-
Notifications
You must be signed in to change notification settings - Fork 28.2k
/
column.R
458 lines (432 loc) · 12.4 KB
/
column.R
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
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
#
# 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.
#
# Column Class
#' @include generics.R jobj.R schema.R
NULL
setOldClass("jobj")
#' S4 class that represents a SparkDataFrame column
#'
#' The column class supports unary, binary operations on SparkDataFrame columns
#'
#' @rdname column
#'
#' @slot jc reference to JVM SparkDataFrame column
#' @note Column since 1.4.0
setClass("Column",
slots = list(jc = "jobj"))
#' A set of operations working with SparkDataFrame columns
#' @rdname columnfunctions
#' @name columnfunctions
NULL
setMethod("initialize", "Column", function(.Object, jc) {
.Object@jc <- jc
.Object
})
#' @rdname column
#' @name column
#' @aliases column,jobj-method
setMethod("column",
signature(x = "jobj"),
function(x) {
new("Column", x)
})
#' @rdname show
#' @name show
#' @aliases show,Column-method
#' @note show(Column) since 1.4.0
setMethod("show", "Column",
function(object) {
cat("Column", callJMethod(object@jc, "toString"), "\n")
})
operators <- list(
"+" = "plus", "-" = "minus", "*" = "multiply", "/" = "divide", "%%" = "mod",
"==" = "equalTo", ">" = "gt", "<" = "lt", "!=" = "notEqual", "<=" = "leq", ">=" = "geq",
# we can not override `&&` and `||`, so use `&` and `|` instead
"&" = "and", "|" = "or", "^" = "pow"
)
column_functions1 <- c("asc", "desc", "isNaN", "isNull", "isNotNull")
column_functions2 <- c("like", "rlike", "getField", "getItem", "contains")
createOperator <- function(op) {
setMethod(op,
signature(e1 = "Column"),
function(e1, e2) {
jc <- if (missing(e2)) {
if (op == "-") {
callJMethod(e1@jc, "unary_$minus")
} else {
callJMethod(e1@jc, operators[[op]])
}
} else {
if (class(e2) == "Column") {
e2 <- e2@jc
}
if (op == "^") {
jc <- callJStatic("org.apache.spark.sql.functions", operators[[op]], e1@jc, e2)
} else {
callJMethod(e1@jc, operators[[op]], e2)
}
}
column(jc)
})
}
createColumnFunction1 <- function(name) {
setMethod(name,
signature(x = "Column"),
function(x) {
column(callJMethod(x@jc, name))
})
}
createColumnFunction2 <- function(name) {
setMethod(name,
signature(x = "Column"),
function(x, data) {
if (class(data) == "Column") {
data <- data@jc
}
jc <- callJMethod(x@jc, name, data)
column(jc)
})
}
createMethods <- function() {
for (op in names(operators)) {
createOperator(op)
}
for (name in column_functions1) {
createColumnFunction1(name)
}
for (name in column_functions2) {
createColumnFunction2(name)
}
}
createMethods()
#' @rdname alias
#' @name alias
#' @aliases alias,Column-method
#' @family colum_func
#' @examples
#' \dontrun{
#' df <- createDataFrame(iris)
#'
#' head(select(
#' df, alias(df$Sepal_Length, "slength"), alias(df$Petal_Length, "plength")
#' ))
#' }
#' @note alias(Column) since 1.4.0
setMethod("alias",
signature(object = "Column"),
function(object, data) {
if (is.character(data)) {
column(callJMethod(object@jc, "as", data))
} else {
stop("data should be character")
}
})
#' substr
#'
#' An expression that returns a substring.
#'
#' @rdname substr
#' @name substr
#' @family colum_func
#' @aliases substr,Column-method
#'
#' @param x a Column.
#' @param start starting position. It should be 1-base.
#' @param stop ending position.
#' @examples
#' \dontrun{
#' df <- createDataFrame(list(list(a="abcdef")))
#' collect(select(df, substr(df$a, 1, 4))) # the result is `abcd`.
#' collect(select(df, substr(df$a, 2, 4))) # the result is `bcd`.
