FreeStatistics.org

Free Statistics

of Irreproducible Research!

Description of Statistical Computation

Author's title

Author*The author of this computation has been verified*
R Software ModuleRscript (source code is shown below)
Title produced by softwareR console
Date of computationTue, 25 May 2010 12:54:06 +0000
Cite this page as followsStatistical Computations at FreeStatistics.org, Office for Research Development and Education, URL https://freestatistics.org/blog/index.php?v=date/2010/May/25/t1274792047ryasw6b110c9xey.htm/, Retrieved Thu, 02 May 2024 02:43:41 +0000
Statistical Computations at FreeStatistics.org, Office for Research Development and Education, URL https://freestatistics.org/blog/index.php?pk=76381, Retrieved Thu, 02 May 2024 02:43:41 +0000
QR Codes:

Original text written by user:Warning: you must have the RWeka R package installed to reproduce this computation. The RWeka package requires Sun Java on your machine!
IsPrivate?No (this computation is public)
User-defined keywordsICEL 2010, peer review, regression tree, evaluation, social constructivism, reproducible computing, educational technology, e-learning
Estimated Impact164

Tree of Dependent Computations

Family? (F = Feedback message, R = changed R code, M = changed R Module, P = changed Parameters, D = changed Data)
-       [R console] [Reviewing Peer Re...] [2010-05-25 12:54:06] [d76b387543b13b5e3afd8ff9e5fdc89f] [Current]
Feedback Forum

Post a new message

Dataset

Tables (Output of Computation)

> {
+     library(RWeka)
+     con <- url('https://automated.biganalytics.eu/download/ICEL2010')
+     load(con)
+     close(con)
+     y <- y[!is.na(y$X1), ]
+    .... [TRUNCATED] 
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  0.000   3.000   3.500   3.346   4.000   6.000 
J48 pruned tree
------------------

x$NNZFG <= 71
|   x$BC <= 44
|   |   x$Year <= 0
|   |   |   x$Pop <= 0
|   |   |   |   x$NNZFG <= 36
|   |   |   |   |   x$BC <= 6: Fail (16.0/4.0)
|   |   |   |   |   x$BC > 6: Pass (3.0)
|   |   |   |   x$NNZFG > 36: Pass (11.0/1.0)
|   |   |   x$Pop > 0: Pass (20.0/2.0)
|   |   x$Year > 0
|   |   |   x$AFL <= 212.17: Fail (31.0/5.0)
|   |   |   x$AFL > 212.17
|   |   |   |   x$Pop <= 0
|   |   |   |   |   x$AFL <= 280.35: Fail (4.0/1.0)
|   |   |   |   |   x$AFL > 280.35: Pass (5.0)
|   |   |   |   x$Pop > 0: Pass (5.0/1.0)
|   x$BC > 44: Pass (27.0/3.0)
x$NNZFG > 71: Pass (389.0/25.0)

Number of Leaves  : 	10

Size of the tree : 	19


=== Summary ===

Correctly Classified Instances         469               91.7808 %
Incorrectly Classified Instances        42                8.2192 %
Kappa statistic                          0.6162
Mean absolute error                      0.1468
Root mean squared error                  0.2709
Relative absolute error                 59.7092 %
Root relative squared error             77.4279 %
Coverage of cases (0.95 level)         100      %
Mean rel. region size (0.95 level)      99.2172 %
Total Number of Instances              511     

=== Confusion Matrix ===

   a   b   <-- classified as
  41  32 |   a = Fail
  10 428 |   b = Pass
=== 10 Fold Cross Validation ===

=== Summary ===

Correctly Classified Instances         445               87.0841 %
Incorrectly Classified Instances        66               12.9159 %
Kappa statistic                          0.4046
Mean absolute error                      0.1823
Root mean squared error                  0.3301
Relative absolute error                 74.0901 %
Root relative squared error             94.3177 %
Coverage of cases (0.95 level)          98.4344 %
Mean rel. region size (0.95 level)      94.5205 %
Total Number of Instances              511     

=== Confusion Matrix ===

   a   b   <-- classified as
  30  43 |   a = Fail
  23 415 |   b = Pass

Figures (Output of Computation)

Input Parameters & R Code

Parameters (Session):
Parameters (R input):
R code (body of R function):
{
    library(RWeka)
    con <- url("https://automated.biganalytics.eu/download/ICEL2010")
    load(con)
    close(con)
    y <- y[!is.na(y$X1), ]
    x <- y
    x <- x[!is.na(x$PSCORE), ]
    x <- cbind(x[, 1:3], x[, 5], x[, 8:9], x[, 12], x[, 21:22])
    colnames(x)[4] <- "name2"
    colnames(x)[7] <- "AFL"
    x <- x[complete.cases(x), ]
    xx <- as.numeric(x$PSCORE)
    print(summary(xx))
    n <- length(xx)
    myy <- array("Fail", dim = c(n, 1))
    for (i in 1:n) {
        if (xx[i] > 2.7) 
            myy[i] <- "Pass"
    }
    m1 <- J48(as.factor(myy) ~ x$NNZFG + x$Year + x$AFL + x$BC + 
        x$Gender + x$Pop)
    print(m1)
    print(summary(m1))
    print(e <- evaluate_Weka_classifier(m1, numFolds = 10))
    
    plot(m1)
    
}