MLcomp version alpha Statistics: 1403 users, 461 datasets, 360 programs, 16577 runs (0 queued, 0 running), 0 workers

Run 1321

Creator	pliang
Program	xterm-knnsvd_shrunk_unbias_rev-r
Dataset	eachmovie-1to5
Task type	CollaborativeFiltering
Created	28d16h ago

Status: Done!

Total Time	4h32m
Max Memory Usage	1887M
Domain	CollaborativeFiltering
Learn time	3h45m
Train RMSE	0.806
Train MAE	0.621
Predict train time	37m3s
Test RMSE	0.919
Test MAE	0.710
Predict test time

Log file

Usage: "run learn trainingFileName" OR "run predict testFileName predictionFileName"
=== Starting: cd /home/mlcomp/worker1/scratch/program0/../program1 && ./run learn '/home/mlcomp/worker1/scratch/program0/../dataset2/train'
           used  (Mb) gc trigger   (Mb)  max used   (Mb)
Ncells   109029   3.0     350000    9.4    350000    9.4
Vcells 74266378 566.7  134568651 1026.7 134568348 1026.7
           used  (Mb) gc trigger  (Mb) max used  (Mb)
Ncells   105741   2.9     350000   9.4   350000   9.4
Vcells 74234248 566.4   82180701 627.0 74234650 566.4
[1] 1
[1] "Svd done!"
[1] "data3 update done!"
[1] 2
[1] "Svd done!"
[1] "data3 update done!"
[1] 3
[1] "Svd done!"
[1] "data3 update done!"
[1] 4
[1] "Svd done!"
[1] "data3 update done!"
[1] 5
[1] "Svd done!"
[1] "data3 update done!"
[1] "Computing Similarity Matrix"
10  out of  1648 
20  out of  1648 
30  out of  1648 
40  out of  1648 
50  out of  1648 
60  out of  1648 
70  out of  1648 
80  out of  1648 
90  out of  1648 
100  out of  1648 
110  out of  1648 
120  out of  1648 
130  out of  1648 
140  out of  1648 
150  out of  1648 
160  out of  1648 
170  out of  1648 
180  out of  1648 
190  out of  1648 
200  out of  1648 
210  out of  1648 
220  out of  1648 
230  out of  1648 
240  out of  1648 
250  out of  1648 
260  out of  1648 
270  out of  1648 
280  out of  1648 
290  out of  1648 
300  out of  1648 
310  out of  1648 
320  out of  1648 
330  out of  1648 
340  out of  1648 
350  out of  1648 
360  out of  1648 
370  out of  1648 
380  out of  1648 
390  out of  1648 
400  out of  1648 
410  out of  1648 
420  out of  1648 
430  out of  1648 
440  out of  1648 
450  out of  1648 
460  out of  1648 
470  out of  1648 
480  out of  1648 
490  out of  1648 
500  out of  1648 
510  out of  1648 
520  out of  1648 
530  out of  1648 
540  out of  1648 
550  out of  1648 
560  out of  1648 
570  out of  1648 
580  out of  1648 
590  out of  1648 
600  out of  1648 
610  out of  1648 
620  out of  1648 
630  out of  1648 
640  out of  1648 
650  out of  1648 
660  out of  1648 
670  out of  1648 
680  out of  1648 
690  out of  1648 
700  out of  1648 
710  out of  1648 
720  out of  1648 
730  out of  1648 
740  out of  1648 
750  out of  1648 
760  out of  1648 
770  out of  1648 
780  out of  1648 
790  out of  1648 
800  out of  1648 
810  out of  1648 
820  out of  1648 
830  out of  1648 
840  out of  1648 
850  out of  1648 
860  out of  1648 
870  out of  1648 
880  out of  1648 
890  out of  1648 
900  out of  1648 
910  out of  1648 
920  out of  1648 
930  out of  1648 
940  out of  1648 
950  out of  1648 
960  out of  1648 
970  out of  1648 
980  out of  1648 
990  out of  1648 
1000  out of  1648 
1010  out of  1648 
1020  out of  1648 
1030  out of  1648 
1040  out of  1648 
1050  out of  1648 
1060  out of  1648 
1070  out of  1648 
1080  out of  1648 
1090  out of  1648 
1100  out of  1648 
1110  out of  1648 
1120  out of  1648 
1130  out of  1648 
1140  out of  1648 
1150  out of  1648 
1160  out of  1648 
1170  out of  1648 
1180  out of  1648 
1190  out of  1648 
1200  out of  1648 
1210  out of  1648 
1220  out of  1648 
1230  out of  1648 
1240  out of  1648 
1250  out of  1648 
1260  out of  1648 
1270  out of  1648 
1280  out of  1648 
1290  out of  1648 
1300  out of  1648 
1310  out of  1648 
1320  out of  1648 
1330  out of  1648 
1340  out of  1648 
1350  out of  1648 
1360  out of  1648 
1370  out of  1648 
1380  out of  1648 
1390  out of  1648 
1400  out of  1648 
1410  out of  1648 
1420  out of  1648 
1430  out of  1648 
1440  out of  1648 
1450  out of  1648 
1460  out of  1648 
1470  out of  1648 
1480  out of  1648 
1490  out of  1648 
1500  out of  1648 
1510  out of  1648 
1520  out of  1648 
1530  out of  1648 
1540  out of  1648 
1550  out of  1648 
1560  out of  1648 
1570  out of  1648 
1580  out of  1648 
1590  out of  1648 
1600  out of  1648 
1610  out of  1648 
1620  out of  1648 
1630  out of  1648 
1640  out of  1648 
=== Finished: cd /home/mlcomp/worker1/scratch/program0/../program1 && ./run learn '/home/mlcomp/worker1/scratch/program0/../dataset2/train' --- OK [13535s]
=== Starting: cd /home/mlcomp/worker1/scratch/program0/../program3 && ./run stripLabels '/home/mlcomp/worker1/scratch/program0/../dataset2/train' '/home/mlcomp/worker1/scratch/program0/evalTrain.in'
=== Finished: cd /home/mlcomp/worker1/scratch/program0/../program3 && ./run stripLabels '/home/mlcomp/worker1/scratch/program0/../dataset2/train' '/home/mlcomp/worker1/scratch/program0/evalTrain.in' --- OK [7s]
=== Starting: cd /home/mlcomp/worker1/scratch/program0/../program1 && ./run predict '/home/mlcomp/worker1/scratch/program0/evalTrain.in' '/home/mlcomp/worker1/scratch/program0/evalTrain.out'
[1] "/home/mlcomp/worker1/scratch/program0/evalTrain.in"
[1] "/home/mlcomp/worker1/scratch/program0/evalTrain.out"
[1] "Computing SVD..."
[1] "Computing KNN and merging..."
=== Finished: cd /home/mlcomp/worker1/scratch/program0/../program1 && ./run predict '/home/mlcomp/worker1/scratch/program0/evalTrain.in' '/home/mlcomp/worker1/scratch/program0/evalTrain.out' --- OK [2223s]
=== Starting: cd /home/mlcomp/worker1/scratch/program0/../program4 && ./run evaluate '/home/mlcomp/worker1/scratch/program0/../dataset2/train' '/home/mlcomp/worker1/scratch/program0/evalTrain.out'
=== Finished: cd /home/mlcomp/worker1/scratch/program0/../program4 && ./run evaluate '/home/mlcomp/worker1/scratch/program0/../dataset2/train' '/home/mlcomp/worker1/scratch/program0/evalTrain.out' --- OK [13s]
=== Starting: cd /home/mlcomp/worker1/scratch/program0/../program3 && ./run stripLabels '/home/mlcomp/worker1/scratch/program0/../dataset2/test' '/home/mlcomp/worker1/scratch/program0/evalTest.in'
=== Finished: cd /home/mlcomp/worker1/scratch/program0/../program3 && ./run stripLabels '/home/mlcomp/worker1/scratch/program0/../dataset2/test' '/home/mlcomp/worker1/scratch/program0/evalTest.in' --- OK [0s]
=== Starting: cd /home/mlcomp/worker1/scratch/program0/../program1 && ./run predict '/home/mlcomp/worker1/scratch/program0/evalTest.in' '/home/mlcomp/worker1/scratch/program0/evalTest.out'
[1] "/home/mlcomp/worker1/scratch/program0/evalTest.in"
[1] "/home/mlcomp/worker1/scratch/program0/evalTest.out"
[1] "Computing SVD..."
[1] "Computing KNN and merging..."
=== Finished: cd /home/mlcomp/worker1/scratch/program0/../program1 && ./run predict '/home/mlcomp/worker1/scratch/program0/evalTest.in' '/home/mlcomp/worker1/scratch/program0/evalTest.out' --- OK [591s]
=== Starting: cd /home/mlcomp/worker1/scratch/program0/../program4 && ./run evaluate '/home/mlcomp/worker1/scratch/program0/../dataset2/test' '/home/mlcomp/worker1/scratch/program0/evalTest.out'
=== Finished: cd /home/mlcomp/worker1/scratch/program0/../program4 && ./run evaluate '/home/mlcomp/worker1/scratch/program0/../dataset2/test' '/home/mlcomp/worker1/scratch/program0/evalTest.out' --- OK [2s]

