% \iffalse meta-comment
% vim: tw=80 spl=en
%
%% File: statistics.dtx (C) Copyright 2014-2019 RIVAUD Julien
%%
%% It may be distributed and/or modified under the conditions of the
%% General Public License (GPL), either version 3 of this
%% license or (at your option) any later version.
%
%<*driver|package>
% The version of expl3 required is tested as early as possible, as
% some really old versions do not define \ProvidesExplPackage.
\NeedsTeXFormat{LaTeX2e}[1995/12/01]
\RequirePackage{expl3}[2018/06/19]
%</driver|package>
%<*driver>
\documentclass[full]{l3doc}
\usepackage{statistics}
\usepackage{fontspec}
\usepackage{xparse}
\usepackage{xcolor}
\usepackage{geometry}
\usetikzlibrary{patterns}
\geometry{
a4paper,
vmargin=2.5cm, right=1.5cm, textwidth=385pt,
marginparwidth=21cm-1.5cm-0.5cm-0.4cm-385pt,
%marginparsep=0.4cm,
}
%</driver>
%<*driver|package>
\def\ExplFileName{statistics}
\def\ExplFileDescription{Compute and typeset statistics table and graphics}
\def\ExplFileDate{2019/09/29}
\def\ExplFileVersion{2.2}
%</driver|package>
%<*driver>
\ExplSyntaxOn
\let\tltostr\tl_to_str:N
\NewDocumentEnvironment{demo}{}{
\char_set_catcode_other:N \\
\peek_meaning:NTF [ {
\__statsdocs_demo_begin:
}{
\__statsdocs_demo_begin: []
}
}{
\mode_if_vertical:TF {
\penalty 0
}{
\par\nobreak
}
\skip_vertical:N \abovedisplayskip
\noindent\leavevmode
\hbox_set:Nn \l_tmpb_box {
\colorbox{yellow!5!white}{
\parbox{\linewidth}{
\raggedright
\tl_use:N \l_tmpb_tl
}
}
}
\hbox_set:Nn \l_tmpa_box {
\colorbox{blue!5!white}{
\parbox{\linewidth}{
\ttfamily
\raggedright
\tl_use:N \l_tmpa_tl
}
}
}
\fp_set:Nn \l_tmpa_fp {
round(
3000 *
\dim_ratio:nn { \box_ht:N \l_tmpb_box } { \box_ht:N \l_tmpa_box }
)
}
\box_use:N \l_tmpa_box \\ \box_use:N \l_tmpb_box
\int_set:Nn \interlinepenalty {\fp_to_int:N \l_tmpa_fp}
\par
\penalty 0
\skip_vertical:N \belowdisplayskip
}
\cs_new_protected:Nn \__statsdocs_demo_begin: {
\char_set_catcode_escape:N \\
\__statsdocs_demo_begin:w
}
\NewDocumentCommand \__statsdocs_demo_begin:w { +O{} } {
\char_set_catcode_other:N \^^M
\char_set_catcode_other:n {32}
\char_set_catcode_other:N \#
\char_set_catcode_other:N \\
\char_set_catcode_other:N \{
\char_set_catcode_other:N \}
\__statsdocs_read_demo:w
}
\group_begin:
\char_set_catcode_group_begin:N \[
\char_set_catcode_group_end:N \]
\char_set_catcode_escape:N \|
\char_set_catcode_other:N \{
\char_set_catcode_other:N \}
\char_set_catcode_other:N \\
|cs_new_protected:Npn |__statsdocs_read_demo:w #1 \end{demo}[
|__statsdocs_do_demo:n [#1]
]
|group_end:
\cs_new_protected:Nn \__statsdocs_do_demo:n {
\str_set:Nn \l_tmpa_str {#1}
\tl_trim_spaces:N \l_tmpa_str
\str_set:Nx \l_tmpb_str {\char_generate:nn{`\^^M}{12}}
\str_if_eq:eeT \l_tmpb_str { \str_head:N \l_tmpa_str } {
\str_set:Nx \l_tmpa_str { \str_tail:N \l_tmpa_str }
}
\tl_reverse:N \l_tmpa_str
\str_if_eq:eeT \l_tmpb_str { \str_head:N \l_tmpa_str } {
\str_set:Nx \l_tmpa_str { \str_tail:N \l_tmpa_str }
}
\tl_reverse:N \l_tmpa_str
\tl_set:Nx \l_tmpa_tl {~\l_tmpa_str}
\exp_args:NNV \tl_replace_all:Nnn \l_tmpa_tl \l_tmpb_str {\par}
\tl_set:Nx \l_tmpb_tl {\char_generate:nn{32}{12}}
\exp_args:NNnV \tl_replace_all:Nnn \l_tmpa_tl {~} \l_tmpb_tl
\exp_args:NNnV \tl_set_rescan:Nnn \l_tmpb_tl {
\char_set_catcode_escape:N \\
\char_set_catcode_space:n {32}
\char_set_catcode_parameter:N \#
\char_set_catcode_end_line:N \^^M
\char_set_catcode_group_begin:N \{
\char_set_catcode_group_end:N \}
} \l_tmpa_str
\end{demo}
}
\ExplSyntaxOff
\NewDocumentEnvironment{key}{}{\begin{variable}}{\end{variable}}
\begin{document}
\DocInput{\jobname.dtx}
\end{document}
%</driver>
% \fi
%
% \title{^^A
% The \textsf{\ExplFileName} package\\ \ExplFileDescription^^A
% \thanks{This file describes v\ExplFileVersion,
% last revised \ExplFileDate.}^^A
% }
%
% \author{^^A
% Julien ``\_FrnchFrgg\_'' \textsc{Rivaud}\thanks
% {^^A
% E-mail:
% \href{mailto:frnchfrgg@free.fr}
% {frnchfrgg@free.fr}^^A
% }^^A
% }
%
% \date{Released \ExplFileDate}
%
% \maketitle
%
% \tableofcontents
%
% \begin{documentation}
%
% \section{\pkg{\ExplFileName} documentation}
%
% The \pkg{\ExplFileName} package can compute and typeset statistics like
% frequency tables, cumulative distribution functions (increasing or decreasing,
% in frequency or absolute count domain), from the counts of individual values,
% or ranges, or even the raw value list with repetitions.
%
% It can also compute and draw a bar diagram in case of individual values, or,
% when the data repartition is known from ranges, an histogram or the continuous
% cumulative distribution function.
%
% You can ask \pkg{\ExplFileName} to display no result, selective results or all
% of them. Similarly \pkg{\ExplFileName} can draw only some parts of the graphs.
% Every part of the generated tables or graphics is customizable.
%
% \subsection{Specifying and converting data}
%
% To compute and typeset things, \pkg{\ExplFileName} starts from what this
% documentation calls a \meta{data source}. Such a source can take two forms:
% \begin{itemize}
% \item A comma-separated list of \meta{value} |[=| \meta{count} |]|;
% \item A \cs{\meta{macro}} containing such a list.
% \end{itemize}
%
% If \meta{count} is missing, it defaults to~$1$. \emph{A priori} the
% \meta{value}s need not be unique nor sorted, but \cs{StatsTable} and
% \cs{StatsGraph} expect them to be. If you want your data to be in the form of
% a raw list of unsorted and repeated values, you can thus use the following
% command to convert the data to a form suitable for \cs{StatsTable} and
% \cs{StatsGraph}:
%
% \begin{function}{\StatsSortData}
% \begin{syntax}
% \cs{StatsSortData} \cs{\meta{destination}} = \marg{data source}
% \end{syntax}
% This command expect each \meta{value} in the \meta{data source} to be
% convertible to a floating point number (as understood by \pkg{l3fp} from the
% \LaTeX3 kernel). It defines \cs{\meta{destination}} to hold an equivalent
% data source, where \meta{value}s are sorted in increasing order, and
% \meta{count}s are consolidated. As for all other \pkg{\ExplFileName}
% commands, \meta{data source} can be either given directly between braces, or
% as a \cs{\meta{macro}} which contains the list.
% \end{function}
%
% \begin{demo}
% \StatsSortData \mydata = { 2, 11=8, 6=3, 2=2, 11=1 }
% \def \rawdata { 2=2, 11=9, 6, 2, 6, 6 }
% \StatsSortData \yourdata = \rawdata
% mydata contains [\mydata]\\
% yourdata contains [\yourdata]
% \end{demo}
%
% The \cs{StatsTable} command will always assume that the \meta{data source} is
% sorted and will not try to parse the \meta{value}s. On the contrary,
% \cs{StatsGraph} \emph{will} parse each \meta{value}, and will act differently
% depending on whether every \meta{value} is a \meta{range} or the form
% \hbox{\cs{IN} \meta{|[| or |]|} \meta{min} |;| \meta{max} \meta{|[| or |]|}},
% or not.
%
% If your \meta{data source} is not given in ranges, but you want to count the
% values falling in each \meta{range} of a list you can use:
%
% \begin{function}{\StatsRangeData}
% \begin{syntax}
%\cs{StatsSortData}\
%\cs{\meta{destination}}\
%=\
%\marg{data source}\
%(\meta{range list})
% \end{syntax}
% This command expect each \meta{value} in the \meta{data source} to be
% convertible to a floating point number (as understood by \pkg{l3fp} from the
% \LaTeX3 kernel). It also expects \meta{range list} to be a comma-separated
% list of \meta{range}s, and will define \cs{\meta{destination}} to a
% \meta{data source} whose \meta{value}s are the said \meta{range}s and whose
% counts are, well\dots\ the number of floating point values that lie in those
% \meta{range}s.
%
% \cs{StatsRangeData} does not need the \meta{range}s to be sorted, nor even
% disjoint, but in that case the behavior of \cs{StatsGraph} is unspecified.
% \end{function}
%
% Here is an example\footnote{The \cs{tltostr} command is defined in this
% documentation to be an alias for the \LaTeX3 command \cs{tl_to_str:N} which is
% equivalent to \cs{detokenize}\cs{expandafter}|\{|\cs{\meta{macro}}|\}|.}:
% \begin{demo}
% \StatsRangeData \facebook = { 0, 1, 1.5, 1.5, 2, 3, 2.4, 2, 2.4=5,
% 3, 4=10, 5=6, 6=9, 6.5=5, 7, 7.1, 7.2,
% 7.3, 7.4, 7.5, 7.6, 7.7, 7, 7, 8, 8, 8,
% 9=5, 12=12}
% (\IN[0;1;[, \IN[1;2;[, \IN[2;4;[,
% \IN[4;7;[, \IN[7;10;[, \IN[10;14;[)
% \tltostr \facebook
% \end{demo}
% \def \facebook {
% \IN[0;1;[ = 1, \IN[1;2;[ = 3, \IN[2;4;[ = 10,
% \IN[4;7;[ = 30, \IN[7;10;[ = 18, \IN[10;14;[ = 12
% }
%
% This data source will be used throughout the documentation.
% \label{def:datasource}
%
% \subsection{Setting options}
%
% \begin{function}{\statisticssetup}
% \begin{syntax}
% \cs{statisticssetup} \oarg{module} \marg{options}
% \end{syntax}
% This command lets you specify options for several tables or graphs. The
% options are set locally to the current group. Options for tables are in the
% |table| \meta{module} and are the same as in the optional arguments of
% \cs{StatsTable}. Options for grapsh are in the |graph| \meta{module} and are
% the same as in the optional arguments of \cs{StatsGraph}. You can also use
% \cs{statisticssetup} without a \meta{module} and prefix all keys by the module
% name and a forward slash.
% % \end{function}
%
% \begin{demo}
% \statisticssetup{table/values=My values}
% \statisticssetup[table]{counts=FooBar}
% \StatsTable \facebook
% \end{demo}
%
% \subsection{Statistics tables}
%
% \subsubsection{\cs{StatsTable} invocation}
%
% To typeset a table full of statistics values, you use the command:
%
% \begin{function}{\StatsTable}
% \begin{syntax}
% \cs{StatsTable} \oarg{options_1} \marg{data source} \oarg{options_2}
% \end{syntax}
% \meta{options_1} and \meta{options_2} are both optional and taken into
% account. You will probably not use both at the same time even if
% \cs{StatsTable} will accept it (and apply \meta{options_2} after
% \meta{options_1}, potentially overriding some settings). The idea is to let
% you decide where you feel the options should be. I find more logical to
% specify options after a \cs{macro} data source, but before an inline
% \marg{data source}. Your mileage may vary.
% \end{function}
%
% If you do not use any option, you only get the line of values\footnote{The
% \cs{facebook} data source is defined on page \pageref{def:datasource}.}:
% \begin{demo}
% \StatsTable \facebook
% \end{demo}
%
% OK, this is ugly. Let us add some reasonable amount of space (a better choice
% would be to use the \pkg{cellprops} package to control the spacing and a lot
% more):
% \begin{demo}
% \setlength\extrarowheight{1.5pt}
% \StatsTable \facebook
% \end{demo}
% \setlength\extrarowheight{1.5pt}
%
% \subsubsection{Choosing and naming rows}
%
% Let's add some rows to the table:
%
% \begin{key}{values, counts, frequencies, icc, icf, dcc, dcf}
% \begin{syntax}
% values $[$ = \meta{row header text} $]$
% counts $[$ = \meta{row header text} $]$
% frequencies $[$ = \meta{row header text} $]$
% icc $[$ = \meta{row header text} $]$
% icf $[$ = \meta{row header text} $]$
% dcc $[$ = \meta{row header text} $]$
% dcf $[$ = \meta{row header text} $]$
% \end{syntax}
% These keys add the corresponding rows to the table. |icc| means increasing
% cumulative counts, |icf| is the same with frequencies, |dcc| is the row of
% decreasing cumulative counts and |dcf| for frequencies. If you omit
% \meta{row header text} the key only activates the corresponding row; if you
% additionally use a value then the first cell of the row will use that value as
% text.
%
% The initial header is |\valuename| for values, |\countname| for counts,
% |\freqname| for frequencies, |\iccname| for icc, |\icfname| for icf,
% |\dccname| for dcc and |\dcfname| for dcf.
% \end{key}
%
% \begin{demo}
% \StatsTable \facebook[
% values=Time in \si{h},
% counts, frequencies, icc, dcc, icf, dcf
% ]
% \end{demo}
%
% \begin{key}{novalues, nocounts, nofrequencies,
% noicc, nodcc, noicf, nodcf}
% \begin{syntax}
% novalues, nocounts, nofrequencies, noicc, nodcc, noicf, nodcf
% \end{syntax}
% If you want to \emph{disable} a row you can use the \texttt{no\meta{row}}~key.
% This is particularly useful for the |values| row, but you might need these
% keys to disable a row that you previously enabled with \cs{statisticssetup}.
%
% \begin{demo}
% \StatsTable \facebook [novalues, counts, icc]
% \end{demo}
% \end{key}
%
% \begin{key}{values/header, counts/header, frequencies/header,
% icc/header, icf/header, dcc/header, dcf/header}
% \begin{syntax}
% values/header = \meta{row header text}
% counts/header = \meta{row header text}
% frequencies/header = \meta{row header text}
% icc/header = \meta{row header text}
% icf/header = \meta{row header text}
% dcc/header = \meta{row header text}
% dcf/header = \meta{row header text}
% \end{syntax}
% These keys set the corresponding row header text, which will be used as the
% first cell of the row if the row is enabled. These keys does not enable their
% row by themselves, contrary to keys like |values| or |counts|.
%
% The initial header is |\valuename| for values, |\countname| for counts,
% |\freqname| for frequencies, |\iccname| for icc, |\icfname| for icf,
% |\dccname| for dcc and |\dcfname| for dcf.
% \end{key}
%
% \begin{demo}
% \statisticssetup{table/counts/header=People count}
% \StatsTable \facebook[counts, frequencies, icc]
% \end{demo}
%
% \subsubsection{Formatting cells}
%
% \begin{key}[label={table/values/format, table/counts/format,
% table/frequencies/format, table/icc/format, table/icf/format,
% table/dcc/format, table/dcf/format}]
% {values/format, counts/format, frequencies/format,
% icc/format, icf/format, dcc/format, dcf/format}
% \begin{syntax}
% values/format = \meta{formatting code}
% counts/format = \meta{formatting code}
% frequencies/format = \meta{formatting code}
% icc/format = \meta{formatting code}
% icf/format = \meta{formatting code}
% dcc/format = \meta{formatting code}
% dcf/format = \meta{formatting code}
% \end{syntax}
% Each key in this list takes a value which will be used for each cell in the
% corresponding row. In this value, every occurrence of |#1| will be replaced by
% the content of the cell, which can be further configured by the
% |allcounts/format| key (for the rows |counts|, |icc| and~|dcc|) or the
% |allfreqs/format| key (for the rows |frequencies|, |icf| and~|dcf|). The idea
% is that the latter keys are intended for number formatting (decimal count,
% decimal separator, etc.) while the \texttt{\meta{row}/format} keys are
% intended for font/color changes. In this key, \cs{currentcolumn} expands to
% the data column number, starting from~$1$, to enable different formatting
% depending on the column. These keys are all initially equal to |#1| which means
% they pass-through the content unmodified.
