richiam commited on
Commit
00a5e70
·
verified ·
1 Parent(s): f628452

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +25 -0
  2. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.5_ALL_FIELDS.csv.gz +3 -0
  3. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  4. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.6_ALL_FIELDS.csv.gz +3 -0
  5. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  6. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.7_ALL_FIELDS.csv.gz +3 -0
  7. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  8. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.8_ALL_FIELDS.csv.gz +3 -0
  9. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  10. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.9_ALL_FIELDS.csv.gz +3 -0
  11. data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv +14 -0
  12. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.5_ALL_FIELDS.csv.gz +3 -0
  13. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  14. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.6_ALL_FIELDS.csv.gz +3 -0
  15. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  16. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.7_ALL_FIELDS.csv.gz +3 -0
  17. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  18. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.8_ALL_FIELDS.csv.gz +3 -0
  19. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  20. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.9_ALL_FIELDS.csv.gz +3 -0
  21. data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv +14 -0
  22. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.5_ALL_FIELDS.csv.gz +3 -0
  23. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  24. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.6_ALL_FIELDS.csv.gz +3 -0
  25. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  26. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.7_ALL_FIELDS.csv.gz +3 -0
  27. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  28. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.8_ALL_FIELDS.csv.gz +3 -0
  29. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  30. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.9_ALL_FIELDS.csv.gz +3 -0
  31. data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv +14 -0
  32. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.5_ALL_FIELDS.csv.gz +3 -0
  33. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  34. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.6_ALL_FIELDS.csv.gz +3 -0
  35. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  36. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.7_ALL_FIELDS.csv.gz +3 -0
  37. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  38. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.8_ALL_FIELDS.csv.gz +3 -0
  39. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  40. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.9_ALL_FIELDS.csv.gz +3 -0
  41. data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv +14 -0
  42. data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.5_ALL_FIELDS.csv.gz +3 -0
  43. data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  44. data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.6_ALL_FIELDS.csv.gz +3 -0
  45. data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  46. data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.7_ALL_FIELDS.csv.gz +3 -0
  47. data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  48. data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.8_ALL_FIELDS.csv.gz +3 -0
  49. data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  50. data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.9_ALL_FIELDS.csv.gz +3 -0
