formatting

examples/advanced/bionemo/downstream/sabdab/jobs/central_sabdab_esm1nv/app/custom/downstream_flip.py

@@ -13,29 +13,26 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nemo.core.config import hydra_runner
-from nemo.utils import logging
-from omegaconf.omegaconf import OmegaConf
-
 from bionemo.data import FLIPPreprocess
 from bionemo.data.metrics import accuracy, mse, per_token_accuracy
 from bionemo.model.protein.downstream import FineTuneProteinModel
-from bionemo.model.utils import (
-    setup_trainer,
-)
+from bionemo.model.utils import setup_trainer
+from nemo.core.config import hydra_runner
+from nemo.utils import logging
+from omegaconf.omegaconf import OmegaConf
 
 # (0): import nvflare lightning api
 import nvflare.client.lightning as flare
 from nvflare.client.api import init
 
 micro_batch_size = 32
 val_check_intervals = {
-    "site-1": int(416/micro_batch_size),
-    "site-2": int(238/micro_batch_size),
-    "site-3": int(282/micro_batch_size),
-    "site-4": int(472/micro_batch_size),
-    "site-5": int(361/micro_batch_size),
-    "site-6": int(157/micro_batch_size)
+    "site-1": int(416 / micro_batch_size),
+    "site-2": int(238 / micro_batch_size),
+    "site-3": int(282 / micro_batch_size),
+    "site-4": int(472 / micro_batch_size),
+    "site-5": int(361 / micro_batch_size),
+    "site-6": int(157 / micro_batch_size),
 }
 
 
@@ -53,7 +50,7 @@ def main(cfg) -> None:
     print(f"Running client {site_name} with train data: {cfg.model.data.dataset.train}")
 
     logging.info("\n\n************* Finetune config ****************")
-    logging.info(f'\n{OmegaConf.to_yaml(cfg)}')
+    logging.info(f"\n{OmegaConf.to_yaml(cfg)}")
 
     if cfg.do_training:
         logging.info("************** Starting Training ***********")
@@ -111,5 +108,5 @@ def main(cfg) -> None:
         preprocessor.prepare_all_datasets(output_dir=cfg.model.data.preprocessed_data_path)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

examples/advanced/bionemo/downstream/sabdab/jobs/fedavg_sabdab_esm1nv/app/custom/downstream_flip.py

@@ -13,16 +13,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nemo.core.config import hydra_runner
-from nemo.utils import logging
-from omegaconf.omegaconf import OmegaConf
-
 from bionemo.data import FLIPPreprocess
 from bionemo.data.metrics import accuracy, mse, per_token_accuracy
 from bionemo.model.protein.downstream import FineTuneProteinModel
-from bionemo.model.utils import (
-    setup_trainer,
-)
+from bionemo.model.utils import setup_trainer
+from nemo.core.config import hydra_runner
+from nemo.utils import logging
+from omegaconf.omegaconf import OmegaConf
 
 # (0): import nvflare lightning api
 import nvflare.client.lightning as flare
@@ -52,12 +49,12 @@
 
 # alpha 1.0
 val_check_intervals = {
-    "site-1": int(80/micro_batch_size),
-    "site-2": int(365/micro_batch_size),
-    "site-3": int(216/micro_batch_size),
-    "site-4": int(578/micro_batch_size),
-    "site-5": int(568/micro_batch_size),
-    "site-6": int(119/micro_batch_size)
+    "site-1": int(80 / micro_batch_size),
+    "site-2": int(365 / micro_batch_size),
+    "site-3": int(216 / micro_batch_size),
+    "site-4": int(578 / micro_batch_size),
+    "site-5": int(568 / micro_batch_size),
+    "site-6": int(119 / micro_batch_size),
 }
 
 
@@ -75,7 +72,7 @@ def main(cfg) -> None:
     print(f"Running client {site_name} with train data: {cfg.model.data.dataset.train}")
 
     logging.info("\n\n************* Finetune config ****************")
-    logging.info(f'\n{OmegaConf.to_yaml(cfg)}')
+    logging.info(f"\n{OmegaConf.to_yaml(cfg)}")
 
     if cfg.do_training:
         logging.info("************** Starting Training ***********")
@@ -133,5 +130,5 @@ def main(cfg) -> None:
         preprocessor.prepare_all_datasets(output_dir=cfg.model.data.preprocessed_data_path)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

examples/advanced/bionemo/downstream/sabdab/jobs/local_sabdab_esm1nv/app/custom/downstream_flip.py

@@ -13,16 +13,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nemo.core.config import hydra_runner
-from nemo.utils import logging
-from omegaconf.omegaconf import OmegaConf
-
 from bionemo.data import FLIPPreprocess
 from bionemo.data.metrics import accuracy, mse, per_token_accuracy
 from bionemo.model.protein.downstream import FineTuneProteinModel
-from bionemo.model.utils import (
-    setup_trainer,
-)
+from bionemo.model.utils import setup_trainer
+from nemo.core.config import hydra_runner
+from nemo.utils import logging
+from omegaconf.omegaconf import OmegaConf
 
