[pymvpa] Calculation of TN(True Negative)

[Jiang, Zhiguo]

Hi, All

a bit confused by the output from tutorial Part 4:

so here is the output from the confusion matrix summary

----------.
predictions\targets     bottle         cat          chair          face
    house        scissors    scrambledpix      shoe
            `------  ------------  ------------  ------------  ------------
 ------------  ------------  ------------  ------------ P'   N'   FP   FN
PPV  NPV  TPR  SPC  FDR  MCC  F1
       bottle             6             0             3             0
      0             5             0             1       15   75    9    6
0.4 0.92  0.5 0.88  0.6 0.34 0.44
        cat               0             10            0             0
      0             0             0             0       10   67    0    2
 1  0.97 0.83   1    0  0.79 0.91
       chair              0             0             7             0
      0             0             0             0        7   73    0    5
 1  0.93 0.58   1    0  0.66 0.74
        face              0             2             0             12
       0             0             0             0       14   63    2    0
 0.86   1    1  0.97 0.14  0.8 0.92
       house              0             0             0             0
      12            0             0             0       12   63    0    0
 1    1    1    1    0  0.87   1
      scissors            2             0             1             0
      0             6             0             0        9   75    3    6
 0.67 0.92  0.5 0.96 0.33 0.48 0.57
    scrambledpix          2             0             1             0
      0             0             12            1       16   63    4    0
 0.75   1    1  0.94 0.25 0.75 0.86
        shoe              2             0             0             0
      0             1             0             10      13   67    3    2
 0.77 0.97 0.83 0.96 0.23 0.69  0.8
Per target:          ------------  ------------  ------------  ------------
 ------------  ------------  ------------  ------------
         P                12            12            12            12
       12            12            12            12
         N                84            84            84            84
       84            84            84            84
         TP               6             10            7             12
       12            6             12            10
         TN               69            65            68            63
       63            69            63            65


for example, in bottle category,

P=12, N=84;

True Positive= 6; False Positve=3+5+1; False Negative=2+2+2=6; that left us
with TN=84-9=75..

so where does the reported 69 comes from?

Best,
Tony
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20140117/446e2870/attachment.html>