.gitattributes CHANGED
@@ -50,3 +50,28 @@ data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.6_ALL_FIELDS.csv.gz
50
  data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
51
  data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
52
  data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
51
  data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
52
  data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
53
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
54
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
55
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
56
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
57
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
58
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
59
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
60
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
61
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
62
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
63
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
64
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
65
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
66
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
67
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
68
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
69
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
70
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
71
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
72
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
73
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
74
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
75
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
76
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
77
+ data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.5_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4005ad6f18f2d6de62a2c6fdab8149e1e4eb8e5b8a3790f2cdc622ab85c5b93f
3
+ size 1558301
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ desalting_process,3720,3720,1,,,10,0.5
3
+ elution_buffer,3530,3530,1,,,10,0.5
4
+ enzyme_name,7975,7974,1,,,10,0.5
5
+ expression_strain,5677,5677,1,,,10,0.5
6
+ inducer,7889,7889,1,,,10,0.5
7
+ induction_temperature,3656,3656,1,,,10,0.5
8
+ lysis_buffer,3714,3714,1,,,10,0.5
9
+ medium_name,4806,4806,1,,,10,0.5
10
+ molecular_weight,295,295,1,,,10,0.5
11
+ organism_source,6292,6292,1,,,10,0.5
12
+ plasmid,5480,5480,1,,,10,0.5
13
+ source_key,8021,8021,1,,,10,0.5
14
+ strain,2444,2444,1,,,10,0.5
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.6_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6abad8c4df456bd8fddab3dc3a7cc9e7a30813253da29fcad891c00b3e20b7f
3
+ size 1558407
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ desalting_process,3720,3717,1,,,10,0.6
3
+ elution_buffer,3530,3530,1,,,10,0.6
4
+ enzyme_name,7975,7963,1,,,10,0.6
5
+ expression_strain,5677,5677,1,,,10,0.6
6
+ inducer,7889,7889,1,,,10,0.6
7
+ induction_temperature,3656,3656,1,,,10,0.6
8
+ lysis_buffer,3714,3714,1,,,10,0.6
9
+ medium_name,4806,4797,1,,,10,0.6
10
+ molecular_weight,295,295,1,,,10,0.6
11
+ organism_source,6292,6291,1,,,10,0.6
12
+ plasmid,5480,5479,1,,,10,0.6
13
+ source_key,8021,8021,1,,,10,0.6
14
+ strain,2444,2444,1,,,10,0.6
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.7_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32ab559273f3f550008a630a2874bb28fc6f6e82f02a99d13bdcf1dab6abc7de
3
+ size 1566427
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ induction_temperature,3656,3656,4,0.6627772450447083,1.1823972748567493,10,0.7
3
+ lysis_buffer,3714,3712,3,0.6512054800987244,0.5597431189532935,10,0.7
4
+ elution_buffer,3530,3525,3,0.5317150354385376,0.9367101267444128,10,0.7
5
+ desalting_process,3720,3706,4,0.347188264131546,1.5986349181268862,10,0.7
6
+ organism_source,6292,6280,12,0.1915419101715088,2.521667636984773,10,0.7
7
+ plasmid,5480,5469,5,0.1896328330039978,3.425409702045188,10,0.7
8
+ medium_name,4806,4798,14,0.14736753702163696,2.4178326716435614,10,0.7
9
+ inducer,7889,7886,6,0.12862633168697357,3.204190195029217,10,0.7
10
+ enzyme_name,7975,7953,15,0.11348489671945572,3.514647735071455,10,0.7
11
+ expression_strain,5677,5672,1,,,10,0.7
12
+ molecular_weight,295,295,1,,,10,0.7
13
+ source_key,8021,8021,1,,,10,0.7
14
+ strain,2444,2442,1,,,10,0.7
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.8_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f40aff22cffff4dce541ad71690790eaa50a5a718f257d063adf4b93bd44e2
3
+ size 1598683
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ inducer,7889,7860,12,0.6319077014923096,2.137532021175971,10,0.8
3
+ strain,2444,2426,3,0.5695046782493591,1.3598672991119427,10,0.8
4
+ expression_strain,5677,5662,4,0.5600995421409607,1.6591133086482361,10,0.8
5
+ induction_temperature,3656,3643,6,0.44256794452667236,0.9276276107601739,10,0.8
6
+ lysis_buffer,3714,3689,15,0.4113427400588989,2.3560256621742095,10,0.8
7
+ molecular_weight,295,286,3,0.21472853422164917,1.7193933405595152,10,0.8
8
+ desalting_process,3720,3663,29,0.14809754490852356,2.6134126248370997,10,0.8
9
+ organism_source,6292,6201,32,0.11843235790729523,1.7218445877351405,10,0.8
10
+ elution_buffer,3530,3497,17,0.04049689695239067,2.28741624153559,10,0.8
11
+ medium_name,4806,4744,50,0.03293968737125397,2.7278527342424748,10,0.8
12
+ enzyme_name,7975,7800,85,0.022498253732919693,3.7066310196283667,10,0.8
13
+ plasmid,5480,5387,37,-0.06774506717920303,3.034729457616567,10,0.8
14
+ source_key,8021,8016,1,,,10,0.8
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.9_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a2a55f747e95ab20077908c5c40300d31694224d62857ecab3fbca43e38973
3
+ size 1642449
data/clustering/model=allenai__scibert_scivocab_uncased/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,6292,5789,42,0.8733616471290588,0.688214520897005,10,0.9
3
+ inducer,7889,7692,53,0.593494713306427,2.329531355134785,10,0.9
4
+ molecular_weight,295,234,5,0.5289047956466675,1.49154853121991,10,0.9
5
+ strain,2444,2306,20,0.3486863970756531,2.3095017409567733,10,0.9
6
+ induction_temperature,3656,3566,15,0.26848459243774414,1.489497011384619,10,0.9
7
+ source_key,8021,7967,25,0.22413617372512817,2.438281823097242,10,0.9
8
+ expression_strain,5677,5601,22,0.1667768955230713,2.0251820289461313,10,0.9
9
+ plasmid,5480,4344,99,0.14378848671913147,2.344800672298131,10,0.9
10
+ medium_name,4806,4044,85,0.13443398475646973,2.4307877203634396,10,0.9
11
+ lysis_buffer,3714,3466,36,0.1066657230257988,2.3836721448903577,10,0.9
12
+ desalting_process,3720,3116,65,0.08506450057029724,2.5474723208220116,10,0.9
13
+ elution_buffer,3530,3176,63,0.08221063762903214,2.7122350037709233,10,0.9
14
+ enzyme_name,7975,5646,146,0.038066498935222626,3.175632188216351,10,0.9
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.5_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:731a7b87f9f57bc0c4955c0ef55d8795a60c3ad27116f253636e46744fefa452
3
+ size 1558301
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ desalting_process,3720,3720,1,,,2,0.5
3
+ elution_buffer,3530,3530,1,,,2,0.5
4
+ enzyme_name,7975,7974,1,,,2,0.5
5
+ expression_strain,5677,5677,1,,,2,0.5
6
+ inducer,7889,7889,1,,,2,0.5
7
+ induction_temperature,3656,3656,1,,,2,0.5
8
+ lysis_buffer,3714,3714,1,,,2,0.5
9
+ medium_name,4806,4806,1,,,2,0.5
