You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by fe...@apache.org on 2017/06/30 04:35:05 UTC
spark git commit: [SPARK-20889][SPARKR] Grouped documentation for
MISC column methods
Repository: spark
Updated Branches:
refs/heads/master e2f32ee45 -> fddb63f46
[SPARK-20889][SPARKR] Grouped documentation for MISC column methods
## What changes were proposed in this pull request?
Grouped documentation for column misc methods.
Author: actuaryzhang <ac...@gmail.com>
Author: Wayne Zhang <ac...@gmail.com>
Closes #18448 from actuaryzhang/sparkRDocMisc.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/fddb63f4
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/fddb63f4
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/fddb63f4
Branch: refs/heads/master
Commit: fddb63f46345be36c40d9a7f3660920af6502bbd
Parents: e2f32ee
Author: actuaryzhang <ac...@gmail.com>
Authored: Thu Jun 29 21:35:01 2017 -0700
Committer: Felix Cheung <fe...@apache.org>
Committed: Thu Jun 29 21:35:01 2017 -0700
----------------------------------------------------------------------
R/pkg/R/functions.R | 98 ++++++++++++++++++++++--------------------------
R/pkg/R/generics.R | 15 +++++---
2 files changed, 55 insertions(+), 58 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/fddb63f4/R/pkg/R/functions.R
----------------------------------------------------------------------
diff --git a/R/pkg/R/functions.R b/R/pkg/R/functions.R
index cb09e84..67cb7a7 100644
--- a/R/pkg/R/functions.R
+++ b/R/pkg/R/functions.R
@@ -150,6 +150,27 @@ NULL
#' df <- createDataFrame(cbind(model = rownames(mtcars), mtcars))}
NULL
+#' Miscellaneous functions for Column operations
+#'
+#' Miscellaneous functions defined for \code{Column}.
+#'
+#' @param x Column to compute on. In \code{sha2}, it is one of 224, 256, 384, or 512.
+#' @param y Column to compute on.
+#' @param ... additional Columns.
+#' @name column_misc_functions
+#' @rdname column_misc_functions
+#' @family misc functions
+#' @examples
+#' \dontrun{
+#' # Dataframe used throughout this doc
+#' df <- createDataFrame(cbind(model = rownames(mtcars), mtcars)[, 1:2])
+#' tmp <- mutate(df, v1 = crc32(df$model), v2 = hash(df$model),
+#' v3 = hash(df$model, df$mpg), v4 = md5(df$model),
+#' v5 = sha1(df$model), v6 = sha2(df$model, 256))
+#' head(tmp)
+#' }
+NULL
+
#' @details
#' \code{lit}: A new Column is created to represent the literal value.
#' If the parameter is a Column, it is returned unchanged.
@@ -569,19 +590,13 @@ setMethod("count",
column(jc)
})
-#' crc32
-#'
-#' Calculates the cyclic redundancy check value (CRC32) of a binary column and
-#' returns the value as a bigint.
-#'
-#' @param x Column to compute on.
+#' @details
+#' \code{crc32}: Calculates the cyclic redundancy check value (CRC32) of a binary column
+#' and returns the value as a bigint.
#'
-#' @rdname crc32
-#' @name crc32
-#' @family misc functions
-#' @aliases crc32,Column-method
+#' @rdname column_misc_functions
+#' @aliases crc32 crc32,Column-method
#' @export
-#' @examples \dontrun{crc32(df$c)}
#' @note crc32 since 1.5.0
setMethod("crc32",
signature(x = "Column"),
@@ -590,19 +605,13 @@ setMethod("crc32",
column(jc)
})
-#' hash
-#'
-#' Calculates the hash code of given columns, and returns the result as a int column.
-#'
-#' @param x Column to compute on.
-#' @param ... additional Column(s) to be included.
+#' @details
+#' \code{hash}: Calculates the hash code of given columns, and returns the result
+#' as an int column.
#'
-#' @rdname hash
-#' @name hash
-#' @family misc functions
-#' @aliases hash,Column-method
+#' @rdname column_misc_functions
+#' @aliases hash hash,Column-method
#' @export
-#' @examples \dontrun{hash(df$c)}
#' @note hash since 2.0.0
setMethod("hash",
signature(x = "Column"),
@@ -1055,19 +1064,13 @@ setMethod("max",
column(jc)
})
-#' md5
-#'
-#' Calculates the MD5 digest of a binary column and returns the value
+#' @details
+#' \code{md5}: Calculates the MD5 digest of a binary column and returns the value
#' as a 32 character hex string.
