3 ;;; Time-stamp: <2010-02-10 14:23:42 tony>
4 ;;; Creation: <2009-04-19 09:41:09 tony>
5 ;;; File: basic-eda.lisp
6 ;;; Author: AJ Rossini <blindglobe@gmail.com>
7 ;;; Copyright: (c)2009--, AJ Rossini. BSD, MIT, LLGPL, or
8 ;;; GPLv2+, or GPLv3+ depending on how it arrives.
9 ;;; Purpose: Example of basic exploratory data analysis in CLS.
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.
15 (in-package :cls-examples
)
17 ;; We assume that the "loading-data.lisp" code has been run, and one
18 ;; now wants to analyze the data loaded into *chickwts-df*
20 (load (localized-pathto "loading-data.lisp")
25 ;; Summarize is the basic EDA tool -- it accepts symbols or lists of
26 ;; symbols, to describe what, when, and how to do it. The resulting
27 ;; data structure has a means for re-invoking the result as well as
28 ;; partial storage of key results (when appropriate) as well as
29 ;; metadata about the results (time / context if provided).
31 ;; numerical: (txt / *ml / , variable / stream / spec'd to file)
32 ;; visual: (static/dynamic, fixed/interactive) (need better term than fixed)
34 ;; context -- using dataset metadata, to drive the resulting summary.
36 ;; #1 sampling scheme -
37 ;; retro / prospect collection
38 ;; random, biased, convenience sampling;
39 ;; #2 purpose of dataset integration/manipulation
40 ;; #3 sampling/temporal component of variables
43 (defparameter *my-df-smry-num
*
44 (summarize *chickwts
* :type
'numerical
:io
'listing
)
45 "First numerical summary of *my-df-smry*")
47 (defparameter *my-df-smry-num
*
51 :device
'(file "output.pdf"))
52 "First numerical summary of *my-df-smry*")
54 (defparameter *my-df-smry-vis
*
61 (defparameter *my-df-smry-vis
*
62 (summarize *my-df
* :type
'visual
:io
'interactive-dynamic
)
65 (defparameter *my-df-smry-vis
*
66 (summarize *my-df
* :type
'visual
:io
'static
)