10
+ molecular_weight,295,295,1,,,2,0.5
11
+ organism_source,6292,6292,1,,,2,0.5
12
+ plasmid,5480,5480,1,,,2,0.5
13
+ source_key,8021,8021,1,,,2,0.5
14
+ strain,2444,2444,1,,,2,0.5
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.6_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3c08a9b6106bfd907445da95a2b8f4e93df583e4f41725dee18aa9571400fca
3
+ size 1559210
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ desalting_process,3720,3719,2,0.5046607255935669,0.5465752017603626,2,0.6
3
+ enzyme_name,7975,7974,5,0.3783629238605499,1.6372414511670677,2,0.6
4
+ medium_name,4806,4806,4,0.19658061861991882,2.068067229225386,2,0.6
5
+ elution_buffer,3530,3530,1,,,2,0.6
6
+ expression_strain,5677,5677,1,,,2,0.6
7
+ inducer,7889,7889,1,,,2,0.6
8
+ induction_temperature,3656,3656,1,,,2,0.6
9
+ lysis_buffer,3714,3714,1,,,2,0.6
10
+ molecular_weight,295,295,1,,,2,0.6
11
+ organism_source,6292,6291,1,,,2,0.6
12
+ plasmid,5480,5479,1,,,2,0.6
13
+ source_key,8021,8021,1,,,2,0.6
14
+ strain,2444,2444,1,,,2,0.6
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.7_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574ae70177b889b7a6b94413b1fa77fdef2d8aa5582033095f5fb9648308f23a
3
+ size 1568010
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ expression_strain,5677,5676,2,0.7273215651512146,0.3580780150539831,2,0.7
3
+ induction_temperature,3656,3656,7,0.6444817185401917,0.7892197605564716,2,0.7
4
+ lysis_buffer,3714,3714,5,0.6335355639457703,0.7461351528705394,2,0.7
5
+ elution_buffer,3530,3529,6,0.20170536637306213,1.0774166603364448,2,0.7
6
+ plasmid,5480,5478,13,0.15255507826805115,2.3897466827857854,2,0.7
7
+ organism_source,6292,6290,25,0.1519341766834259,1.7809959322076483,2,0.7
8
+ desalting_process,3720,3720,14,0.060512471944093704,1.0549027781153073,2,0.7
9
+ medium_name,4806,4804,31,0.02809773199260235,1.5675333882278357,2,0.7
10
+ enzyme_name,7975,7972,42,0.0018679153872653842,2.2523031141345586,2,0.7
11
+ inducer,7889,7888,7,-0.08286139369010925,2.849269636559066,2,0.7
12
+ molecular_weight,295,295,1,,,2,0.7
13
+ source_key,8021,8021,1,,,2,0.7
14
+ strain,2444,2442,1,,,2,0.7
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.8_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300a2dd219efc911b51e9ab1f3c9232584f221740c76c58e3302782c29fa7bc7
3
+ size 1604643
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ inducer,7889,7884,29,0.6104239225387573,1.4440317893646206,2,0.8
3
+ source_key,8021,8020,3,0.5819582343101501,0.47155582609184904,2,0.8
4
+ expression_strain,5677,5673,8,0.5116296410560608,1.2754380743232214,2,0.8
5
+ strain,2444,2442,11,0.5082018375396729,1.5746010745390977,2,0.8
6
+ induction_temperature,3656,3656,15,0.3688565194606781,0.8257841639466411,2,0.8
7
+ lysis_buffer,3714,3709,44,0.25828009843826294,1.2873195106814859,2,0.8
8
+ organism_source,6292,6282,65,0.12260919064283371,1.396477319723267,2,0.8
9
+ molecular_weight,295,295,11,0.12151861935853958,1.8539726174658613,2,0.8
10
+ desalting_process,3720,3711,89,0.05191513150930405,1.5851566777536485,2,0.8
11
+ elution_buffer,3530,3527,42,0.023788681253790855,1.6927704653033655,2,0.8
12
+ medium_name,4806,4799,127,-0.022193608805537224,1.6994699497668582,2,0.8
13
+ enzyme_name,7975,7932,270,-0.030749863013625145,2.2730291088327577,2,0.8
14
+ plasmid,5480,5457,88,-0.0919530987739563,2.1235462078950107,2,0.8
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.9_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80fc34f0189e7ca6e2d716cf3e1a4bc9ce1685a9a5f1f71795849961e025f12
3
+ size 1699781
data/clustering/model=allenai__scibert_scivocab_uncased/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,6292,6203,163,0.8686584234237671,0.5873112468192365,2,0.9
3
+ inducer,7889,7844,159,0.5482650399208069,1.5583810792295352,2,0.9
4
+ strain,2444,2427,76,0.2827732563018799,1.4374286041016406,2,0.9
5
+ molecular_weight,295,285,26,0.23288972675800323,1.457620119862179,2,0.9
6
+ source_key,8021,8020,68,0.15553538501262665,1.4186058651246507,2,0.9
7
+ expression_strain,5677,5659,59,0.15145327150821686,1.4777384758032481,2,0.9
8
+ plasmid,5480,5151,448,0.1419195532798767,1.5373288212546268,2,0.9
9
+ medium_name,4806,4663,374,0.1350567787885666,1.462412897468189,2,0.9
10
+ induction_temperature,3656,3638,44,0.11852046102285385,1.1065257640061932,2,0.9
11
+ lysis_buffer,3714,3662,151,0.08576786518096924,1.2524176981686574,2,0.9
12
+ desalting_process,3720,3568,280,0.07909117639064789,1.478940198107327,2,0.9
13
+ elution_buffer,3530,3457,246,0.03994994983077049,1.6083889081049658,2,0.9
14
+ enzyme_name,7975,7248,838,0.037669889628887177,1.7528244943553992,2,0.9
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.5_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d10a2c4c416a6fb60b1f1bdd6309c26939375567581ded54bee2d4c876f6c8e
3
+ size 1558301
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ desalting_process,3720,3720,1,,,20,0.5
3
+ elution_buffer,3530,3530,1,,,20,0.5
4
+ enzyme_name,7975,7974,1,,,20,0.5
5
+ expression_strain,5677,5677,1,,,20,0.5
6
+ inducer,7889,7889,1,,,20,0.5
7
+ induction_temperature,3656,3656,1,,,20,0.5
8
+ lysis_buffer,3714,3714,1,,,20,0.5
9
+ medium_name,4806,4806,1,,,20,0.5
10
+ molecular_weight,295,295,1,,,20,0.5
11
+ organism_source,6292,6292,1,,,20,0.5
12
+ plasmid,5480,5480,1,,,20,0.5
13
+ source_key,8021,8021,1,,,20,0.5
14
+ strain,2444,2444,1,,,20,0.5
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.6_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:086e79a661ed929c0005c139d47fc3ad1f5bc1800d97d02f76f34c244dde8adb
3
+ size 1558407
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ desalting_process,3720,3717,1,,,20,0.6
3
+ elution_buffer,3530,3530,1,,,20,0.6
4
+ enzyme_name,7975,7963,1,,,20,0.6
5
+ expression_strain,5677,5677,1,,,20,0.6
6
+ inducer,7889,7889,1,,,20,0.6
7
+ induction_temperature,3656,3656,1,,,20,0.6
8
+ lysis_buffer,3714,3714,1,,,20,0.6
9
+ medium_name,4806,4797,1,,,20,0.6
10
+ molecular_weight,295,295,1,,,20,0.6
11
+ organism_source,6292,6291,1,,,20,0.6
12
+ plasmid,5480,5479,1,,,20,0.6
13
+ source_key,8021,8021,1,,,20,0.6
14
+ strain,2444,2444,1,,,20,0.6
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.7_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f675686d22da049d3777504c9c1d84c698d359ed0c5d17a7e81abf08727681c0
3
+ size 1564571
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ lysis_buffer,3714,3697,2,0.7049791216850281,0.547591009804754,20,0.7
3
+ induction_temperature,3656,3656,3,0.6845682859420776,0.606578411248807,20,0.7
4
+ elution_buffer,3530,3514,2,0.584594190120697,0.8433117454662783,20,0.7
5
+ desalting_process,3720,3699,3,0.4134037494659424,1.3551602221273702,20,0.7
6
+ plasmid,5480,5444,2,0.27559787034988403,2.9936732252957965,20,0.7
7
+ medium_name,4806,4790,9,0.20659440755844116,2.981056719726013,20,0.7
8
+ organism_source,6292,6270,8,0.20566721260547638,2.762361368206177,20,0.7
9
+ inducer,7889,7885,4,0.13935799896717072,2.0380549710772096,20,0.7
10
+ enzyme_name,7975,7937,10,0.12720035016536713,3.5991064615986588,20,0.7
11
+ expression_strain,5677,5672,1,,,20,0.7
12
+ molecular_weight,295,295,1,,,20,0.7
13
+ source_key,8021,8021,1,,,20,0.7
14
+ strain,2444,2442,1,,,20,0.7
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.8_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1fc3e1e4b77b4d0768cf5d0c4580707c162a0446054efc5a84608f8154b98ed
3
+ size 1589943
