These set operations can be used to compare single classes or complete classifications having the same class names.
| clinsec | Evaluate the intersection of two classes |
| -cl1 <data1> | source class 1 |
| -cl2 <data2> | source class 2 |
| -clout <dataout> | target class |
| clunion | Evaluate the union of two classes |
| -cl1 <data1> | source class 1 |
| -cl2 <data2> | source class 2 |
| -clout <dataout> | target class |
| cldiff | Evaluate the difference of two classes |
| -cl1 <data1> | source class 1 |
| -cl2 <data2> | source class 2 |
| -clout <dataout> | target class |
These three commands perform normal set operations intersection, union or difference to two classified data classes. Intersection contains those data record indices included in both classes, union contains a superset of all indices within the two classes and difference those indices within just one of the classes, but not in both of them.
Example: For a thorough example, see the example of classification comparisons. Here is just a basic example with a small data set.
... # Data file with 8 numbers (1, 2, 3, 5, 8, 6, 7 and 4) NDA> getdata k x # Field name 1 # Data type (integer) 1 # Data values 2 3 5 8 6 7 4 # Select two classes containing indices to values larger than # or equal to 3 (first) and values between 5 and 7 (sec) NDA> selcl -cout cli -clout first -expr 'k.x' >= 3; NDA> selcl -cout cli -clout sec -expr 'k.x' >= 5 and 'k.x' <= 7; # Evaluate difference of classes NDA> cldiff -cl1 cli.first -cl2 cli.sec -clout cli.result NDA> save cli ... # This results in cli.cld containing the following data lines: ... class_info 201 1 first 6 2 3 4 5 6 7 201 1 sec 3 3 5 6 201 1 result 3 7 4 2 # Class first: 6 indices (234567), class sec 3 indices (356), # Difference(result): 3 indices (247)
| cldinsec | Evaluate the intersection of two classifications |
| -c1 <cldata1> | source classified data 1 |
| -c2 <cldata2> | source classified data 2 |
| -cout <cldataout> | target classified data |
| cldunion | Evaluate the union of two classifications |
| -c1 <cldata1> | source classified data 1 |
| -c2 <cldata2> | source classified data 2 |
| -cout <cldataout> | target classified data |
| clddiff | Evaluate the difference of two classifications |
| -c1 <cldata1> | source classified data 1 |
| -c2 <cldata2> | source classified data 2 |
| -cout <cldataout> | target classified data |
These commands perform class by class set operations for entire classifications. Each class name of classified data <cldata1> is compared to the names of classes in <cldata2>. If a match is found, a new class with the same name is created into the target classified data containing the intersection, union or difference.
Example: To compare the classification results of two different layers of TS-SOM, union and intersection can be used.
... # Data loaded into d - Selection of fields, training of a SOM NDA> select datas -f d.GP d.GN d.TP d.TN NDA> somtr -d datas -sout som -cout cldata -l 4 Trained layer: 0 Trained layer: 1 Trained layer: 2 Trained layer: 3 # Average value calculation for each neuron NDA> clstat -c cldata -d datas -dout st -avg NDA> ls -fr st st.GP_avg st.GN_avg st.TP_avg st.TN_avg # TS-SOM layer info is needed for selection of data records NDA> somlayer -s som -fout sl NDA> selcl -cout g2 -clout GP -expr 'sl'=2 and 'st.GP_avg'>=0.7; NDA> selcl -cout g2 -clout GN -expr 'sl'=2 and 'st.GN_avg'>=0.7; NDA> selcl -cout g2 -clout TP -expr 'sl'=2 and 'st.TP_avg'>=0.7; NDA> selcl -cout g2 -clout TN -expr 'sl'=2 and 'st.TN_avg'>=0.7; NDA> selcl -cout g3 -clout GP -expr 'sl'=3 and 'st.GP_avg'>=0.7; NDA> selcl -cout g3 -clout GN -expr 'sl'=3 and 'st.GN_avg'>=0.7; NDA> selcl -cout g3 -clout TP -expr 'sl'=3 and 'st.TP_avg'>=0.7; NDA> selcl -cout g3 -clout TN -expr 'sl'=3 and 'st.TN_avg'>=0.7; # Selected groups of records need to be converted into cldatas NDA> mergecld -c1 g2 -c2 cldata -cout clo2 NDA> mergecld -c1 g3 -c2 cldata -cout clo3 # Compute intersection and union of indices in classifications NDA> cldinsec -c1 clo2 -c2 clo3 -cout clo_insec NDA> cldunion -c1 clo2 -c2 clo3 -cout clo_union # Calculate the index counts of each class into a frame NDA> clhits -c clo_insec -fout ins NDA> clhits -c clo_union -fout uni NDA> select clp -f ins uni NDA> ls -fr clp clp.ins clp.uni # Calculate the ratio of the set sizes (intersection / union) # for each class (GP, GN, TP and TN) NDA> expr -dout props -fout prop -expr 'clp.ins' / 'clp.uni'; NDA> getdata props prop 2 0.870521 0.940236 0.810526 0.972215 ...