SparkR_3.2.1.tar.gz

# # 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. # #' @include generics.R column.R NULL #' Aggregate functions for Column operations #' #' Aggregate functions defined for \code{Column}. #' #' @param x Column to compute on. #' @param y,na.rm,use currently not used. #' @param ... additional argument(s). For example, it could be used to pass additional Columns. #' @name column_aggregate_functions #' @rdname column_aggregate_functions #' @family aggregate functions #' @examples #' \dontrun{ #' # Dataframe used throughout this doc #' df <- createDataFrame(cbind(model = rownames(mtcars), mtcars))} NULL #' Date time functions for Column operations #' #' Date time functions defined for \code{Column}. #' #' @param x Column to compute on. In \code{window}, it must be a time Column of #' \code{TimestampType}. This is not used with \code{current_date} and #' \code{current_timestamp} #' @param format The format for the given dates or timestamps in Column \code{x}. See the #' format used in the following methods: #' \itemize{ #' \item \code{to_date} and \code{to_timestamp}: it is the string to use to parse #' Column \code{x} to DateType or TimestampType. #' \item \code{trunc}: it is the string to use to specify the truncation method. #' 'year', 'yyyy', 'yy' to truncate by year, #' or 'month', 'mon', 'mm' to truncate by month #' Other options are: 'week', 'quarter' #' \item \code{date_trunc}: it is similar with \code{trunc}'s but additionally #' supports #' 'day', 'dd' to truncate by day, #' 'microsecond', 'millisecond', 'second', 'minute' and 'hour' #' } #' @param ... additional argument(s). #' @name column_datetime_functions #' @rdname column_datetime_functions #' @family data time functions #' @examples #' \dontrun{ #' dts <- c("2005-01-02 18:47:22", #' "2005-12-24 16:30:58", #' "2005-10-28 07:30:05", #' "2005-12-28 07:01:05", #' "2006-01-24 00:01:10") #' y <- c(2.0, 2.2, 3.4, 2.5, 1.8) #' df <- createDataFrame(data.frame(time = as.POSIXct(dts), y = y))} NULL #' Date time arithmetic functions for Column operations #' #' Date time arithmetic functions defined for \code{Column}. #' #' @param y Column to compute on. #' @param x For class \code{Column}, it is the column used to perform arithmetic operations #' with column \code{y}. For class \code{numeric}, it is the number of months or #' days to be added to or subtracted from \code{y}. For class \code{character}, it is #' \itemize{ #' \item \code{date_format}: date format specification. #' \item \code{from_utc_timestamp}, \code{to_utc_timestamp}: A string detailing #' the time zone ID that the input should be adjusted to. It should be in the format #' of either region-based zone IDs or zone offsets. Region IDs must have the form #' 'area/city', such as 'America/Los_Angeles'. Zone offsets must be in the format #' (+|-)HH:mm', for example '-08:00' or '+01:00'. Also 'UTC' and 'Z' are supported #' as aliases of '+00:00'. Other short names are not recommended to use #' because they can be ambiguous. #' \item \code{next_day}: day of the week string. #' } #' @param ... additional argument(s). #' \itemize{ #' \item \code{months_between}, this contains an optional parameter to specify the #' the result is rounded off to 8 digits. #' } #' #' @name column_datetime_diff_functions #' @rdname column_datetime_diff_functions #' @family data time functions #' @examples #' \dontrun{ #' dts <- c("2005-01-02 18:47:22", #' "2005-12-24 16:30:58", #' "2005-10-28 07:30:05", #' "2005-12-28 07:01:05", #' "2006-01-24 00:01:10") #' y <- c(2.0, 2.2, 3.4, 2.5, 1.8) #' df <- createDataFrame(data.frame(time = as.POSIXct(dts), y = y))} NULL #' Math functions for Column operations #' #' Math functions defined for \code{Column}. #' #' @param x Column to compute on. In \code{shiftLeft}, \code{shiftRight} and #' \code{shiftRightUnsigned}, this is the number of bits to shift. #' @param y Column to compute on. #' @param ... additional argument(s). #' @name column_math_functions #' @rdname column_math_functions #' @family math functions #' @examples #' \dontrun{ #' # Dataframe used throughout this doc #' df <- createDataFrame(cbind(model = rownames(mtcars), mtcars)) #' tmp <- mutate(df, v1 = log(df$mpg), v2 = cbrt(df$disp), #' v3 = bround(df$wt, 1), v4 = bin(df$cyl), #' v5 = hex(df$wt), v6 = degrees(df$gear), #' v7 = atan2(df$cyl, df$am), v8 = hypot(df$cyl, df$am), #' v9 = pmod(df$hp, df$cyl), v10 = shiftLeft(df$disp, 1), #' v11 = conv(df$hp, 10, 16), v12 = sign(df$vs - 0.5), #' v13 = sqrt(df$disp), v14 = ceil(df$wt)) #' head(tmp)} NULL #' String functions for Column operations #' #' String functions defined for \code{Column}. #' #' @param x Column to compute on except in the following methods: #' \itemize{ #' \item \code{instr}: \code{character}, the substring to check. See 'Details'. #' \item \code{format_number}: \code{numeric}, the number of decimal place to #' format to. See 'Details'. #' } #' @param y Column to compute on. #' @param pos In \itemize{ #' \item \code{locate}: a start position of search. #' \item \code{overlay}: a start position for replacement. #' } #' @param len In \itemize{ #' \item \code{lpad} the maximum length of each output result. #' \item \code{overlay} a number of bytes to replace. #' } #' @param ... additional Columns. #' @name column_string_functions #' @rdname column_string_functions #' @family string functions #' @examples #' \dontrun{ #' # Dataframe used throughout this doc #' df <- createDataFrame(as.data.frame(Titanic, stringsAsFactors = FALSE))} NULL #' Non-aggregate functions for Column operations #' #' Non-aggregate functions defined for \code{Column}. #' #' @param x Column to compute on. In \code{lit}, it is a literal value or a Column. #' In \code{expr}, it contains an expression character object to be parsed. #' @param y Column to compute on. #' @param ... additional Columns. #' @name column_nonaggregate_functions #' @rdname column_nonaggregate_functions #' @seealso coalesce,SparkDataFrame-method #' @family non-aggregate functions #' @examples #' \dontrun{ #' # Dataframe used throughout this doc #' 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 <- c