#' }
#' @note substr since 1.4.0
setMethod("substr", signature(x = "Column"),
function(x, start, stop) {
jc <- callJMethod(x@jc, "substr", as.integer(start), as.integer(stop - start + 1))
column(jc)
})
#' startsWith
#'
#' Determines if entries of x start with string (entries of) prefix respectively,
#' where strings are recycled to common lengths.
#'
#' @rdname startsWith
#' @name startsWith
#' @family colum_func
#' @aliases startsWith,Column-method
#'
#' @param x vector of character string whose "starts" are considered
#' @param prefix character vector (often of length one)
#' @note startsWith since 1.4.0
setMethod("startsWith", signature(x = "Column"),
function(x, prefix) {
jc <- callJMethod(x@jc, "startsWith", as.vector(prefix))
column(jc)
})
#' endsWith
#'
#' Determines if entries of x end with string (entries of) suffix respectively,
#' where strings are recycled to common lengths.
#'
#' @rdname endsWith
#' @name endsWith
#' @family colum_func
#' @aliases endsWith,Column-method
#'
#' @param x vector of character string whose "ends" are considered
#' @param suffix character vector (often of length one)
#' @note endsWith since 1.4.0
setMethod("endsWith", signature(x = "Column"),
function(x, suffix) {
jc <- callJMethod(x@jc, "endsWith", as.vector(suffix))
column(jc)
})
#' between
#'
#' Test if the column is between the lower bound and upper bound, inclusive.
#'
#' @rdname between
#' @name between
#' @family colum_func
#' @aliases between,Column-method
#'
#' @param x a Column
#' @param bounds lower and upper bounds
#' @note between since 1.5.0
setMethod("between", signature(x = "Column"),
function(x, bounds) {
if (is.vector(bounds) && length(bounds) == 2) {
jc <- callJMethod(x@jc, "between", bounds[1], bounds[2])
column(jc)
} else {
stop("bounds should be a vector of lower and upper bounds")
}
})
#' Casts the column to a different data type.
#'
#' @param x a Column.
#' @param dataType a character object describing the target data type.
#' See
# nolint start
#' \href{https://spark.apache.org/docs/latest/sparkr.html#data-type-mapping-between-r-and-spark}{
#' Spark Data Types} for available data types.
# nolint end
#' @rdname cast
#' @name cast
#' @family colum_func
#' @aliases cast,Column-method
#'
#' @examples
#' \dontrun{
#' cast(df$age, "string")
#' }
#' @note cast since 1.4.0
setMethod("cast",
signature(x = "Column"),
function(x, dataType) {
if (is.character(dataType)) {
column(callJMethod(x@jc, "cast", dataType))
} else {
stop("dataType should be character")
}
})
#' Match a column with given values.
#'
#' @param x a Column.
#' @param table a collection of values (coercible to list) to compare with.
#' @rdname match
#' @name %in%
#' @aliases %in%,Column-method
#' @return A matched values as a result of comparing with given values.
#' @examples
#' \dontrun{
#' filter(df, "age in (10, 30)")
#' where(df, df$age %in% c(10, 30))
#' }
#' @note \%in\% since 1.5.0
setMethod("%in%",
signature(x = "Column"),
function(x, table) {
jc <- callJMethod(x@jc, "isin", as.list(table))
return(column(jc))
})
#' otherwise
#'
#' If values in the specified column are null, returns the value.
#' Can be used in conjunction with \code{when} to specify a default value for expressions.
#'
#' @param x a Column.
#' @param value value to replace when the corresponding entry in \code{x} is NA.
#' Can be a single value or a Column.
#' @rdname otherwise
#' @name otherwise
#' @family colum_func
#' @aliases otherwise,Column-method
#' @note otherwise since 1.5.0
setMethod("otherwise",
signature(x = "Column", value = "ANY"),
function(x, value) {
value <- if (class(value) == "Column") { value@jc } else { value }
jc <- callJMethod(x@jc, "otherwise", value)
column(jc)
})
#' \%<=>\%
#'
#' Equality test that is safe for null values.
#'
#' Can be used, unlike standard equality operator, to perform null-safe joins.