#'
-#' @param x Column to compute on.
-#'
-#' @rdname md5
-#' @name md5
-#' @family misc functions
-#' @aliases md5,Column-method
+#' @rdname column_misc_functions
+#' @aliases md5 md5,Column-method
#' @export
-#' @examples \dontrun{md5(df$c)}
#' @note md5 since 1.5.0
setMethod("md5",
signature(x = "Column"),
@@ -1307,19 +1310,13 @@ setMethod("second",
column(jc)
})
-#' sha1
-#'
-#' Calculates the SHA-1 digest of a binary column and returns the value
+#' @details
+#' \code{sha1}: Calculates the SHA-1 digest of a binary column and returns the value
#' as a 40 character hex string.
#'
-#' @param x Column to compute on.
-#'
-#' @rdname sha1
-#' @name sha1
-#' @family misc functions
-#' @aliases sha1,Column-method
+#' @rdname column_misc_functions
+#' @aliases sha1 sha1,Column-method
#' @export
-#' @examples \dontrun{sha1(df$c)}
#' @note sha1 since 1.5.0
setMethod("sha1",
signature(x = "Column"),
@@ -2309,19 +2306,14 @@ setMethod("format_number", signature(y = "Column", x = "numeric"),
column(jc)
})
-#' sha2
-#'
-#' Calculates the SHA-2 family of hash functions of a binary column and
-#' returns the value as a hex string.
+#' @details
+#' \code{sha2}: Calculates the SHA-2 family of hash functions of a binary column and
+#' returns the value as a hex string. The second argument \code{x} specifies the number
+#' of bits, and is one of 224, 256, 384, or 512.
#'
-#' @param y column to compute SHA-2 on.
-#' @param x one of 224, 256, 384, or 512.
-#' @family misc functions
-#' @rdname sha2
-#' @name sha2
-#' @aliases sha2,Column,numeric-method
+#' @rdname column_misc_functions
+#' @aliases sha2 sha2,Column,numeric-method
#' @export
-#' @examples \dontrun{sha2(df$c, 256)}
#' @note sha2 since 1.5.0
setMethod("sha2", signature(y = "Column", x = "numeric"),
function(y, x) {
http://git-wip-us.apache.org/repos/asf/spark/blob/fddb63f4/R/pkg/R/generics.R
----------------------------------------------------------------------
diff --git a/R/pkg/R/generics.R b/R/pkg/R/generics.R
index 1deb057..bdd4b36 100644
--- a/R/pkg/R/generics.R
+++ b/R/pkg/R/generics.R
@@ -992,8 +992,9 @@ setGeneric("conv", function(x, fromBase, toBase) { standardGeneric("conv") })
#' @name NULL
setGeneric("countDistinct", function(x, ...) { standardGeneric("countDistinct") })
-#' @rdname crc32
+#' @rdname column_misc_functions
#' @export
+#' @name NULL
setGeneric("crc32", function(x) { standardGeneric("crc32") })
#' @rdname column_nonaggregate_functions
@@ -1006,8 +1007,9 @@ setGeneric("create_array", function(x, ...) { standardGeneric("create_array") })
#' @name NULL
setGeneric("create_map", function(x, ...) { standardGeneric("create_map") })
-#' @rdname hash
+#' @rdname column_misc_functions
#' @export
+#' @name NULL
setGeneric("hash", function(x, ...) { standardGeneric("hash") })
#' @param x empty. Should be used with no argument.
@@ -1205,8 +1207,9 @@ setGeneric("lpad", function(x, len, pad) { standardGeneric("lpad") })
#' @name NULL
setGeneric("ltrim", function(x) { standardGeneric("ltrim") })
-#' @rdname md5
+#' @rdname column_misc_functions
#' @export
+#' @name NULL
setGeneric("md5", function(x) { standardGeneric("md5") })
#' @rdname column_datetime_functions
@@ -1350,12 +1353,14 @@ setGeneric("sd", function(x, na.rm = FALSE) { standardGeneric("sd") })
#' @name NULL
setGeneric("second", function(x) { standardGeneric("second") })
-#' @rdname sha1
+#' @rdname column_misc_functions
#' @export
+#' @name NULL
setGeneric("sha1", function(x) { standardGeneric("sha1") })
-#' @rdname sha2
+#' @rdname column_misc_functions
#' @export
+#' @name NULL
setGeneric("sha2", function(y, x) { standardGeneric("sha2") })
#' @rdname column_math_functions
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org