% \end{key}
%
% \begin{demo}
% \StatsTable \facebook[
% counts, icc,
% icc/format = \colorbox{blue!\currentcolumn 0!white}{#1}
% ]
% \end{demo}
%
% \begin{key}{allcounts/format}
% \begin{syntax}
% allcounts/format = \meta{formatting code}
% \end{syntax}
% This key take some formatting code, in which every occurrence of |#1| will be
% replaced by the integer count\footnotemark in each cell of every row
% containing counts. The initial value is |\num{#1}|, using the \pkg{siunitx}
% package.
%
% The result of this formatting code will then be passed to |counts/format|,
% |icc/format| or |dcc/format| depending on the row, for further parsing and
% formatting.
% \end{key}
% \footnotetext{As returned by \cs{fp_use:N} or \cs{fp_eval:n}.}
%
% \begin{demo}
% \StatsTable \facebook[
% counts, icc,
% icc/format = \colorbox{blue!\currentcolumn 0!white}{#1},
% allcounts/format = {\num[round-integer-to-decimal,
% round-mode=figures]{#1}}
% ]
% \end{demo}
%
% \begin{key}{allfreqs/format}
% \begin{syntax}
% allfreqs/format = \meta{formatting code}
% \end{syntax}
% This key take some formatting code, in which every occurrence of |#1| will be
% replaced by the current frequency\footnotemark in each cell of every row
% containing frequencies. The initial value is |\num{#1}|, using the
% \pkg{siunitx} package.
%
% The result of this formatting code will then be passed to |freqs/format|,
% |icf/format| or |dcf/format| depending on the row, for further parsing and
% formatting.
%
% The initial value is set by the |allfreqs/format/percent| key and typesets
% values in percentage (that is, multiplied by~$100$ with a trailing~$\%$).
% \end{key}
% \footnotetext{As returned by \cs{fp_use:N} or \cs{fp_eval:n}.}
%
% \begin{demo}
% \StatsTable \facebook[
% icc, frequencies, icf,
% allfreqs/format = {\num[round-mode=places,
% round-integer-to-decimal,
% round-precision=3]{#1}}
% ]
% \end{demo}
% Note that if you use |allfreqs/format| to round the frequencies to an
% acceptable precision, your frequencies might not add up to~$1$ anymore, and
% summing the frequencies up to some value might not give the same result as
% computing the cumulative frequency from the cumulative count. If you
% want to avoid that, consider using the |digits| key of the |table| module,
% which rounds the cumulative frequencies \emph{then} computes the individual
% frequencies as differences of consecutive cumulative ones. This essentially
% spreads the rounding errors so that they cancel each other, with a result not
% unlike that of the \textsc{Bresenham} algorithm.
%
% \begin{key}{allfreqs/format/percent}
% \begin{syntax}
% allfreqs/format/percent
% \end{syntax}
% This key sets up |allfreqs/format| to display the frequencies as percentages,
% that is, multiplied by~$100$ with a trailing~$\%$. This is the initial
% setting.
%
% \begin{texnote}
% This key is a shorthand for\\
% |allfreqs/format = \SI{\fp_eval:n{#1*100}}{\percent}|.
% \end{texnote}
% \end{key}
%
% \begin{demo}
% \StatsTable \facebook[ frequencies, icf, allfreqs/format/percent ]
% \end{demo}
%
% \begin{key}{allfreqs/format/real}
% \begin{syntax}
% allfreqs/format/real
% \end{syntax}
% This key sets up |allfreqs/format| to |\num{#1}| which displays the
% frequencies as straight real numbers.
% \end{key}
%
% \begin{demo}
% \StatsTable \facebook[ frequencies, icf, allfreqs/format/real ]
% \end{demo}
%
% \begin{key}{digits}
% \begin{syntax}
% digits = \meta{integer}
% \end{syntax}
% This key sets the number of digits after the decimal point to use for rounding
% cumulative frequencies. Point-wise frequencies are computed from these rounded
% cumulative frequencies to ensure consistency with the cumulative counts, and
% ensure the sum of frequencies equals~$1$. This essentially
% spreads the rounding errors so that they cancel each other, with a result not
% unlike that of the \textsc{Bresenham} algorithm.
%
% The rounding takes place before any formatting by |allfreqs/format| or
% individual \texttt{\meta{row}/format}. The initial value is~$3$ (which means
% one digit after the decimal separator in percentage).
% \end{key}
%
% \begin{demo}
% \StatsTable \facebook[ frequencies, icf, digits=2 ]
% \end{demo}
%
% \subsubsection{Hiding and showing column contents}
%
% In addition to \texttt{\meta{row}/format}, |allcounts/format| and
% |allfreqs/format| which can all use \cs{currentcolumn} to apply different
% formatting to different columns, you can also use the following keys:
%
% \begin{key}[label=table/showonly]{showonly, showonly/hidden, showonly/shown}
% \begin{syntax}
% showonly = \meta{integer and integer range list}
% showonly/hidden = \meta{formatting code}
% showonly/shown = \meta{formatting code}
% \end{syntax}
% The |showonly| key enables you to choose which columns you want \emph{shown}
% --- and thus which ones you want to have their contents hidden. It takes a
% comma-separated list of single numbers or \texttt{\meta{start}-\meta{end}}
% ranges of numbers. An empty value means \emph{show everything}, and this is
% the initial value. To hide all contents, you can set |showonly| to a
% non-existent column number like~$0$.
%
% Every column whose number is in the |showonly| list (of ranges) is deemed
% \emph{shown}, which means all cells will be ultimately wrapped in the
% |showonly/shown| formatting code, where as usual |#1|~is replaced by the
% contents. That key initially just passes through the contents as-is.
%
% Every column whose number is \emph{not} in the list is \emph{hidden},
% \emph{i.e.} its cell contents are wrapped in the |showonly/hidden| formatting
% code. This key is initially empty which means the contents are ignored and the
% cell stays empty --- which means its width will collapse and only the column
% separation will remain. You can decide to still typeset the contents in white,
% or even put them in a PDF~``OCG layer'' with the \pkg{ocgx2} package for
% instance.
% \end{key}
%
% \begin{demo}
% \StatsTable \facebook[ counts, frequencies, showonly={2,4-6} ]
% \StatsTable \facebook[ counts, frequencies, showonly={2,4-6},
% showonly/hidden = \color{white}#1 ]
% \end{demo}
%
% \subsubsection{Formatting the table}
%
% \begin{key}{maxcols}
% \begin{syntax}
% maxcols = \meta{comma-separated list of integers}
% \end{syntax}
% Setting this key to a positive integer~$n$ makes \cs{StatsTable} wrap after
% having added $n$~columns to the current table. The table is closed, and a new
% one is created with the row headers typeset anew. Setting this key to a
% negative number or zero disables wrapping. If you set the key to a list of
% integers, each one is used as the value for the corresponding subtable, with
% the last number staying in effect for all remaining subtables. The initial
% value is~$0$.
% \end{key}
%
% \begin{texnote}
% If there is a non-positive integer in the list, all subsequent integers are
% ignored since there will be no further wrapping thus no other subtable.
% \end{texnote}
%
% \begin{key}{tablesep}
% \begin{syntax}
% tablesep = \meta{\TeX\ content}
% \end{syntax}
% This key holds some \TeX\ content that will be inserted after each table when
% wrapping. It should probably contain something that creates a line return
% (either |\\| or |\par|), but can contain arbitrary code.
% The initial value is |\\|.
% \end{key}
%
% \begin{demo}
% \StatsTable \facebook[ counts, maxcols=4,
% tablesep=\par{\color{red}\hrule} ]
% \end{demo}
%
% \begin{key}{preline}
% \begin{syntax}
% preline = \meta{array content}
% \end{syntax}
% This key holds some \TeX\ content that will be inserted first in the
% \env{array} environment, before any row content. It should probably be some
% kind of \cs{noalign} material, like a \cs{hline} or similar constructs.
% The initial value is \cs{firsthline}, with a fallback to \cs{hline} if the
% former doesn't exist.
% \end{key}
%
% \begin{key}{postline}
% \begin{syntax}
% postline = \meta{array content}
% \end{syntax}
% This key holds some \TeX\ content that will be inserted last in the
% \env{array} environment, after any row content. It should probably be some
% kind of \cs{noalign} material, like a \cs{hline} or similar constructs.
% The initial value is \cs{lasthline}, with a fallback to \cs{hline} if the
% former doesn't exist.
% \end{key}
%
% \begin{key}{outline}
% \begin{syntax}
% outline = \meta{array content}
% \end{syntax}
% This key sets both |preline| and |postline| to the same value.
% \end{key}
%
% \begin{key}{newline}
% \begin{syntax}
% newline = \meta{array content}
% \end{syntax}
% This key holds some \TeX\ content that will be inserted at the end of each
% row, to separate it from the next. \emph{It should contain some kind of
% \cs{cr}}, probably in the form of |\\|, but can also contain \cs{hline}s after
% the |\\|. The initial value is |\\| which creates tables without lines
% separating rows (as \pkg{booktabs} would recommend).
% \end{key}
%
% \begin{demo}
% \setlength\extrarowheight{1ex}
% \StatsTable \facebook[ counts, preline=\hline\hline,
% postline=\hline\hline\hline,
% newline=\\[1ex]\hline ]
% \end{demo}
%
% \begin{key}{coltype}
% \begin{syntax}
% coltype = \meta{preamble elements}
% \end{syntax}
% This key sets the part of the array preamble that will be repeated for each
% content column in the table. It can contain any preamble content, like "|" for
% vertical lines, but should only countain a single column specifier.
% The initial value is "c".
% \end{key}
%
% \begin{key}{headcoltype}
% \begin{syntax}
% headcoltype = \meta{preamble elements}
% \end{syntax}
% This key sets the part of the array preamble that will be used for the first
% column in the table, which contains the headers. It can contain any preamble
% content, like "|" for vertical lines, but should only countain a single column
% specifier. The initial value is "l".
% \end{key}
%
% \begin{demo}
% \StatsTable \facebook[ counts, coltype=@{}c, headcoltype=r ]
% \end{demo}
%
% Note: these keys are here for convenience, but if you find yourself trying to
% do very clever things in them, you should consider using the \pkg{cellprops}
% package which is able to do much more complex border and background layouts
% with ease. In particular they probably shouldn't be used to workaround the
% very poor spacing of \env{array}: there are better solutions.
%
% Several classic uses of these keys can be replaced by the following key:
% \begin{key}{frame}
% \begin{syntax}
% frame = none $\vert$ clean $\vert$ full
% \end{syntax}
% The |frame| key selects a preset for |preline|, |postline|, |headcoltype| and
% |coltype|. The possible presets are:
% \begin{itemize}
% \item |none|: clears |preline| and |postline|, sets |headcoltype = l| and
% |coltype = c|. This removes all lines in the table and is useful if you
% use other means like \pkg{cellprops} to style the table.
% \item |clean|: sets |preline = \firsthline|, |postline = \lasthline|,
% |headcoltype = l| and |coltype = c|. This corresponds to the initial
% setting, and yields a layout similar to \pkg{booktabs} recommendations,
% especially if you set \cs{firsthline} and \cs{lasthline} to be a little
% thicker.
% \item |full|: sets |preline = \firsthline|, |postline = \lasthline|,
% "headcoltype = |l|" and "coltype = c|". This separates all cells
% with rules.
% \end{itemize}
% \end{key}
%
% \begin{demo}
% \statisticssetup{table/showonly/hidden=\color{white}#1}
% \StatsTable \facebook[ counts, frequencies, frame=none ]
% \StatsTable \facebook[ counts, frequencies, frame=full, showonly=2-4 ]
% \end{demo}
%
% \begin{key}{valign}
% \begin{syntax}
% valign = t $\vert$ c $\vert$ b
% \end{syntax}
% The value of this key is used for the optional argument of the \env{array}
% environment. This enables to align either the baseline of the first line, that
% of the last line, or the vertical center of the table with the surrounding
% baseline. The initial value is |t|.
% \end{key}
%
%
% \subsection{Statistics graphs}
%
% \subsubsection{\cs{StatsGraph} invocation}
%
% To typeset a graphic from the statistics values, you use the command:
% \begin{function}{\StatsGraph}
% \begin{syntax}
% \cs{StatsGraph} \oarg{options_1} \marg{data source} \oarg{options_2}
% \end{syntax}
% \meta{options_1} and \meta{options_2} are both optional and taken into
% account. You will probably not use both at the same time even if
% \cs{StatsGraph} will accept it (and apply \meta{options_2} after
% \meta{options_1}, potentially overriding some settings). The idea is to let
% you decide where you feel the options should be. I find more logical to
% specify options after a \cs{macro} data source, but before an inline
% \marg{data source}. Your mileage may vary.
% \end{function}
%
% \begin{demo}
% \StatsGraph \facebook
% \end{demo}
%
% \cs{StatsGraph} will draw a different kind of graph depending on the
% \meta{data source} itself, and the |cumulative| option key. A summary is
% shown in the table below:
% \begin{center}
% \setlength\extrarowheight{1ex}
% \begin{tabular}{ccc}
% \firsthline
% values are ranges & without |cumulative| & with |cumulative| \\[0.8ex]
% \hline
% no & bar diagram\footnotemark & \emph{not implemented yet} \\[1ex]
% yes & histogram &
% \parbox[c]{10em}{\centering cumulative distribution function} \\[2ex]
% \lasthline
% \end{tabular}
% \footnotetext{In this documentation this is called a \emph{comb graph}.}
% \end{center}
%
% \begin{demo}
% \def \combdata { 36=3, 37=8, 38=2, 39=6, 40=6, 41=3, 42=2, 45=2, 46=2 }
% \StatsGraph \combdata
% \end{demo}
% \def \combdata { 36=3, 37=8, 38=2, 39=6, 40=6, 41=3, 42=2, 45=2, 46=2 }
%
% \begin{demo}
% \StatsGraph \facebook [cumulative]
% \end{demo}
%
% \subsubsection{TikZ picture and datavisualization settings}
%
% \begin{key}{picture, picture/reset}
% \begin{syntax}
% picture = \meta{TikZ key options}
% picture/reset
% \end{syntax}
% The |picture| key \emph{appends} content to the optional argument of the
% \env{tikzpicture} environment. It can contain any list of TikZ keys. The
% |picture/reset| key clears all content accumulated by the |picture| key,
% including the initial value.
%
% The initial value is:\\
% |baseline = (current bounding box.center), label position = right|.
% \end{key}
%
% \begin{key}{axissystem, axissystem/reset}
% \begin{syntax}
% axissystem = \meta{TikZ cartesian axis system options}
% axissystem/reset
% \end{syntax}
% The |axissystem| key adds keys to the list of options passed to the
% |scientific axes| datavisualization key, The |axissystem/reset| key clears all
% content accumulated by the |axissystem| key, including the initial value,
% which is set by the initial value of the |width| key.
% \end{key}
%
% \begin{demo}
% \StatsGraph \combdata [axissystem={end labels, clean}]
% \end{demo}
%
% Two small helper keys are provided for a very common usage of |axissystem|:
%
% \begin{key}{width}
% \begin{syntax}
% width = \meta{\TeX\ dimension expression}
% \end{syntax}
% This key sets the width of the graphic to the given \meta{\TeX\ dimension
% expression}, labels and padding excluded. The expression is evaluated at graph
% creation time. The initial value is |0.75\columnwidth|.
% \begin{texnote}
% This key is a shortcut for |axissystem = { width = |\meta{dimension}| }|
% \end{texnote}
% \end{key}
%
% \begin{key}{height}
% \begin{syntax}
% height = \meta{\TeX\ dimension expression}
% \end{syntax}
% This key sets the width of the graphic to the given \meta{\TeX\ dimension
% expression}, labels and padding excluded. The expression is evaluated at graph
% creation time. Initially this is \emph{unset}, which means the default of
% the cartesian axis system will be used, that is the choosen width divided by
% the golden ratio $\varphi = \frac{1+\sqrt{5}}{2}$.
% \begin{texnote}
% This key is a shortcut for |axissystem = { height = |\meta{dimension}| }|
% \end{texnote}
% \end{key}
%
% To have more precise control over the scale of the graph, you can use the
% individual axis options provided by \pkg{\ExplFileName} to set an explicit
% scaling with TikZ DataVisualization keys like |unit length|. See the PGF/TikZ
% manual for more information.
%
% \begin{demo}
% \statisticssetup[graph]{ width = 0.25\columnwidth, height=4cm }
% \centering
% \StatsGraph \facebook
% \StatsGraph \facebook [cumulative]
% \StatsGraph \combdata
% \end{demo}
%
% \begin{key}{tikzinfo', tikzinfo'/reset}
% \begin{syntax}
% tikzinfo' = \meta{TikZ picture code}
% tikzinfo'/reset
% \end{syntax}
% This key \emph{appends} content to be added in the |info'| section of the
% |\datavisualization| command. It can contain any TikZ code, and can use the
% |visualization cs| coordinate system. The result of this TikZ code is drawn
% \emph{before} the data itself and will end up behind unless you play with TikZ
% layers. Some information might be unavailable or wrong since the data has not
% been drawn yet.
