merging incanter

README.textile

@@ -60,9 +60,9 @@ The online documentation for most Incanter functions contain usage examples. The
 ** "Datasets":http://wiki.github.com/liebke/incanter/datasets
 ** "Statistics examples":http://wiki.github.com/liebke/incanter/statistics-examples
 ** "Probability distributions":http://wiki.github.com/liebke/incanter/probability-distributions
-* See the @examples/@ directory and @tests/test-cases.clj@ for additional usage examples
+* See the @examples/@ directory and @test/incanter/*-tests.clj@ for additional usage examples
 ** Run @examples/run_prob_plots.clj@ to generate example probability distribution plots
-** Run @tests/runtests.clj@ to run test cases
+** Run @bin/runtests.clj@ to run test cases
 
 
 <a name="docs"></a>
@@ -92,7 +92,7 @@ To build Incanter, test it, and generate the api documentation yourself, run the
 * cd into the incanter directory
 * Download and uncompress Incanter's dependencies: @ant deps@
 * Build incanter.jar: @ant@
-* Run unit tests: @tests/runtests.clj@
+* Run unit tests: @bin/runtests.clj@
 * Generate API docs: @bin/generate_docs.clj@
 
 (Note: the @bin/clj@ and @*.clj@ scripts won't run on Windows systems as is. Although, the Clojure code contained in the @*.clj@ scripts can be run from the Clojure shell.)

bin/clj

@@ -17,12 +17,12 @@ JFREECHART_JARS=$INCANTER_LIB_DIR/jfreechart-1.0.13.jar:$INCANTER_LIB_DIR/jcommo
 OPENCSV_JARS=$INCANTER_LIB_DIR/opencsv-1.8.jar
 PROCESSING_JARS=$INCANTER_LIB_DIR/processing/core.jar:$INCANTER_LIB_DIR/processing/
 
-echo "java -server -cp .:..:$INCANTER_JAR:$COLT_JARS:$JLINE_JARS:$CLOJURE_JARS:$JFREECHART_JARS:$OPENCSV_JARS:$PROCESSING_JARS -Dclojure.compile.path=$CLASSES_DIR -Dincanter.home=$INCANTER_HOME jline.ConsoleRunner clojure.main"
+TESTS_DIR=$INCANTER_HOME/test
 
 if [ -z "$1" ]; then
-        java -server -cp .:..:$INCANTER_JAR:$COLT_JARS:$JLINE_JARS:$CLOJURE_JARS:$JFREECHART_JARS:$OPENCSV_JARS:$PROCESSING_JARS -Dclojure.compile.path=$CLASSES_DIR -Dincanter.home=$INCANTER_HOME jline.ConsoleRunner clojure.main
+        java -server -cp .:..:$INCANTER_JAR:$COLT_JARS:$JLINE_JARS:$CLOJURE_JARS:$JFREECHART_JARS:$OPENCSV_JARS:$PROCESSING_JARS:$TESTS_DIR -Dclojure.compile.path=$CLASSES_DIR -Dincanter.home=$INCANTER_HOME jline.ConsoleRunner clojure.main
 else
         scriptname=$1
-        java -server -cp .:..:$INCANTER_JAR:$COLT_JARS:$JLINE_JARS:$CLOJURE_JARS:$JFREECHART_JARS:$OPENCSV_JARS:$PROCESSING_JARS -Dclojure.compile.path=$CLASSES_DIR -Dincanter.home=$INCANTER_HOME clojure.lang.Script $scriptname -- $*
+        java -server -cp .:..:$INCANTER_JAR:$COLT_JARS:$JLINE_JARS:$CLOJURE_JARS:$JFREECHART_JARS:$OPENCSV_JARS:$PROCESSING_JARS:$TESTS_DIR -Dclojure.compile.path=$CLASSES_DIR -Dincanter.home=$INCANTER_HOME clojure.lang.Script $scriptname -- $*
 fi
 

bin/runtests.clj

@@ -0,0 +1,26 @@
+#!/usr/bin/env bin/clj
+
+
+;;; test-incanter.clj -- Unit tests of Incanter functions
+
+;; by David Edgar Liebke http://incanter.org
+;; March 12, 2009
+
+;; Copyright (c) David Edgar Liebke, 2009. All rights reserved.  The use
+;; and distribution terms for this software are covered by the Eclipse
+;; Public License 1.0 (http://opensource.org/licenses/eclipse-1.0.php)
+;; which can be found in the file epl-v10.html at the root of this
+;; distribution.  By using this software in any fashion, you are
+;; agreeing to be bound by the terms of this license.  You must not
+;; remove this notice, or any other, from this software.
+
+;; CHANGE LOG
+;; March 12, 2009: First version
+
+
+(ns test.runtests
+  (:use [clojure.test :only (run-tests)]
+        (incanter tests)))
+
+(run)
+

examples/blog/annotations.clj

@@ -0,0 +1,64 @@
+;; from the following blog post
+;; http://incanter-blog.org/2009/06/07/annotating-incanter-plots/
+
+(use '(incanter core charts))
+
+(def x (range (* -2 Math/PI) (* 2 Math/PI) 0.01))
+(def plot (xy-plot x (sin x)))
+(view plot)
+
+;; annotate the plot
+(doto plot
+  (add-pointer (- Math/PI) (sin (- Math/PI)) 
+               :text "(-pi, (sin -pi))")
+  (add-pointer Math/PI (sin Math/PI) 
+               :text "(pi, (sin pi))" :angle :ne)
+  (add-pointer (* 1/2 Math/PI) (sin (* 1/2 Math/PI)) 
+               :text "(pi/2, (sin pi/2))" :angle :south))
+
+
+;; try the different angle options
+(doto plot
+  (add-pointer 0 0 :text "north" :angle :north)
+  (add-pointer 0 0 :text "nw" :angle :nw)
+  (add-pointer 0 0 :text "ne" :angle :ne)
+  (add-pointer 0 0 :text "west" :angle :west)
+  (add-pointer 0 0 :text "east" :angle :east)
+  (add-pointer 0 0 :text "south" :angle :south)
+  (add-pointer 0 0 :text "sw" :angle :sw)
+  (add-pointer 0 0 :text "se" :angle :se))
+
+
+
+;; PCA chart example
+(use '(incanter core stats charts datasets))
+;; load the iris dataset
+(def iris (to-matrix (get-dataset :iris)))
+;; run the pca
+(def pca (principal-components (sel iris :cols (range 4))))
+;; extract the first two principal components
+(def pc1 (sel (:rotation pca) :cols 0))
+(def pc2 (sel (:rotation pca) :cols 1))
+
+;; project the first four dimension of the iris data onto the first
+;; two principal components
+(def x1 (mmult (sel iris :cols (range 4)) pc1)) 
+(def x2 (mmult (sel iris :cols (range 4)) pc2)) 
+
+;; now plot the transformed data, coloring each species a different color
+(def plot (scatter-plot x1 x2 
+            :group-by (sel iris :cols 4)
+            :x-label "PC1" :y-label "PC2" :title "Iris PCA"))
+
+(view plot)
+
+
+;; add some text annotations
+(doto plot
+  (add-text -2.5 -6.5 "Setosa")
+  (add-text -5 -5.5 "Versicolor") 
+  (add-text -8 -5.5 "Virginica"))
+
+;; put box around the first group
+(add-polygon plot [[-3.2 -6.3] [-2 -6.3] [-2 -3.78] [-3.2 -3.78]])
+

examples/blog/bayesian_multinomial.clj

@@ -0,0 +1,50 @@
+;; from the following blog post:
+;; http://incanter-blog.org/2009/07/01/bayes-multinomial/
+
+;; Bayesian inference of multinomial distribution parameters
+
+(use '(incanter core stats bayes charts))
+
+
+(def y [727 583 137])
+
+(div y 1447.) ;; (0.502 0.403 0.095)
+
+
+(def  theta (sample-multinomial-params 1000 y))
+(def theta1 (sel theta :cols 0))
+(def theta2 (sel theta :cols 1))
+(def theta3 (sel theta :cols 2))
+
+;; view means, 95% CI, and histograms of the proportion parameters
+(mean theta1) ;; 0.502
+(sd theta1) ;; 0.0129
+(quantile theta1 :probs [0.025 0.975]) ;; (0.476 0.528)
+(view (histogram theta1
+                 :title "Bush, Sr. Support"))
+
+(mean theta2) ;; 0.403
+(sd theta2) ;; 0.013
+(quantile theta2 :probs [0.025 0.975]) ;; (0.376 0.427)
+(view (histogram theta2
+                 :title "Dukakis Support"))
+
+(mean theta3) ;; 0.095
+(sd theta3) ;; 0.008
+(quantile theta3 :probs [0.025 0.975]) ;; (0.082 0.111)
+(view (histogram theta3
+                 :title "Other/Undecided"))
+
+;; view  a histogram of the difference in proportions between the first
+;; two candidates
+(view (histogram (minus theta1 theta2) 
+                 :title "Bush, Sr. and Dukakis Diff"))
+
+
+
+;; sample the proportions directly from a Dirichlet distribution
+(def alpha [1 1 1])
+(def  props (sample-dirichlet 1000 (plus y alpha)))
+
+
+