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ inducer,7889,7835,7,0.6386350393295288,2.038314736297951,20,0.8
3
+ expression_strain,5677,5649,3,0.5636011362075806,1.166848016044762,20,0.8
4
+ induction_temperature,3656,3633,5,0.46175822615623474,0.7536326560555656,20,0.8
5
+ lysis_buffer,3714,3664,8,0.40172040462493896,2.6191856195210708,20,0.8
6
+ desalting_process,3720,3647,18,0.15723207592964172,3.253854701395701,20,0.8
7
+ organism_source,6292,6157,21,0.10941556096076965,1.8531291581211857,20,0.8
8
+ elution_buffer,3530,3462,10,0.05491543933749199,3.1950476718498693,20,0.8
9
+ medium_name,4806,4682,29,0.036153048276901245,3.0125029167355035,20,0.8
10
+ enzyme_name,7975,7663,47,0.032765280455350876,4.4400197334953955,20,0.8
11
+ plasmid,5480,5319,23,-0.03853259235620499,3.3704625839475715,20,0.8
12
+ molecular_weight,295,261,1,,,20,0.8
13
+ source_key,8021,8016,1,,,20,0.8
14
+ strain,2444,2403,1,,,20,0.8
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.9_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71786ef9eb6aaef7db77b04c695d565bdbd2cd2e9c7dd2d472d8e6c5ad4b2c3e
3
+ size 1610291
data/clustering/model=allenai__scibert_scivocab_uncased/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,6292,5534,21,0.8782880902290344,0.6365580798750166,20,0.9
3
+ inducer,7889,7594,31,0.6224454045295715,2.385876788770475,20,0.9
4
+ molecular_weight,295,212,3,0.6095542311668396,1.0829931944618536,20,0.9
5
+ strain,2444,2246,11,0.36441531777381897,2.9873650467684816,20,0.9
6
+ induction_temperature,3656,3506,9,0.28357774019241333,1.239502198409213,20,0.9
7
+ source_key,8021,7937,17,0.2490386664867401,2.7278160674384284,20,0.9
8
+ expression_strain,5677,5546,13,0.1667066514492035,2.1892559549282002,20,0.9
9
+ plasmid,5480,3956,49,0.16226057708263397,2.613297278929496,20,0.9
10
+ medium_name,4806,3721,43,0.13695277273654938,3.0492271120379146,20,0.9
11
+ lysis_buffer,3714,3332,18,0.1197529211640358,2.8503344094360488,20,0.9
12
+ elution_buffer,3530,2938,32,0.09622426331043243,3.207443075047453,20,0.9
13
+ desalting_process,3720,2960,37,0.0782092809677124,2.9219434006151634,20,0.9
14
+ enzyme_name,7975,5131,73,0.04491160437464714,3.6584696987515777,20,0.9
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.5_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aacea777a0077246cead5877ea91db929d1383390e98292b57567e9f0ac8f852
3
+ size 1558301
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ desalting_process,3720,3720,1,,,30,0.5
3
+ elution_buffer,3530,3530,1,,,30,0.5
4
+ enzyme_name,7975,7974,1,,,30,0.5
5
+ expression_strain,5677,5677,1,,,30,0.5
6
+ inducer,7889,7889,1,,,30,0.5
7
+ induction_temperature,3656,3656,1,,,30,0.5
8
+ lysis_buffer,3714,3714,1,,,30,0.5
9
+ medium_name,4806,4806,1,,,30,0.5
10
+ molecular_weight,295,295,1,,,30,0.5
11
+ organism_source,6292,6292,1,,,30,0.5
12
+ plasmid,5480,5480,1,,,30,0.5
13
+ source_key,8021,8021,1,,,30,0.5
14
+ strain,2444,2444,1,,,30,0.5
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.6_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:086e79a661ed929c0005c139d47fc3ad1f5bc1800d97d02f76f34c244dde8adb
3
+ size 1558407
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ desalting_process,3720,3717,1,,,30,0.6
3
+ elution_buffer,3530,3530,1,,,30,0.6
4
+ enzyme_name,7975,7963,1,,,30,0.6
5
+ expression_strain,5677,5677,1,,,30,0.6
6
+ inducer,7889,7889,1,,,30,0.6
7
+ induction_temperature,3656,3656,1,,,30,0.6
8
+ lysis_buffer,3714,3714,1,,,30,0.6
9
+ medium_name,4806,4797,1,,,30,0.6
10
+ molecular_weight,295,295,1,,,30,0.6
11
+ organism_source,6292,6291,1,,,30,0.6
12
+ plasmid,5480,5479,1,,,30,0.6
13
+ source_key,8021,8021,1,,,30,0.6
14
+ strain,2444,2444,1,,,30,0.6