real	272m51.470s
user	265m36.840s
sys	1m20.581s

Run specification

• supervised-learning: Main entry for supervised learning for training and testing a program on a dataset.
  • (learner:Program) xterm-knnsvd_shrunk_unbias_rev-r: KNN with 21 neighbors and cosine distance, and SVD with EM, 10 iterations, and K=10. Combined using fixed weights of 1/3 and 2/3 resp.
  • (dataset:Dataset) eachmovie-1to5: Modified EachMovie movie ratings dataset from HP/Compaq (more information on http://www.grouplens.org/). The original EachMovie dataset contained 2,811,983 ratings (1-6 stars) entered by 72,916 users for 1628 different movies. This sub-dataset includes the ratings of 30,000 randomly selected users with 20 or more ratings. A single rating from each user was withheld to form the test set. Ratings values outside of the 1-6 range have been discarded. Finally, ratings in the range 1-6 were mapped to the range 1-5 via r = 1 + (r-1)*(4/5).
  • (stripper:Program[Strip]) collaborativefiltering-utils: Validates, inspects, and evaluates a dataset in CollaborativeFiltering format.
  • (evaluator:Program[Evaluate]) collaborativefiltering-utils: Validates, inspects, and evaluates a dataset in CollaborativeFiltering format.

Results

• doTest:
  • evaluate:
    • meanAbsoluteError: 0.710151300686707
    • meanSquaredError: 0.844372513292079
    • numExamples: 29998
    • rootMeanSquaredError: 0.918897444382167
    • success: true
    • time: 2
  • predict:
    • success: true
    • time: 591
  • strip:
    • success: true
    • time: 0
• doTrain:
  • evaluate:
    • meanAbsoluteError: 0.621413858075128
    • meanSquaredError: 0.650025152338052
    • numExamples: 2079628
    • rootMeanSquaredError: 0.806241373496828
    • success: true
    • time: 13
  • predict:
    • success: true
    • time: 2223
  • strip:
    • success: true
    • time: 7
• exitCode: 0
• learn:
  • success: true
  • time: 13535
• success: true

Comments: