Geneformer / geneformer

11.5 MB

19 contributors

History: 159 commits

IchigoJiken

Update geneformer/evaluation_utils.py to be compatible with different versions of the datasets package.

fc7a1c0 verified 5 months ago

gene_dictionaries_30m
Update geneformer/tokenizer.py (#415) over 1 year ago
mtl
move import wandb to conditional 8 months ago
__init__.py
1.65 kB

update with V2 models 7 months ago
classifier.py
66.6 kB

move V1 autoformatting to after validate_options 7 months ago
classifier_utils.py
23.6 kB

add option for relabeling data from prior label class dict, update dict paths in manifest 7 months ago
collator_for_classification.py
31.7 kB

silence tensor copy warning 7 months ago
emb_extractor.py
33.3 kB

plot umap for all labels in same view 6 months ago
ensembl_mapping_dict_gc104M.pkl
3.96 MB
xet

add V2 models 7 months ago
evaluation_utils.py
10.1 kB

Update geneformer/evaluation_utils.py to be compatible with different versions of the datasets package. 5 months ago
gene_median_dictionary_gc104M.pkl
1.51 MB
xet

add V2 models 7 months ago
gene_name_id_dict_gc104M.pkl
1.66 MB
xet

add V2 models 7 months ago
in_silico_perturber.py
67.5 kB

update V1 token dict usage to self attr 7 months ago
in_silico_perturber_stats.py
45.7 kB

update with V2 models 7 months ago
mtl_classifier.py
14.5 kB

fully qualified imports to resolve name-space conflicts (#532) 8 months ago
perturber_utils.py
32.1 kB

fix to properly move model after checking device 7 months ago
pretrainer.py
29.5 kB

remove unused imports while no longer using distributed sampler about 1 year ago
token_dictionary_gc104M.pkl
426 kB
xet

add V2 models 7 months ago
tokenizer.py
34.3 kB

add input_identifier to tokenize specific matched files 6 months ago