зеркало из https://github.com/microsoft/wpa.git
docs: improve documentation
This commit is contained in:
Martin Chan
Родитель
4c8ca2d581
Коммит
a50d956640
|
|
@ -2,6 +2,7 @@
|
|||
#' using the binary week-based (bw) method.
|
||||
#'
|
||||
#' @description
|
||||
#' `r lifecycle::badge('experimental')`
|
||||
#' Apply a rule based algorithm to emails sent by hour of day,
|
||||
#' using the binary week-based (bw) method.
|
||||
#'
|
||||
|
|
@ -97,60 +98,6 @@ workpatterns_classify_bw <- function(data,
|
|||
## Signal label
|
||||
sig_label <- ifelse(length(signal_set) > 1, "Signals_sent", signal_set)
|
||||
|
||||
# ## Select input variable names
|
||||
# if("email" %in% signals & "IM" %in% signals){
|
||||
#
|
||||
# ## Create 24 summed `Signals_sent` columns
|
||||
# signal_cols <-
|
||||
# purrr::map(0:23, ~combine_signals(data2, hr = .)) %>%
|
||||
# dplyr::bind_cols()
|
||||
#
|
||||
# ## Use names for matching
|
||||
# input_var <- names(signal_cols)
|
||||
#
|
||||
# ## Signals sent by Person and date
|
||||
# signals_df <-
|
||||
# data2 %>%
|
||||
# .[, c("PersonId", "Date")] %>%
|
||||
# cbind(signal_cols)
|
||||
#
|
||||
# ## Signal label
|
||||
# sig_label <- "Signals_sent"
|
||||
#
|
||||
# } else if(signals == "IM"){
|
||||
#
|
||||
# match_index <- grepl(pattern = "^IMs_sent", x = names(data2))
|
||||
# input_var <- names(data2)[match_index]
|
||||
# input_var2 <- c("PersonId", "Date", input_var)
|
||||
#
|
||||
# ## signals sent by Person and date
|
||||
# signals_df <-
|
||||
# data2 %>%
|
||||
# .[, ..input_var2]
|
||||
#
|
||||
# sig_label <- "IMs_sent"
|
||||
#
|
||||
#
|
||||
# } else if(signals == "email"){
|
||||
#
|
||||
# match_index <- grepl(pattern = "^Emails_sent", x = names(data2))
|
||||
# input_var <- names(data2)[match_index]
|
||||
# input_var2 <- c("PersonId", "Date", input_var)
|
||||
#
|
||||
# ## signals sent by Person and date
|
||||
# signals_df <-
|
||||
# data2 %>%
|
||||
# .[, ..input_var2]
|
||||
#
|
||||
# sig_label <- "Emails_sent"
|
||||
#
|
||||
# } else {
|
||||
#
|
||||
# stop("Invalid input for `signals`.")
|
||||
#
|
||||
# }
|
||||
|
||||
|
||||
## Create binary variable 0 or 1
|
||||
num_cols <- names(which(sapply(signals_df, is.numeric))) # Get numeric columns
|
||||
|
||||
|
|
|
|||
|
|
@ -2,22 +2,29 @@
|
|||
#' the person-average volume-based (pav) method.
|
||||
#'
|
||||
#' @description
|
||||
#' `r lifecycle::badge('experimental')`
|
||||
#' Apply a rule based algorithm to emails or instant messages sent by hour of day.
|
||||
#' This uses a person-average volume-based (pav) method.
|
||||
#'
|
||||
#' @param data A data frame containing data from the Hourly Collaboration query.
|
||||
#'
|
||||
#' @param return Character vector to specify what to return.
|
||||
#' Valid options include "plot" (default), "data", "table" and "plot-area".
|
||||
#' "plot" returns a bar plot, whilst "plot-area" returns an overlapping area plot.
