...
#copy data into /shared/ohsumed/data
No Format |
---|
cp /shared/ohsumed/ohsu-trec/trec9-test/ohsumed.88-91 /shared/ohsumed/data
cp /shared/ohsumed/ohsu-trec/trec9-train/ohsumed.87 /shared/ohsumed/data |
#convert data into trec format
...
Using orig queries (pre-test queries included)
Model | MAP | NDCG | P@20 | NDCG@20 | P@100 | NDCG@100 | Notes | Date |
---|---|---|---|---|---|---|---|---|
tfidf | 0.2204 | 0.4538 | 0.2995 | 0.2904 | 0.1735 | 0.3376 | Sweep b and k1 | 06/07/17 |
Okapi | 0.2218 | 0.4557 | 0.2819- | 0.3035 | 0.1717 | 0.3386 | Sweep b, k1, k3 | 06/07/17 |
QL (JM) | 0.1876- | 0.4212- | 0.2505- | 0.2773 | 0.1403- | 0.295- | Sweep lambda | 06/07/17 |
QL (Dir) | 0.2032- | 0.4359- | 0.2713- | 0.2927 | 0.1633- | 0.1403 | Sweep mu | 06/07/17 |
QL (TS) | 0.2101- | 0.4415- | 0.2761- | 0.3029 | 0.1638- | 0.3277 | Sweep mu and lambda | 06/07/17 |
RM3 | Sweep mu, fbDocs, fbTerms, and lambda |
No Format |
---|
root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf dir orig
[1] "map 0.2204 0.2032 p= 0.9988 |
No Format |
root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf dir orig [1] "map 0.2204 0.2032 p= 0.9988" [1] "ndcg 0.4538 0.4359 p= 0.9987" [1] "P_20 0.2995 0.2713 p= 0.9985" [1] "ndcg_cut_20 0.2904 0.2927 p= 0.417" [1] "P_100 0.1735 0.1633 p= 0.9945" [1] "ndcg_cut_100 0.3376 0.3304 p= 0.7764" root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf jm orig [1] "map 0.2204 0.1876 p= 0.9966" [1] "ndcg 0.4538 0.4212 p= 0.9992" [1] "P_20 0.2995 0.2505 p= 0.9999" [1] "ndcg_cut_20 0.2904 0.2773 p= 0.8572" [1] "P_100 0.1735 0.1403 p= 1" [1] "ndcg_cut_100 0.3376 0.4538 0.2954359 p= 0.9996" root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf two orig 9987" [1] "mapP_20 0.22042995 0.21012713 p= 0.9729985" [1] "ndcg_cut_20 0.45382904 0.44152927 p= 0.9859417" [1] "P_20100 0.29951735 0.27611633 p= 0.99549945" [1] "ndcg_cut_20100 0.29043376 0.30293304 p= 0.1072" 7764" root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf jm orig [1] "P_100map 0.17352204 0.16381876 p= 0.99929966" [1] "ndcg_cut_100 0.33764538 0.32774212 p= 0.8579992" root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf okapi orig[1] "P_20 0.2995 0.2505 p= 0.9999" [1] "map 0.2204 0.2218 p= 0.4445" [1] "ndcg 0.4538 0.4557 p= 0.414" [1] "P_20 0.2995 0.2819 p= 0.975" [1] "ndcg_cut_20 0.2904 0.3035 p= 0.1157" [1] "P_100 0.1735 0.1717 p= 0.6907" [1] "ndcg_cut_100 0.3376 0.3386 p= 0.4437" |
...
ndcg_cut_20 0.2904 0.2773 p= 0.8572"
[1] "P_100 0.1735 0.1403 p= 1"
[1] "ndcg_cut_100 0.3376 0.295 p= 0.9996"
root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf two orig
[1] "map 0.2204 0.2101 p= 0.972"
[1] "ndcg 0.4538 0.4415 p= 0.9859"
[1] "P_20 0.2995 0.2761 p= 0.9954"
[1] "ndcg_cut_20 0.2904 0.3029 p= 0.1072"
[1] "P_100 0.1735 0.1638 p= 0.9992"
[1] "ndcg_cut_100 0.3376 0.3277 p= 0.857"
root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf okapi orig
[1] "map 0.2204 0.2218 p= 0.4445"
[1] "ndcg 0.4538 0.4557 p= 0.414"
[1] "P_20 0.2995 0.2819 p= 0.975"
[1] "ndcg_cut_20 0.2904 0.3035 p= 0.1157"
[1] "P_100 0.1735 0.1717 p= 0.6907"
[1] "ndcg_cut_100 0.3376 0.3386 p= 0.4437" |
Using short queries (pre-test queries not included)
Model | MAP | NDCG | P@20 | NDCG@20 | P@100 | NDCG@100 | Notes | Date |
---|---|---|---|---|---|---|---|---|
tfidf | 0.3188 | 0.6084 | 0.45 | 0.4255 | 0.2657 | 0.4625 | Sweep b and k1 | 06/07/17 |
Okapi | 0.3117 | 0.6044 | 0.4408 | 0.4277 | 0.261 | 0.4569 | Sweep b, k1, k3 | 06/07/17 |
QL (JM) | 0.2545- | 0.5527- | 0.3908- | 0.3882- | 0.2135- | 0.3883- | Sweep lambda | 06/07/17 |
QL (Dir) | 0.2924- | 0.5866- | 0.3975 | 0.4018- | 0.2492- | 0.432- | Sweep mu | 06/07/17 |
QL (TS) | 0.2934- | 0.5828- | 0.4092- | 0.4122 | 0.2508- | 0.4385- | Sweep mu and lambda | 06/07/17 |
RM3 | Sweep mu, fbDocs, fbTerms, and lambda |
No Format |
---|
root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf dir short [1] "map 0.3188 0.2924 p= 0.9997" [1] "ndcg 0.6084 0.5866 p= 0.9994" [1] "P_20 0.45 0.3975 p= 0.9998" [1] "ndcg_cut_20 0.4255 0.4018 p= 0.9881" [1] "P_100 0.2657 0.2492 p= 0.9947" [1] "ndcg_cut_100 0.4625 0.432 p= 0.9999" root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf jm short [1] "map 0.3188 0.2545 p= 1" [1] "ndcg 0.6084 0.5527 p= 1" [1] "P_20 0.45 0.3908 p= 0.9984" [1] "ndcg_cut_20 0.4255 0.3882 p= 0.9973" [1] "P_100 0.2657 0.2135 p= 1" [1] "ndcg_cut_100 0.4625 0.3883 p= 1" root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf okapi short [1] "map 0.3188 0.3117 p= 0.7974" [1] "ndcg 0.6084 0.6044 p= 0.6834" [1] "P_20 0.45 0.4408 p= 0.7506" [1] "ndcg_cut_20 0.4255 0.4277 p= 0.4236" [1] "P_100 0.2657 0.261 p= 0.791" [1] "ndcg_cut_100 0.4625 0.4569 p= 0.747" root@integration-1:~/biocaddie# Rscript scripts/compare_ohsumed.R combined tfidf two short [1] "map 0.3188 0.2934 p= 1" [1] "ndcg 0.6084 0.5828 p= 0.9997" [1] "P_20 0.45 0.4092 p= 0.9989" [1] "ndcg_cut_20 0.4255 0.4122 p= 0.89" [1] "P_100 0.2657 0.2508 p= 0.9991" [1] "ndcg_cut_100 0.4625 0.4385 p= 0.9992" |
...