.\" -*- mode: troff; coding: utf-8 -*-
.\" Automatically generated by Pod::Man 5.01 (Pod::Simple 3.43)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" \*(C` and \*(C' are quotes in nroff, nothing in troff, for use with C<>.
.ie n \{\
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds C`
.    ds C'
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is >0, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.\"
.\" Avoid warning from groff about undefined register 'F'.
.de IX
..
.nr rF 0
.if \n(.g .if rF .nr rF 1
.if (\n(rF:(\n(.g==0)) \{\
.    if \nF \{\
.        de IX
.        tm Index:\\$1\t\\n%\t"\\$2"
..
.        if !\nF==2 \{\
.            nr % 0
.            nr F 2
.        \}
.    \}
.\}
.rr rF
.\" ========================================================================
.\"
.IX Title "DBD::SQLite::Cookbook 3pm"
.TH DBD::SQLite::Cookbook 3pm 2024-01-10 "perl v5.38.2" "User Contributed Perl Documentation"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH NAME
DBD::SQLite::Cookbook \- The DBD::SQLite Cookbook
.SH DESCRIPTION
.IX Header "DESCRIPTION"
This is the DBD::SQLite cookbook.
.PP
It is intended to provide a place to keep a variety of functions and
formals for use in callback APIs in DBD::SQLite.
.SH "AGGREGATE FUNCTIONS"
.IX Header "AGGREGATE FUNCTIONS"
.SS Variance
.IX Subsection "Variance"
This is a simple aggregate function which returns a variance. It is
adapted from an example implementation in pysqlite.
.PP
.Vb 1
\&  package variance;
\&  
\&  sub new { bless [], shift; }
\&  
\&  sub step {
\&      my ( $self, $value ) = @_;
\&  
\&      push @$self, $value;
\&  }
\&  
\&  sub finalize {
\&      my $self = $_[0];
\&  
\&      my $n = @$self;
\&  
\&      # Variance is NULL unless there is more than one row
\&      return undef unless $n || $n == 1;
\&  
\&      my $mu = 0;
\&      foreach my $v ( @$self ) {
\&          $mu += $v;
\&      }
\&      $mu /= $n;
\&  
\&      my $sigma = 0;
\&      foreach my $v ( @$self ) {
\&          $sigma += ($v \- $mu)**2;
\&      }
\&      $sigma = $sigma / ($n \- 1);
\&  
\&      return $sigma;
\&  }
\&  
\&  # NOTE: If you use an older DBI (< 1.608),
\&  # use $dbh\->func(..., "create_aggregate") instead.
\&  $dbh\->sqlite_create_aggregate( "variance", 1, \*(Aqvariance\*(Aq );
.Ve
.PP
The function can then be used as:
.PP
.Vb 3
\&  SELECT group_name, variance(score)
\&  FROM results
\&  GROUP BY group_name;
.Ve
.SS "Variance (Memory Efficient)"
.IX Subsection "Variance (Memory Efficient)"
A more efficient variance function, optimized for memory usage at the
expense of precision:
.PP
.Vb 1
\&  package variance2;
\&  
\&  sub new { bless {sum => 0, count=>0, hash=> {} }, shift; }
\&  
\&  sub step {
\&      my ( $self, $value ) = @_;
\&      my $hash = $self\->{hash};
\&  
\&      # by truncating and hashing, we can comsume many more data points
\&      $value = int($value); # change depending on need for precision
\&                            # use sprintf for arbitrary fp precision
\&      if (exists $hash\->{$value}) {
\&          $hash\->{$value}++;
\&      } else {
\&          $hash\->{$value} = 1;
\&      }
\&      $self\->{sum} += $value;
\&      $self\->{count}++;
\&  }
\&  
\&  sub finalize {
\&      my $self = $_[0];
\&  
\&      # Variance is NULL unless there is more than one row
\&      return undef unless $self\->{count} > 1;
\&  
\&      # calculate avg
\&      my $mu = $self\->{sum} / $self\->{count};
\&  
\&      my $sigma = 0;
\&      while (my ($h, $v) = each %{$self\->{hash}}) {
\&          $sigma += (($h \- $mu)**2) * $v;
\&      }
\&      $sigma = $sigma / ($self\->{count} \- 1);
\&  
\&      return $sigma;
\&  }
.Ve
.PP
The function can then be used as:
.PP
.Vb 3
\&  SELECT group_name, variance2(score)
\&  FROM results
\&  GROUP BY group_name;
.Ve
.SS "Variance (Highly Scalable)"
.IX Subsection "Variance (Highly Scalable)"
A third variable implementation, designed for arbitrarily large data sets:
.PP
.Vb 1
\&  package variance3;
\&  
\&  sub new { bless {mu=>0, count=>0, S=>0}, shift; }
\&  
\&  sub step {
\&      my ( $self, $value ) = @_;
\&      $self\->{count}++;
\&      my $delta = $value \- $self\->{mu};
\&      $self\->{mu} += $delta/$self\->{count};
\&      $self\->{S} += $delta*($value \- $self\->{mu});
\&  }
\&  
\&  sub finalize {
\&      my $self = $_[0];
\&      return $self\->{S} / ($self\->{count} \- 1);
\&  }
.Ve
.PP
The function can then be used as:
.PP
.Vb 3
\&  SELECT group_name, variance3(score)
\&  FROM results
\&  GROUP BY group_name;
.Ve
.SH SUPPORT
.IX Header "SUPPORT"
Bugs should be reported via the CPAN bug tracker at
.PP
<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=DBD\-SQLite>
.SH "TO DO"
.IX Header "TO DO"
.IP \(bu 4
Add more and varied cookbook recipes, until we have enough to
turn them into a separate CPAN distribution.
.IP \(bu 4
Create a series of tests scripts that validate the cookbook recipes.
.SH AUTHOR
.IX Header "AUTHOR"
Adam Kennedy <adamk@cpan.org>
.SH COPYRIGHT
.IX Header "COPYRIGHT"
Copyright 2009 \- 2012 Adam Kennedy.
.PP
This program is free software; you can redistribute
it and/or modify it under the same terms as Perl itself.
.PP
The full text of the license can be found in the
LICENSE file included with this module.