| 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 |
a boolean value setting |
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 |
suffixes |
a string vector of length 2 used to make colnames of
|
... |
additional argument(s) passed to the method. |
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.
merge 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; [,
[,SparkDataFrame-method, [[,
[[,SparkDataFrame,numericOrcharacter-method,
subset, subset,
subset,SparkDataFrame-method;
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;
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;
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;
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;
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,character-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; 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,Column-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
## Not run:
##D sparkR.session()
##D df1 <- read.json(path)
##D df2 <- read.json(path2)
##D merge(df1, df2) # Performs a Cartesian
##D merge(df1, df2, by = "col1") # Performs an inner join based on expression
##D merge(df1, df2, by.x = "col1", by.y = "col2", all.y = TRUE)
##D merge(df1, df2, by.x = "col1", by.y = "col2", all.x = TRUE)
##D merge(df1, df2, by.x = "col1", by.y = "col2", all.x = TRUE, all.y = TRUE)
##D merge(df1, df2, by.x = "col1", by.y = "col2", all = TRUE, sort = FALSE)
##D merge(df1, df2, by = "col1", all = TRUE, suffixes = c("-X", "-Y"))
## End(Not run)