examples/blog/bootstrapping.clj

@@ -0,0 +1,89 @@
+;; from the following blog post
+;; http://incanter-blog.org/2009/07/04/bootstrapping/
+
+;; example with smoothing
+;; Newcomb's speed of light data
+
+(use '(incanter core stats charts))
+
+
+;; A numeric vector giving the Third Series of measurements of the
+;; passage time of light recorded by Newcomb in 1882. The given
+;; values divided by 1000 plus 24 give the time in millionths of a
+;; second for light to traverse a known distance. The 'true' value is
+;; now considered to be 33.02.
+
+(def x [28 -44  29  30  24  28  37  32  36  
+        27  26  28  29 26  27  22  23  20  
+        25 25  36  23  31  32  24  27 33  
+        16  24  29  36  21  28  26  27  27  
+        32  25 28 24  40  21  31  32  28  
+        26  30  27  26  24  32  29 34  -2  
+        25  19  36 29  30  22  28  33  39  
+        25  16  23])
+
+;; view histogram of data to see outlier observations
+(view (histogram x 
+                 :nbins 20
+                 :title "Newcomb's speed of light data"))
+
+
+
+;; calculate the median of the data
+(median x) ;; 27
+
+;; define a function that converts Newcomb's data into speeds
+(defn to-speed 
+  "Converts Newcomb's data into speed (meters/sec)"
+  ([x] (div 7400 (div (plus 24800 x) 1E9))))
+
+
+;; convert the data to speeds and calculate the median
+(median (to-speed x)) ;; 2.981E8
+
+
+
+;; Draw 10000 bootstrap samples of the median
+(def t* (bootstrap x median :size 10000))
+
+;; view a histogram of the bootstrap medians
+(view (histogram t* 
+                 :density true 
+                 :nbins 20
+                 :title "Bootstrap sample of medians"
+                 :x-label "median"))
+
+;; Calculate the estimate of the median: 27.301
+(mean t*)
+
+;; Convert bootstrap median estimate to speed: 2.981E8
+(to-speed (mean t*))
+
+;; Calculate a 95% CI for the median: (26.0 28.5)
+(quantile t* :probs [0.025 0.975])
+
+;; Convert to speed and calculate 95% CI: (2.9804E8 2.9807E8)
+(quantile (to-speed t*) :probs [0.025 0.975])
+
+;; estimate the standard error of the median: 0.681
+(sd t*)
+
+;; estimate the bias of the sample median: -0.3
+(- (mean t*) (median x))
+
+
+;; draw 10000 smoothed bootstrap samples of the median
+(def smooth-t* (bootstrap x median :size 10000 :smooth true))
+
+(view (histogram smooth-t* 
+                 :density true 
+                 :nbins 20
+                 :title "Smoothed bootstrap sample of medians"
+                 :x-label "median"))(mean smooth-samp)
+
+;; Calculate the estimate of the median
+(mean smooth-t*)
+
+;; Calculate a 95% CI: (25.905 28.446)
+(quantile smooth-t* :probs [0.025 0.975])
+

examples/blog/categorical_plots.clj

@@ -0,0 +1,59 @@
+;; from the following blog post
+;; http://incanter-blog.org/2009/06/13/plotting-with-non-numeric-data/
+;; plotting categorical data
+
+(use '(incanter core charts datasets))
+
+;; bar-charts
+(view (bar-chart ["a" "b" "c" "d" "e"] [10 20 30 25 20]))
+
+(view (bar-chart ["a" "a" "b" "b" "c" "c" ] [10 20 30 10 40 20]
+                     :legend true 
+                     :group-by ["I" "II" "I" "II" "I" "II"]))
+
+(view (line-chart ["a" "b" "c" "d" "e"] [20 10 30 25 40]))
+
+
+(def data (get-dataset :airline-passengers))
+(def by-year (group-by data 0))
+(view (bar-chart (sel (last by-year) :cols 2) 
+                 (sel (last by-year) :cols 1)
+                 :title "Airline Travel in 1960"
+                 :y-label "Passengers"
+                 :x-label "Month"))
+
+
+;; line-charts
+(view (line-chart (sel (last by-year) :cols 2) 
+                 (sel (last by-year) :cols 1)
+                 :title "Airline Travel in 1960"
+                 :y-label "Passengers"
+                 :x-label "Month"))
+
+(view (line-chart (sel data :cols 2) 
+                 (sel data :cols 1)
+                 :group-by (sel data :cols 0)
+                 :title "Airline Travel in 1949-1960"
+                 :legend true
+                 :y-label "Passengers"
+                 :x-label "Month"))
+
+
+;; more bar-charts
+(view (bar-chart (sel data :cols 2) 
+                 (sel data :cols 1)
+                 :group-by (sel data :cols 0)
+                 :title "Airline Travel in 1949-1960"
+                 :legend true
+                 :y-label "Passengers"
+                 :x-label "Year"))
+
+(view (bar-chart (sel data :cols 0) 
+                 (sel data :cols 1)
+                 :group-by (sel data :cols 2)
+                 :title "Airline Travel in 1949-1960"
+                 :legend true
+                 :y-label "Passengers"
+                 :x-label "Year")
+       :width 525)
+