%
% The |tikzinfo'/reset| key clears all content accumulated by the |tikzinfo'|
% key. The initial value is empty.
% \end{key}
%
% \begin{key}{tikzinfo, tikzinfo/reset}
% \begin{syntax}
% tikzinfo = \meta{TikZ picture code}
% tikzinfo/reset
% \end{syntax}
% This key \emph{appends} content to be added in the |info| section of the
% |\datavisualization| command. It can contain any TikZ code, and can use the
% |visualization cs| coordinate system. The result of this TikZ code is drawn
% \emph{after} the data itself and will end up in front of it unless you play
% with TikZ layers.
%
% The |tikzinfo/reset| key clears all content accumulated by the |tikzinfo|
% key. The initial value is empty.
% \end{key}
%
% \begin{demo}
% \StatsGraph \facebook [
% cumulative,
% tikzinfo = {
% \path (data bounding box.south west) coordinate (O);
% \path (visualization cs:x=8, y=50) coordinate (A);
% \draw[red] (O |- A) -- (A) -- (A |- O);
% }
% ]
% \end{demo}
%
% \subsubsection{Styling the graph}
%
% \begin{key}{style, style/reset,
% comb/style, comb/style/reset,
% histogram/style, histogram/style/reset,
% cumulative/style, cumulative/style/reset,}
% \begin{syntax}
% style = \meta{TikZ path options}
% \meta{graph type}/style = \meta{TikZ path options}
% style/reset, \meta{graph type}/style/reset
% \end{syntax}
% The \texttt{\meta{graph type}/style} keys append options to the TikZ path
% created by the datavisualization when the corresponding graph type is used.
% You can clear these options with \texttt{\meta{graph type}/style/reset}.
% If you omit the graph type, this sets the label for all graph types
% simultaneously.
%
% The initial values are:
% \begin{verbatim}
% comb/style = ultra-thick,
% cumulative/style = %empty
% histogram/style = {
% every~path/.prefix~style=fill,
% semithick, black, fill=black, fill~opacity=0.1
% },
% \end{verbatim}
% \end{key}
%
% \begin{demo}
% \statisticssetup[graph]{width=0.45\linewidth,
% style=blue, cumulative/style=densely dashed }
% \StatsGraph \facebook [ cumulative ]
% \hfill \StatsGraph \facebook[style={
% fill opacity=0, pattern=north west lines,
% }]
% \end{demo}
%
% \subsubsection{Selecting which parts of the graph are shown}
%
% By default, the complete graph is shown; you can ask \cs{StatsGraph} to only
% show the parts corresponding to some of the input data:
%
% \begin{key}[label=graph/showonly]{showonly}
% \begin{syntax}
% showonly = \meta{integer and integer range list}
% \end{syntax}
% The |showonly| key enables you to set which parts of the graph you want
% \emph{shown}. It takes a comma-separated list of single numbers or
% \texttt{\meta{start}-\meta{end}} ranges of numbers. An empty value means
% \emph{show everything}, and this is the initial value. To hide all contents,
% you can set |showonly| to a non-existent part number like~$-1$.
% \end{key}
%
% \medskip
% For comb graphs, the $n$-th part is the vertical bar corresponding to the
% $n$-th value in the data source. For histograms, this is the rectangle
% corresponding to the $n$-th range.
%
% For cumulative distribution functions of data sources with ranges, this is the
% direct image of the $n$-th range by the function. The horizontal segment
% between $-\infty$ and the lower bound of the first range is assigned
% number~$0$, and the part right of the last range is selected by number~$N+1$
% where $N$~is the total number of ranges.
%
% Currently, the drawing of hidden parts is inhibited altogether, but in the
% future it is planned to have them drawn with another visualizer and a separate
% style.
%
% \begin{demo}
% \statisticssetup{ graph/width=0.45\columnwidth }
% \StatsGraph \facebook [ showonly={2,4-6} ]
% \StatsGraph \facebook [ cumulative, showonly={1,3-5,7} ]
% \end{demo}
%
% \subsubsection{Unit selection and vertical axis settings}
%
% \begin{key}[label={graph/counts, graph/frequencies}]{counts, frequencies}
% \begin{syntax}
% counts $[$ = \meta{label} $]$
% frequencies $[$ = \meta{label} $]$
% \end{syntax}
% These keys select the corresponding unit to use for the vertical axis of comb
% graphs and cumulative distribution graphs, and for the area display of
% histograms. Additionnally, if a \meta{label} is provided, it is passed to the
% |counts/label| or the |frequencies/label| key.
%
% The initially selected unit is |counts|.
% \end{key}
%
% \begin{key}{comb/counts, comb/frequencies,
% histogram/counts, histogram/frequencies,
% cumulative/counts, cumulative/frequencies}
% \begin{syntax}
% \meta{graph type}/counts $[$ = \meta{label} $]$
% \meta{graph type}/frequencies $[$ = \meta{label} $]$
% \end{syntax}
% These keys select the unit to use for specific types of graphs separately.
% They can be used in the inline options of \cs{StatsGraph} too, but they
% probably only make sense in \cs{statisticssetup} to define different defaults
% for different graph types.
% \begin{texnote}
% The |counts| key is actually a meta-key for\\
% |comb/counts, histogram/counts, cumulative/counts|, which applies the same
% value (or no value at all) to all three type-specific keys. The |frequencies|
% key is similar.
% \end{texnote}
% \end{key}
%
% \begin{demo}
% \statisticssetup[graph]{
% width=0.4\columnwidth,
% frequencies=Hello world, comb/counts=Students
% }
% \StatsGraph \facebook \hfill \StatsGraph \combdata \\
% \StatsGraph \facebook [cumulative] \hfill \StatsGraph \facebook[counts]
% \end{demo}
%
% Note that setting a label for the vertical axis of histogram does not make
% much sense, even if your decision will be respected.
%
% \begin{key}{counts/label, frequencies/label,
% comb/counts/label, comb/frequencies/label,
% histogram/counts/label, histogram/frequencies/label,
% cumulative/counts/label, cumulative/frequencies/label}
% \begin{syntax}
% \meta{unit}/label = \meta{label}
% \meta{graph type}/\meta{unit}/label = \meta{label}
% \end{syntax}
% These keys set the label to use for the $y$~axis of the graph when the
% corresponding unit is selected, \emph{without} selecting it at that point.
% This is useful to provide your own defaults through \cs{statisticssetup}.
%
% The keys |counts/label| and |frequencies/label| set the label for all three
% graph types, while the others are here to set individual defaults.
% \end{key}
%
% Initial values are as follows:
% \begin{itemize}
% \item |comb/counts/label = \countname|
% \item |comb/frequencies/label = \freqname|
% \item |cumulative/counts/label = \ccountname|
% \item |cumulative/frequencies/label = \cfreqname|
% \item |histogram/counts/label| and |histogram/frequencies/label| are unset
% \end{itemize}
%
% \begin{texnote}
% The \texttt{\meta{type}/\meta{unit}/label} key is a shorthand for
% \texttt{\meta{type}/\meta{unit}/axis} | = { label = |\meta{label}| }|, which
% means that using \texttt{\meta{type}/\meta{unit}/axis/reset} will also remove
% any defined label.
% \end{texnote}
% \begin{texnote}
% As before, \texttt{\meta{unit}/label = \meta{label}} is equivalent to\par
% \begingroup\obeylines\ttfamily
% comb/\meta{unit}/label = \meta{label},
% histogram/\meta{unit}/label = \meta{label},
% cumulative/\meta{unit}/label = \meta{label}
% \endgroup
% \end{texnote}
%
% \begin{key}{y/label, comb/y/label, histogram/y/label, cumulative/y/label}
% \begin{syntax}
% y/label = \meta{label}
% \meta{graph type}/y/label = \meta{label}
% \end{syntax}
% These keys set the label to use for the $y$~axis of the graph for both units
% at the same time. |y/label| sets the label for all graph types and all units
% simultaneously, while \texttt{\meta{graph type}/y/label} can be used for
% individual graph types.
% \end{key}
%
% This can be useful to set the label in inline options without having to
% explicitely type the graph type or the selected unit:
%
% \begin{demo}
% \statisticssetup[graph]{
% width=0.38\columnwidth,
% comb/frequencies, cumulative/counts,
% }
% \StatsGraph \combdata [ y/label=Students ]
% \StatsGraph \facebook [ cumulative, y/label=Respondents ]
% \end{demo}
%
% \begin{key}{counts/axis, frequencies/axis,
% comb/counts/axis, comb/frequencies/axis,
% histogram/counts/axis, histogram/frequencies/axis,
% cumulative/counts/axis, cumulative/frequencies/axis,
% counts/axis/reset, frequencies/axis/reset,
% comb/.../axis/reset,
% histogram/.../axis/reset,
% cumulative/.../axis/reset}
% \begin{syntax}
% \meta{unit}/axis = \meta{TikZ datavisualization axis options}
% \meta{unit}/axis/reset
% \meta{graph type}/\meta{unit}/axis =\
%\meta{TikZ datavisualization axis options}
% \meta{graph type}/\meta{unit}/axis/reset
% \end{syntax}
% The \texttt{\meta{unit}/axis} keys append options to the TikZ $y$~axis when
% the corresponding unit is selected. You can clear these options with
% \texttt{\meta{unit}/axis/reset}. The \texttt{\meta{graph
% type}/\meta{unit}/axis} and \texttt{\meta{graph type}/\meta{unit}/axis/reset}
% keys do the same, but only for a specific graph type.
%
% Initial values are as follows:
% \begin{itemize}
% \item |comb/counts/axis| and |cumulative/counts/axis| are equal to\\
% |ticks and grid={many, int about strategy, integer minor steps*},|\\
% |label=|\meta{initial value of the label key}
% \item |cumulative/counts/axis| and |cumulative/frequencies/axis| are
% equal to\\
% |ticks and grid=many, label=|\meta{initial value of the label key}
% \item |histogram/counts/axis| and |histogram/frequencies/axis| are equal to\\
% |ticks=none, grid=|\meta{code to auto-compute the step} (see the
% |histogram/autostep| key below).
% \end{itemize}
% \end{key}
%
% \begin{key}{y/axis, y/axis/reset,
% comb/axis, comb/axis/reset,
% histogram/axis, histogram/axis/reset,
% cumulative/axis, cumulative/axis/reset}
% \begin{syntax}
% y/axis = \meta{TikZ datavisualization axis options}
% y/axis/reset
% \meta{graph type}/y/axis = \meta{TikZ datavisualization axis options}
% \meta{graph type}/y/axis/reset
% \end{syntax}
% The \texttt{y/axis} keys append options to the TikZ $y$~axis for all possible
% units and all graph types at the same time. The \texttt{y/axis/reset} key
% clears these options for all units and all types simultaneously.
%
% The \texttt{\meta{graph type}/y/axis} and \texttt{\meta{graph
% type}/y/axis/reset} keys do the same, but only for a specific graph type.
% \end{key}
%
% \begin{demo}
% \statisticssetup[graph]{
% width=0.4\columnwidth,
% comb/frequencies/axis = { ticks={step=0.08} },
% histogram/y/axis = { grid = none },
% }
% \StatsGraph \combdata [ frequencies, y/axis = {
% ticks={style=blue}, unit length=4cm per 0.25 units,
% } ]
% \hfill \StatsGraph \facebook
% \end{demo}
%
% \begin{key}{/tikz/datavisualization/integer minor steps,
% /tikz/datavisualization/integer minor steps*}
% \begin{syntax}
% integer minor steps $[$ = \meta{integer expression} $]$
% integer minor steps* $[$ = \meta{integer expression} $]$
% \end{syntax}
% These are not keys in the |graph| module, but TikZ keys. They add code to
% automatically compute |minor steps between steps| after the axis step has been
% computed with the choosen strategy, so that the following constraints are
% respected:
% \begin{itemize}
% \item a minor step corresponds to an integer number;
% \item at most \meta{integer expression} ticks are present on the axis (minor
% and major included, subminor not counted).
% \end{itemize}
% In addition, the starred version ensures that the major step is never below
% one, which makes sense for counts where sub-unit graduations are confusing at
% best.
% \end{key}
%
% If ommited, the \meta{integer expression} defaults to~$50$.
%
% These TikZ keys should not explode if the computed step is not an integer, but
% will probably not give a useful result, and in particular whether the minor
% step will be integer is not defined in that case.
%
% \begin{texnote}
% The keys are independent of \pkg{statistics} and could be reused elsewhere.
% \end{texnote}
%
% \begin{key}{counts/format, frequencies/format, y/format,
% comb/counts/format, comb/frequencies/format, comb/y/format,
% histogram/counts/format, histogram/frequencies/format,
% histogram/y/format,
% cumulative/counts/format, cumulative/frequencies/format,
% cumulative/y/format}
% \begin{syntax}
% \meta{unit}/format = \meta{formatting code}
% \meta{graph type}/\meta{unit}/format = \meta{formatting code}
% \end{syntax}
% These keys set the format to use for all counts or frequenties that are
% typeset on the graphs. This includes the ticks on axes, and areas above
% histogram rectangles. The value should be \TeX\ code to render the actual
% number, in which all occurrences of |#1| are replaced by the number to
% typeset.
%
% Keys of the form |\meta{graph type}/\meta{unit}/format| are used to set the
% formatter of numbers in a specific unit when used in a specific graph. Keys of
% the form |\meta{unit}/format| set the formatter for all graph types at the
% same time, which is often desirable since it is rare that a frequency needs to
% be typeset differently in \emph{e.g.} comb graphs and histograms.
%
% You can use |\meta{graph type}/y/format| or |y/format| to set the formatter
% for both units at the same time, which is mainly useful for inline options to
% avoid repeating the selected unit for each key.
%
% Initial settings are: |counts/format = \num{#1}| and
% |frequencies/format/percent| (see below for an exlpanation of that key).
% \end{key}
%
% \begin{demo}
% \StatsGraph \combdata [
% y/label=, width=0.4\columnwidth,
% y/format=#1\text{ student\ifnum#1=1\else s\fi}
% ]
% \end{demo}
%
% \begin{key}{frequencies/format/real,
% comb/frequencies/format/real,
% histogram/frequencies/format/real,
% cumulative/frequencies/format/real}
% \begin{syntax}
% frequencies/format/real = \meta{number of decimals}
% \meta{graph type}/frequencies/format/real = \meta{number of decimals}
% \end{syntax}
% These keys make the corresponding format typeset its argument as a real
% number, using the \cs{num} command of the \pkg{siunitx} package.
% \begin{texnote}
% This is equivalent to:\\
% |frequencies/format = \num[round-mode=places,round-precision=##1]{####1}|
% \end{texnote}
% \end{key}
%
% \begin{key}{frequencies/format/percent,
% comb/frequencies/format/percent,
% histogram/frequencies/format/percent,
% cumulative/frequencies/format/percent}
% \begin{syntax}
% frequencies/format/percent = \meta{number of decimals}
% \meta{graph type}/frequencies/format/percent = \meta{number of decimals}
% \end{syntax}
% These keys make the corresponding format typeset its argument as a percentage,
% using the \cs{num} command of the \pkg{siunitx} package. This is the initial
% setting.
% \begin{texnote}
% This is equivalent to:\\
% |frequencies/format = { \SI[round-mode=places,round-precision=##1]{| \\
% | \fp_eval:n{####1*100}| \\
% |}{\percent}|
% \end{texnote}
% \end{key}
%
% \begin{key}{counts/margin, frequencies/margin, y/margin,
% comb/counts/margin, comb/frequencies/margin, comb/y/margin,
% histogram/counts/margin, histogram/frequencies/margin,
% histogram/y/margin,
% cumulative/counts/margin, cumulative/frequencies/margin,
% cumulative/y/margin}
% \begin{syntax}
% \meta{unit}/margin = \meta{numeric expression}
% \meta{graph type}/\meta{unit}/margin = \meta{numeric expression}
% \end{syntax}
% These keys set the margin that will be used for the relevant axis in the
% corresponding graph type, that is the amount of space above the data that
% will be reserved by \cs{StatsGraph}. The \meta{numeric expression} should
% compute a count or a frequency depending on the selected unit, and will
% correspond to the empty space reserved above the graph \emph{in this very
% unit}.
%
% In this expression, the following constants will be available: \cs{min} which
% is the minimum count or frequency where something is drawn in the graph
% (currently this is always zero); \cs{max} which is the maximum count or
% frequency in the graph; and \cs{range} which is |\max - \min|.
%
% As usual, keys of the form |\meta{graph type}/\meta{unit}/margin| are used to
% define the margin in a specific unit when used in a specific graph, whereas
% keys of the form |\meta{unit}/margin| set the margin for all graph types at
% the same time.
