Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Pushing update for metacat training #18

Merged
merged 2 commits into from
Feb 17, 2025
Merged

Pushing update for metacat training #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ff8f5e1
Pushing update for metacat training
shubham-s-agarwal Jan 24, 2025
85cc0bd
Pushing update - removing demo
shubham-s-agarwal Feb 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
63 changes: 9 additions & 54 deletions medcat/2_train_model/2_supervised_training/meta_annotation_training.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,7 +114,7 @@
"id": "83701c19",
"metadata": {},
"source": [
"# For LSTM model"
"# For LSTM and BERT model"
]
},
{
Expand All @@ -125,68 +125,23 @@
"outputs": [],
"source": [
"for meta_model in meta_model_names:\n",
" vocab_file = os.path.join(base_dir_meta_models,\"meta_\"+meta_model,'bbpe-vocab.json')\n",
" merges_file = os.path.join(base_dir_meta_models,\"meta_\"+meta_model,'bbpe-merges.txt')\n",
" tokenizer = TokenizerWrapperBPE(ByteLevelBPETokenizer(vocab=vocab_file,\n",
" merges=merges_file,\n",
" lowercase=True))\n",
" # load and sort out the config\n",
" config_file = os.path.join(base_dir_meta_models,\"meta_\"+meta_model,\"config.json\")\n",
" with open(config_file, 'r') as jfile:\n",
" config_dict = json.load(jfile)\n",
" config = ConfigMetaCAT()\n",
" for key, value in config_dict.items():\n",
" setattr(config, key, value['py/state']['__dict__'])\n",
" \n",
" \n",
" # load the meta_model\n",
" mc = MetaCAT.load(save_dir_path=os.path.join(base_dir_meta_models,\"meta_\"+meta_model))\n",
"\n",
" # changing parameters\n",
" mc.config.train['nepochs'] = 15\n",
"\n",
" save_dir_path= \"test_meta_\"+meta_model # Where to save the meta_model and results. \n",
" #Ideally this should replace the meta_models inside the modelpack\n",
"\n",
" # Initialise and train meta_model\n",
" mc = MetaCAT(tokenizer=tokenizer, embeddings=None, config=config)\n",
" # train the meta_model\n",
" results = mc.train_from_json(mctrainer_export_path, save_dir_path=save_dir_path)\n",
" \n",
" # Save results\n",
" json.dump(results['report'], open(os.path.join(save_dir_path,'meta_'+meta_model+'_results.json'), 'w'))"
]
},
{
"cell_type": "markdown",
"id": "91ff4e28",
"metadata": {},
"source": [
"# For BERT model"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e255dda2",
"metadata": {},
"outputs": [],
"source": [
"for meta_model in meta_model_names:\n",
" # load and sort out the config\n",
" config_file = os.path.join(base_dir_meta_models,\"meta_\"+meta_model,\"config.json\")\n",
" with open(config_file, 'r') as jfile:\n",
" config_dict = json.load(jfile)\n",
" config = ConfigMetaCAT()\n",
" for key, value in config_dict.items():\n",
" setattr(config, key, value['py/state']['__dict__'])\n",
"\n",
" tokenizer = TokenizerWrapperBERT.load(os.path.join(base_dir_meta_models,\"meta_\"+meta_model), \n",
" config.model['model_variant'])\n",
" \n",
" # change model name if training BERT for the first time\n",
" config.model['model_name'] = 'bert'\n",
" \n",
" save_dir_path= \"test_meta_\"+meta_model # Where to save the meta_model and results. \n",
" #Ideally this should replace the meta_models inside the modelpack\n",
"\n",
" # Initialise and train meta_model\n",
" mc = MetaCAT(tokenizer=tokenizer, embeddings=None, config=config)\n",
" results = mc.train_from_json(mctrainer_export_path, save_dir_path=save_dir_path)"
]
},
{
"cell_type": "markdown",
"id": "ab23e424",
Expand Down
Loading
Loading