#' Equivalent to Scala \code{Column.<=>} and \code{Column.eqNullSafe}.
#'
#' @param x a Column
#' @param value a value to compare
#' @rdname eq_null_safe
#' @name %<=>%
#' @aliases %<=>%,Column-method
#' @examples
#' \dontrun{
#' df1 <- createDataFrame(data.frame(
#' x = c(1, NA, 3, NA), y = c(2, 6, 3, NA)
#' ))
#'
#' head(select(df1, df1$x == df1$y, df1$x %<=>% df1$y))
#'
#' df2 <- createDataFrame(data.frame(y = c(3, NA)))
#' count(join(df1, df2, df1$y == df2$y))
#'
#' count(join(df1, df2, df1$y %<=>% df2$y))
#' }
#' @note \%<=>\% since 2.3.0
setMethod("%<=>%",
signature(x = "Column", value = "ANY"),
function(x, value) {
value <- if (class(value) == "Column") { value@jc } else { value }
jc <- callJMethod(x@jc, "eqNullSafe", value)
column(jc)
})
#' !
#'
#' Inversion of boolean expression.
#'
#' @rdname not
#' @name not
#' @aliases !,Column-method
#' @examples
#' \dontrun{
#' df <- createDataFrame(data.frame(x = c(-1, 0, 1)))
#'
#' head(select(df, !column("x") > 0))
#' }
#' @note ! since 2.3.0
setMethod("!", signature(x = "Column"), function(x) not(x))
#' withField
#'
#' Adds/replaces field in a struct \code{Column} by name.
#'
#' @param x a Column
#' @param fieldName a character
#' @param col a Column expression
#'
#' @rdname withField
#' @aliases withField withField,Column-method
#' @examples
#' \dontrun{
#' df <- withColumn(
#' createDataFrame(iris),
#' "sepal",
#' struct(column("Sepal_Width"), column("Sepal_Length"))
#' )
#'
#' head(select(
#' df,
#' withField(df$sepal, "product", df$Sepal_Length * df$Sepal_Width)
#' ))
#' }
#' @note withField since 3.1.0
setMethod("withField",
signature(x = "Column", fieldName = "character", col = "Column"),
function(x, fieldName, col) {
jc <- callJMethod(x@jc, "withField", fieldName, col@jc)
column(jc)
})
#' dropFields
#'
#' Drops fields in a struct \code{Column} by name.
#'
#' @param x a Column
#' @param ... names of the fields to be dropped.
#'
#' @rdname dropFields
#' @aliases dropFields dropFields,Column-method
#' @examples
#' \dontrun{
#' df <- select(
#' createDataFrame(iris),
#' alias(
#' struct(
#' column("Sepal_Width"), column("Sepal_Length"),
#' alias(
#' struct(
#' column("Petal_Width"), column("Petal_Length"),
#' alias(
#' column("Petal_Width") * column("Petal_Length"),
#' "Petal_Product"
#' )
#' ),
#' "Petal"
#' )
#' ),
#' "dimensions"
#' )
#' )
#' head(withColumn(df, "dimensions", dropFields(df$dimensions, "Petal")))
#'
#' head(
#' withColumn(
#' df, "dimensions",
#' dropFields(df$dimensions, "Sepal_Width", "Sepal_Length")
#' )
#' )
#'
#' # This method supports dropping multiple nested fields directly e.g.
#' head(
#' withColumn(
#' df, "dimensions",
#' dropFields(df$dimensions, "Petal.Petal_Width", "Petal.Petal_Length")
#' )
#' )
#'
#' # However, if you are going to add/replace multiple nested fields,
#' # it is preffered to extract out the nested struct before
#' # adding/replacing multiple fields e.g.
#' head(
#' withColumn(
#' df, "dimensions",
#' withField(
#' column("dimensions"),
#' "Petal",
#' dropFields(column("dimensions.Petal"), "Petal_Width", "Petal_Length")
#' )
#' )
#' )
#' }
#' @note dropFields since 3.1.0
setMethod("dropFields",
signature(x = "Column"),
function(x, ...) {
jc <- callJMethod(x@jc, "dropFields", list(...))
column(jc)
})