%
% You can use |\meta{graph type}/y/margin| or |y/margin| to set the margin
% for both units at the same time, which is mainly useful for inline options to
% avoid repeating the selected unit for each key.
%
% The inital value is |y/margin = \range / 10|.
% \end{key}
%
% \begin{texnote}
% This expression will be evaluated with the rules of |\fp_eval:n|
% (with |\fp_gset:Nn| to be exact).
% \end{texnote}
%
% \begin{demo}
% \StatsGraph \combdata [ width=0.4\columnwidth, y/margin=2 ]
% \end{demo}
%
% \subsubsection{Horizontal axis settings}
%
% \begin{key}{values/label, x/label,
% comb/values/label, comb/x/label,
% histogram/values/label, histogram/x/label,
% cumulative/values/label, cumulative/x/label}
% \begin{syntax}
% values/label = \meta{label}, x/label = \meta{label}
% \meta{graph type}/values/label = \meta{label}
% \meta{graph type}/x/label = \meta{label}
% \end{syntax}
% These keys set the label to use for the $x$~axis of the graph when the
% corresponding graph type is used. The keys with |x| are aliases for the
% similar keys with |values|. If you omit the graph type, this sets the label
% for all graph types simultaneously.
%
% The initial value is |values/label = \valuename|.
% \end{key}
%
% \begin{texnote}
% The \texttt{\meta{type}/values/label} key is a shorthand for
% \texttt{\meta{type}/values/axis} | = { label = |\meta{label}| }|, which
% means that using \texttt{\meta{type}/values/axis/reset} will also remove
% any defined label.
% \end{texnote}
%
% \begin{demo}
% \statisticssetup[graph]{
% width=0.38\columnwidth,
% comb/frequencies, cumulative/counts,
% }
% \StatsGraph \combdata [ values/label=Shoe size ]
% \StatsGraph \facebook [ cumulative, x/label=Time spent on Facebook ]
% \end{demo}
%
% \begin{key}{values/axis, x/axis,
% comb/values/axis, comb/x/axis,
% histogram/values/axis, histogram/x/axis,
% cumulative/values/axis, cumulative/x/axis,
% values/axis/reset, x/axis/reset,
% comb/values/axis/reset, comb/x/axis/reset,
% histogram/values/axis/reset, histogram/x/axis/reset,
% cumulative/values/axis/reset, cumulative/x/axis/reset}
% \begin{syntax}
% \meta{graph type}/values/axis = \meta{TikZ datavisualization axis options}
% \meta{graph type}/x/axis = \meta{TikZ datavisualization axis options}
% \meta{graph type}/values/axis/reset, \meta{graph type}/x/axis/reset
% \end{syntax}
% The \texttt{\meta{graph type}/values/axis} keys append options to the TikZ
% $x$~axis when the corresponding graph type is used. You can clear these
% options with \texttt{\meta{graph type}/values/axis/reset}. The keys with |x|
% are aliases for the similar keys with |values|. If you omit the graph type,
% this sets the label for all graph types simultaneously.
%
% The initial value is:
% \begin{verbatim}
% values/axis = {
% label = \valuename,
% ticks and grid={many, integer minor steps}
% }
% \end{verbatim}
% \end{key}
%
% \begin{demo}
% \statisticssetup[graph]{
% width=0.4\columnwidth,
% comb/frequencies/axis = { ticks={step=0.08} },
% histogram/y/axis = { grid = none },
% }
% \StatsGraph \combdata [ frequencies, y/axis = {
% ticks={style=blue}, unit length=4cm per 0.25 units,
% } ]
% \hfill \StatsGraph \facebook
% \end{demo}
%
% \begin{key}{values/format, x/format,
% comb/values/format, comb/x/format,
% histogram/values/format, histogram/x/format,
% cumulative/values/format, cumulative/x/format}
% \begin{syntax}
% values/format = \meta{formatting code}, x/format = \meta{formatting code}
% \meta{graph type}/values/format = \meta{formatting code}
% \meta{graph type}/x/format = \meta{formatting code}
% \end{syntax}
% These keys set the format to use for all values that are typeset on the
% graphs, which currently means the values typeset alongside ticks on the
% x~axis. The \meta{formatting code} should be \TeX\ code to render the actual
% number, in which all occurrences of |#1| are replaced by the value to
% typeset. The formatting code is typeset in math mode.
%
% Keys of the form |\meta{graph type}/value/format| are used to set the
% formatter of values when used in a specific graph. The keys with |x| are
% aliases for the similar keys with |values|. If you omit the graph type, this
% sets the label for all graph types simultaneously.
%
% The initial value is |values/format = \num{#1}|.
% \end{key}
%
% \begin{demo}
% \StatsGraph \combdata [
% width=0.5\columnwidth,
% x/format=\fbox{$#1$}
% ]
% \end{demo}
%
% \begin{key}{values/margin, x/margin,
% comb/values/margin, comb/x/margin,
% histogram/values/margin, histogram/x/margin,
% cumulative/values/margin, cumulative/x/margin}
% \begin{syntax}
% values/margin = \meta{numeric expression},\
%x/margin = \meta{numeric expression}
% \meta{graph type}/values/margin = \meta{numeric expression}
% \meta{graph type}/x/margin = \meta{numeric expression}
% \end{syntax}
% These keys set the margin that will be used for the x~axis in the
% corresponding graph type, that is the amount of space left and right of the
% data that will be reserved by \cs{StatsGraph}. The \meta{numeric expression},
% when evaluated, will correspond to the empty space reserved left of the
% smallest value and right of the biggest one, with the same scale as the values
% themselves.
%
% In this expression, the following constants will be available: \cs{min} which
% is the minimum value in the graph; \cs{max} which is the maximum value;
% \cs{range} which is |\max - \min|; and \cs{xstep} which is the distance
% between two minor ticks in the graph (this is the axis step if
% |minor steps between steps| is empty).
%
% The inital value is |x/margin = \xstep / 2|.
% \end{key}
%
% \begin{texnote}
% This expression will be evaluated with the rules of |\fp_eval:n|
% (with |\fp_gset:Nn| to be exact).
% \end{texnote}
%
% \begin{demo}
% \StatsGraph \combdata [ width=0.5\columnwidth, x/margin=2 ]
% \end{demo}
%
% \subsubsection{Settings specific to cumulative graphs}
%
% \begin{key}{cumulative}
% \begin{syntax}
% cumulative $[$ = \meta{truth value} $]$
% \end{syntax}
% This key activates or deactivates the cumulative mode of \cs{StatsGraph}. The
% \meta{truth value} must be either |true| or |false| or be ommited, in which
% case it defaults to |true|.
%
% This mode is currently ignored if the counts are given for pointwise values,
% as opposed to value ranges. Support is planned but a suitable interface still
% needs to be devised for settings corresponding to the discontinuities.
%
% The initial value is |cumulative = false|.
% \end{key}
%
% \begin{key}{decreasing}
% \begin{syntax}
% decreasing $[$ = \meta{truth value} $]$
% \end{syntax}
% This key selects whether the cumulative mode of \cs{StatsGraph} plots the
% decreasing cumulative distribution function (that maps $x$ to the frequency of
% $\left[x;+\infty\right[$) instead of the classical increasing one (mapping $x$
% to the frequency of $\left]-\infty;x\right]$). The \meta{truth value} must be
% either |true| or |false| or be ommited, in which case it defaults to |true|.
%
% The initial value is |decreasing = false|.
% \end{key}
%
% \begin{demo}
% \statisticssetup[graph]{ width = 0.25\columnwidth, height=4cm }
% \centering
% \StatsGraph \facebook
% \StatsGraph \facebook [cumulative]
% \StatsGraph \facebook [cumulative, decreasing]
% \end{demo}
%
% \subsubsection{Settings specific to histograms}
%
% \begin{key}{histogram/areas}
% \begin{syntax}
% histogram/areas $[$ = \meta{truth value} $]$
% \end{syntax}
% This key activates or deactivates the typesetting of counts or frequencies
% above the rectangles in the histogram. They correspond to the area of the
% rectangle according to histogram rules, which explains the name of the key.
%
% If ommited the \meta{truth value} defaults to |true|, which is also the
% initial value.
% \end{key}
%
% \begin{demo}
% \StatsGraph \facebook [width=0.5\columnwidth, histogram/areas = false]
% \end{demo}
%
% \begin{key}{histogram/areas/style, histogram/areas/style/reset}
% \begin{syntax}
% histogram/areas/style = \meta{TikZ node options}
% histogram/areas/style/reset
% \end{syntax}
% This key appends options to the TikZ nodes containing the areas (counts or
% frequencies). Note that the typesetting of the areas will be controlled by
% the \texttt{histogram/\meta{unit}/format} keys, which means that the
% |histogram/areas/style| is intended for common styling.
%
% The initial value is |histogram/areas/style = { auto, font=\small }|.
%
% \begin{texnote}
% The node is positionned in the middle of the top edge of the rectangle so if
% you do not want it there some style option like |auto| or |above| should be
% used.
% \end{texnote}
% \end{key}
%
% \begin{demo}
% \StatsGraph \facebook [ histogram/areas/style/reset,
% histogram/areas/style = { fill=white } ]
% \end{demo}
%
% \begin{key}{histogram/counts/autostep, histogram/frequencies/autostep,
% histogram/y/autostep}
% \begin{syntax}
% histogram/\meta{unit}/autostep $[$ = \meta{floating point expression} $]$
% histogram/y/autostep $[$ = \meta{floating point expression} $]$
% \end{syntax}
% This key setups the y~axis grid so that a grid tile corresponds to
% \meta{floating point expression} items. This expression is interpreted as a
% count, but you can use the \cs{total} constant which is the total count.
% In particular, |\total/100| represents exactly \SI{1}{\percent}.
%
% This key essentially divides the \meta{floating point expression} by the
% horizontal distance between minor steps of the values axis, then uses the
% result as the vertical step. As a convenience, |histogram/y/autostep| forwards
% its value to |histogram/legend/area| in addition to the
% \texttt{histogram/\meta{unit}/autostep} keys.
%
% If ommited the \meta{floating point expression} defaults to $1$.
% The initial value is |histogram/y/autostep = 1|.
%
% \begin{texnote}
% \texttt{histogram/\meta{unit}/autostep} uses
% \texttt{histogram/\meta{unit}/axis} internally, so
% \texttt{histogram/\meta{unit}/axis/reset} will neuter its effect.
% \end{texnote}
% \end{key}
%
% \begin{demo}
% \StatsGraph \facebook [frequencies, histogram/y/autostep=2*\total/100]
% \end{demo}
%
% \begin{key}{histogram/legend, histogram/legend/x, histogram/legend/w}
% \begin{syntax}
% histogram/legend = "{" \meta{legend keys} "}"
% histogram/legend/x = $[$ \meta{floating point expression} $]$
% histogram/legend/w = \meta{floating point expression}
% \end{syntax}
% If |histogram/legend/x| is set to an empty value, no legend will be typeset.
% Else, it should be a \meta{floating point expression} which corresponds to the
% \emph{value} at which the left side of the legend rectangle will lie. In that
% case |histogram/legend/w| should be a \meta{floating point expression}
% representing the width (in value units) of the legend rectangle.
%
% In both of these expressions, the following constants are available:
% \end{key}
% \begin{itemize}
% \item \cs{min} which is the minimum value where data is present;
% \item \cs{max} which is the maximum value where data is present;
% \item \cs{range} which is |\max - \min|;
% \item \cs{xstep} which is the distance between two minor steps of the x axis.
% \end{itemize}
%
% In fact, you probably will not set these keys directly, but will use the
% |histogram/legend| key, which requires as value a comma-separated list of
% sub-keys that will be used under the |histogram/legend/| path. In particular,
% |histogram/legend = { x=2, y=3 }| is equivalent to
% |histogram/legend/x=2, histogram/legend/y=3|.
%
% \begin{key}{histogram/legend/y, histogram/legend/h, histogram/legend/area}
% \begin{syntax}
% histogram/legend/y = \meta{floating point expression}
% histogram/legend/h = \meta{floating point expression}
% histogram/legend/area = \meta{floating point expression}
% \end{syntax}
% If |histogram/legend/x| is not empty, |histogram/legend/y| and
% |histogram/legend/h| should be \meta{floating point expression}s which
% correspond to the y~coordinate of the bottom side and the vertical dimension
% respectively of the legend rectangle, in count per value units.
%
% In both of these expressions, the following constants are available:
% \end{key}
% \begin{itemize}
% \item \cs{min} which is the $y$~coordinate of the bottom of all histogram
% rectangles (this is always~$0$);
% \item \cs{max} which is the $y$~coordinate of the tallest histogram rectangle;
% \item \cs{range} which is |\max - \min|;
% \item \cs{xstep} which is the distance between two minor steps of the x axis.
% \item \cs{width} which is the width of the legend rectangle as computed by
% evaluating |histogram/legend/w|;
% \item \cs{total} which is the total number of elements, useful when you want
% to size the legend using frequencies (the dimensions here always use counts).
% \end{itemize}
% Additionnally, when evaluating |histogram/legend/y| the |\height|~constant
% will be available and equal to the just computed value of
% |histogram/legend/h|.
%
% The key |histogram/legend/area = |\meta{fp expression} is a shorthand for:\\
% |histogram/legend/h = (|\meta{fp expression}|) / \width|.
%
% Again, you probably will not set these keys directly but using the
% |histogram/legend| key.
%
% \begin{key}{histogram/legend/options, histogram/legend/options/reset,
% histogram/legend/label}
% \begin{syntax}
% histogram/legend/options = \meta{TikZ node options}
% histogram/legend/options/reset
% histogram/legend/label = \meta{TikZ label value}
% \end{syntax}
% The key |histogram/legend/options| appends the \meta{TikZ node options} to the
% list of options that will be passed to the TikZ node responsible for the
% legend rectangle, \emph{after} the options in |histogram/style|. You can use
% it to tweak the apparance of the legend.
%
% The key |histogram/legend/label = |\meta{label} is a shorthand for:\\
% |histogram/legend/options = { label = {|\meta{fp expression}|} }|, and thus
% uses the TikZ label syntax.
%
% Again, you probably will not set these keys directly but using the
% |histogram/legend| key.
% \end{key}
%
% The initial value is |histogram/legend = { x=, y=0, w=\xstep, area=1 }| which
% means that no legend is typeset, and the legend options are empty.
%
% \begin{texnote}
% |area=1| is actually set by the initial value of |histogram/y/autostep|.
% \end{texnote}
%
% \begin{demo}
% \statisticssetup[graph]{ width = 0.48\columnwidth }
% \StatsGraph \facebook [
% histogram/legend = { x=9, y=8, label=1 student }
% ]
% \StatsGraph \facebook [
% frequencies, histogram/y/autostep=0.02*\total,
% histogram/legend = { x=12, y=2*\height, w=2, area=0.08*\total,
% label=above:\SI{8}{\percent} }
% ]
% \end{demo}
%
% \end{documentation}
%
% \cleardoublepage
% \begin{implementation}
%
% \section{\pkg{\ExplFileName} implementation}
%
% \begin{macrocode}
%<*package>
%<@@=statistics>
% \end{macrocode}
%
% \begin{macrocode}
\ProvidesExplPackage
{\ExplFileName}{\ExplFileDate}{\ExplFileVersion}{\ExplFileDescription}
% \end{macrocode}
%
% \begin{macrocode}
\RequirePackage{xparse}
\RequirePackage{siunitx}
\RequirePackage{tikz}
\RequirePackage{etoolbox}
\ExplSyntaxOff
\usetikzlibrary{datavisualization, fit}
\ExplSyntaxOn
% \end{macrocode}
%
% Translations
%
% \begin{macrocode}
\tl_new:N \valuename
\tl_new:N \countname
\tl_new:N \freqname
\tl_new:N \ccountname
\tl_new:N \cfreqname
\tl_new:N \iccname
\tl_new:N \icfname
\tl_new:N \dccname
\tl_new:N \dcfname
\tl_set:Nn \valuename { Values }
\tl_set:Nn \countname { Count }
\tl_set:Nn \ccountname { Cumulative~count }
\tl_set:Nn \freqname { Frequency }
\tl_set:Nn \cfreqname { Cumulative~frequency }
\tl_set:Nn \iccname { ICC }
\tl_set:Nn \icfname { ICF }
\tl_set:Nn \dccname { DCC }
\tl_set:Nn \dcfname { DCF }
\AtEndPreamble {
\tl_if_exist:NT \captionsfrench {
\tl_put_right:Nn \captionsfrench {
\tl_set:Nn \valuename { Modalit\'e }
\tl_set:Nn \countname { Effectif }
\tl_set:Nn \ccountname { Effectif~cumul\'e }
\tl_set:Nn \freqname { Fr\'equence }
\tl_set:Nn \cfreqname { Fr\'equence~cumul\'ee }
\tl_set:Nn \iccname { ECC }
\tl_set:Nn \icfname { FCC }
\tl_set:Nn \dccname { ECD }
\tl_set:Nn \dcfname { FCD }
}
}
}
% \end{macrocode}
%
% \subsection{Common facilities}
%
% \begin{macrocode}
\cs_new_protected:Nn \@@_keys_define:nn {
\keys_define:nn { statistics / #1 } { #2 }
}
\cs_new_protected:Nn \@@_setup:nn {
\keys_set:nn { statistics / #1 } { #2 }
}
\NewDocumentCommand \statisticssetup { o +m } {
\IfNoValueTF { #1 } {
\keys_set:nn { statistics } { #2 }
}{
\keys_set:nn { statistics / #1 } { #2 }
}
}
\tl_new:N \l_@@_data_tl
\seq_new:N \l_@@_show_seq
\int_new:N \l_@@_nbvals_int
\int_new:N \l_@@_currange_int
\fp_new:N \l_@@_total_fp
\fp_new:N \l_@@_curtotal_fp
\fp_new:N \l_@@_range_min_fp
\fp_new:N \l_@@_range_max_fp
\tl_new:N \l_@@_range_minrel_tl
\tl_new:N \l_@@_range_maxrel_tl
\cs_new_protected_nopar:Npn
\@@_parse_range:w \IN#1#2;#3;#4#5\q_stop {
% \end{macrocode}
%
% \begin{itemize}
% \item |#1| is the first |[| or |]|
% \item |#4| is the second |[| or |]| and |#5| eats all trailing tokens
% \end{itemize}
%
% \begin{macrocode}
\fp_set:Nn \l_@@_range_min_fp { #2 }
\fp_set:Nn \l_@@_range_max_fp { #3 }
}
\cs_new_protected_nopar:Npn
\@@_parse_range_full:w \IN#1#2;#3;#4#5\q_stop {
\fp_set:Nn \l_@@_range_min_fp { #2 }
\fp_set:Nn \l_@@_range_max_fp { #3 }
\tl_if_eq:nnTF { #1 } { [ } {
\tl_set:Nn \l_@@_range_minrel_tl { <=}
}{
\tl_set:Nn \l_@@_range_minrel_tl { < }
}
\tl_if_eq:nnTF { #4 } { ] } {
\tl_set:Nn \l_@@_range_maxrel_tl { <= }
}{
\tl_set:Nn \l_@@_range_maxrel_tl { < }
}
\exp_args:NNnx
\prg_set_conditional:Nnn \@@_if_in_range:n { T } {
\exp_not:N \fp_compare:nTF {
\exp_not:N \l_@@_range_min_fp
\exp_not:V \l_@@_range_minrel_tl
\exp_not:n { ##1 }
\exp_not:V \l_@@_range_maxrel_tl
\exp_not:N \l_@@_range_max_fp }{
\exp_not:N \prg_return_true:
}{
\exp_not:N \prg_return_false:
}
}
}
% \end{macrocode}
%
% \subsection{Compute and typeset statistics tables}
%
% \begin{macrocode}
\NewDocumentCommand \@@_IN:w { m u{;} u{;} m } {
\ensuremath{ \left#1 \num{#2} \mathbin{;} \num{#3} \right#4 }
}
\cs_new_protected:Nn \@@_setshow:n {
\seq_clear:N \l_@@_show_seq
\clist_map_inline:nn {#1} {
\tl_if_in:nnTF {##1} {-} {
\@@_setshow_aux:w ##1 \q_stop
}{
\seq_put_right:Nn \l_@@_show_seq {##1}
}
}
}
\cs_new_protected:Npn \@@_setshow_aux:w #1 - #2 \q_stop {
\int_step_inline:nnnn {#1} {1} {#2} {
\seq_put_right:Nn \l_@@_show_seq {##1}
}
}
\cs_new_protected_nopar:Nn \@@_set_if_shown:N {
\seq_if_empty:NTF \l_@@_show_seq {
\bool_set_true:N #1
}{
\seq_if_in:NVTF
\l_@@_show_seq
\l_@@_currange_int {
\bool_set_true:N #1
}{
\bool_set_false:N #1
}
}
}
\int_new:N \l_@@_table_maxcols_int
\int_set:Nn \l_@@_table_maxcols_int {0}
\@@_keys_define:nn { table } {
showonly .value_required:n = true,
showonly .code:n = \@@_setshow:n{#1},
showonly/hidden .value_required:n = true,
showonly/hidden .code:n = {
\cs_set_protected:Nn
\@@_table_hidden_format:n
{ #1 }
},
showonly/hidden .initial:n = ,
showonly/shown .value_required:n = true,
showonly/shown .code:n = {
\cs_set_protected:Nn
\@@_table_shown_format:n
{ #1 }
},
showonly/shown .initial:n = #1,
maxcols .clist_set:N = \l_@@_table_maxcols_clist,
maxcols .value_required:n = true,
maxcols .initial:n = ,
tablesep .tl_set:N = \l_@@_table_sep_tl,
tablesep .value_required:n = true,
tablesep .initial:n = \\,
valign .tl_set:N = \l_@@_table_valign_tl,
valign .value_required:n = true,
valign .initial:n = t,
coltype .tl_set:N = \l_@@_table_coltype_tl,
coltype .value_required:n = true,
headcoltype .tl_set:N = \l_@@_table_headcoltype_tl,
headcoltype .value_required:n = true,
newline .tl_set:N = \l_@@_table_newline_tl,
newline .value_required:n = true,
preline .tl_set:N = \l_@@_table_preline_tl,
preline .value_required:n = true,
postline .tl_set:N = \l_@@_table_postline_tl,
postline .value_required:n = true,
outline .meta:n = { preline={#1}, postline={#1} },
outline .value_required:n = true,
frame .choice:,
frame/full .meta:n = { preline=\firsthline, postline=\lasthline,
newline=\\\hline,
headcoltype=|l|, coltype=c| },
frame/full .value_forbidden:n = true,
frame/none .meta:n = { outline=, newline=\\,
headcoltype=l, coltype=c },
frame/none .value_forbidden:n = true,
frame/clean .meta:n = { preline=\firsthline, postline=\lasthline,
newline=\\,
headcoltype=l, coltype=c },
frame/clean .initial:n = ,
frame/clean .value_forbidden:n = true,
digits .int_set:N = \l_@@_table_round_int,
digits .initial:n = 3,
allcounts/format .code:n = {
\cs_set_protected:Nn
\@@_table_allcounts_format:n
{ #1 }
},
allcounts/format .value_required:n = true,
allcounts/format .initial:n = { \num{#1} },
allfreqs/format .code:n = {
\cs_set_protected:Nn
\@@_table_allfreqs_format:n
{ #1 }
},
allfreqs/format .value_required:n = true,
allfreqs/format/real .meta:n = {
allfreqs/format = \num{##1}
},
allfreqs/format/real .value_forbidden:n = true,
allfreqs/format/percent .meta:n = {
allfreqs/format = \SI{\fp_eval:n{##1*100}}{\percent}
},
allfreqs/format/percent .initial:n = ,
allfreqs/format/percent .value_forbidden:n = true,
allfreqs/format/scaled .meta:n = {
allfreqs/format = \num{\fp_eval:n{##1*#1}}
},
allfreqs/format/scaled .value_required:n = true,
}
\cs_new:Nn \@@_define_row:nnn {
% \end{macrocode}
%
% \begin{itemize}
% \item |#1| (tl): row name;
% \item |#2| (bool): enabled by default
% \item |#3| (tl): default header;
% \end{itemize}
%
% \begin{macrocode}
\tl_new:c { l_@@_table_#1_name_tl }
\bool_new:c { l_@@_table_#1_bool }
\@@_keys_define:nn { table } {
#1 .code:n = {
\bool_set_true:c { l_@@_table_#1_bool }
\quark_if_no_value:nF { ##1 } {
\@@_setup:nn { table } {
#1/header = { ##1 }
}
}
},
#1 .default:n = \q_no_value,
no#1 .code:n =
\bool_set_false:c { l_@@_table_#1_bool },
no#1 .value_forbidden:n = true,
#1/header .tl_set:c = { l_@@_table_#1_name_tl },
#1/header .value_required:n = true,
#1/header .initial:n = { #3 },
#1/format .code:n = {
\cs_set_protected:cn
{ _@@_table_#1_format:n }
{ ##1 }
},
#1/format .value_required:n = true,
#1/format .initial:n = { ##1 },
}
\bool_set:cn { l_@@_table_#1_bool } { #2 }
}
\@@_define_row:nnn { values } \c_true_bool \valuename
\@@_define_row:nnn { counts } \c_false_bool \countname
\@@_define_row:nnn { frequencies } \c_false_bool \freqname
\@@_define_row:nnn { icc } \c_false_bool \iccname
\@@_define_row:nnn { icf } \c_false_bool \icfname
\@@_define_row:nnn { dcc } \c_false_bool \dccname
\@@_define_row:nnn { dcf } \c_false_bool \dcfname
\@@_setup:nn { table } {
values/format = \ensuremath{#1},
}
\cs_undefine:N \@@_define_row:nnn
\seq_new:N \l_@@_table_contents_seq
\tl_new:N \l_@@_table_preamble_tl
\tl_new:N \l_@@_table_values_tl
\tl_new:N \l_@@_table_counts_tl
\tl_new:N \l_@@_table_frequencies_tl
\tl_new:N \l_@@_table_icc_tl
\tl_new:N \l_@@_table_icf_tl
\tl_new:N \l_@@_table_dcc_tl
\tl_new:N \l_@@_table_dcf_tl
\fp_new:N \l_@@_table_curICF_fp
\fp_new:N \l_@@_table_prevICF_fp
\bool_new:N \l_@@_table_firstrow_bool
\seq_new:N \l_@@_store_values_seq
\seq_new:N \l_@@_store_counts_seq
\cs_generate_variant:Nn \keyval_parse:NNn { NNV }
\NewDocumentCommand \StatsTable { +O{} +m +O{} } {
\group_begin:
% \end{macrocode}
%
% Ensure some macros exist with sensible definitions
%
% \begin{macrocode}
\cs_if_exist:NF \firsthline {
\cs_set_eq:NN \firsthline \hline
}
\cs_if_exist:NF \lasthline {
\cs_set_eq:NN \lasthline \hline
}
\cs_if_exist:NF \IN {
\cs_set_eq:NN \IN \@@_IN:w
}
% \end{macrocode}
%
% Handle optional settings
%
% \begin{macrocode}
\@@_setup:nn { table } { #1, #3 }
% \end{macrocode}
%
% Get the data inline or from a variable
%
% \begin{macrocode}
\tl_if_single:nTF { #2 } {
% \end{macrocode}
%
% Generate meaningful error by using the non-existent variable
%
% \begin{macrocode}
\cs_if_exist:NF #2 { #2 }
\tl_set_eq:NN \l_@@_data_tl #2
}{
\tl_set:Nn \l_@@_data_tl { #2 }
}
% \end{macrocode}
%
% Define getters for some items of the table, to be used for instance to
% programmatically choose the formatting.
%
% \begin{macrocode}
\cs_set_nopar:Npn \getvalue {
\seq_item:Nn \l_@@_store_values_seq
}
\cs_set_nopar:Npn \getcount {
\seq_item:Nn \l_@@_store_count_seq
}
% \end{macrocode}
%
% Compute the total population count/frequency
%
% \begin{macrocode}
\fp_zero:N \l_@@_total_fp
\keyval_parse:NNV
\@@_table_count:n
\@@_table_count:nn
\l_@@_data_tl
% \end{macrocode}
%
% Loop again and output the table
%
% \begin{macrocode}
\@@_table_start:
\fp_zero:N \l_@@_table_prevICF_fp
\keyval_parse:NNV
\@@_table_make:n
\@@_table_make:nn
\l_@@_data_tl
\@@_table_end:
% \end{macrocode}
%
% Done
%
% \begin{macrocode}
\group_end:
}
% \end{macrocode}
%
% table building functions
%
% \begin{macrocode}
\cs_new_protected_nopar:Nn \@@_table_start: {
% \end{macrocode}
%
% Init column count and fetch the next maxcols value (or keep the current one if
% we reached the end of the list).
%
% \begin{macrocode}
\int_zero:N \l_@@_nbvals_int
\clist_pop:NNT \l_@@_table_maxcols_clist \l_tmpa_tl {
\int_set:Nn \l_@@_table_maxcols_int { \l_tmpa_tl }
}
% \end{macrocode}
%
% Start rows with headers
%
% \begin{macrocode}
\clist_map_inline:nn { values, counts, frequencies, icc, icf, dcc, dcf } {
\tl_set:cx { l_@@_table_##1_tl } {
\exp_not:N \ensuremath { \exp_not:N \hbox {
\exp_not:c { l_@@_table_##1_name_tl }
} }
}
}
}
\cs_new_protected_nopar:Nn \@@_table_end: {
% \end{macrocode}
%
% Build-up the table preamble
%
% \begin{macrocode}
\tl_set:Nx \l_@@_table_preamble_tl {
\exp_not:n { \begin{array}[ }
\exp_not:V \l_@@_table_valign_tl
\exp_not:n { ] }
{ \exp_not:V \l_@@_table_headcoltype_tl
\prg_replicate:nn { \l_@@_nbvals_int }
{ \exp_not:V \l_@@_table_coltype_tl } }
}
% \end{macrocode}
%
% Add each row if needed.