|
||||
#' @param return Character vector to specify what to return. Valid options include:
|
||||
#' - "plot": returns a bar plot of signal distribution by hour and archetypes (default)
|
||||
#' - "data": returns the raw data with the classified archetypes
|
||||
#' - "table": returns a summary table of the archetypes
|
||||
#' - "plot-area": returns an overlapping area plot
|
||||
#'
|
||||
#' @param values Character vector to specify whether to return percentages
|
||||
#' or absolute values in "data" and "plot". Valid values are "percent" (default)
|
||||
#' and "abs".
|
||||
#' or absolute values in "data" and "plot". Valid values are:
|
||||
#' - "percent": percentage of signals divided by total signals (default)
|
||||
#' - "abs": absolute count of signals
|
||||
#'
|
||||
#' @param signals Character vector to specify which collaboration metrics to use:
|
||||
#' You may use "email" (default) for emails only, "IM" for Teams messages only,
|
||||
#' or a combination of the two `c("email", "IM")`.
|
||||
#' - "email" (default) for emails only
|
||||
#' - "IM" for Teams messages only,
|
||||
#' - "unscheduled_calls" for Unscheduled Calls only
|
||||
#' - "meetings" for Meetings only
|
||||
#' - or a combination of signals, such as `c("email", "IM")`
|
||||
#'
|
||||
#' @param start_hour A character vector specifying starting hours,
|
||||
#' e.g. "0900"
|
||||
|
|
@ -29,13 +36,14 @@
|
|||
#' @import ggplot2
|
||||
#'
|
||||
#' @examples
|
||||
#' \dontrun{
|
||||
#' # Returns a plot by default
|
||||
#' workpatterns_classify(em_data)
|
||||
#' ## Returns a plot by default
|
||||
#' workpatterns_classify_pav(em_data)
|
||||
#'
|
||||
#' # Returning a table
|
||||
#' workpatterns_classify(em_data, return = "table")
|
||||
#' }
|
||||
#' ## Return a table
|
||||
#' workpatterns_classify_pav(em_data, return = "table")
|
||||
#'
|
||||
#' ## Return an area plot
|
||||
#' workpatterns_classify_pav(em_data, return = "plot-area")
|
||||
#'
|
||||
#' @family Work Patterns
|
||||
#'
|
||||
|
|
@ -82,65 +90,6 @@ workpatterns_classify_pav <- function(data,
|
|||
## Signal label
|
||||
sig_label <- ifelse(length(signal_set) > 1, "Signals_sent", signal_set)
