richiam commited on
Commit
3e7647f
·
verified ·
1 Parent(s): e09fd63

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=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.5_ALL_FIELDS.csv.gz +3 -0
  3. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  4. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.6_ALL_FIELDS.csv.gz +3 -0
  5. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  6. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.7_ALL_FIELDS.csv.gz +3 -0
  7. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  8. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.8_ALL_FIELDS.csv.gz +3 -0
  9. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  10. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.9_ALL_FIELDS.csv.gz +3 -0
  11. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv +14 -0
  12. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.5_ALL_FIELDS.csv.gz +3 -0
  13. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  14. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.6_ALL_FIELDS.csv.gz +3 -0
  15. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  16. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.7_ALL_FIELDS.csv.gz +3 -0
  17. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  18. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.8_ALL_FIELDS.csv.gz +3 -0
  19. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  20. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.9_ALL_FIELDS.csv.gz +3 -0
  21. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv +14 -0
  22. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.5_ALL_FIELDS.csv.gz +3 -0
  23. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  24. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.6_ALL_FIELDS.csv.gz +3 -0
  25. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  26. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.7_ALL_FIELDS.csv.gz +3 -0
  27. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  28. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.8_ALL_FIELDS.csv.gz +3 -0
  29. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  30. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.9_ALL_FIELDS.csv.gz +3 -0
  31. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv +14 -0
  32. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.5_ALL_FIELDS.csv.gz +3 -0
  33. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  34. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.6_ALL_FIELDS.csv.gz +3 -0
  35. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  36. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.7_ALL_FIELDS.csv.gz +3 -0
  37. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  38. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.8_ALL_FIELDS.csv.gz +3 -0
  39. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  40. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.9_ALL_FIELDS.csv.gz +3 -0
  41. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv +14 -0
  42. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.5_ALL_FIELDS.csv.gz +3 -0
  43. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv +14 -0
  44. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.6_ALL_FIELDS.csv.gz +3 -0
  45. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv +14 -0
  46. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.7_ALL_FIELDS.csv.gz +3 -0
  47. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv +14 -0
  48. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.8_ALL_FIELDS.csv.gz +3 -0
  49. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv +14 -0
  50. data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.9_ALL_FIELDS.csv.gz +3 -0
.gitattributes CHANGED
@@ -225,3 +225,28 @@ data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.6_ALL_F
225
  data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
226
  data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
227
  data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
225
  data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
226
  data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
227
  data/clustering/model=pritamdeka__S-BioBert-snli-multinli-stsb/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