%
% \begin{macrocode}
\seq_clear:N \l_@@_table_contents_seq
\clist_map_inline:nn { values, counts, icc, dcc, frequencies, icf, dcf } {
\bool_if:cT { l_@@_table_##1_bool } {
\seq_put_right:Nv
\l_@@_table_contents_seq
{ l_@@_table_##1_tl }
}
}
$\tl_use:N \l_@@_table_preamble_tl
\l_@@_table_preline_tl
\seq_use:Nn
\l_@@_table_contents_seq
{ \l_@@_table_newline_tl }
\\ \l_@@_table_postline_tl
\end{array}$
}
% \end{macrocode}
%
% Counting auxiliaries
%
% \begin{macrocode}
\cs_new_protected_nopar:Nn \@@_table_count:n {
\@@_table_count:nn {} { 1 }
}
\cs_new_protected_nopar:Nn \@@_table_count:nn {
\fp_add:Nn \l_@@_total_fp { #2 }
}
% \end{macrocode}
%
% Accumulating content
%
% \begin{macrocode}
\cs_new_protected_nopar:Nn \@@_table_make:n {
\@@_table_make:nn { #1 } { 1 }
}
\cs_new_protected_nopar:Nn \@@_table_make:nn {
% \end{macrocode}
%
% Maybe close the table and create a new one
%
% \begin{macrocode}
\int_compare:nT
{ 0 < \l_@@_table_maxcols_int
= \l_@@_nbvals_int } {
\@@_table_end:
\tl_use:N \l_@@_table_sep_tl
\@@_table_start:
}
\int_incr:N \l_@@_nbvals_int
\int_incr:N \l_@@_currange_int
\fp_add:Nn \l_@@_curtotal_fp { #2 }
% \end{macrocode}
%
% Hidden or not
%
% \begin{macrocode}
\@@_set_if_shown:N \l_tmpa_bool
\tl_set:Nx \l_tmpa_tl {
\exp_not:n { & \tl_set:Nn \currentcolumn } {
\int_use:N \l_@@_currange_int
}
}
\bool_if:NTF \l_tmpa_bool {
\tl_put_right:Nn \l_tmpa_tl
{\@@_table_shown_format:n}
}{
\tl_put_right:Nn \l_tmpa_tl
{\@@_table_hidden_format:n}
}
% \end{macrocode}
%
% Values
%
% \begin{macrocode}
\seq_put_right:Nn \l_@@_store_values_seq { #1 }
\bool_if:NT \l_@@_table_values_bool {
\tl_put_right:Nx \l_@@_table_values_tl {
\exp_not:V \l_tmpa_tl {
\exp_not:n {
\@@_table_values_format:n { #1 }
}
}
}
}
% \end{macrocode}
%
% Counts
%
% \begin{macrocode}
\seq_put_right:Nx \l_@@_store_counts_seq { \fp_eval:n {#2} }
\bool_if:NT \l_@@_table_counts_bool {
\tl_put_right:Nx \l_@@_table_counts_tl {
\exp_not:V \l_tmpa_tl {
\exp_not:n {
\@@_table_counts_format:n {
{ \@@_table_allcounts_format:n { #2 } }
}
}
}
}
}
% \end{macrocode}
%
% ICC
%
% \begin{macrocode}
\bool_if:NT \l_@@_table_icc_bool {
\tl_put_right:Nx \l_@@_table_icc_tl {
\exp_not:V \l_tmpa_tl {
\exp_not:n { \@@_table_icc_format:n }
{
\exp_not:n{ \@@_table_allcounts_format:n }
{ \fp_use:N \l_@@_curtotal_fp }
}
}
}
}
% \end{macrocode}
%
% DCC ( = 1 - ICC + curcount )
%
% \begin{macrocode}
\bool_if:NT \l_@@_table_dcc_bool {
\tl_put_right:Nx \l_@@_table_dcc_tl {
\exp_not:V \l_tmpa_tl {
\exp_not:n { \@@_table_dcc_format:n }
{
\exp_not:n{ \@@_table_allcounts_format:n }
{
\fp_eval:n {
\l_@@_total_fp
- \l_@@_curtotal_fp
+ #2
}
}
}
}
}
}
% \end{macrocode}
%
% Frequencies (we compute them from the ICFs so that rounded freqs add up to 1)
%
% \begin{macrocode}
\fp_set:Nn \l_@@_table_curICF_fp {
round(\l_@@_curtotal_fp
/ \l_@@_total_fp,
\l_@@_table_round_int)
}
\bool_if:NT \l_@@_table_frequencies_bool {
\tl_put_right:Nx \l_@@_table_frequencies_tl {
\exp_not:V \l_tmpa_tl {
\exp_not:n { \@@_table_frequencies_format:n }
{
\exp_not:n{ \@@_table_allfreqs_format:n }
{
\fp_eval:n {
\l_@@_table_curICF_fp
- \l_@@_table_prevICF_fp
}
}
}
}
}
}
% \end{macrocode}
%
% ICF
%
% \begin{macrocode}
\bool_if:NT \l_@@_table_icf_bool {
\tl_put_right:Nx \l_@@_table_icf_tl {
\exp_not:V \l_tmpa_tl {
\exp_not:n { \@@_table_icf_format:n }
{
\exp_not:n{ \@@_table_allfreqs_format:n }
{ \fp_to_decimal:N \l_@@_table_curICF_fp }
}
}
}
}
% \end{macrocode}
%
% DCF ( = 1 - ICF + curfreq = 1 - prevICF )
%
% \begin{macrocode}
\bool_if:NT \l_@@_table_dcf_bool {
\tl_put_right:Nx \l_@@_table_dcf_tl {
\exp_not:V \l_tmpa_tl {
\exp_not:n { \@@_table_dcf_format:n }
{
\exp_not:n{ \@@_table_allfreqs_format:n }
{
\fp_eval:n {
1 - \l_@@_table_prevICF_fp
}
}
}
}
}
}
% \end{macrocode}
%
% Prepare for next iteration
%
% \begin{macrocode}
\fp_set_eq:NN
\l_@@_table_prevICF_fp
\l_@@_table_curICF_fp
}
% \end{macrocode}
%
% \subsection{Compute and typeset statistics graphics}
%
% \begin{macrocode}
\cs_new_protected:Nn \@@_make_forwarded_key:nnnn {
% \end{macrocode}
%
% \begin{itemize}
% \item |#1| (tl): common prefix
% \item |#2| (tl): middle
% \item |#3| (clist): replacements
% \item |#4| (tl): common suffix
% \end{itemize}
%
% \begin{macrocode}
\tl_clear:N \l_tmpa_tl
\clist_map_inline:nn {#3} {
\tl_put_right:Nx \l_tmpa_tl {
\exp_not:n {#1}
\tl_if_empty:nF {#1} { \tl_if_empty:nF {##1} {\exp_not:N /} }
\exp_not:n {##1}
\tl_if_empty:nF {#4} { \tl_if_empty:nF {##1} {\exp_not:N /} }
\exp_not:n {#4,}
}
}
\tl_set:Nx \l_tmpb_tl {
\exp_not:n {#1}
\tl_if_empty:nF {#1} { \tl_if_empty:nF {#2} {\exp_not:N /} }
\exp_not:n {#2}
\tl_if_empty:nF {#4} { \tl_if_empty:nF {#2} {\exp_not:N /} }
\exp_not:n {#4}
}
\use:x {
\exp_not:n { \@@_keys_define:nn { graph } }
{
\exp_not:V \l_tmpb_tl \exp_not:n { .default:n = \q_no_value, }
\exp_not:V \l_tmpb_tl
\exp_not:n { .code:n = \@@_forwarded_key:nn }
{ \exp_not:V \l_tmpa_tl }
{ \exp_not:n { ##1 } }
}
}
}
\cs_new_protected:Nn \@@_forwarded_key:nn {
\quark_if_no_value:nTF { #2 } {
\@@_setup:nn { graph } { #1 }
}{
\clist_set:Nn \l_tmpa_clist { #1,{} }
\use:x {
\exp_not:n { \@@_setup:nn { graph } } {
\clist_use:Nn \l_tmpa_clist { = {#2}, }
}
}
}
}
\cs_new_protected_nopar:Nn \@@_forward_keys:nn {
% \end{macrocode}
%
% \begin{itemize}
% \item |#1| (clist): destination prefixes
% \item |#2| (clist): keys
% \end{itemize}
%
% \begin{macrocode}
\clist_map_inline:nn {#2} {
\@@_make_forwarded_key:nnnn {} {} { #1 } { ##1 }
}
}
\cs_new:Nn \@@_create_append_reset:nn {
% \end{macrocode}
%
% \begin{itemize}
% \item |#1| (tl): key basename
% \item |#2| (var): suffix of variable to store options into
% \end{itemize}
%
% \begin{macrocode}
\tl_new:c { l_@@_graph_#2_tl }
\@@_keys_define:nn { graph } {
#1 .value_required:n = true,
#1 .code:n = \tl_put_right:cn
{ l_@@_graph_#2_tl }
{ ##1, },
#1/reset .value_forbidden:n = true,
#1/reset .code:n = \tl_clear:c
{ l_@@_graph_#2_tl },
}
}
\cs_new:Nn \@@_DO:nn { \@@_create_append_reset:nn {#1}{options_#2} }
\cs_new:Nn \@@_define_unit:nn {
% \end{macrocode}
%
% \begin{itemize}
% \item |#1| (tl): unit name (plural)
% \item |#2| (tl): graph type
% \end{itemize}
%
% \begin{macrocode}
\@@_DO:nn { #2/#1/axis } { #2_#1axis }
\@@_keys_define:nn { graph } {
#2/#1 .code:n = {
\tl_set:cn {l_@@_graph_#2_unit_tl} { #1 }
\quark_if_no_value:nF { ##1 } {
\@@_setup:nn { graph }{ #2/#1/label = { ##1 } }
}
},
#2/#1 .default:n = \q_no_value,
#2/#1/label .meta:n = { #2/#1/axis = { label = { ##1 } } },
#2/#1/label .value_required:n = true,
#2/#1/format .code:n = {
\cs_set_protected:cn
{ @@_graph_#2_#1_format:n }
{ ##1 }
},
#2/#1/format .value_required:n = true,
#2/#1/margin .tl_set:c = l_@@_graph_#2_#1_vmargin_tl,
#2/#1/margin .value_required:n = true,
}
}
\@@_DO:nn { picture } { pic }
\@@_DO:nn { axissystem } { system }
\@@_DO:nn { histogram/areas/style } { areas }
\@@_DO:nn { histogram/legend/options } { legend }
\clist_map_inline:nn { histogram, cumulative, comb } {
\@@_define_unit:nn { counts } { #1 }
\@@_define_unit:nn { frequencies } { #1 }
\@@_DO:nn { #1/style } { #1 }
\@@_DO:nn { #1/values/axis } { #1_xaxis }
\@@_keys_define:nn { graph/#1 } {
values/margin .value_required:n = true,
values/margin .tl_set:c = l_@@_graph_#1_hmargin_tl,
values/label .meta:n = { values/axis = { label = { ##1 } } },
values/label .value_required:n = true,
values/format .code:n = { \cs_set_protected:cn
{@@_graph_#1_values_format:n} { ##1 }
},
values/format .value_required:n = true,
frequencies/format/real .meta:n = {
frequencies/format = {
\num[round-mode=places,round-precision=##1]{####1}
}
},
frequencies/format/real .default:n = 1,
frequencies/format/percent .meta:n = {
frequencies/format = {
\SI[round-mode=places,round-precision=##1]{
\fp_eval:n{####1*100}
}{\percent}
}
},
frequencies/format/percent .default:n = 1,
}
\@@_make_forwarded_key:nnnn {#1/values}{}{label}{}
\clist_map_inline:nn { axis, axis/reset, label, margin, format } {
\@@_make_forwarded_key:nnnn {#1}{x}{values}{##1}
\@@_make_forwarded_key:nnnn {#1}{y}{counts, frequencies}{##1}
}
}
\cs_undefine:N \@@_DO:nn
\cs_undefine:N \@@_define_unit:nnn
\@@_forward_keys:nn { histogram, cumulative, comb } {
values, values/label, values/margin, values/format,
values/axis, values/axis/reset,
x/label, x/axis, x/axis/reset, x/margin, x/format,
counts, counts/label, counts/margin, counts/format,
counts/axis, counts/axis/reset,
frequencies, frequencies/label, frequencies/margin,
frequencies/format, frequencies/format/real, frequencies/format/percent,
frequencies/axis, frequencies/axis/reset,
y/label, y/axis, y/axis/reset, y/margin, y/format,
style, style/reset
}
\@@_create_append_reset:nn { tikzinfo' } { userpreinfo }
\@@_create_append_reset:nn { tikzinfo } { userpostinfo }
\cs_undefine:N \@@_forward_keys:nn
\cs_undefine:N \@@_make_forwarded_key:nnnn
\cs_undefine:N \@@_create_append_reset:nn
\@@_keys_define:nn { graph } {
showonly .value_required:n = true,
showonly .code:n = \@@_setshow:n{#1},
height .value_required:n = true,
height .meta:n = { axissystem = { height = { #1 } } },
width .value_required:n = true,
width .meta:n = { axissystem = { width = { #1 } } },
cumulative .bool_set:N = \l_@@_graph_cumulative_bool,
cumulative .default:n = true,
decreasing .bool_set:N = \l_@@_graph_decreasing_bool,
decreasing .default:n = true,
histogram/areas .bool_set:N = \l_@@_graph_areas_bool,
histogram/areas .default:n = true,
histogram/legend/label .value_required:n = true,
histogram/legend/label .meta:n = {
histogram/legend/options = {label={#1}} },
histogram/legend/area .value_required:n = true,
histogram/legend/area .meta:n = {
histogram/legend/h = (#1)/\width },
histogram/legend .value_required:n = true,
histogram/legend .code:n = {
\@@_setup:nn { graph / histogram/legend } {
#1
}
},
histogram/y/autostep .value_required:n = true,
histogram/y/autostep .meta:n = {
histogram/counts/autostep = {#1},
histogram/frequencies/autostep = {#1},
histogram/legend/area = {#1},
},
}
\tl_map_inline:nn {xywh} {
\@@_keys_define:nn { graph / histogram / legend } {
#1 .value_required:n = true,
#1 .tl_set:c = {l_@@_graph_legend_#1_tl},
}
}
\clist_map_inline:nn { counts, frequencies } {
\@@_keys_define:nn { graph/histogram/#1 } {
autostep .default:n = 1,
autostep .meta:n = { axis = {
grid = { compute~step =
\group_begin:
\tl_set:Nx \total { \fp_to_decimal:N \l_@@_total_fp }
\fp_gset:Nn \g_tmpa_fp { ##1 }
\group_end:
\tl_set:Nx \tikz@lib@dv@step {
\fp_eval:n {\g_tmpa_fp / \g_@@_graph_xstep_fp }
}
}
}},
}
}
\@@_setup:nn { graph }{
width = 0.75\columnwidth,
cumulative = false,
decreasing = false,
values/axis = {
label = \valuename,
ticks~and~grid={many, integer~minor~steps}
},
values/margin = \xstep / 2,
values/format = \num{#1},
y/margin = \range/10,
counts/format = { \num{#1} },
counts/axis = { ticks~and~grid={
many, int~about~strategy, integer~minor~steps*,
} },
comb/counts/label = \countname,
cumulative/counts/label = \ccountname,
frequencies/format/percent,
frequencies/axis = { ticks~and~grid=many },
comb/frequencies/label = \freqname,
cumulative/frequencies/label = \cfreqname,
histogram/y/axis/reset,
histogram/y/axis = {ticks = none},
histogram/y/autostep = 1,
histogram/legend = { x=, y=0, w=\xstep },
histogram/style = {
every~path/.prefix~style=fill,
semithick, black, fill=black, fill~opacity=0.1
},
histogram/areas,
histogram/areas/style = { auto, font=\small },
comb/style = { ultra~thick },
counts,
picture = {
baseline = (current~bounding~box.center),
label~position = right,
},
}
\tl_const:Nn \c_@@_graph_savexstep_tl {
grid = { compute~step/.append = {
\cs_if_eq:NNF \tikz@lib@dv@step \relax {
\pgfkeysgetvalue
{/tikz/data~visualization/minor~steps~between~steps}
\l_tmpa_tl
\fp_gset:Nn \g_@@_graph_xstep_fp {
\tikz@lib@dv@step
/ (\fp_max:nn{0\l_tmpa_tl + 1}{1})
}
}
}}
}
% \end{macrocode}
%
% To detect that the user didn't set |minor steps between steps| himself after
% having used |integer minor steps| (which can be a default setting), we add a
% handler to the key that sets its value but also empties
% \cs{l_@@_graph_maxminor_tl} so that we do not overwrite anything.
%
% \begin{macrocode}
\tl_new:N \l_@@_graph_maxminor_tl
\int_new:N \l_@@_graph_minorsteps_int
\fp_new:N \l_@@_graph_ims_step_fp
\fp_new:N \l_@@_graph_ims_range_fp
\fp_new:N \l_@@_graph_ims_threshold_fp
\tikzdatavisualizationset{
integer~minor~steps/.style={
/utils/exec = \tl_set:Nn \l_@@_graph_maxminor_tl {#1},
minor~steps~between~steps/.code=
\tl_clear:N \l_@@_graph_maxminor_tl
\pgfkeyssetvalue
{/tikz/data~visualization/minor~steps~between~steps}
{##1} ,
compute~step/.append = {
\tl_set_eq:NN \l_tmpa_tl \tikz@lib@dv@step
\tl_if_empty:NT \l_@@_graph_maxminor_tl {
\tl_set_eq:NN \l_tmpa_tl \relax
}
\tl_if_eq:NNF \l_tmpa_tl \relax {
\fp_set:Nn \l_@@_graph_ims_step_fp { \l_tmpa_tl }
\tikz@lib@dv@mapper.get~in~range~interval()
\pgfdvinrangeinterval.get~min~and~max()
\pgfdvmathexitbyscientificformat \l_tmpa_tl \pgfdvmin
\pgfdvmathexitbyscientificformat \l_tmpb_tl \pgfdvmax
\fp_set:Nn \l_@@_graph_ims_range_fp { \l_tmpb_tl - \l_tmpa_tl }
\fp_set:Nn \l_@@_graph_ims_threshold_fp {
\fp_max:nn {
\l_@@_graph_ims_step_fp * (\l_@@_graph_maxminor_tl)
}{
\l_@@_graph_ims_range_fp
}
}
\int_set:Nn \l_@@_graph_minorsteps_int
{ \fp_to_int:N \l_@@_graph_ims_step_fp }
\bool_while_do:nn {
\fp_compare_p:n {
\l_@@_graph_minorsteps_int * \l_@@_graph_ims_range_fp
> \l_@@_graph_ims_threshold_fp
}
}{
\tl_map_inline:nn {{2}{5}{10}} {
\fp_compare:nF {
\l_@@_graph_minorsteps_int * \l_@@_graph_ims_range_fp
> \l_@@_graph_ims_threshold_fp * ##1
}{
\int_compare:nT {
\int_mod:nn{\l_@@_graph_minorsteps_int}{##1} = 0
}{
\int_set:Nn
\l_@@_graph_minorsteps_int
{ \l_@@_graph_minorsteps_int / ##1 }
\tl_map_break:
}
}
}
\fp_compare:nT {
\l_@@_graph_minorsteps_int * \l_@@_graph_ims_range_fp
> \l_@@_graph_ims_threshold_fp
}{
\tl_map_inline:nn {{3}{2}{5}{\l_@@_graph_minorsteps_int}} {
\int_compare:nT {
\int_mod:nn{\l_@@_graph_minorsteps_int}{##1} = 0
}{
\int_set:Nn
\l_@@_graph_minorsteps_int
{ \l_@@_graph_minorsteps_int / ##1 }
\tl_map_break:
}
}
}
}
\int_compare:nNnTF \l_@@_graph_minorsteps_int > 1 {
\use:x { \exp_not:n {
\pgfkeyssetvalue
{/tikz/data~visualization/minor~steps~between~steps}
}
{ \int_eval:n {\l_@@_graph_minorsteps_int-1} }
}
}{
\pgfkeyssetvalue
{/tikz/data~visualization/minor~steps~between~steps}
{}
}
\tl_clear:N \l_@@_graph_maxminor_tl
}
}
},
integer~minor~steps/.default=50,
integer~minor~steps*/.style={
compute~step/.append = {
\tl_set_eq:NN \l_tmpa_tl \tikz@lib@dv@step
\tl_if_eq:NNF \l_tmpa_tl \relax {
\fp_compare:nT { \l_tmpa_tl < 1 } {
\tl_set:Nx \tikz@lib@dv@step {1}
}
}
},
integer~minor~steps=#1,
},
integer~minor~steps*/.default=50,
}
% \end{macrocode}
%
% First define a lot of variables:
%
% \begin{macrocode}
\bool_new:N \l_@@_graph_allranges_bool
\fp_new:N \l_@@_graph_curvalue_fp
\fp_new:N \l_@@_graph_curheight_fp
\fp_new:N \l_@@_graph_prevheight_fp
\fp_new:N \l_@@_graph_maxheight_fp
\fp_new:N \l_@@_graph_minvalue_fp
\fp_new:N \l_@@_graph_maxvalue_fp
\fp_new:N \g_@@_graph_xstep_fp
\int_new:N \g_@@_graph_last_int
\tl_new:N \l_@@_graph_tikzdata_tl
\tl_new:N \l_@@_graph_tikzinfo_tl
\clist_new:N \l_@@_graph_tikzincludex_clist
\clist_new:N \l_@@_graph_tikzincludey_clist
\tl_new:N \l_@@_graph_tikzpicture_tl
% \end{macrocode}
%
% No scale for counts, divide by total for freqs
%
% \begin{macrocode}
\fp_new:N \l_@@_graph_scale_fp
\fp_new:N \l_@@_graph_counts_scale_fp
\fp_new:N \l_@@_graph_frequencies_scale_fp
\fp_set:Nn \l_@@_graph_counts_scale_fp { 1 }
\NewDocumentCommand \StatsGraph { +O{} +m +O{} } {
\group_begin:
\int_gincr:N \g_@@_graph_last_int
% \end{macrocode}
%
% Read saved x step, for automatic margin and histogram y step
%
% \begin{macrocode}
\tl_set:Nx \l_tmpa_tl {
\exp_not:n { g_@@_graph_xstep_ }
\int_use:N \g_@@_graph_last_int
\exp_not:n { _tl }
}
\tl_if_exist:cTF { \l_tmpa_tl } {
\fp_gset:Nn \g_@@_graph_xstep_fp
{ \tl_use:c {\l_tmpa_tl} }
}{
\fp_gset:Nn \g_@@_graph_xstep_fp { \c_one_int }
}
% \end{macrocode}
%
% Handle optional settings
%
% \begin{macrocode}
\@@_setup:nn { graph } { #1, #3 }
% \end{macrocode}
%
% Get the data inline or from a variable
%
% \begin{macrocode}
\tl_if_single:nTF { #2 } {
% \end{macrocode}
%
% Generate meaningful error by using the non-existent variable.
%
% \begin{macrocode}
\cs_if_exist:NF #2 { #2 }
\tl_set_eq:NN \l_@@_data_tl #2
}{
\tl_set:Nn \l_@@_data_tl { #2 }
}
% \end{macrocode}
%
% Zero the maximum height in the graph, and setup min and max values.
%
% \begin{macrocode}
\fp_zero:N \l_@@_graph_maxheight_fp
\fp_set:Nn \l_@@_graph_minvalue_fp {inf}
\fp_set:Nn \l_@@_graph_maxvalue_fp {-inf}
% \end{macrocode}
%
% The following loop does 2 things:
% \begin{itemize}
% \item Counting the number of ranges and the total population count
% \item Detecting whether the ranges are intervals or single numbers
% \end{itemize}
%
% \begin{macrocode}
\fp_zero:N \l_@@_total_fp
\int_zero:N \l_@@_nbvals_int
\bool_set_true:N \l_@@_graph_allranges_bool
\keyval_parse:NNV
\@@_graph_prepare:n
\@@_graph_prepare:nn
\l_@@_data_tl
% \end{macrocode}
%
% The remainder is different whether we do histogram, cumulative, or comb
%
% \begin{macrocode}
\tl_clear:N \l_@@_graph_tikzdata_tl
\tl_clear:N \l_@@_graph_tikzinfo_tl
\int_zero:N \l_@@_currange_int
\bool_if:NTF \l_@@_graph_allranges_bool {
\bool_if:NTF \l_@@_graph_cumulative_bool {
% \end{macrocode}
%
% We draw a cumulative distribution function
%
% \begin{macrocode}
\@@_graph_dopicture_cumulative:
}{
% \end{macrocode}
%
% We draw an histogram
%
% \begin{macrocode}
\@@_graph_dopicture_hist:
}
}{
% \end{macrocode}
%
% We draw a comb graph
%
% \begin{macrocode}
\@@_graph_dopicture_comb:
}
% \end{macrocode}
%
% Write xstep info to aux file
%
% \begin{macrocode}
\iow_now:Nx \@auxout {
\exp_not:n {
\ExplSyntaxOn
\tl_gset:cn
}
{
\exp_not:n {g_@@_graph_xstep_}
\int_use:N \g_@@_graph_last_int
\exp_not:n {_tl}
}
{
\fp_to_decimal:N \g_@@_graph_xstep_fp
}
\exp_not:n {
\ExplSyntaxOff
}
}
\group_end:
}
% \end{macrocode}
%
% First pass
%
% \begin{macrocode}
\cs_new_protected_nopar:Nn \@@_graph_prepare:n {
\@@_graph_prepare:nn { #1 } { 1 }
}
\cs_new_protected_nopar:Nn \@@_graph_prepare:nn {
\int_incr:N \l_@@_nbvals_int
\fp_add:Nn \l_@@_total_fp { #2 }
\exp_args:Nx \tl_if_eq:nnF { \tl_head:n {#1} }{ \IN } {
\bool_set_false:N \l_@@_graph_allranges_bool
}
}
% \end{macrocode}
%
% Shared utility functions
%
% \begin{macrocode}
\cs_new_protected_nopar:Nn \@@_graph_addpoint:nnn {
\tl_put_right:Nx \l_@@_graph_tikzdata_tl {
\exp_not:N \pgfkeys {
\exp_not:n { /data~point/name = #1 }
\int_use:N \l_@@_currange_int
\exp_not:n { ,/data~point/x = } \fp_eval:n { #2 }
\exp_not:n { ,/data~point/y = } \fp_eval:n { #3 }
}
\exp_not:n { \pgfdatapoint }
}
}
\cs_new_protected_nopar:Nn \@@_graph_outlier: {
\tl_put_right:Nn \l_@@_graph_tikzdata_tl {
\pgfkeys{/data~point/outlier = true}
\pgfdatapoint
\pgfkeys{/data~point/outlier = }
}
}
\cs_new_protected_nopar:Nn \@@_graph_setup:n {
\fp_set_eq:Nc \l_@@_graph_hmargin_tl {l_@@_graph_#1_hmargin_tl}
\tl_set_eq:Nc \l_@@_graph_unit_tl { l_@@_graph_#1_unit_tl }
\tl_set_eq:Nc \l_@@_graph_vmargin_tl
{l_@@_graph_#1_ \l_@@_graph_unit_tl _vmargin_tl}
\tl_set_eq:Nc
\l_@@_graph_options_yaxis_tl
{l_@@_graph_options_#1_ \l_@@_graph_unit_tl axis_tl}
\cs_set_eq:Nc
\@@_graph_y_format:n
{@@_graph_#1_ \l_@@_graph_unit_tl _format:n}
\cs_set_eq:Nc
\@@_graph_values_format:n
{@@_graph_#1_values_format:n}
\fp_set_eq:NN
\l_@@_graph_frequencies_scale_fp
\l_@@_total_fp
\fp_set_eq:Nc
\l_@@_graph_scale_fp
{l_@@_graph_ \l_@@_graph_unit_tl _scale_fp}
}
\cs_new_protected_nopar:Nn \@@_graph_update_minmaxval:NN {
\fp_set:Nn \l_@@_graph_minvalue_fp {
min( \l_@@_graph_minvalue_fp, #1 )
}
\fp_set:Nn \l_@@_graph_maxvalue_fp {
max( \l_@@_graph_maxvalue_fp, #2 )
}
}
\cs_new_protected_nopar:Nn \@@_graph_update_maxheight: {
\fp_set:Nn \l_@@_graph_maxheight_fp {
max( \l_@@_graph_maxheight_fp , \l_@@_graph_curheight_fp )
}
}
\cs_new_protected_nopar:Nn \@@_graph_handle_hmargin: {
\group_begin:
\tl_set:Nx \min { \fp_to_decimal:N \l_@@_graph_minvalue_fp }
\tl_set:Nx \max { \fp_to_decimal:N \l_@@_graph_maxvalue_fp }
\tl_set:Nx \range {
\fp_eval:n { \l_@@_graph_maxvalue_fp - \l_@@_graph_minvalue_fp }
}
\tl_set:Nx \xstep { \fp_to_decimal:N \g_@@_graph_xstep_fp }
\exp_args:NNV \fp_gset:Nn \g_tmpa_fp \l_@@_graph_hmargin_tl
\group_end:
\clist_put_right:Nx \l_@@_graph_tikzincludex_clist {
\fp_eval:n { \l_@@_graph_minvalue_fp - \g_tmpa_fp }
}
\clist_put_right:Nx \l_@@_graph_tikzincludex_clist {
\fp_eval:n { \l_@@_graph_maxvalue_fp + \g_tmpa_fp }
}
}
\cs_new_protected_nopar:Nn \@@_graph_handle_vmargin: {
\group_begin:
\tl_set:Nn \min { 0 }
\tl_set:Nx \max { \fp_to_decimal:N \l_@@_graph_maxheight_fp }
\tl_set_eq:NN \range \max
\exp_args:NNV \fp_gset:Nn \g_tmpa_fp \l_@@_graph_vmargin_tl
\group_end:
\clist_put_right:Nx \l_@@_graph_tikzincludey_clist {
\fp_eval:n { \l_@@_graph_maxheight_fp + \g_tmpa_fp }
}
}
% \end{macrocode}
%
% Second pass, histogram
%
% \begin{macrocode}
\cs_new_protected_nopar:Nn \@@_graph_dopicture_hist: {
\@@_graph_setup:n {histogram}
% \end{macrocode}
%
% Loop through the list again to fill tikz data and labels
%
% \begin{macrocode}
\keyval_parse:NNV
\@@_graph_make_hist:n
\@@_graph_make_hist:nn
\l_@@_data_tl
% \end{macrocode}
%
% Maybe add a legend
%
% \begin{macrocode}
\tl_if_empty:NF \l_@@_graph_legend_x_tl {
\group_begin:
\tl_set:Nx \min { \fp_to_decimal:N \l_@@_graph_minvalue_fp }
\tl_set:Nx \max { \fp_to_decimal:N \l_@@_graph_maxvalue_fp }
\tl_set:Nx \range {
\fp_eval:n { \l_@@_graph_maxvalue_fp - \l_@@_graph_minvalue_fp }
}
\tl_set:Nx \xstep { \fp_to_decimal:N \g_@@_graph_xstep_fp }
\exp_args:NNV \fp_gset:Nn \g_tmpa_fp \l_@@_graph_legend_x_tl
\exp_args:NNV \fp_gset:Nn \g_tmpb_fp \l_@@_graph_legend_w_tl
\group_end:
\tl_set:Nx \l_@@_graph_legend_x_tl { \fp_to_decimal:N \g_tmpa_fp }
\tl_set:Nx \l_@@_graph_legend_w_tl { \fp_to_decimal:N \g_tmpb_fp }
\group_begin:
\tl_set:Nn \min { 0 }
\tl_set:Nx \max { \fp_to_decimal:N \l_@@_graph_maxheight_fp }
\tl_set_eq:NN \range \max
\tl_set:Nx \xstep { \fp_to_decimal:N \g_@@_graph_xstep_fp }
\tl_set_eq:NN \width \l_@@_graph_legend_w_tl
\tl_set:Nx \total { \fp_to_decimal:N \l_@@_total_fp }
\exp_args:NNV \fp_gset:Nn \g_tmpb_fp \l_@@_graph_legend_h_tl
\tl_set:Nx \height { \fp_to_decimal:N \g_tmpb_fp }
\exp_args:NNV \fp_gset:Nn \g_tmpa_fp \l_@@_graph_legend_y_tl
\group_end:
\tl_put_right:Nx \l_@@_graph_tikzinfo_tl {
\exp_not:n { \path (visualization~cs }
\token_to_str:N : \exp_not:n { x= }
\exp_not:V \l_@@_graph_legend_x_tl
\exp_not:n { ,y= }
\fp_to_decimal:N \g_tmpa_fp
\exp_not:n { ) coordinate (LSW) (visualization~cs }
\token_to_str:N : \exp_not:n { x= }
\fp_eval:n {
\l_@@_graph_legend_x_tl +
\l_@@_graph_legend_w_tl
}
\exp_not:n { ,y= }
\fp_eval:n { \g_tmpa_fp + \g_tmpb_fp }
\exp_not:n { ) coordinate (LNE);
\node[ fit=(LSW)~(LNE), draw, inner~sep=0pt,
}
\exp_not:V \l_@@_graph_options_histogram_tl
\exp_not:N ,
\exp_not:V \l_@@_graph_options_legend_tl
\exp_not:n { ] {}; }
}
}
% \end{macrocode}
%
% Create the picture itself
%
% \begin{macrocode}
\@@_graph_handle_hmargin:
\@@_graph_handle_vmargin:
\tl_set:Nx \l_@@_graph_tikzpicture_tl {
\exp_not:n { \begin{tikzpicture}[ }
\exp_not:V \l_@@_graph_options_pic_tl
\exp_not:n { ] \datavisualization
[scientific~axes = } {
\exp_not:V
\l_@@_graph_options_system_tl
}
\exp_not:n { , x~axis = } {
\exp_not:n { include~value/.list = } {
\exp_not:V \l_@@_graph_tikzincludex_clist
}
\exp_not:n { , ticks = { tick~typesetter/.code = {
$\@@_graph_values_format:n { \fp_eval:n{####1} }$ }}, }
\exp_not:V
\l_@@_graph_options_histogram_xaxis_tl
\exp_not:n { , }
\exp_not:V
\c_@@_graph_savexstep_tl
}
\exp_not:n { , y~axis = } {
\exp_not:n { include~value/.list = } {
\exp_not:V \l_@@_graph_tikzincludey_clist
}
\exp_not:n { , }
\exp_not:V
\l_@@_graph_options_yaxis_tl
}
\exp_not:n { , visualize~as~line = histogram,
histogram = } {
\exp_not:n { polygon, style = } {
\exp_not:V \l_@@_graph_options_histogram_tl
} }
\exp_not:n { ] data [set = histogram, format = TeX~code] } {
\exp_not:V \l_@@_graph_tikzdata_tl
}
\exp_not:n { info' } {
\exp_not:V \l_@@_graph_userpreinfo_tl
}
\exp_not:n { info } {
\exp_not:V \l_@@_graph_tikzinfo_tl
\exp_not:V \l_@@_graph_userpostinfo_tl
}
\exp_not:n { ; \end{tikzpicture} }
}
\tl_use:N \l_@@_graph_tikzpicture_tl
}
\cs_new_protected_nopar:Nn \@@_graph_make_hist:n {
\@@_graph_make_hist:nn { #1 } { 1 }
}
\cs_new_protected_nopar:Nn \@@_graph_make_hist:nn {
\int_incr:N \l_@@_currange_int
% \end{macrocode}
%
% Extract interval data
%
% \begin{macrocode}
\@@_parse_range:w #1 \q_stop
% \end{macrocode}
%
% Compute rectangle height
%
% \begin{macrocode}
\fp_set:Nn \l_@@_graph_curheight_fp {
(#2) / ( \l_@@_range_max_fp -
\l_@@_range_min_fp)
}
% \end{macrocode}
%
% Add margins to axes
%
% \begin{macrocode}
\@@_graph_update_minmaxval:NN \l_@@_range_min_fp \l_@@_range_max_fp
\@@_graph_update_maxheight:
% \end{macrocode}
%
% Check if we want to show this element
%
% \begin{macrocode}
\@@_set_if_shown:N \l_tmpa_bool
% \end{macrocode}
%
% Append the rectangle to the TikZ datavisualization content
%
% \begin{macrocode}
\@@_graph_addpoint:nnn { SW }
{ \l_@@_range_min_fp }
{ 0 }
\bool_if:NF \l_tmpa_bool {
% \end{macrocode}
%
% Add an outlier point to inhibit the rectangle drawing
%
% \begin{macrocode}
\@@_graph_outlier:
}
\@@_graph_addpoint:nnn { NW }
{ \l_@@_range_min_fp }
{ \l_@@_graph_curheight_fp }
\bool_if:NF \l_tmpa_bool { \@@_graph_outlier: }
\@@_graph_addpoint:nnn { NE }
{ \l_@@_range_max_fp }
{ \l_@@_graph_curheight_fp }
\bool_if:NF \l_tmpa_bool { \@@_graph_outlier: }
\@@_graph_addpoint:nnn { SE }
{ \l_@@_range_max_fp }
{ 0 }
\bool_if:NT \l_tmpa_bool {
% \end{macrocode}
%
% Maybe append a freq or count label on middle top of the rect
%
% \begin{macrocode}
\bool_if:NT \l_@@_graph_areas_bool {
\@@_graph_addlabel:nn
\@@_graph_y_format:n
{ \fp_eval:n {#2 / \l_@@_graph_scale_fp} }
}
}
\@@_graph_outlier:
}
\cs_new_protected_nopar:Nn \@@_graph_addlabel:nn {
\tl_put_right:Nx \l_@@_graph_tikzinfo_tl {
\exp_not:n { \path (NW }
\int_use:N \l_@@_currange_int
\exp_not:n { ) -- node[ }
\exp_not:V \l_@@_graph_options_areas_tl
\exp_not:N ] {
\exp_not:n { $ #1 } { #2 } \exp_not:N $
} \exp_not:n { (NE }
\int_use:N \l_@@_currange_int
\exp_not:n { ); }
}
}
% \end{macrocode}
%
% second pass, comb
%
% \begin{macrocode}
\cs_new_protected:Nn \@@_graph_dopicture_comb: {
\@@_graph_setup:n {comb}
% \end{macrocode}
%
% Loop through the list again to fill tikz data and labels
%
% \begin{macrocode}
\keyval_parse:NNV
\@@_graph_make_comb:n
\@@_graph_make_comb:nn
\l_@@_data_tl
% \end{macrocode}
%
% Create the picture itself
%
% \begin{macrocode}
\@@_graph_handle_hmargin:
\@@_graph_handle_vmargin:
\tl_set:Nx \l_@@_graph_tikzpicture_tl {
\exp_not:n { \begin{tikzpicture}[ }
\exp_not:V \l_@@_graph_options_pic_tl
\exp_not:n { ] \datavisualization
[scientific~axes = } {
\exp_not:V
\l_@@_graph_options_system_tl
}
\exp_not:n { , x~axis = } {
\exp_not:n { include~value/.list = } {