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.7_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d686706183ea83af0e8ea7de96b33ab6edf07cf767e8f222c695a17092c3da5
3
+ size 1564137
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ lysis_buffer,3714,3711,2,0.6859591603279114,1.061737235298568,30,0.7
3
+ induction_temperature,3656,3656,3,0.6845682859420776,0.606578411248807,30,0.7
4
+ desalting_process,3720,3695,2,0.5643947124481201,0.9861700503261336,30,0.7
5
+ plasmid,5480,5449,2,0.2872803807258606,2.914194045706897,30,0.7
6
+ medium_name,4806,4756,6,0.21389955282211304,3.2264113765711646,30,0.7
7
+ organism_source,6292,6265,7,0.2083117514848709,2.9361478378100045,30,0.7
8
+ enzyme_name,7975,7927,7,0.14433211088180542,3.4761818616040334,30,0.7
9
+ inducer,7889,7859,3,0.1424984633922577,1.2425167228591067,30,0.7
10
+ elution_buffer,3530,3493,1,,,30,0.7
11
+ expression_strain,5677,5672,1,,,30,0.7
12
+ molecular_weight,295,295,1,,,30,0.7
13
+ source_key,8021,8021,1,,,30,0.7
14
+ strain,2444,2442,1,,,30,0.7
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.8_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa7f112eecaa9d3cc4cc41d0ce80dafc475c43a286813abfc631b2cf938c110
3
+ size 1583356
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ inducer,7889,7815,6,0.6423656940460205,1.9956477158764063,30,0.8
3
+ expression_strain,5677,5638,2,0.5961320996284485,1.2577751695022001,30,0.8
4
+ lysis_buffer,3714,3600,4,0.5018066167831421,2.3054553276594225,30,0.8
5
+ induction_temperature,3656,3633,4,0.46488967537879944,0.7723206216281062,30,0.8
6
+ desalting_process,3720,3594,12,0.1714477837085724,3.2381968105205163,30,0.8
7
+ organism_source,6292,6060,16,0.10731783509254456,1.7578808042942025,30,0.8
8
+ elution_buffer,3530,3394,6,0.06213323026895523,3.251761511147142,30,0.8
9
+ enzyme_name,7975,7597,36,0.05154474824666977,4.54071701245485,30,0.8
10
+ medium_name,4806,4615,21,0.03273481875658035,3.201950158826976,30,0.8
11
+ plasmid,5480,5289,17,-0.02933574467897415,3.5127946905532297,30,0.8
12
+ molecular_weight,295,261,1,,,30,0.8
13
+ source_key,8021,8016,1,,,30,0.8
14
+ strain,2444,2403,1,,,30,0.8
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.9_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900bc97fdd4eac251543a1f2992e75733944830b017a9dbac72c25429727d3d5
3
+ size 1589941
data/clustering/model=allenai__scibert_scivocab_uncased/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ organism_source,6292,5346,13,0.8839830756187439,0.6108984121801071,30,0.9
3
+ inducer,7889,7505,21,0.6298406720161438,2.5105820379040003,30,0.9
4
+ molecular_weight,295,212,3,0.6095542311668396,1.0829931944618536,30,0.9
5
+ strain,2444,2192,7,0.375827431678772,3.0776355399558732,30,0.9
6
+ induction_temperature,3656,3481,8,0.28172048926353455,1.2934043993308943,30,0.9
7
+ source_key,8021,7896,11,0.2649918496608734,2.8003039039423454,30,0.9
8
+ expression_strain,5677,5528,11,0.21119418740272522,2.1439638745734553,30,0.9
9
+ plasmid,5480,3768,33,0.19401319324970245,2.554745179594176,30,0.9
10
+ medium_name,4806,3524,27,0.15977458655834198,2.8540503609616046,30,0.9
11
+ lysis_buffer,3714,3267,11,0.13374441862106323,2.689937452468055,30,0.9
12
+ elution_buffer,3530,2794,22,0.10247805714607239,3.3111909344192894,30,0.9
13
+ desalting_process,3720,2782,23,0.08839929103851318,3.175021057883283,30,0.9
14
+ enzyme_name,7975,4897,52,0.0703735202550888,3.8467919700885465,30,0.9
data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.5_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d10a2c4c416a6fb60b1f1bdd6309c26939375567581ded54bee2d4c876f6c8e
3
+ size 1558301
data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ desalting_process,3720,3720,1,,,5,0.5
3
+ elution_buffer,3530,3530,1,,,5,0.5