228
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
229
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
230
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
231
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
232
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
233
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
234
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
235
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
236
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
237
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
238
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
239
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
240
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
241
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
242
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
243
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
244
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
245
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
246
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
247
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
248
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
249
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
250
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
251
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
252
+ data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:75a9282189ac05b23ee5dbc8800e3f71d9142980ad73e2585db4fb1e43b4b68d
3
+ size 2599265
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9596,51,0.7460201978683472,1.6887730934060938,10,0.5
3
+ inducer,11954,11872,39,0.5273939967155457,2.1744469258014374,10,0.5
4
+ induction_temperature,5383,5378,13,0.473476380109787,1.8148764512513564,10,0.5
5
+ expression_strain,8268,8173,23,0.365772008895874,2.3467884569021615,10,0.5
6
+ molecular_weight,495,482,5,0.28011366724967957,3.421290202866129,10,0.5
7
+ source_key,12179,12175,7,0.2602461278438568,2.187915670441884,10,0.5
8
+ strain,3834,3609,29,0.0859280377626419,2.4384739913703144,10,0.5
9
+ elution_buffer,5198,5072,64,0.06460962444543839,2.902420923138261,10,0.5
10
+ lysis_buffer,5625,5518,43,0.04666098952293396,2.804873789526554,10,0.5
11
+ plasmid,8217,7760,159,0.018768208101391792,3.344110308632014,10,0.5
12
+ enzyme_name,12099,10423,438,0.007272707298398018,3.284777301312303,10,0.5
13
+ medium_name,7644,7401,103,-0.01754457876086235,2.7640458006606234,10,0.5
14
+ desalting_process,5540,5377,63,-0.035330772399902344,3.1115545698874447,10,0.5
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:7b4e0c57e34393696ac973eea1d7181149b79e199bfd57635883cfb60a6ab192
3
+ size 2607220
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9369,45,0.7690165638923645,0.9254316207534041,10,0.6
3
+ inducer,11954,11745,41,0.6220369935035706,2.1499132713415694,10,0.6
4
+ strain,3834,3396,29,0.4679825007915497,2.1215490653718225,10,0.6
5
+ induction_temperature,5383,5342,15,0.4243480861186981,2.1610119381809327,10,0.6
6
+ expression_strain,8268,8052,32,0.27054449915885925,2.266023549345032,10,0.6
7
+ molecular_weight,495,451,7,0.2527922987937927,2.973337869247824,10,0.6
8
+ enzyme_name,12099,7321,341,0.11924233287572861,2.6156596931767426,10,0.6
9
+ source_key,12179,12173,40,0.101241834461689,2.9081997110910507,10,0.6
10
+ plasmid,8217,6882,187,0.09228947758674622,3.008170447026438,10,0.6
11
+ medium_name,7644,6929,134,0.08985279500484467,2.7538009772546386,10,0.6
12
+ elution_buffer,5198,4841,112,0.023976845666766167,2.932002058249657,10,0.6
13
+ desalting_process,5540,5078,125,-0.012747454456984997,2.8750545637804517,10,0.6
14
+ lysis_buffer,5625,5307,74,-0.03438568115234375,2.9349518510739196,10,0.6
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:84d5801be7dcd40b54a380b271c921e94d31589f31485f7a34ae80f4eb38cb05
3
+ size 2580365
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9256,43,0.9203191995620728,0.6735050627226745,10,0.7
3
+ inducer,11954,11598,70,0.5961443185806274,2.3824719692751026,10,0.7
4
+ strain,3834,3088,39,0.5060166120529175,1.4541856249350005,10,0.7
5
+ expression_strain,8268,7820,63,0.414533793926239,2.0499527288757866,10,0.7
6
+ enzyme_name,12099,3963,195,0.34467777609825134,1.759643232905823,10,0.7