|
||||
|
||||
# ## Select input variable names
|
||||
# if("email" %in% signals & "IM" %in% signals){
|
||||
#
|
||||
# ## Create 24 summed `Signals_sent` columns
|
||||
# signal_cols <-
|
||||
# purrr::map(0:23,
|
||||
# ~combine_signals(data,
|
||||
# hr = .)) %>%
|
||||
# bind_cols()
|
||||
#
|
||||
# ## Use names for matching
|
||||
# input_var <- names(signal_cols)
|
||||
#
|
||||
# ## Average signals sent by Person
|
||||
# signals_df <-
|
||||
# data %>%
|
||||
# select(PersonId) %>%
|
||||
# cbind(signal_cols) %>%
|
||||
# group_by(PersonId) %>%
|
||||
# summarise_all(~mean(.))
|
||||
#
|
||||
# ## Signal label
|
||||
# sig_label <- "Signals_sent"
|
||||
#
|
||||
# } else if(signals == "IM"){
|
||||
#
|
||||
# match_index <- grepl(pattern = "^IMs_sent", x = names(data))
|
||||
# input_var <-names(data)[match_index]
|
||||
#
|
||||
# ## Average signals sent by Person
|
||||
# signals_df <-
|
||||
# data %>%
|
||||
# select(PersonId, all_of(input_var)) %>%
|
||||
# group_by(PersonId) %>%
|
||||
# summarise_all(~mean(.))
|
||||
#
|
||||
# sig_label <- "IMs_sent"
|
||||
#
|
||||
# } else if(signals == "email"){
|
||||
#
|
||||
# match_index <- grepl(pattern = "^Emails_sent", x = names(data))
|
||||
# input_var <-names(data)[match_index]
|
||||
#
|
||||
# ## Average signals sent by Person
|
||||
# signals_df <-
|
||||
# data %>%
|
||||
# select(PersonId, all_of(input_var)) %>%
|
||||
# group_by(PersonId) %>%
|
||||
# summarise_all(~mean(.))
|
||||
#
|
||||
# sig_label <- "Emails_sent"
|
||||
#
|
||||
# } else {
|
||||
#
|
||||
# stop("Invalid input for `signals`.")
|
||||
#
|
||||
# }
|
||||
|
||||
|
||||
## Normalised pattern data
|
||||
ptn_data_norm <-
|
||||
signals_df %>%
|
||||
|
|
|
|||
|
|
@ -18,15 +18,19 @@
|
|||
#'
|
||||
#' @param data A data frame containing data from the Hourly Collaboration query.
|
||||
#' @param k Numeric vector to specify the `k` number of clusters to cut by.
|
||||
#' @param return Character vector to specify what to return.
|
||||
#' Valid options include "plot" (default), "data", "table", "plot-area", "hclust", and "dist".
|
||||
#' "plot" returns a bar plot, whilst "plot-area" returns an overlapping area plot.
|
||||
#' "hclust" returns the hierarchical model generated by the function.
|
||||
#' "dist" returns the distance matrix used to build the clustering model.
|
||||
#' @param return Character vector to specify what to return. Valid options include:
|
||||
#' - "plot": returns a bar plot (default)
|
||||
#' - "data": returns raw data with the clusters
|
||||
#' - "table": returns a summary table
|
||||
#' - "plot-area": returns an overlapping area plot
|
||||
#' - "hclust": returns the hierarchical model generated by the function
|
||||
#' - "dist": returns the distance matrix used to build the clustering model
|
||||
#'
|
||||
#' @param values Character vector to specify whether to return percentages
|
||||
#' or absolute values in "data" and "plot". Valid values are "percent" (default)
|
||||
#' and "abs".
|
||||
#' or absolute values in "data" and "plot". Valid values are:
|
||||
#' - "percent": percentage of signals divided by total signals (default)
|
||||
#' - "abs": absolute count of signals
|
||||
#'
|
||||
#' @param signals Character vector to specify which collaboration metrics to use:
|
||||
#' - "email" (default) for emails only
|
||||
#' - "IM" for Teams messages only
|
||||
|
|
|
|||
|
|
@ -39,6 +39,7 @@ Valid options include "plot" (default), "data", "table" and "plot-area".
|
|||
"plot" returns a bar plot, whilst "plot-area" returns an overlapping area plot.}
|
||||
}
|
||||
\description{
|
||||
\ifelse{html}{\out{<a href='https://www.tidyverse.org/lifecycle/#experimental'><img src='figures/lifecycle-experimental.svg' alt='Experimental lifecycle'></a>}}{\strong{Experimental}}
|
||||
Apply a rule based algorithm to emails sent by hour of day,
|
||||
using the binary week-based (bw) method.
|
||||
}
|
||||
|
|
|
|||
|
|
@ -18,12 +18,20 @@ workpatterns_classify_pav(
|
|||
\item{data}{A data frame containing data from the Hourly Collaboration query.}
|
||||
|
||||
\item{values}{Character vector to specify whether to return percentages
|
||||
or absolute values in "data" and "plot". Valid values are "percent" (default)
|
||||
and "abs".}
|
||||
or absolute values in "data" and "plot". Valid values are:
|
||||
\itemize{
|
||||
\item "percent": percentage of signals divided by total signals (default)
|
||||
\item "abs": absolute count of signals
|
||||
}}
|
||||
|
||||
\item{signals}{Character vector to specify which collaboration metrics to use:
|
||||
You may use "email" (default) for emails only, "IM" for Teams messages only,
|
||||
or a combination of the two \code{c("email", "IM")}.}
|
||||
\itemize{
|
||||
\item "email" (default) for emails only
|
||||
\item "IM" for Teams messages only,
|
||||
\item "unscheduled_calls" for Unscheduled Calls only
|
||||
\item "meetings" for Meetings only
|
||||
\item or a combination of signals, such as \code{c("email", "IM")}
|
||||
}}
|
||||
|
||||
\item{start_hour}{A character vector specifying starting hours,
|
||||
e.g. "0900"}
|
||||
|
|
@ -31,22 +39,28 @@ e.g. "0900"}
|
|||
\item{end_hour}{A character vector specifying starting hours,
|
||||
e.g. "1700"}
|
||||
|
||||
\item{return}{Character vector to specify what to return.
|
||||
Valid options include "plot" (default), "data", "table" and "plot-area".
|
||||
"plot" returns a bar plot, whilst "plot-area" returns an overlapping area plot.}
|
||||
\item{return}{Character vector to specify what to return. Valid options include:
|
||||
\itemize{
|
||||
\item "plot": returns a bar plot of signal distribution by hour and archetypes (default)
|
||||
\item "data": returns the raw data with the classified archetypes
|
||||
\item "table": returns a summary table of the archetypes
|
||||
\item "plot-area": returns an overlapping area plot
|
||||
}}
|
||||
}
|
||||
\description{
|
||||
\ifelse{html}{\out{<a href='https://www.tidyverse.org/lifecycle/#experimental'><img src='figures/lifecycle-experimental.svg' alt='Experimental lifecycle'></a>}}{\strong{Experimental}}
|
||||
Apply a rule based algorithm to emails or instant messages sent by hour of day.
|
||||
This uses a person-average volume-based (pav) method.
|
||||
}
|
||||
\examples{
|
||||
\dontrun{
|
||||
# Returns a plot by default
|
||||
workpatterns_classify(em_data)
|
||||
## Returns a plot by default
|
||||
workpatterns_classify_pav(em_data)
|
||||
|
||||
# Returning a table
|
||||
workpatterns_classify(em_data, return = "table")
|
||||
}
|
||||
## Return a table
|
||||
workpatterns_classify_pav(em_data, return = "table")
|
||||
|
||||
## Return an area plot
|
||||
workpatterns_classify_pav(em_data, return = "plot-area")
|
||||
|
||||
}
|
||||
\seealso{
|
||||
|
|
|
|||
|
|
@ -19,15 +19,22 @@ workpatterns_hclust(
|
|||
|
||||
\item{k}{Numeric vector to specify the \code{k} number of clusters to cut by.}
|
||||
|
||||
\item{return}{Character vector to specify what to return.
|
||||
Valid options include "plot" (default), "data", "table", "plot-area", "hclust", and "dist".
|
||||
"plot" returns a bar plot, whilst "plot-area" returns an overlapping area plot.
|
||||
"hclust" returns the hierarchical model generated by the function.
|
||||
"dist" returns the distance matrix used to build the clustering model.}
|
||||
\item{return}{Character vector to specify what to return. Valid options include:
|
||||
\itemize{
|
||||
\item "plot": returns a bar plot (default)
|
||||
\item "data": returns raw data with the clusters
|
||||
\item "table": returns a summary table
|
||||
\item "plot-area": returns an overlapping area plot
|
||||
\item "hclust": returns the hierarchical model generated by the function
|
||||
\item "dist": returns the distance matrix used to build the clustering model
|
||||
}}
|
||||
|
||||
\item{values}{Character vector to specify whether to return percentages
|
||||
or absolute values in "data" and "plot". Valid values are "percent" (default)
|
||||
and "abs".}
|
||||
or absolute values in "data" and "plot". Valid values are:
|
||||
\itemize{
|
||||
\item "percent": percentage of signals divided by total signals (default)
|
||||
\item "abs": absolute count of signals
|
||||
}}
|
||||
|
||||
\item{signals}{Character vector to specify which collaboration metrics to use:
|
||||
\itemize{
|
||||
|
|
|
|||
Загрузка…
Ссылка в новой задаче