limit
,
limit
; mutate
,
mutate
, transform
,
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
,
write.df
; selectExpr
;
showDF
, showDF
;
show
, show
,
show,GroupedData-method
,
show,WindowSpec-method
; str
;
take
; unpersist
;
withColumn
, withColumn
;
write.jdbc
, write.jdbc
;
write.json
, write.json
;
write.text
, write.text
## Not run: sc <- sparkR.init() sqlContext <- sparkRSQL.init(sc) df1 <- read.json(sqlContext, path) df2 <- read.json(sqlContext, path2) merge(df1, df2) # Performs a Cartesian merge(df1, df2, by = "col1") # Performs an inner join based on expression merge(df1, df2, by.x = "col1", by.y = "col2", all.y = TRUE) merge(df1, df2, by.x = "col1", by.y = "col2", all.x = TRUE) merge(df1, df2, by.x = "col1", by.y = "col2", all.x = TRUE, all.y = TRUE) merge(df1, df2, by.x = "col1", by.y = "col2", all = TRUE, sort = FALSE) merge(df1, df2, by = "col1", all = TRUE, suffixes = c("-X", "-Y")) ## End(Not run)