7
+ molecular_weight,495,365,7,0.28069156408309937,1.9998089247437199,10,0.7
8
+ induction_temperature,5383,5292,23,0.19382092356681824,2.0739905916828034,10,0.7
9
+ plasmid,8217,5401,146,0.15947742760181427,2.474931846214174,10,0.7
10
+ medium_name,7644,6011,139,0.07719448953866959,2.4393840147006634,10,0.7
11
+ desalting_process,5540,4216,143,0.06864091008901596,2.6699689251969914,10,0.7
12
+ elution_buffer,5198,4264,119,-0.0048587084747850895,2.6919543909653623,10,0.7
13
+ source_key,12179,12016,113,-0.02704201266169548,2.7953254923022044,10,0.7
14
+ lysis_buffer,5625,4850,109,-0.03320225328207016,2.778057491841044,10,0.7
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:c53df9bc5a100ac145017aabb9c48726dfbfd64f6920d1c4adbd6c3ab434c899
3
+ size 2487577
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9083,47,0.955744743347168,0.46082271223380544,10,0.8
3
+ strain,3834,2668,39,0.690335214138031,0.9451420765614943,10,0.8
4
+ inducer,11954,11215,88,0.6349779367446899,1.9961216902901868,10,0.8
5
+ enzyme_name,12099,1652,87,0.6116449236869812,0.9881129288967144,10,0.8
6
+ expression_strain,8268,7265,79,0.5255471467971802,1.2672469131578,10,0.8
7
+ plasmid,8217,3613,111,0.26736465096473694,1.601540650702087,10,0.8
8
+ desalting_process,5540,2362,102,0.22686031460762024,2.0346584710217366,10,0.8
9
+ induction_temperature,5383,5120,25,0.20523770153522491,1.618335994253824,10,0.8
10
+ medium_name,7644,4503,118,0.2031335085630417,2.0630460210936405,10,0.8
11
+ molecular_weight,495,279,9,0.2013857364654541,2.372094332623716,10,0.8
12
+ elution_buffer,5198,3108,107,0.1381397247314453,2.1344197927477366,10,0.8
13
+ source_key,12179,11149,312,0.04135052114725113,2.1779882426680404,10,0.8
14
+ lysis_buffer,5625,3900,132,0.033819250762462616,2.563921520194219,10,0.8
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:c1c8670413efc01c2dc5774a34475432b6be49fc46181b0c2b7351aa0f4c1d36
3
+ size 2373745
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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,9834,8969,46,0.9970184564590454,0.26733536430925814,10,0.9
3
+ strain,3834,2425,33,0.9137516021728516,0.3813182449561522,10,0.9
4
+ enzyme_name,12099,759,48,0.7379592657089233,0.7240564878294999,10,0.9
5
+ inducer,11954,10420,78,0.7260915637016296,1.4300686158179077,10,0.9
6
+ desalting_process,5540,838,44,0.6956301927566528,0.9087862554771149,10,0.9
7
+ plasmid,8217,2301,78,0.6033712029457092,0.7231066189376532,10,0.9
8
+ expression_strain,8268,6647,77,0.5771089196205139,0.7641760157403331,10,0.9
9
+ medium_name,7644,2831,91,0.571212887763977,1.0891205854978088,10,0.9
10
+ source_key,12179,6820,329,0.5558285713195801,1.122890079174709,10,0.9
11
+ induction_temperature,5383,4846,28,0.5557082891464233,0.7739951945420042,10,0.9
12
+ molecular_weight,495,167,9,0.4197975695133209,1.3174185983646456,10,0.9
13
+ elution_buffer,5198,1516,58,0.40572789311408997,1.4002709522834251,10,0.9
14
+ lysis_buffer,5625,1890,91,0.39623644948005676,1.476158393049321,10,0.9
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:9966b365b1e546641f17968230e1985c78ea15b67526b26d794377346401d6eb
3
+ size 2650979
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9796,128,0.7330772280693054,1.2177437672812101,2,0.5
3
+ inducer,11954,11936,128,0.49493980407714844,1.543483755535246,2,0.5
4
+ induction_temperature,5383,5380,26,0.45671167969703674,1.2940881820451202,2,0.5
5
+ expression_strain,8268,8261,73,0.3578158915042877,1.634625170020749,2,0.5
6
+ source_key,12179,12179,15,0.24524171650409698,1.5404349963214974,2,0.5
7
+ molecular_weight,495,494,13,0.24103260040283203,2.517173559649244,2,0.5
8
+ strain,3834,3803,127,0.06624983251094818,1.4944871694622301,2,0.5
9
+ elution_buffer,5198,5177,193,0.0035868072882294655,1.9368861321013193,2,0.5
10
+ lysis_buffer,5625,5614,146,0.002002735622227192,1.663814134961166,2,0.5
11
+ plasmid,8217,8147,546,-0.018121693283319473,2.11264454379486,2,0.5
12
+ medium_name,7644,7610,310,-0.025155536830425262,1.752036109513151,2,0.5
13
+ enzyme_name,12099,11846,1576,-0.0462726354598999,2.159034623266487,2,0.5
14
+ desalting_process,5540,5499,185,-0.06901531666517258,2.0008511639351783,2,0.5
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:f7f2f354a742689283b61fcbddf688b4cdd60dfea241b88d6e3debaa57ad20aa
3
+ size 2711310
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9772,162,0.7472842931747437,0.8623324670817736,2,0.6
3
+ inducer,11954,11913,139,0.5978211760520935,1.4397757072418784,2,0.6
4
+ strain,3834,3763,171,0.4080716073513031,1.269226110358989,2,0.6
5
+ induction_temperature,5383,5375,47,0.34694403409957886,1.406861242640833,2,0.6
6
+ expression_strain,8268,8238,109,0.22371354699134827,1.562504808025177,2,0.6
7
+ molecular_weight,495,486,24,0.17563697695732117,2.1822045882219094,2,0.6
8
+ medium_name,7644,7516,469,0.10115430504083633,1.6882540755825177,2,0.6
9
+ plasmid,8217,7924,785,0.06929244101047516,1.9065446411947606,2,0.6
10
+ enzyme_name,12099,11155,2008,0.0689069926738739,1.7882491662623405,2,0.6
11
+ source_key,12179,12176,86,0.06045494228601456,1.8640656038704326,2,0.6
12
+ elution_buffer,5198,5122,385,0.002002537250518799,1.841174508289693,2,0.6
13
+ desalting_process,5540,5420,415,-0.028971370309591293,1.8428108128607295,2,0.6
14
+ lysis_buffer,5625,5573,270,-0.057007141411304474,1.6980855004688897,2,0.6
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:ce06ae6b2c1ed5657f3654326ad65565b89cfac27835c5db08505826fc609232
3
+ size 2729725
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9745,182,0.9042774438858032,0.5929863929519255,2,0.7
3
+ inducer,11954,11884,218,0.5529628992080688,1.5312973819860363,2,0.7
4
+ strain,3834,3638,227,0.5036919116973877,1.022891145900225,2,0.7
5
+ expression_strain,8268,8186,221,0.3879445195198059,1.4086592165092016,2,0.7
6
+ enzyme_name,12099,9554,2111,0.3223089277744293,1.2795597199236275,2,0.7
7
+ plasmid,8217,7373,916,0.1709492951631546,1.5037244446594098,2,0.7
8
+ induction_temperature,5383,5367,69,0.16854745149612427,1.4974970382730906,2,0.7
9
+ molecular_weight,495,461,46,0.15808796882629395,1.6706423569327866,2,0.7
10
+ medium_name,7644,7282,691,0.1343625783920288,1.3998874253155262,2,0.7
11
+ desalting_process,5540,5149,633,0.1036912128329277,1.5854958806600874,2,0.7
12
+ elution_buffer,5198,4960,484,0.008607295341789722,1.684827977239222,2,0.7
13
+ lysis_buffer,5625,5470,437,-0.010889582335948944,1.537710598025551,2,0.7
14
+ source_key,12179,12171,298,-0.11043651401996613,1.675344210402772,2,0.7
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:36d3acc598996b22e5b39e11ba7af6549922895694cd7315f0137cf6952aa669
3
+ size 2701519
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9701,228,0.9497328400611877,0.4400848973646063,2,0.8
3
+ strain,3834,3474,305,0.6736136674880981,0.75227882413281,2,0.8
4
+ enzyme_name,12099,7474,2063,0.5968204736709595,0.8360650849137063,2,0.8
5
+ inducer,11954,11773,339,0.5678071975708008,1.2605893154729444,2,0.8
6
+ expression_strain,8268,8002,313,0.5150949954986572,0.9551490847625322,2,0.8
7
+ desalting_process,5540,4527,872,0.3925132155418396,1.0980996892728472,2,0.8
8
+ plasmid,8217,6452,1103,0.38407477736473083,1.0095113802655444,2,0.8
9
+ medium_name,7644,6766,913,0.2936963140964508,1.1163043335223213,2,0.8
10
+ molecular_weight,495,411,66,0.20805300772190094,1.2169009159027988,2,0.8
11
+ elution_buffer,5198,4511,684,0.2079390585422516,1.2476798769357005,2,0.8
12
+ lysis_buffer,5625,5189,679,0.12997141480445862,1.3319653929478348,2,0.8
13
+ induction_temperature,5383,5321,104,0.1063813641667366,1.1070196281055038,2,0.8
14
+ source_key,12179,12111,754,0.00840182788670063,1.5057357693905067,2,0.8
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:1d3e56733c698064950be94489ec82e9c5df83a27ac929986e755a5e47adaa55
3
+ size 2598514
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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,9834,9653,252,0.995211660861969,0.25672967764886956,2,0.9
3
+ strain,3834,3309,317,0.8627116680145264,0.3565827878115917,2,0.9
4
+ desalting_process,5540,3657,1012,0.8306248784065247,0.5327435491221582,2,0.9
5
+ enzyme_name,12099,5144,1652,0.8266789317131042,0.4725514550668031,2,0.9
6
+ plasmid,8217,5253,1101,0.7201522588729858,0.502181025363143,2,0.9
7
+ inducer,11954,11563,466,0.6757156848907471,0.8357730970927064,2,0.9
8
+ medium_name,7644,5958,1123,0.6756159067153931,0.590616209253433,2,0.9
9
+ elution_buffer,5198,3768,837,0.607062041759491,0.6750198101076686,2,0.9
10
+ expression_strain,8268,7796,424,0.5967133641242981,0.5373926967134398,2,0.9
11
+ lysis_buffer,5625,4476,958,0.5764248967170715,0.7611312265870879,2,0.9
12
+ source_key,12179,11697,1584,0.5564283132553101,0.817233956851559,2,0.9
13
+ induction_temperature,5383,5246,149,0.5447086691856384,0.5513262599973541,2,0.9
14
+ molecular_weight,495,333,65,0.4246528446674347,0.90019538932634,2,0.9
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:ba0a195b250705f644c319799ba972f1180f66e4b0b167a436cc0b5ad69d37eb
3
+ size 2550834
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9410,30,0.7545626759529114,1.7875745589155505,20,0.5
3
+ inducer,11954,11779,23,0.5381662845611572,2.51092890275953,20,0.5
4
+ induction_temperature,5383,5361,8,0.5083310008049011,1.72943282936312,20,0.5
5
+ molecular_weight,495,474,3,0.3823849856853485,3.62090573436553,20,0.5
6
+ expression_strain,8268,8183,17,0.37117764353752136,2.3366896562048463,20,0.5
7
+ source_key,12179,12162,3,0.30924925208091736,2.537872998316253,20,0.5
8
+ elution_buffer,5198,4970,37,0.10113094002008438,3.311825791931296,20,0.5
9
+ strain,3834,3491,14,0.09089567512273788,2.5381086076899844,20,0.5
10
+ lysis_buffer,5625,5409,23,0.058853667229413986,3.1067000154662674,20,0.5
11
+ plasmid,8217,7467,88,0.04227817803621292,3.7835981517997186,20,0.5
12
+ enzyme_name,12099,9272,220,0.024349844083189964,3.6851284204748533,20,0.5
13
+ medium_name,7644,7208,60,-0.007994486950337887,3.19581622259398,20,0.5
14
+ desalting_process,5540,5291,39,-0.02409580908715725,3.452604689953524,20,0.5
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:c11170b846ab1e604c0e3adb5f7f333255a775ce1da57a8cc90223b0d5b3334d
3
+ size 2538655
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9118,25,0.7736923098564148,0.9495526330685806,20,0.6
3
+ inducer,11954,11610,22,0.6432458758354187,2.1931652189252637,20,0.6
4
+ strain,3834,3247,17,0.48099657893180847,2.4045671747084065,20,0.6
5
+ molecular_weight,495,422,3,0.4389037489891052,2.630679979994922,20,0.6
6
+ induction_temperature,5383,5306,10,0.43808531761169434,2.16489858434415,20,0.6
7
+ expression_strain,8268,8014,23,0.30637988448143005,2.407208023355711,20,0.6
8
+ enzyme_name,12099,5230,126,0.11681858450174332,3.0280433456043294,20,0.6
9
+ plasmid,8217,6338,96,0.11124440282583237,3.324485799237337,20,0.6
10
+ source_key,12179,12117,24,0.11011461168527603,3.4812927808558967,20,0.6
11
+ medium_name,7644,6587,76,0.09596442431211472,3.209727063254655,20,0.6
12
+ elution_buffer,5198,4579,57,0.04882028326392174,3.260264078636643,20,0.6
13
+ desalting_process,5540,4798,67,-0.007492265198379755,3.4663110577259886,20,0.6
14
+ lysis_buffer,5625,5165,42,-0.01968666911125183,3.323258165641324,20,0.6
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:9634f50ac956d1f26965af692211a5fdcd14997ccfc85f50b8c3dd2d6740b674
3
+ size 2508892
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9003,24,0.9385966658592224,0.6856712948357284,20,0.7
3
+ inducer,11954,11419,39,0.6136992573738098,2.696942184122555,20,0.7
4
+ strain,3834,2888,20,0.5742690563201904,1.4089876202338536,20,0.7
5
+ expression_strain,8268,7605,39,0.4257473349571228,2.02997910491136,20,0.7
6
+ enzyme_name,12099,2216,52,0.3626209497451782,1.9176253721676912,20,0.7
7
+ molecular_weight,495,301,2,0.2804478108882904,2.727829433095843,20,0.7
8
+ induction_temperature,5383,5238,15,0.20305056869983673,1.925239482185454,20,0.7
9
+ plasmid,8217,4620,63,0.1792355179786682,2.7082481355451637,20,0.7
10
+ medium_name,7644,5592,76,0.10604217648506165,2.7123996607892904,20,0.7
11
+ desalting_process,5540,3657,71,0.060088787227869034,3.066542926248514,20,0.7
12
+ elution_buffer,5198,4002,68,0.019270263612270355,2.889558938248756,20,0.7
13
+ source_key,12179,11843,70,-0.009235946461558342,3.2553850878774075,20,0.7
14
+ lysis_buffer,5625,4545,57,-0.012638517655432224,3.249185252921317,20,0.7
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:cbf27f3bfc640e71943088fb2b7edca63ee4c56701bd8de803dbc2440ff76064
3
+ size 2425532
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,8749,22,0.961005449295044,0.43437749840605105,20,0.8
3
+ strain,3834,2392,18,0.7391887903213501,1.001143088459065,20,0.8
4
+ inducer,11954,10983,50,0.6610154509544373,2.1539679672500283,20,0.8
5
+ enzyme_name,12099,789,18,0.6184878349304199,1.028149246385555,20,0.8
6
+ expression_strain,8268,6805,42,0.5397751331329346,1.1940936917002776,20,0.8
7
+ plasmid,8217,2894,48,0.23509402573108673,1.9029582036411472,20,0.8
8
+ induction_temperature,5383,5029,14,0.2305130958557129,1.5277718344018987,20,0.8
9
+ medium_name,7644,3858,58,0.19556303322315216,2.3332877213245893,20,0.8
10
+ desalting_process,5540,1703,37,0.19179314374923706,2.3450759368021945,20,0.8
11
+ molecular_weight,495,226,3,0.16473272442817688,2.8247639610279536,20,0.8
12
+ elution_buffer,5198,2648,50,0.1305939108133316,2.3747508044887744,20,0.8
13
+ source_key,12179,9990,164,0.05262074992060661,2.5338683519624867,20,0.8
14
+ lysis_buffer,5625,3491,68,0.03416689485311508,2.9403020587993205,20,0.8
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:d347018a76a1833a14f7c2b9e981d74bb1fdb8485b5275371748cdd1e8b1cc8f
3
+ size 2329380
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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,9834,8639,21,0.9985089898109436,0.2457862285616127,20,0.9
3
+ strain,3834,2207,16,0.9272205829620361,0.3754318445869632,20,0.9
4
+ inducer,11954,10040,42,0.7506003379821777,1.4932936235962007,20,0.9
5
+ desalting_process,5540,425,11,0.7045263648033142,0.991718506570228,20,0.9
6
+ enzyme_name,12099,240,8,0.6632827520370483,0.9891145448411446,20,0.9
7
+ medium_name,7644,2176,34,0.5976153612136841,1.3637655225618008,20,0.9
8
+ expression_strain,8268,6252,46,0.5961406230926514,0.8538624269024279,20,0.9
9
+ induction_temperature,5383,4738,18,0.5923945307731628,0.8821502519559422,20,0.9
10
+ source_key,12179,4084,118,0.5856494903564453,1.1303735092425313,20,0.9
11
+ plasmid,8217,1717,28,0.5797383189201355,0.9286529169179578,20,0.9
12
+ elution_buffer,5198,1161,25,0.40900731086730957,1.5584319272428941,20,0.9
13
+ lysis_buffer,5625,1190,31,0.40274444222450256,1.458330820768114,20,0.9
14
+ molecular_weight,495,112,4,0.34911981225013733,1.644816337158467,20,0.9
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:0e1241848e93da47167923a01adf3a8e1710683d748f405f6ab28abcf7a0fe40
3
+ size 2522417
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9270,22,0.7595456838607788,1.8536159992832977,30,0.5
3
+ inducer,11954,11727,16,0.5489020943641663,2.593415868884513,30,0.5
4
+ induction_temperature,5383,5320,5,0.52628493309021,1.6498951594512536,30,0.5
5
+ molecular_weight,495,466,2,0.403279572725296,1.9174480903324922,30,0.5
6
+ expression_strain,8268,8108,12,0.3746895492076874,2.6633675584950005,30,0.5
7
+ source_key,12179,12140,2,0.32162854075431824,2.4398855912098973,30,0.5
8
+ elution_buffer,5198,4867,26,0.11239206045866013,3.338409435160434,30,0.5
9
+ strain,3834,3459,12,0.09261278808116913,2.636410840524985,30,0.5
10
+ lysis_buffer,5625,5316,15,0.08250151574611664,3.197233746869553,30,0.5
11
+ plasmid,8217,7270,65,0.047029733657836914,4.015105785303876,30,0.5
12
+ enzyme_name,12099,8360,137,0.037200361490249634,3.904599834165825,30,0.5
13
+ medium_name,7644,7038,42,-0.005229556933045387,3.4208674001627677,30,0.5
14
+ desalting_process,5540,5144,26,-0.011297185905277729,3.711215304610257,30,0.5
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:5e06fddf3ee8df3932ccfb5bf217d88f37625df7173bf9249aadaf7685d85eda
3
+ size 2502964
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9000,20,0.7784529328346252,0.9480141276519575,30,0.6
3
+ inducer,11954,11533,16,0.6466438174247742,1.9734534096867649,30,0.6
4
+ molecular_weight,495,407,2,0.5341723561286926,1.457017211705419,30,0.6
5
+ strain,3834,3232,15,0.4860413670539856,2.439473205160486,30,0.6
6
+ induction_temperature,5383,5332,9,0.44035106897354126,2.2972091756319366,30,0.6
7
+ expression_strain,8268,7939,16,0.3326137065887451,2.2667168302266525,30,0.6
8
+ enzyme_name,12099,4238,72,0.13740892708301544,3.017735741799952,30,0.6
9
+ plasmid,8217,6023,62,0.12114646285772324,3.5263697025271377,30,0.6
10
+ source_key,12179,12132,19,0.11861468106508255,3.9404219329391466,30,0.6
11
+ medium_name,7644,6412,58,0.09481208026409149,3.45155410082957,30,0.6
12
+ elution_buffer,5198,4503,43,0.05660587176680565,3.4475775554985355,30,0.6
13
+ desalting_process,5540,4597,46,-0.0004577396030072123,3.548530198495519,30,0.6
14
+ lysis_buffer,5625,5075,32,-0.015384052880108356,3.4571410499578414,30,0.6
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:083593d43371266b48ba47b49cced079d68ee53e71dd0cc0c623f886e098b165
3
+ size 2468850
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,8817,16,0.9444844722747803,0.5706785269089778,30,0.7
3
+ inducer,11954,11287,28,0.621810793876648,2.803540345095928,30,0.7
4
+ strain,3834,2654,10,0.6064627170562744,1.393106958450692,30,0.7
5
+ expression_strain,8268,7524,31,0.4314994215965271,2.069647361621258,30,0.7
6
+ enzyme_name,12099,1672,27,0.3712556064128876,2.205990090505188,30,0.7
7
+ induction_temperature,5383,5199,12,0.21620076894760132,1.7528651243092837,30,0.7
8
+ plasmid,8217,4224,40,0.1957389861345291,2.793365114687711,30,0.7
9
+ medium_name,7644,5239,47,0.1078391820192337,2.8113804770197235,30,0.7
10
+ desalting_process,5540,3363,47,0.07427738606929779,3.3059905940863947,30,0.7
11
+ elution_buffer,5198,3717,44,0.018902942538261414,3.1531135642881907,30,0.7
12
+ source_key,12179,11751,52,0.0036600232124328613,3.53563228311283,30,0.7
13
+ lysis_buffer,5625,4375,41,-0.008223122917115688,3.5184745817378955,30,0.7
14
+ molecular_weight,495,281,1,,,30,0.7
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:045829eb327f9076a169ec8e467adafeec3bb193e60cb80b9c164f7dcccb3d55
3
+ size 2389855
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,8670,19,0.9607642889022827,0.4429744344745803,30,0.8
3
+ strain,3834,2245,11,0.7380449771881104,0.879254105430165,30,0.8
4
+ inducer,11954,10795,37,0.6709197163581848,2.2765532760175304,30,0.8
5
+ enzyme_name,12099,525,7,0.6599843502044678,0.9439161638701282,30,0.8
6
+ expression_strain,8268,6453,26,0.554749608039856,1.140843557588623,30,0.8
7
+ molecular_weight,495,216,2,0.3021887540817261,2.0123216857043142,30,0.8
8
+ plasmid,8217,2589,32,0.2214026302099228,1.9202221133377861,30,0.8
9
+ induction_temperature,5383,4974,10,0.21705348789691925,1.4259128937408312,30,0.8
10
+ medium_name,7644,3625,43,0.2146606147289276,2.2501685323117973,30,0.8
11
+ desalting_process,5540,1400,21,0.2071319967508316,2.503990281967763,30,0.8
12
+ elution_buffer,5198,2344,29,0.13950017094612122,2.48493621270591,30,0.8
13
+ source_key,12179,9151,112,0.05147195979952812,2.7703354742997703,30,0.8
14
+ lysis_buffer,5625,3015,40,0.03762975335121155,2.9671702309639185,30,0.8
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:9afcb4239ca1647af3be1ca86ec62602d8ebe71dacd6174fe396729cfe15b5f3
3
+ size 2310471
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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,9834,8531,17,0.999043345451355,0.13374430934560377,30,0.9
3
+ strain,3834,2094,11,0.9275811314582825,0.3881873842842337,30,0.9
4
+ enzyme_name,12099,118,3,0.782673716545105,0.7102206298173654,30,0.9
5
+ desalting_process,5540,333,7,0.7715973854064941,0.8371344866276778,30,0.9
6
+ inducer,11954,9712,25,0.7659939527511597,1.623259525658633,30,0.9
7
+ medium_name,7644,1926,21,0.6770955920219421,1.0239245199136118,30,0.9
8
+ induction_temperature,5383,4645,14,0.6158416271209717,0.8400696601085839,30,0.9
9
+ expression_strain,8268,5846,27,0.6051554679870605,0.9872213684342688,30,0.9
10
+ source_key,12179,2936,68,0.6000562906265259,1.1084339667760912,30,0.9
11
+ plasmid,8217,1494,18,0.5934682488441467,1.0746292927475045,30,0.9
12
+ lysis_buffer,5625,864,16,0.4373406171798706,1.3972883833762948,30,0.9
13
+ elution_buffer,5198,974,16,0.43263691663742065,1.4698700314202966,30,0.9
14
+ molecular_weight,495,66,2,0.3739505410194397,1.6772175573473036,30,0.9
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:da46e89d3c82e749ca66b342f1b48156274a187e6aa3b5735cd851b58102a74a
3
+ size 2634111
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9707,75,0.7437057495117188,1.5224580968082047,5,0.5
3
+ inducer,11954,11907,70,0.5216519832611084,1.8930290206348628,5,0.5
4
+ induction_temperature,5383,5378,17,0.4647209942340851,1.6214147648863126,5,0.5
5
+ expression_strain,8268,8226,43,0.361826628446579,2.0860377581178637,5,0.5
6
+ molecular_weight,495,489,7,0.2675812542438507,3.1762779854939,5,0.5
7
+ source_key,12179,12172,8,0.25710582733154297,1.948883815528403,5,0.5
8
+ strain,3834,3715,59,0.0716174840927124,1.990286889887064,5,0.5
9
+ lysis_buffer,5625,5581,79,0.03385056555271149,2.3153778499955178,5,0.5
10
+ elution_buffer,5198,5125,104,0.03223052993416786,2.5575297916485464,5,0.5
11
+ plasmid,8217,7967,283,0.008708305656909943,2.816253992429704,5,0.5
12
+ enzyme_name,12099,11205,794,-0.010325651615858078,2.7851942187730305,5,0.5
13
+ medium_name,7644,7533,192,-0.018939759582281113,2.2289413917379517,5,0.5
14
+ desalting_process,5540,5447,104,-0.051097966730594635,2.6045172353521524,5,0.5
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:e7fa3510881107f6646c8781c57061b6710f4931c743113bcc0864050cd49e72
3
+ size 2665085
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9586,84,0.7535935044288635,0.9753474458700483,5,0.6
3
+ inducer,11954,11839,70,0.6059759855270386,1.8777092899939687,5,0.6
4
+ strain,3834,3564,62,0.45000457763671875,1.7566390749814549,5,0.6
5
+ induction_temperature,5383,5361,25,0.4054846167564392,1.8835613230446915,5,0.6
6
+ expression_strain,8268,8162,58,0.23977479338645935,1.9362351178156494,5,0.6
7
+ molecular_weight,495,471,14,0.20004130899906158,2.7070398918505973,5,0.6
8
+ enzyme_name,12099,9258,809,0.10060599446296692,2.2948530995579266,5,0.6
9
+ source_key,12179,12174,56,0.09327293932437897,2.448699674863992,5,0.6
10
+ medium_name,7644,7244,239,0.09265284985303879,2.2701133539831626,5,0.6
11
+ plasmid,8217,7351,344,0.08537054061889648,2.5764837136871535,5,0.6
12
+ elution_buffer,5198,4989,202,0.012056732550263405,2.4657655778088254,5,0.6
13
+ desalting_process,5540,5210,206,-0.023350464180111885,2.472664279804631,5,0.6
14
+ lysis_buffer,5625,5451,132,-0.047319259494543076,2.4223112041048456,5,0.6
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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:f82a86c48b9b482e08f813cd20cb76b3cc34202cbc8991eb4dc117f0515c9e68
3
+ size 2643342
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9486,80,0.9168286919593811,0.633453024465574,5,0.7
3
+ inducer,11954,11727,109,0.5882758498191833,2.0619733270501106,5,0.7
4
+ strain,3834,3310,82,0.49831676483154297,1.3927414572055679,5,0.7
5
+ expression_strain,8268,7984,103,0.4039284586906433,1.803062177229719,5,0.7
6
+ enzyme_name,12099,6058,566,0.33208125829696655,1.622664726871804,5,0.7
7
+ molecular_weight,495,411,16,0.23013721406459808,2.0616400451707526,5,0.7
8
+ induction_temperature,5383,5335,39,0.17531512677669525,1.8400882786618324,5,0.7
9
+ plasmid,8217,6136,305,0.15392045676708221,2.113404467795009,5,0.7
10
+ medium_name,7644,6578,286,0.1002240851521492,1.96701840919535,5,0.7
11
+ desalting_process,5540,4596,265,0.07085943222045898,2.239273576148579,5,0.7
12
+ elution_buffer,5198,4561,214,-0.0029381616041064262,2.347759853423207,5,0.7
13
+ lysis_buffer,5625,5113,196,-0.029453134164214134,2.2455845744076086,5,0.7
14
+ source_key,12179,12128,186,-0.06116426736116409,2.236348398517785,5,0.7
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:7f8031ec3ebfe50b3c5ce1184107aea90e6e66314edbb368330f76ec86aad875
3
+ size 2565577
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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
+ organism_source,9834,9349,90,0.9523667693138123,0.4548424049570813,5,0.8
3
+ strain,3834,2922,83,0.6567615270614624,0.8956261792346506,5,0.8
4
+ inducer,11954,11451,158,0.6239180564880371,1.7563620773501303,5,0.8
5
+ enzyme_name,12099,3394,379,0.5754901766777039,1.0148181856058383,5,0.8
6
+ expression_strain,8268,7559,128,0.5264717936515808,1.1717170713166603,5,0.8
7
+ plasmid,8217,4453,259,0.293895423412323,1.4098566954472547,5,0.8
8
+ desalting_process,5540,3201,263,0.29079824686050415,1.6116959614309834,5,0.8
9
+ medium_name,7644,5348,288,0.23630718886852264,1.6200442002824396,5,0.8
10
+ molecular_weight,495,325,19,0.16986966133117676,1.9131705487902544,5,0.8
11
+ induction_temperature,5383,5198,40,0.1512833833694458,1.4688680099025113,5,0.8
12
+ elution_buffer,5198,3621,231,0.1453622430562973,1.8359220269870584,5,0.8
13
+ lysis_buffer,5625,4372,254,0.06515921652317047,2.016508707071194,5,0.8
14
+ source_key,12179,11734,486,0.030177611857652664,1.8669660932663505,5,0.8
data/clustering/model=sentence-transformers__all-MiniLM-L6-v2/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 sha256:760e21171eff49d7fc55da38b374205455c32c72596a619771ac87ac01871c53
3
+ size 2437525