4
+ enzyme_name,7975,7974,1,,,5,0.5
5
+ expression_strain,5677,5677,1,,,5,0.5
6
+ inducer,7889,7889,1,,,5,0.5
7
+ induction_temperature,3656,3656,1,,,5,0.5
8
+ lysis_buffer,3714,3714,1,,,5,0.5
9
+ medium_name,4806,4806,1,,,5,0.5
10
+ molecular_weight,295,295,1,,,5,0.5
11
+ organism_source,6292,6292,1,,,5,0.5
12
+ plasmid,5480,5480,1,,,5,0.5
13
+ source_key,8021,8021,1,,,5,0.5
14
+ strain,2444,2444,1,,,5,0.5
data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.6_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67ae2ac49d5282dd5715c98491d0e6d62cb845e1a566ed654e50b8bf629b08f
3
+ size 1558974
data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ enzyme_name,7975,7969,2,0.4107092320919037,1.8781822233629166,5,0.6
3
+ medium_name,4806,4804,2,0.2345324456691742,1.4685700946107538,5,0.6
4
+ desalting_process,3720,3717,1,,,5,0.6
5
+ elution_buffer,3530,3530,1,,,5,0.6
6
+ expression_strain,5677,5677,1,,,5,0.6
7
+ inducer,7889,7889,1,,,5,0.6
8
+ induction_temperature,3656,3656,1,,,5,0.6
9
+ lysis_buffer,3714,3714,1,,,5,0.6
10
+ molecular_weight,295,295,1,,,5,0.6
11
+ organism_source,6292,6291,1,,,5,0.6
12
+ plasmid,5480,5479,1,,,5,0.6
13
+ source_key,8021,8021,1,,,5,0.6
14
+ strain,2444,2444,1,,,5,0.6
data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.7_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e15a71c7f41b57024bef70cc23625b28e45554b6a617d7034c0799b82a9e65
3
+ size 1567887
data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ lysis_buffer,3714,3712,3,0.6512054800987244,0.5597431189532935,5,0.7
3
+ induction_temperature,3656,3656,6,0.6473343968391418,0.8044480546567586,5,0.7
4
+ elution_buffer,3530,3529,5,0.2063065767288208,1.3136933189567448,5,0.7
5
+ organism_source,6292,6286,17,0.18935686349868774,2.108034511000943,5,0.7
6
+ plasmid,5480,5474,8,0.17066426575183868,2.8832450077358267,5,0.7
7
+ inducer,7889,7886,6,0.12862633168697357,3.204190195029217,5,0.7
8
+ medium_name,4806,4801,21,0.11261620372533798,1.9526939619158872,5,0.7
9
+ desalting_process,3720,3710,6,0.09735189378261566,1.3861205092035576,5,0.7
10
+ enzyme_name,7975,7958,23,0.06259457021951675,3.0606052529832763,5,0.7
11
+ expression_strain,5677,5672,1,,,5,0.7
12
+ molecular_weight,295,295,1,,,5,0.7
13
+ source_key,8021,8021,1,,,5,0.7
14
+ strain,2444,2442,1,,,5,0.7
data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.8_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c9da257194aa19d0d554949a89c7b7f677449c001ce81d40a4e0ac1750e0a4
3
+ size 1602717
data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold
2
+ inducer,7889,7876,18,0.6140725612640381,1.7929812963791087,5,0.8
3
+ expression_strain,5677,5662,4,0.5600995421409607,1.6591133086482361,5,0.8
4
+ strain,2444,2440,7,0.5327019095420837,1.7811357961044603,5,0.8
5
+ induction_temperature,3656,3643,7,0.41915184259414673,0.9005930866018999,5,0.8
6
+ lysis_buffer,3714,3696,24,0.2619318664073944,1.812448478884626,5,0.8
7
+ molecular_weight,295,290,5,0.17197100818157196,1.9422738555967345,5,0.8
8
+ desalting_process,3720,3692,47,0.13909035921096802,2.2214048410614784,5,0.8
9
+ organism_source,6292,6257,46,0.12127161771059036,1.6607714395631863,5,0.8
10
+ elution_buffer,3530,3513,24,0.0414656400680542,2.049038785661106,5,0.8
11
+ medium_name,4806,4762,74,0.011377749964594841,2.2295169593707054,5,0.8
12
+ enzyme_name,7975,7860,135,0.005950124002993107,3.1460188368429884,5,0.8
13
+ plasmid,5480,5441,54,-0.07570110261440277,2.6212905554031685,5,0.8
14
+ source_key,8021,8016,1,,,5,0.8
data/clustering/model=allenai__scibert_scivocab_uncased/min=5/t=0.9_ALL_FIELDS.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1614228de6183291b158b25fb8372e8d9f04a9208e49caa3418cdce8604968
3
+ size 1673594