Skip to content

Instantly share code, notes, and snippets.

@danbri
Created June 22, 2011 07:14
Show Gist options
  • Save danbri/1039631 to your computer and use it in GitHub Desktop.
Save danbri/1039631 to your computer and use it in GitHub Desktop.
TellyClub:danbri danbri$ wget http://www.graphlab.ml.cmu.edu/movielens
--2011-06-22 09:11:30-- http://www.graphlab.ml.cmu.edu/movielens
Resolving www.graphlab.ml.cmu.edu... 128.2.204.146
Connecting to www.graphlab.ml.cmu.edu|128.2.204.146|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 14403024 (14M) [text/plain]
Saving to: `movielens'
100%[==============================================================================>] 14,403,024 412K/s in 39s w
2011-06-22 09:12:10 (356 KB/s) - `movielens' saved [14403024/14403024]
TellyClub:danbri danbri$ wget http://www.graphlab.ml.cmu.edu/movielense
--2011-06-22 09:12:45-- http://www.graphlab.ml.cmu.edu/movielense
Resolving www.graphlab.ml.cmu.edu... 128.2.204.146
Connecting to www.graphlab.ml.cmu.edu|128.2.204.146|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1600352 (1.5M) [text/plain]
Saving to: `movielense'
100%[==============================================================================>] 1,600,352 368K/s in 4.9s
2011-06-22 09:12:50 (316 KB/s) - `movielense' saved [1600352/1600352]
TellyClub:danbri danbri$ ./PMF movielens 0 --float=true --scheduler="round_robin(max_iterations=15)"
-bash: ./PMF: No such file or directory
TellyClub:danbri danbri$ PMF movielens 0 --float=true --scheduler="round_robin(max_iterations=15)"
INFO: pmf.cpp(main:1285): PMF/ALS/SVD++/SGD Code written By Danny Bickson, CMU
Send bug reports and comments to [email protected]
WARNING: pmf.cpp(main:1287): Code compiled with GL_NO_MULT_EDGES flag - this mode does not support multiple edges between user and movie in different times
Setting run mode ALS_MATRIX
INFO: pmf.cpp(main:1335): ALS_MATRIX starting
loading data file movielens
Loading movielens TRAINING
Matrix size is: USERS 6040 MOVIES 3952 TIME BINS 1
Creating 900188 edges (observed ratings)...
.....loading data file movielense
Loading movielense VALIDATION
Matrix size is: USERS 6040 MOVIES 3952 TIME BINS 1
Creating 100021 edges (observed ratings)...
.loading data file movielenst
Loading movielenst TEST
skipping file
setting regularization weight to 1
ALS_MATRIX for matrix (6040, 3952, 1):900188. D=20
pU=1, pV=1, pT=1, muT=1, D=20
complete. Obj=6.1745e+06, TRAIN RMSE=3.7037 VALIDATION RMSE=3.7083.
max iterations = 15
step = 1
max_iterations = 15
INFO: asynchronous_engine.hpp(run:94): Worker 0 started.
INFO: asynchronous_engine.hpp(run:94): Worker 1 started.
Entering last iter with 1
2.04495) Iter ALS_MATRIX 1 Obj=5.78098e+06, TRAIN RMSE=3.5815 VALIDATION RMSE=2.2956.
Entering last iter with 2
4.49808) Iter ALS_MATRIX 2 Obj=740798, TRAIN RMSE=1.2724 VALIDATION RMSE=1.3848.
Entering last iter with 3
6.39016) Iter ALS_MATRIX 3 Obj=811078, TRAIN RMSE=1.3321 VALIDATION RMSE=1.3621.
Entering last iter with 4
8.2037) Iter ALS_MATRIX 4 Obj=826648, TRAIN RMSE=1.3450 VALIDATION RMSE=1.3583.
Entering last iter with 5
10.4919) Iter ALS_MATRIX 5 Obj=830305, TRAIN RMSE=1.3480 VALIDATION RMSE=1.3575.
Entering last iter with 6
12.3052) Iter ALS_MATRIX 6 Obj=831119, TRAIN RMSE=1.3487 VALIDATION RMSE=1.3573.
Entering last iter with 7
14.1042) Iter ALS_MATRIX 7 Obj=831300, TRAIN RMSE=1.3488 VALIDATION RMSE=1.3573.
Entering last iter with 8
15.9663) Iter ALS_MATRIX 8 Obj=831340, TRAIN RMSE=1.3489 VALIDATION RMSE=1.3573.
Entering last iter with 9
17.7536) Iter ALS_MATRIX 9 Obj=831348, TRAIN RMSE=1.3489 VALIDATION RMSE=1.3573.
Entering last iter with 10
19.5681) Iter ALS_MATRIX 10 Obj=831350, TRAIN RMSE=1.3489 VALIDATION RMSE=1.3573.
Entering last iter with 11
21.355) Iter ALS_MATRIX 11 Obj=831351, TRAIN RMSE=1.3489 VALIDATION RMSE=1.3573.
Entering last iter with 12
23.4889) Iter ALS_MATRIX 12 Obj=831351, TRAIN RMSE=1.3489 VALIDATION RMSE=1.3573.
Entering last iter with 13
25.2861) Iter ALS_MATRIX 13 Obj=831351, TRAIN RMSE=1.3489 VALIDATION RMSE=1.3573.
Entering last iter with 14
27.144) Iter ALS_MATRIX 14 Obj=831351, TRAIN RMSE=1.3489 VALIDATION RMSE=1.3573.
Entering last iter with 15
28.8969) Iter ALS_MATRIX 15 Obj=831351, TRAIN RMSE=1.3489 VALIDATION RMSE=1.3573.
INFO: asynchronous_engine.hpp(run:102): Worker 0 finished.
INFO: asynchronous_engine.hpp(run:102): Worker 1 finished.
Final result. Obj=831351, TRAIN RMSE= 1.3489 VALIDATION RMSE= 1.3573.
Finished in 28.926237
Performance counters are: 0) EDGE_TRAVERSAL, 16.5158
Performance counters are: 2) CALC_RMSE_Q, 0.001487
Performance counters are: 3) ALS_LEAST_SQUARES, 23.0641
Performance counters are: 6) CALC_OBJ, 0.009276
=== REPORT FOR core() ===
[Numeric]
ncpus: 2
[Other]
affinities: false
compile_flags:
engine: async
scheduler: round_robin
schedyield: true
scope: edge
=== REPORT FOR engine() ===
[Numeric]
num_edges: 900188
num_syncs: 0
num_vertices: 9992
updatecount: 149880
[Timings]
runtime: 28.9 s
[Other]
termination_reason: task depletion (natural)
[Numeric]
updatecount_vector: 149880 (count: 2, min: 73691, max: 76189, avg: 74940)
updatecount_vector.values: 76189,73691,
TellyClub:danbri danbri$ PMF movielens 0 --float=true --scheduler="round_robin(max_iterations=15)"
TellyClub:danbri danbri$ ls
movielens movielens20.out movielense
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment