diff --git a/.gitattributes b/.gitattributes index 1cddae3d901968f918c46b9d8d32279d686d6fc5..c9fa21e5e70d4544885209a7100edd57bce96b00 100644 --- a/.gitattributes +++ b/.gitattributes @@ -25,3 +25,28 @@ data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.6_ALL_FIELDS.csv.gz data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text data/clustering/model=FremyCompany__BioLORD-2023-C/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.5_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.6_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.7_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.8_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text +data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.9_ALL_FIELDS.csv.gz filter=lfs diff=lfs merge=lfs -text diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..7dadff5814e74867d6b3464baa040d5e4ea6bdcf --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:661411730bda5255877d747a24e83aab84c9b0d2520d13b075db1678c9d16076 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..815b9c3a1ce44549aec9221ffb1d0940015f930e --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,10,0.5 +elution_buffer,3530,3530,1,,,10,0.5 +enzyme_name,7975,7975,1,,,10,0.5 +expression_strain,5677,5677,1,,,10,0.5 +inducer,7889,7889,1,,,10,0.5 +induction_temperature,3656,3656,1,,,10,0.5 +lysis_buffer,3714,3714,1,,,10,0.5 +medium_name,4806,4806,1,,,10,0.5 +molecular_weight,295,295,1,,,10,0.5 +organism_source,6292,6292,1,,,10,0.5 +plasmid,5480,5480,1,,,10,0.5 +source_key,8021,8021,1,,,10,0.5 +strain,2444,2444,1,,,10,0.5 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..4d08cc5f5746b2ab0c794b9540bfbc031069bfb9 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1744bd445f07f826bafdec1797b2098de3887f03cf60d0fb7ac77543a354cbd7 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..d692a69c8ff2d0cb6469033d2d4035360637afc5 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,10,0.6 +elution_buffer,3530,3530,1,,,10,0.6 +enzyme_name,7975,7975,1,,,10,0.6 +expression_strain,5677,5677,1,,,10,0.6 +inducer,7889,7889,1,,,10,0.6 +induction_temperature,3656,3656,1,,,10,0.6 +lysis_buffer,3714,3714,1,,,10,0.6 +medium_name,4806,4806,1,,,10,0.6 +molecular_weight,295,295,1,,,10,0.6 +organism_source,6292,6292,1,,,10,0.6 +plasmid,5480,5480,1,,,10,0.6 +source_key,8021,8021,1,,,10,0.6 +strain,2444,2444,1,,,10,0.6 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..e20f3c692db4423e8c0d9cacbc6110a59c2d12a2 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fd0cb4a13e668176cf04a3d5abd92dc7a82dc11b5d029efcd7dca079b84b058 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..154e0ef5fc8c13d77afe95d67764a117842be7d5 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,10,0.7 +elution_buffer,3530,3530,1,,,10,0.7 +enzyme_name,7975,7975,1,,,10,0.7 +expression_strain,5677,5677,1,,,10,0.7 +inducer,7889,7889,1,,,10,0.7 +induction_temperature,3656,3656,1,,,10,0.7 +lysis_buffer,3714,3714,1,,,10,0.7 +medium_name,4806,4806,1,,,10,0.7 +molecular_weight,295,295,1,,,10,0.7 +organism_source,6292,6292,1,,,10,0.7 +plasmid,5480,5480,1,,,10,0.7 +source_key,8021,8021,1,,,10,0.7 +strain,2444,2444,1,,,10,0.7 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..363cd01c23297162f3fb4d5e52d044f063833bf8 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc1041ea7e4927f4033b78b37f5928f4d45e7641a05229e53d1458dda048d73 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..b81c0bd68b32507f5f8d362694176bf4553d9a8c --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,10,0.8 +elution_buffer,3530,3530,1,,,10,0.8 +enzyme_name,7975,7975,1,,,10,0.8 +expression_strain,5677,5677,1,,,10,0.8 +inducer,7889,7889,1,,,10,0.8 +induction_temperature,3656,3656,1,,,10,0.8 +lysis_buffer,3714,3714,1,,,10,0.8 +medium_name,4806,4806,1,,,10,0.8 +molecular_weight,295,295,1,,,10,0.8 +organism_source,6292,6292,1,,,10,0.8 +plasmid,5480,5480,1,,,10,0.8 +source_key,8021,8021,1,,,10,0.8 +strain,2444,2444,1,,,10,0.8 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..5e4e29f8db9f42f26d0c7195f0155d3ebc638d66 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7de52492c134df751d2573f954ec686648060a428fef03a06ef9fe289a277f6c +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..c45eb1bcbf1a3d8f836b952978374ac99f374834 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=10/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,10,0.9 +elution_buffer,3530,3530,1,,,10,0.9 +enzyme_name,7975,7975,1,,,10,0.9 +expression_strain,5677,5677,1,,,10,0.9 +inducer,7889,7889,1,,,10,0.9 +induction_temperature,3656,3656,1,,,10,0.9 +lysis_buffer,3714,3714,1,,,10,0.9 +medium_name,4806,4806,1,,,10,0.9 +molecular_weight,295,295,1,,,10,0.9 +organism_source,6292,6292,1,,,10,0.9 +plasmid,5480,5480,1,,,10,0.9 +source_key,8021,8021,1,,,10,0.9 +strain,2444,2444,1,,,10,0.9 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..f890ba7d4302541c1443fdccb10b476d6612f4bf --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2263be6ae85f7c1d1ce08be135e3caf5fb951f65c3111f72ba3a399323b69db9 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..590b820067664f8e12688bcfc3467161c4c08fb4 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,2,0.5 +elution_buffer,3530,3530,1,,,2,0.5 +enzyme_name,7975,7975,1,,,2,0.5 +expression_strain,5677,5677,1,,,2,0.5 +inducer,7889,7889,1,,,2,0.5 +induction_temperature,3656,3656,1,,,2,0.5 +lysis_buffer,3714,3714,1,,,2,0.5 +medium_name,4806,4806,1,,,2,0.5 +molecular_weight,295,295,1,,,2,0.5 +organism_source,6292,6292,1,,,2,0.5 +plasmid,5480,5480,1,,,2,0.5 +source_key,8021,8021,1,,,2,0.5 +strain,2444,2444,1,,,2,0.5 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..b9706c800673f98037540247cb7f8d44bf84ab7b --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ba9b01fb9594d7d4b5c8d1bbeaccf45dc0a8c802d4d79997b21c65a73bc32e +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..7cad830d9ef04ed12c1be5d0744f8d8c886a0d37 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,2,0.6 +elution_buffer,3530,3530,1,,,2,0.6 +enzyme_name,7975,7975,1,,,2,0.6 +expression_strain,5677,5677,1,,,2,0.6 +inducer,7889,7889,1,,,2,0.6 +induction_temperature,3656,3656,1,,,2,0.6 +lysis_buffer,3714,3714,1,,,2,0.6 +medium_name,4806,4806,1,,,2,0.6 +molecular_weight,295,295,1,,,2,0.6 +organism_source,6292,6292,1,,,2,0.6 +plasmid,5480,5480,1,,,2,0.6 +source_key,8021,8021,1,,,2,0.6 +strain,2444,2444,1,,,2,0.6 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..91831a8ea7c5f468bdca272f525c2880f89affea --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09596019be5bd134d1b842b52e0f9c03a46db7688a7fa514edc5c7c11049e154 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..3a3a7d9d0f590d73bcd7f3da1df8dd5f85478edf --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,2,0.7 +elution_buffer,3530,3530,1,,,2,0.7 +enzyme_name,7975,7975,1,,,2,0.7 +expression_strain,5677,5677,1,,,2,0.7 +inducer,7889,7889,1,,,2,0.7 +induction_temperature,3656,3656,1,,,2,0.7 +lysis_buffer,3714,3714,1,,,2,0.7 +medium_name,4806,4806,1,,,2,0.7 +molecular_weight,295,295,1,,,2,0.7 +organism_source,6292,6292,1,,,2,0.7 +plasmid,5480,5480,1,,,2,0.7 +source_key,8021,8021,1,,,2,0.7 +strain,2444,2444,1,,,2,0.7 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..0872ad3f402e15be216d7642f0fc6090d422e32e --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d35954674e4c5af53e3bd5cd3ec046274e8a1c2c8a041731fc83458ca635ec +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..2e1da15f5d67a7c393a89a23b5f2b05c6347fbd3 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,2,0.8 +elution_buffer,3530,3530,1,,,2,0.8 +enzyme_name,7975,7975,1,,,2,0.8 +expression_strain,5677,5677,1,,,2,0.8 +inducer,7889,7889,1,,,2,0.8 +induction_temperature,3656,3656,1,,,2,0.8 +lysis_buffer,3714,3714,1,,,2,0.8 +medium_name,4806,4806,1,,,2,0.8 +molecular_weight,295,295,1,,,2,0.8 +organism_source,6292,6292,1,,,2,0.8 +plasmid,5480,5480,1,,,2,0.8 +source_key,8021,8021,1,,,2,0.8 +strain,2444,2444,1,,,2,0.8 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..1dfaf4d146c82df87353cd0367806cef901f181a --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17c1436340bb5299fa52bf334e909bd995e9d5b2f3617710ba361d8887092a50 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..fd94e5097dc527779e0684f3a4833aa320fb9690 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=2/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,2,0.9 +elution_buffer,3530,3530,1,,,2,0.9 +enzyme_name,7975,7975,1,,,2,0.9 +expression_strain,5677,5677,1,,,2,0.9 +inducer,7889,7889,1,,,2,0.9 +induction_temperature,3656,3656,1,,,2,0.9 +lysis_buffer,3714,3714,1,,,2,0.9 +medium_name,4806,4806,1,,,2,0.9 +molecular_weight,295,295,1,,,2,0.9 +organism_source,6292,6292,1,,,2,0.9 +plasmid,5480,5480,1,,,2,0.9 +source_key,8021,8021,1,,,2,0.9 +strain,2444,2444,1,,,2,0.9 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..77b0b73f31a733d5c7af237f77109c72f2c278a4 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4f2a171e5ec00ad5e81aadd7c7c4cafbc3837b872e3ef0b3928bc513601dff +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..16390af52db9406cd55c564a2aa72732f691cf1b --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,20,0.5 +elution_buffer,3530,3530,1,,,20,0.5 +enzyme_name,7975,7975,1,,,20,0.5 +expression_strain,5677,5677,1,,,20,0.5 +inducer,7889,7889,1,,,20,0.5 +induction_temperature,3656,3656,1,,,20,0.5 +lysis_buffer,3714,3714,1,,,20,0.5 +medium_name,4806,4806,1,,,20,0.5 +molecular_weight,295,295,1,,,20,0.5 +organism_source,6292,6292,1,,,20,0.5 +plasmid,5480,5480,1,,,20,0.5 +source_key,8021,8021,1,,,20,0.5 +strain,2444,2444,1,,,20,0.5 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..9f818ba004b66ddb5d6d535f725851326ac3351f --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7829e7ff5105c023aa8487ca25083cf5260b2bf11c96859ff890ad2cf8729a3c +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..8e6f421a7eb2e140261828ae38afea920707cabb --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,20,0.6 +elution_buffer,3530,3530,1,,,20,0.6 +enzyme_name,7975,7975,1,,,20,0.6 +expression_strain,5677,5677,1,,,20,0.6 +inducer,7889,7889,1,,,20,0.6 +induction_temperature,3656,3656,1,,,20,0.6 +lysis_buffer,3714,3714,1,,,20,0.6 +medium_name,4806,4806,1,,,20,0.6 +molecular_weight,295,295,1,,,20,0.6 +organism_source,6292,6292,1,,,20,0.6 +plasmid,5480,5480,1,,,20,0.6 +source_key,8021,8021,1,,,20,0.6 +strain,2444,2444,1,,,20,0.6 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..2a4a09c7bafdad47c1b8945d4b0485904421fafb --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac453b07e90d704350d4837db7288874e2fdb72976d5f0dc61f9a951ecc19535 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..3ed40eb67255b9d35ee329cf846068d0e2b84236 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,20,0.7 +elution_buffer,3530,3530,1,,,20,0.7 +enzyme_name,7975,7975,1,,,20,0.7 +expression_strain,5677,5677,1,,,20,0.7 +inducer,7889,7889,1,,,20,0.7 +induction_temperature,3656,3656,1,,,20,0.7 +lysis_buffer,3714,3714,1,,,20,0.7 +medium_name,4806,4806,1,,,20,0.7 +molecular_weight,295,295,1,,,20,0.7 +organism_source,6292,6292,1,,,20,0.7 +plasmid,5480,5480,1,,,20,0.7 +source_key,8021,8021,1,,,20,0.7 +strain,2444,2444,1,,,20,0.7 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..16b0f77190a4a6a135fcf7813c5e2ad36b527150 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a7e04ad5d302cfeb4d5d5e3b6cc4eeeb538b957a99eb4f3dda1f54e8d377b99 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..f1b29487a2930e7532082bf1394f78fa710ddcfb --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,20,0.8 +elution_buffer,3530,3530,1,,,20,0.8 +enzyme_name,7975,7975,1,,,20,0.8 +expression_strain,5677,5677,1,,,20,0.8 +inducer,7889,7889,1,,,20,0.8 +induction_temperature,3656,3656,1,,,20,0.8 +lysis_buffer,3714,3714,1,,,20,0.8 +medium_name,4806,4806,1,,,20,0.8 +molecular_weight,295,295,1,,,20,0.8 +organism_source,6292,6292,1,,,20,0.8 +plasmid,5480,5480,1,,,20,0.8 +source_key,8021,8021,1,,,20,0.8 +strain,2444,2444,1,,,20,0.8 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..23c0cc9da702e42f221dcad3913c5ce51e31a6f6 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5819815fb76d4eb6684e3cc7b6addba9557a4b828bcd1466d97d13f587d6ea07 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..b38ffd235c71d36c509c9ae3c6e018e9db0d552b --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=20/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,20,0.9 +elution_buffer,3530,3530,1,,,20,0.9 +enzyme_name,7975,7975,1,,,20,0.9 +expression_strain,5677,5677,1,,,20,0.9 +inducer,7889,7889,1,,,20,0.9 +induction_temperature,3656,3656,1,,,20,0.9 +lysis_buffer,3714,3714,1,,,20,0.9 +medium_name,4806,4806,1,,,20,0.9 +molecular_weight,295,295,1,,,20,0.9 +organism_source,6292,6292,1,,,20,0.9 +plasmid,5480,5480,1,,,20,0.9 +source_key,8021,8021,1,,,20,0.9 +strain,2444,2444,1,,,20,0.9 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..93164361a262c81f707629cd8474a8a3273dd1c1 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb6785b794b35271ee03214ad9795144778ee7fbff80d9f7cb59bf436ef9bb8e +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..560e48120e0b1c35ec315d6e722ea4474213ce4b --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,30,0.5 +elution_buffer,3530,3530,1,,,30,0.5 +enzyme_name,7975,7975,1,,,30,0.5 +expression_strain,5677,5677,1,,,30,0.5 +inducer,7889,7889,1,,,30,0.5 +induction_temperature,3656,3656,1,,,30,0.5 +lysis_buffer,3714,3714,1,,,30,0.5 +medium_name,4806,4806,1,,,30,0.5 +molecular_weight,295,295,1,,,30,0.5 +organism_source,6292,6292,1,,,30,0.5 +plasmid,5480,5480,1,,,30,0.5 +source_key,8021,8021,1,,,30,0.5 +strain,2444,2444,1,,,30,0.5 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..13627842b63d4bf54cdab21ae7653948ede71f80 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b52b2c81ef6a577626f76dfb5a824d428209c126a004d3f2a90cad42a96c4265 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..c1c7ecd93365aac458718d5715bb47b6fbcd0a5e --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,30,0.6 +elution_buffer,3530,3530,1,,,30,0.6 +enzyme_name,7975,7975,1,,,30,0.6 +expression_strain,5677,5677,1,,,30,0.6 +inducer,7889,7889,1,,,30,0.6 +induction_temperature,3656,3656,1,,,30,0.6 +lysis_buffer,3714,3714,1,,,30,0.6 +medium_name,4806,4806,1,,,30,0.6 +molecular_weight,295,295,1,,,30,0.6 +organism_source,6292,6292,1,,,30,0.6 +plasmid,5480,5480,1,,,30,0.6 +source_key,8021,8021,1,,,30,0.6 +strain,2444,2444,1,,,30,0.6 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..81bfb7e26dfede3ec371168a0d60821b9e006430 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb70c99bbbaac4beb609ff92269721702c6f79c8e048b13de2c537c6ab2f571 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..7b958b4a2aa0166053862e24eba1fc08c5435b30 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,30,0.7 +elution_buffer,3530,3530,1,,,30,0.7 +enzyme_name,7975,7975,1,,,30,0.7 +expression_strain,5677,5677,1,,,30,0.7 +inducer,7889,7889,1,,,30,0.7 +induction_temperature,3656,3656,1,,,30,0.7 +lysis_buffer,3714,3714,1,,,30,0.7 +medium_name,4806,4806,1,,,30,0.7 +molecular_weight,295,295,1,,,30,0.7 +organism_source,6292,6292,1,,,30,0.7 +plasmid,5480,5480,1,,,30,0.7 +source_key,8021,8021,1,,,30,0.7 +strain,2444,2444,1,,,30,0.7 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..d547c2042a28edfa356b9d6f68fb1d96ddce852b --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:067c3b8cc3f98e2c2c2af60656376263cd61684fe96f042b01f644eb5da86e33 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..a00251b3dd30a3dc94da3a55ee153b1058cbf72b --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,30,0.8 +elution_buffer,3530,3530,1,,,30,0.8 +enzyme_name,7975,7975,1,,,30,0.8 +expression_strain,5677,5677,1,,,30,0.8 +inducer,7889,7889,1,,,30,0.8 +induction_temperature,3656,3656,1,,,30,0.8 +lysis_buffer,3714,3714,1,,,30,0.8 +medium_name,4806,4806,1,,,30,0.8 +molecular_weight,295,295,1,,,30,0.8 +organism_source,6292,6292,1,,,30,0.8 +plasmid,5480,5480,1,,,30,0.8 +source_key,8021,8021,1,,,30,0.8 +strain,2444,2444,1,,,30,0.8 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..f5f8bdbb84dd8af4b1f66d1364be97f739b9245a --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a4a51f28114a46655294d0ed1d72f2f71fa2f6ee926692a6b8c2685f0b1d32b +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..a967799a47829ca509d6094cc625b22522ed9e6f --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=30/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,30,0.9 +elution_buffer,3530,3530,1,,,30,0.9 +enzyme_name,7975,7975,1,,,30,0.9 +expression_strain,5677,5677,1,,,30,0.9 +inducer,7889,7889,1,,,30,0.9 +induction_temperature,3656,3656,1,,,30,0.9 +lysis_buffer,3714,3714,1,,,30,0.9 +medium_name,4806,4806,1,,,30,0.9 +molecular_weight,295,295,1,,,30,0.9 +organism_source,6292,6292,1,,,30,0.9 +plasmid,5480,5480,1,,,30,0.9 +source_key,8021,8021,1,,,30,0.9 +strain,2444,2444,1,,,30,0.9 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.5_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.5_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..a09d926640157ef8c9791521a0570f334a4ed12b --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.5_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cffaced89594a613581476359651bdfd801e039a2bf467df19680db425d3198e +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..a93b8e60e56a6d7db5edf122d94ba5a7324fdb86 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.5_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,5,0.5 +elution_buffer,3530,3530,1,,,5,0.5 +enzyme_name,7975,7975,1,,,5,0.5 +expression_strain,5677,5677,1,,,5,0.5 +inducer,7889,7889,1,,,5,0.5 +induction_temperature,3656,3656,1,,,5,0.5 +lysis_buffer,3714,3714,1,,,5,0.5 +medium_name,4806,4806,1,,,5,0.5 +molecular_weight,295,295,1,,,5,0.5 +organism_source,6292,6292,1,,,5,0.5 +plasmid,5480,5480,1,,,5,0.5 +source_key,8021,8021,1,,,5,0.5 +strain,2444,2444,1,,,5,0.5 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.6_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.6_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..22fff78b7a1734635a661bc3e37f2bea376b8f64 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.6_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:843327acf589724882f250abfe9b877cb101dae29e24dca77c18b65a55c0476d +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..a698f94d11f0b8e94d9b0a0679f88b0f40424611 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.6_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,5,0.6 +elution_buffer,3530,3530,1,,,5,0.6 +enzyme_name,7975,7975,1,,,5,0.6 +expression_strain,5677,5677,1,,,5,0.6 +inducer,7889,7889,1,,,5,0.6 +induction_temperature,3656,3656,1,,,5,0.6 +lysis_buffer,3714,3714,1,,,5,0.6 +medium_name,4806,4806,1,,,5,0.6 +molecular_weight,295,295,1,,,5,0.6 +organism_source,6292,6292,1,,,5,0.6 +plasmid,5480,5480,1,,,5,0.6 +source_key,8021,8021,1,,,5,0.6 +strain,2444,2444,1,,,5,0.6 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.7_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.7_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..82dce6e1c1956528da317a9e28ef026a8b92b081 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.7_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718e20cd82d0dcfb61d162a7db39edc17afcda366e371e0315c1599aa7d18727 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..e0258c2fe55d97a067126c9acefd3db90bf5a7cf --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.7_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,5,0.7 +elution_buffer,3530,3530,1,,,5,0.7 +enzyme_name,7975,7975,1,,,5,0.7 +expression_strain,5677,5677,1,,,5,0.7 +inducer,7889,7889,1,,,5,0.7 +induction_temperature,3656,3656,1,,,5,0.7 +lysis_buffer,3714,3714,1,,,5,0.7 +medium_name,4806,4806,1,,,5,0.7 +molecular_weight,295,295,1,,,5,0.7 +organism_source,6292,6292,1,,,5,0.7 +plasmid,5480,5480,1,,,5,0.7 +source_key,8021,8021,1,,,5,0.7 +strain,2444,2444,1,,,5,0.7 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.8_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.8_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..16b0f77190a4a6a135fcf7813c5e2ad36b527150 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.8_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a7e04ad5d302cfeb4d5d5e3b6cc4eeeb538b957a99eb4f3dda1f54e8d377b99 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..cf68188873a75a70fc29ea5c4e41503cb9717c64 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.8_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,5,0.8 +elution_buffer,3530,3530,1,,,5,0.8 +enzyme_name,7975,7975,1,,,5,0.8 +expression_strain,5677,5677,1,,,5,0.8 +inducer,7889,7889,1,,,5,0.8 +induction_temperature,3656,3656,1,,,5,0.8 +lysis_buffer,3714,3714,1,,,5,0.8 +medium_name,4806,4806,1,,,5,0.8 +molecular_weight,295,295,1,,,5,0.8 +organism_source,6292,6292,1,,,5,0.8 +plasmid,5480,5480,1,,,5,0.8 +source_key,8021,8021,1,,,5,0.8 +strain,2444,2444,1,,,5,0.8 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.9_ALL_FIELDS.csv.gz b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.9_ALL_FIELDS.csv.gz new file mode 100644 index 0000000000000000000000000000000000000000..f80cb9fd58505e8f29d0d7c2dc8ac8ff25ec1681 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.9_ALL_FIELDS.csv.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:976be136e5a539b3ef86791347c98c65361a9fac0827d6d203186625ee543c92 +size 1560074 diff --git a/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv new file mode 100644 index 0000000000000000000000000000000000000000..fb592c84245194321de815cc8b86ad7d3f9d19d1 --- /dev/null +++ b/data/clustering/model=allenai__biomed_roberta_base/min=5/t=0.9_FIELD_CLUSTER_METRICS.csv @@ -0,0 +1,14 @@ +field,n_total,n_used,n_clusters,silhouette_cosine,davies_bouldin,min_community_size,threshold +desalting_process,3720,3720,1,,,5,0.9 +elution_buffer,3530,3530,1,,,5,0.9 +enzyme_name,7975,7975,1,,,5,0.9 +expression_strain,5677,5677,1,,,5,0.9 +inducer,7889,7889,1,,,5,0.9 +induction_temperature,3656,3656,1,,,5,0.9 +lysis_buffer,3714,3714,1,,,5,0.9 +medium_name,4806,4806,1,,,5,0.9 +molecular_weight,295,295,1,,,5,0.9 +organism_source,6292,6292,1,,,5,0.9 +plasmid,5480,5480,1,,,5,0.9 +source_key,8021,8021,1,,,5,0.9 +strain,2444,2444,1,,,5,0.9