examples/loading-data.lisp

   1 ;;; -*- mode: lisp -*-
   2
   3 ;;; Time-stamp: <2010-01-15 07:56:57 tony>
   4 ;;; Creation:   <2009-03-12 17:14:56 tony>
   5 ;;; File:       template.lisp
   6 ;;; Author:     AJ Rossini <blindglobe@gmail.com>
   7 ;;; Copyright:  (c)2009--, AJ Rossini.  BSD, LLGPL, or GPLv2, depending
   8 ;;;             on how it arrives.
   9 ;;; Purpose:    Template header file
  10
  11 ;;; What is this talk of 'release'? Klingons do not make software
  12 ;;; 'releases'.  Our software 'escapes', leaving a bloody trail of
  13 ;;; designers and quality assurance people in its wake.
  14
  15 ;; start within the common-lisp-stat-user
  16 (in-package :cls-user)
  17
  18 ;; we'll be loading from directories in the CLS homedir, so we want to
  19 ;; make it easier to reach.
  20 (defun localized-pathto (x)
  21   "return a string denoting the complete path.
  22 FIXME: UNIX-centric (though might work on Mac OSX).  Might want to
  23 return a pathspec, not a string/namespec"
  24   (check-type x string)
  25   (concatenate 'string *cls-home-dir* x))
  26
  27
  28
  29 (progn
  30   ;; LISP-STAT COMPATIBILITY MODE:
  31   ;;
  32   ;; FIXME: Need to clean up data examples, licenses, attributions, etc.
  33   ;; The following breaks because we should use a package to hold
  34   ;; configuration details, and this would be the only package outside
  35   ;; of packages.lisp, as it holds the overall defsystem structure.
  36   (load-data "iris.lsp")  ;; (the above partially fixed).
  37   diabetes
  38   (variables))
  39
  40
  41
  42
  43 (progn
  44   ;; COMMON LISP STATISTICS
  45   ;;
  46   ;; Importing data from DSV text files.
  47
  48 #|
  49
  50   We use as an example a simple R datasert, chickwts, which has one
  51   nominal categorical variable and one continuous categorical
  52   variable.   This dataset can be accessed in R as follows:
  53
  54 > data(chickwts)
  55 > dim(chickwts)
  56 [1] 71  2
  57 > summary(chickwts)
  58      weight             feed
  59  Min.   :108.0   casein   :12
  60  1st Qu.:204.5   horsebean:10
  61  Median :258.0   linseed  :12
  62  Mean   :261.3   meatmeal :11
  63  3rd Qu.:323.5   soybean  :14
  64  Max.   :423.0   sunflower:12
  65 >
  66 |#
  67
  68   (defparameter *chickwts-df* (filename.dsv->dataframe (localized-pathto "Data/R-chickwts.csv")))
  69   ;; *chickwts-df*
  70   (xref *chickwts-df* 1 1) ; => 160
  71   (xref *chickwts-df* 40 2) ; => "sunflower"
  72   )
  73