\exp_not:V \l_@@_graph_tikzincludex_clist
}
\exp_not:n { , ticks = { tick~typesetter/.code = {
$\@@_graph_values_format:n { \fp_eval:n{####1} }$ }}, }
\exp_not:V
\l_@@_graph_options_comb_xaxis_tl
\exp_not:n { , }
\exp_not:V
\c_@@_graph_savexstep_tl
}
\exp_not:n { , y~axis = } {
\exp_not:n { include~value/.list = } {
\exp_not:V \l_@@_graph_tikzincludey_clist
}
\exp_not:n { , }
\exp_not:n { , ticks = { tick~typesetter/.code = {
$\@@_graph_y_format:n { \fp_eval:n{####1} }$ }}, }
\exp_not:V
\l_@@_graph_options_yaxis_tl
}
\exp_not:n { , visualize~as~line = bar~graph,
bar~graph = } {
\exp_not:n { style = } {
\exp_not:V \l_@@_graph_options_comb_tl
} }
\exp_not:n { ] data [set = bar~graph, format = TeX~code] } {
\exp_not:V \l_@@_graph_tikzdata_tl
}
\exp_not:n { info' } {
\exp_not:V \l_@@_graph_userpreinfo_tl
}
\exp_not:n { info } {
\exp_not:V \l_@@_graph_tikzinfo_tl
\exp_not:V \l_@@_graph_userpostinfo_tl
}
\exp_not:n { ; \end{tikzpicture} }
}
\tl_use:N \l_@@_graph_tikzpicture_tl
}
\cs_new_protected_nopar:Nn \@@_graph_make_comb:n {
\@@_graph_make_comb:nn { #1 } { 1 }
}
\cs_new_protected_nopar:Nn \@@_graph_make_comb:nn {
\int_incr:N \l_@@_currange_int
% \end{macrocode}
%
% Set value
%
% \begin{macrocode}
\fp_set:Nn \l_@@_graph_curvalue_fp {
#1
}
% \end{macrocode}
%
% Compute height
%
% \begin{macrocode}
\fp_set:Nn \l_@@_graph_curheight_fp {
(#2) / \l_@@_graph_scale_fp
}
% \end{macrocode}
%
% Add margins to axes
%
% \begin{macrocode}
\@@_graph_update_minmaxval:NN
\l_@@_graph_curvalue_fp \l_@@_graph_curvalue_fp
\@@_graph_update_maxheight:
% \end{macrocode}
%
% Check if we want to show this element
%
% \begin{macrocode}
\@@_set_if_shown:N \l_tmpa_bool
% \end{macrocode}
%
% Append the bar to the TikZ datavisualization content
%
% \begin{macrocode}
\@@_graph_addpoint:nnn { S }
{ \l_@@_graph_curvalue_fp }
{ 0 }
\bool_if:NF \l_tmpa_bool {
% \end{macrocode}
%
% add an outlier to inhibit the bar drawing
%
% \begin{macrocode}
\@@_graph_outlier:
}
\@@_graph_addpoint:nnn { N }
{ \l_@@_graph_curvalue_fp }
{ \l_@@_graph_curheight_fp }
\@@_graph_outlier:
}
% \end{macrocode}
%
% second pass, cumulative
%
% \begin{macrocode}
\cs_new_protected_nopar:Nn \@@_graph_dopicture_cumulative: {
\@@_graph_setup:n {cumulative}
% \end{macrocode}
%
% Increasing or decreasing starting point
%
% \begin{macrocode}
\bool_if:NTF \l_@@_graph_decreasing_bool {
\fp_set_eq:NN \l_@@_curtotal_fp
\l_@@_total_fp
}{
\fp_zero:N \l_@@_curtotal_fp
}
\fp_set:Nn \l_@@_graph_curheight_fp {
\l_@@_curtotal_fp
/ \l_@@_graph_scale_fp
}
\@@_graph_update_maxheight:
% \end{macrocode}
%
% Loop through the list again to fill tikz data and labels
%
% \begin{macrocode}
\keyval_parse:NNV
\@@_graph_make_cumulative:n
\@@_graph_make_cumulative:nn
\l_@@_data_tl
% \end{macrocode}
%
% After the last point we should be piecewise constant, which is the $N+1$-th
% item for |showonly| purposes. We call \cs{@@_graph_handle_hmargin:} even if we
% will add actual data in the margin, because that method computes the correct
% value for the margin from the options.
%
% \begin{macrocode}
\@@_graph_handle_hmargin:
\int_incr:N \l_@@_currange_int
\@@_set_if_shown:N \l_tmpa_bool
\bool_if:NF \l_tmpa_bool { \@@_graph_outlier: }
\@@_graph_addpoint:nnn { E }
{ \l_@@_graph_maxvalue_fp + \g_tmpa_fp }
{ \l_@@_graph_curheight_fp }
% \end{macrocode}
%
% Before the first point we should be piecewise constant. We stash the TikZ data
% away to prepend the first point and maybe an outlier if the segment should be
% hidden, then append the stashed data. The initial segment is numbered~$0$.
%
% \begin{macrocode}
\tl_set_eq:NN \l_tmpa_tl \l_@@_graph_tikzdata_tl
\tl_clear:N \l_@@_graph_tikzdata_tl
\int_zero:N \l_@@_currange_int
\@@_graph_addpoint:nnn { B }
{ \l_@@_graph_minvalue_fp - \g_tmpa_fp }
{ \l_@@_graph_maxheight_fp - \l_@@_graph_curheight_fp }
\@@_set_if_shown:N \l_tmpa_bool
\bool_if:NF \l_tmpa_bool { \@@_graph_outlier: }
\tl_put_right:NV \l_@@_graph_tikzdata_tl \l_tmpa_tl
% \end{macrocode}
%
% Create the picture itself
%
% \begin{macrocode}
\@@_graph_handle_vmargin:
\tl_set:Nx \l_@@_graph_tikzpicture_tl {
\exp_not:n { \begin{tikzpicture}[ }
\exp_not:V \l_@@_graph_options_pic_tl
\exp_not:n { ] \datavisualization
[scientific~axes = } {
\exp_not:V
\l_@@_graph_options_system_tl
}
\exp_not:n { , x~axis = } {
\exp_not:n { include~value/.list = } {
\exp_not:V \l_@@_graph_tikzincludex_clist
}
\exp_not:n { , ticks = { tick~typesetter/.code = {
$\@@_graph_values_format:n { \fp_eval:n{####1} }$ }}, }
\exp_not:V
\l_@@_graph_options_cumulative_xaxis_tl
\exp_not:n { , }
\exp_not:V
\c_@@_graph_savexstep_tl
}
\exp_not:n { , y~axis = } {
\exp_not:n { include~value/.list = } {
\exp_not:V \l_@@_graph_tikzincludey_clist
}
\exp_not:n { , }
\exp_not:n { , ticks = { tick~typesetter/.code = {
$\@@_graph_y_format:n { \fp_eval:n{####1} }$ }}, }
\exp_not:V
\l_@@_graph_options_yaxis_tl
}
\exp_not:n { , visualize~as~line = cumulative,
cumulative = } {
\exp_not:n { style = } {
\exp_not:V \l_@@_graph_options_cumulative_tl
} }
\exp_not:n { ] data [set = cumulative, format = TeX~code] } {
\exp_not:V \l_@@_graph_tikzdata_tl
}
\exp_not:n { info' } {
\exp_not:V \l_@@_graph_userpreinfo_tl
}
\exp_not:n { info } {
\exp_not:V \l_@@_graph_tikzinfo_tl
\exp_not:V \l_@@_graph_userpostinfo_tl
}
\exp_not:n { ; \end{tikzpicture} }
}
\tl_use:N \l_@@_graph_tikzpicture_tl
}
\cs_new_protected_nopar:Nn \@@_graph_make_cumulative:n {
\@@_graph_make_hist:nn { #1 } { 1 }
}
\cs_new_protected_nopar:Nn \@@_graph_make_cumulative:nn {
% \end{macrocode}
%
% Extract interval data
%
% \begin{macrocode}
\@@_parse_range:w #1 \q_stop
% \end{macrocode}
%
% Compute running total and new height
%
% \begin{macrocode}
\fp_set_eq:NN
\l_@@_graph_prevheight_fp
\l_@@_graph_curheight_fp
\bool_if:NTF \l_@@_graph_decreasing_bool {
\fp_sub:Nn \l_@@_curtotal_fp { #2 }
}{
\fp_add:Nn \l_@@_curtotal_fp { #2 }
}
\fp_set:Nn \l_@@_graph_curheight_fp {
\l_@@_curtotal_fp
/ \l_@@_graph_scale_fp
}
\@@_graph_update_minmaxval:NN \l_@@_range_min_fp \l_@@_range_max_fp
\@@_graph_update_maxheight:
% \end{macrocode}
%
% Add points
%
% \begin{macrocode}
\int_incr:N \l_@@_currange_int
\@@_graph_addpoint:nnn { L }
{ \l_@@_range_min_fp }
{ \l_@@_graph_prevheight_fp }
% \end{macrocode}
%
% If we don't want to show this segment, add an outlier so that the
% line is not drawn.
%
% \begin{macrocode}
\@@_set_if_shown:N \l_tmpa_bool
\bool_if:NF \l_tmpa_bool { \@@_graph_outlier: }
\@@_graph_addpoint:nnn { R }
{ \l_@@_range_max_fp }
{ \l_@@_graph_curheight_fp }
% \end{macrocode}
%
% TODO: Median and co
%
% \begin{macrocode}
}
% \end{macrocode}
%
% \subsection{Consolitate and sort values}
%
% \begin{macrocode}
\clist_new:N \l_@@_compute_data_clist
\int_new:N \l_@@_compute_count_int
\fp_new:N \l_@@_compute_curvalue_fp
\seq_new:N \l_@@_data_seq
\NewDocumentCommand \StatsSortData { +O{} u{=} m +O{} } {
\group_begin:
% \end{macrocode}
%
% Handle optional settings (there are none currently)
% |\@@_setup:nn { rangedata } { #1, #5 }|
% Get the data inline or from a variable
%
% \begin{macrocode}
\tl_if_single:nTF { #3 } {
% \end{macrocode}
%
% Generate meaningful error by using the non-existent variable.
%
% \begin{macrocode}
\cs_if_exist:NF #3 { #3 }
\tl_set_eq:NN \l_@@_data_tl #3
}{
\tl_set:Nn \l_@@_data_tl { #3 }
}
% \end{macrocode}
%
% Sort the data according to values.
% We go through sequences because \cs{clist_sort:Nn} puts braces around the
% elements which prevents \cs{keyval_parse:NNn} to detect the equal sign.
%
% \begin{macrocode}
\seq_set_from_clist:NN \l_@@_data_seq \l_@@_data_tl
\seq_sort:Nn \l_@@_data_seq {
\seq_set_split:Nnn \l_tmpa_seq {=} { ##1 }
\seq_set_split:Nnn \l_tmpb_seq {=} { ##2 }
\fp_compare:nNnTF
{ \seq_item:Nn \l_tmpa_seq {1} } > { \seq_item:Nn \l_tmpb_seq {1} }
{
\sort_return_swapped:
}{
\sort_return_same:
}
}
% \end{macrocode}
%
% Append a sentinel NaN to ensure the last value is not trimmed. This value is
% particularly suitable because NaN is equal to no fp (even itself).
%
% \begin{macrocode}
\seq_put_right:Nn \l_@@_data_seq { nan = 0 }
\tl_set:Nx \l_@@_data_tl { \seq_use:Nn \l_@@_data_seq {,} }
% \end{macrocode}
%
% Build the resulting clist while grouping equal values
%
% \begin{macrocode}
\clist_clear:N \l_@@_compute_data_clist
\int_zero:N \l_@@_compute_count_int
\fp_zero:N \l_@@_compute_curvalue_fp
\keyval_parse:NNV
\@@_accumulate:n
\@@_accumulate:nn
\l_@@_data_tl
\exp_args:NNNV
\group_end:
\clist_set:Nn #2 \l_@@_compute_data_clist
}
\cs_new_protected_nopar:Nn \@@_accumulate:n {
\@@_accumulate:nn { #1 } { 1 }
}
\cs_new_protected_nopar:Nn \@@_accumulate:nn {
\fp_compare:nNnTF { #1 } = { \l_@@_compute_curvalue_fp } {
\int_add:Nn \l_@@_compute_count_int { #2 }
}{
\int_compare:nNnT { \l_@@_compute_count_int } > { 0 } {
\clist_put_right:Nx \l_@@_compute_data_clist {
\fp_to_decimal:N \l_@@_compute_curvalue_fp
\exp_not:n { = }
\exp_not:V \l_@@_compute_count_int
}
}
\fp_set:Nn \l_@@_compute_curvalue_fp { #1 }
\int_set:Nn \l_@@_compute_count_int { #2 }
}
}
% \end{macrocode}
%
% \subsection{Count values in ranges to generate grouped counts}
%
% \begin{macrocode}
\NewDocumentCommand \StatsRangeData { +O{} u{=} m +r() +O{} } {
\group_begin:
% \end{macrocode}
%
% Handle optional settings (there are none currently)
% |\@@_setup:nn { rangedata } { #1, #5 }|
% Get the data inline or from a variable
%
% \begin{macrocode}
\tl_if_single:nTF { #3 } {
% \end{macrocode}
%
% Generate meaningful error by using the non-existent variable.
%
% \begin{macrocode}
\cs_if_exist:NF #3 { #3 }
\tl_set_eq:NN \l_@@_data_tl #3
}{
\tl_set:Nn \l_@@_data_tl { #3 }
}
% \end{macrocode}
%
% Loop through the ranges and count values into them
%
% \begin{macrocode}
\clist_clear:N \l_@@_compute_data_clist
\clist_map_inline:nn { #4 } {
% \end{macrocode}
%
% If not a range, bail out
%
% \begin{macrocode}
\exp_args:Nx \tl_if_eq:nnF { \tl_head:n {##1} }{ \IN } {
% \end{macrocode}
%
% TODO: error message
%
% \begin{macrocode}
\clist_map_break:
}
% \end{macrocode}
%
% Extract interval data
%
% \begin{macrocode}
\@@_parse_range_full:w ##1 \q_stop
% \end{macrocode}
%
% Loop through the point data and count matching values
%
% \begin{macrocode}
\int_zero:N \l_@@_compute_count_int
\keyval_parse:NNV
\@@_range_count:n
\@@_range_count:nn
\l_@@_data_tl
\clist_put_right:Nx \l_@@_compute_data_clist {
\exp_not:n { ##1 = }
\exp_not:V \l_@@_compute_count_int
}
}
\exp_args:NNNV
\group_end:
\clist_set:Nn #2 \l_@@_compute_data_clist
}
\cs_new_protected_nopar:Nn \@@_range_count:n {
\@@_range_count:nn { #1 } { 1 }
}
\cs_new_protected_nopar:Nn \@@_range_count:nn {
\@@_if_in_range:nT { #1 } {
\int_add:Nn \l_@@_compute_count_int { #2 }
}
}
%</package>
% \end{macrocode}
%
% \end{implementation}