1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
|
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# group.R - GroupedData class and methods implemented in S4 OO classes
#' @include generics.R jobj.R schema.R column.R
NULL
setOldClass("jobj")
#' S4 class that represents a GroupedData
#'
#' GroupedDatas can be created using groupBy() on a SparkDataFrame
#'
#' @rdname GroupedData
#' @seealso groupBy
#'
#' @param sgd A Java object reference to the backing Scala GroupedData
#' @export
#' @note GroupedData since 1.4.0
setClass("GroupedData",
slots = list(sgd = "jobj"))
setMethod("initialize", "GroupedData", function(.Object, sgd) {
.Object@sgd <- sgd
.Object
})
#' @rdname GroupedData
groupedData <- function(sgd) {
new("GroupedData", sgd)
}
#' @rdname show
#' @note show(GroupedData) since 1.4.0
setMethod("show", "GroupedData",
function(object) {
cat("GroupedData\n")
})
#' Count
#'
#' Count the number of rows for each group.
#' The resulting SparkDataFrame will also contain the grouping columns.
#'
#' @param x a GroupedData
#' @return a SparkDataFrame
#' @rdname count
#' @export
#' @examples
#' \dontrun{
#' count(groupBy(df, "name"))
#' }
#' @note count since 1.4.0
setMethod("count",
signature(x = "GroupedData"),
function(x) {
dataFrame(callJMethod(x@sgd, "count"))
})
#' summarize
#'
#' Aggregates on the entire SparkDataFrame without groups.
#' The resulting SparkDataFrame will also contain the grouping columns.
#'
#' df2 <- agg(df, <column> = <aggFunction>)
#' df2 <- agg(df, newColName = aggFunction(column))
#'
#' @param x a GroupedData
#' @return a SparkDataFrame
#' @rdname summarize
#' @name agg
#' @family agg_funcs
#' @export
#' @examples
#' \dontrun{
#' df2 <- agg(df, age = "sum") # new column name will be created as 'SUM(age#0)'
#' df3 <- agg(df, ageSum = sum(df$age)) # Creates a new column named ageSum
#' df4 <- summarize(df, ageSum = max(df$age))
#' }
#' @note agg since 1.4.0
setMethod("agg",
signature(x = "GroupedData"),
function(x, ...) {
cols <- list(...)
stopifnot(length(cols) > 0)
if (is.character(cols[[1]])) {
cols <- varargsToEnv(...)
sdf <- callJMethod(x@sgd, "agg", cols)
} else if (class(cols[[1]]) == "Column") {
ns <- names(cols)
if (!is.null(ns)) {
for (n in ns) {
if (n != "") {
cols[[n]] <- alias(cols[[n]], n)
}
}
}
jcols <- lapply(cols, function(c) { c@jc })
sdf <- callJMethod(x@sgd, "agg", jcols[[1]], jcols[-1])
} else {
stop("agg can only support Column or character")
}
dataFrame(sdf)
})
#' @rdname summarize
#' @name summarize
#' @note summarize since 1.4.0
setMethod("summarize",
signature(x = "GroupedData"),
function(x, ...) {
agg(x, ...)
})
# Aggregate Functions by name
methods <- c("avg", "max", "mean", "min", "sum")
# These are not exposed on GroupedData: "kurtosis", "skewness", "stddev", "stddev_samp", "stddev_pop",
# "variance", "var_samp", "var_pop"
createMethod <- function(name) {
setMethod(name,
signature(x = "GroupedData"),
function(x, ...) {
sdf <- callJMethod(x@sgd, name, list(...))
dataFrame(sdf)
})
}
createMethods <- function() {
for (name in methods) {
createMethod(name)
}
}
createMethods()
#' gapply
#'
#' Applies a R function to each group in the input GroupedData
#'
#' @param x a GroupedData
#' @param func A function to be applied to each group partition specified by GroupedData.
#' The function `func` takes as argument a key - grouping columns and
#' a data frame - a local R data.frame.
#' The output of `func` is a local R data.frame.
#' @param schema The schema of the resulting SparkDataFrame after the function is applied.
#' The schema must match to output of `func`. It has to be defined for each
#' output column with preferred output column name and corresponding data type.
#' @return a SparkDataFrame
#' @rdname gapply
#' @name gapply
#' @export
#' @examples
#' \dontrun{
#' 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"))
#' df1 <- gapply(
#' df,
#' list("a", "c"),
#' function(key, x) {
#' y <- data.frame(key, mean(x$b), stringsAsFactors = FALSE)
#' },
#' schema)
#' collect(df1)
#'
#' Result
#' ------
#' a c avg
#' 3 3 3.0
#' 1 1 1.5
#' }
#' @note gapply(GroupedData) since 2.0.0
setMethod("gapply",
signature(x = "GroupedData"),
function(x, func, schema) {
try(if (is.null(schema)) stop("schema cannot be NULL"))
packageNamesArr <- serialize(.sparkREnv[[".packages"]],
connection = NULL)
broadcastArr <- lapply(ls(.broadcastNames),
function(name) { get(name, .broadcastNames) })
sdf <- callJStatic(
"org.apache.spark.sql.api.r.SQLUtils",
"gapply",
x@sgd,
serialize(cleanClosure(func), connection = NULL),
packageNamesArr,
broadcastArr,
schema$jobj)
dataFrame(sdf)
})
|