| gapply {SparkR} | R Documentation |
Groups the SparkDataFrame using the specified columns and applies the R function to each group.
gapply
## S4 method for signature 'SparkDataFrame' gapply(x, cols, func, schema) gapply(x, ...) ## S4 method for signature 'GroupedData' gapply(x, func, schema)
x |
a SparkDataFrame or GroupedData. |
cols |
grouping columns. |
func |
a function to be applied to each group partition specified by grouping
column of the SparkDataFrame. The function |
schema |
the schema of the resulting SparkDataFrame after the function is applied.
The schema must match to output of |
... |
additional argument(s) passed to the method. |
A SparkDataFrame.
gapply(SparkDataFrame) since 2.0.0
gapply(GroupedData) since 2.0.0
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;
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,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:
Computes the arithmetic mean of the second column by grouping
on the first and third columns. Output the grouping values and the average.
df <- createDataFrame (
list(list(1L, 1, "1", 0.1), list(1L, 2, "1", 0.2), list(3L, 3, "3", 0.3)),
c("a", "b", "c", "d"))
Here our output contains three columns, the key which is a combination of two
columns with data types integer and string and the mean which is a double.
schema <- structType(structField("a", "integer"), structField("c", "string"),
structField("avg", "double"))
result <- gapply(
df,
c("a", "c"),
function(key, x) {
y <- data.frame(key, mean(x$b), stringsAsFactors = FALSE)
}, schema)
We can also group the data and afterwards call gapply on GroupedData.
For Example:
gdf <- group_by(df, "a", "c")
result <- gapply(
gdf,
function(key, x) {
y <- data.frame(key, mean(x$b), stringsAsFactors = FALSE)
}, schema)
collect(result)
Result
------
a c avg
3 3 3.0
1 1 1.5
Fits linear models on iris dataset by grouping on the 'Species' column and
using 'Sepal_Length' as a target variable, 'Sepal_Width', 'Petal_Length'
and 'Petal_Width' as training features.
df <- createDataFrame (iris)
schema <- structType(structField("(Intercept)", "double"),
structField("Sepal_Width", "double"),structField("Petal_Length", "double"),
structField("Petal_Width", "double"))
df1 <- gapply(
df,
df$"Species",
function(key, x) {
m <- suppressWarnings(lm(Sepal_Length ~
Sepal_Width + Petal_Length + Petal_Width, x))
data.frame(t(coef(m)))
}, schema)
collect(df1)
Result
---------
Model (Intercept) Sepal_Width Petal_Length Petal_Width
1 0.699883 0.3303370 0.9455356 -0.1697527
2 1.895540 0.3868576 0.9083370 -0.6792238
3 2.351890 0.6548350 0.2375602 0.2521257
## End(Not run)