 # (0): import nvflare lightning api
 import nvflare.client.lightning as flare
@@ -32,12 +29,12 @@
 
 # alpha 100.0
 val_check_intervals = {
-    "site-1": int(351/micro_batch_size),
-    "site-2": int(297/micro_batch_size),
-    "site-3": int(312/micro_batch_size),
-    "site-4": int(366/micro_batch_size),
-    "site-5": int(336/micro_batch_size),
-    "site-6": int(265/micro_batch_size)
+    "site-1": int(351 / micro_batch_size),
+    "site-2": int(297 / micro_batch_size),
+    "site-3": int(312 / micro_batch_size),
+    "site-4": int(366 / micro_batch_size),
+    "site-5": int(336 / micro_batch_size),
+    "site-6": int(265 / micro_batch_size),
 }
 
 # alpha 10.0
@@ -75,7 +72,7 @@ def main(cfg) -> None:
     print(f"Running client {site_name} with train data: {cfg.model.data.dataset.train}")
 
     logging.info("\n\n************* Finetune config ****************")
-    logging.info(f'\n{OmegaConf.to_yaml(cfg)}')
+    logging.info(f"\n{OmegaConf.to_yaml(cfg)}")
 
     if cfg.do_training:
         logging.info("************** Starting Training ***********")
@@ -133,5 +130,5 @@ def main(cfg) -> None:
         preprocessor.prepare_all_datasets(output_dir=cfg.model.data.preprocessed_data_path)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

examples/advanced/bionemo/downstream/sabdab/prepare_sabdab_data.py

@@ -13,10 +13,11 @@
 # limitations under the License.
 
 import os
-import pandas as pd
+
 import numpy as np
-from tdc.utils import retrieve_label_name_list
+import pandas as pd
 from tdc.single_pred import Develop
+
 np.random.seed(1234)
 
 out_name = "sabdab_chen"
@@ -73,7 +74,7 @@ def break_chains(df):
 def main():
     seed = 0
 
-    data = Develop(name='SAbDab_Chen', path="/tmp/data")
+    data = Develop(name="SAbDab_Chen", path="/tmp/data")
     split = data.get_split()
 
     train_df = pd.concat([split["train"], split["valid"]])
@@ -86,11 +87,11 @@ def main():
         proportions = np.random.dirichlet(np.repeat(alpha, n_clients))
     else:
         print("Uniform sampling")
-        proportions = n_clients * [1/n_clients]
+        proportions = n_clients * [1 / n_clients]
 
     for client_id in range(n_clients):
         client_name = f"site-{client_id+1}"
-        client_train_df = train_df.sample(frac=proportions[client_id], replace=False, random_state=seed+client_id)
+        client_train_df = train_df.sample(frac=proportions[client_id], replace=False, random_state=seed + client_id)
 
         if do_break_chains:
             client_train_df = break_chains(client_train_df)
@@ -128,8 +129,8 @@ def main():
     print(f"Saved {len(train_df)} training and {len(test_df)} testing proteins.")
 
     for _set, _df in zip(["TRAIN", "TEST"], [train_df, test_df]):
-        n_pos = np.sum(_df['Y'] == 0)
-        n_neg = np.sum(_df['Y'] == 1)
+        n_pos = np.sum(_df["Y"] == 0)
+        n_neg = np.sum(_df["Y"] == 1)
         n = len(_df)
         print(f"  {_set} Pos/Neg ratio: neg={n_neg}, pos={n_pos}: {n_pos/n_neg:0.3f}")
         print(f"  {_set} Trivial accuracy: {n_pos/n:0.3f}")
@@ -144,7 +145,7 @@ def main():
             b = np.asarray(client_train_dfs[j]["Antibody_ID"])
             assert len(np.unique(a)) == len(a)
             assert len(np.unique(b)) == len(b)
-            d[i][j] = len(np.intersect1d(a, b))/len(b)
+            d[i][j] = len(np.intersect1d(a, b)) / len(b)
 
     print(d)
     overlap = np.mean(d[~np.isnan(d)])

examples/advanced/bionemo/downstream/sabdab/run_sim_sabdab.py

@@ -13,6 +13,7 @@
 # limitations under the License.
 
 from nvflare import SimulatorRunner
+
 n_clients = 6
 
 # Choose from one of the available jobs
@@ -21,10 +22,7 @@
 # job_name = "fedavg_sabdab_esm1nv"
 
 simulator = SimulatorRunner(
-    job_folder=f"jobs/{job_name}",
-    workspace=f"/tmp/nvflare/results/{job_name}",
-    n_clients=n_clients,
-    threads=n_clients
+    job_folder=f"jobs/{job_name}", workspace=f"/tmp/nvflare/results/{job_name}", n_clients=n_clients, threads=n_clients
 )
 run_status = simulator.run()
 print("Simulator finished with run_status", run_status)

examples/advanced/bionemo/downstream/scl/jobs/fedavg_scl_finetune_esm2nv/app1/custom/downstream_flip.py

@@ -13,16 +13,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nemo.core.config import hydra_runner
-from nemo.utils import logging
-from omegaconf.omegaconf import OmegaConf
-
 from bionemo.data import FLIPPreprocess
 from bionemo.data.metrics import accuracy, mse, per_token_accuracy
 from bionemo.model.protein.downstream import FineTuneProteinModel
-from bionemo.model.utils import (
-    setup_trainer,
-)
+from bionemo.model.utils import setup_trainer
+from nemo.core.config import hydra_runner
+from nemo.utils import logging
+from omegaconf.omegaconf import OmegaConf
 
 # (0): import nvflare lightning api
 import nvflare.client.lightning as flare
@@ -32,7 +29,7 @@
 # @hydra_runner(config_path="../prott5nv/conf", config_name="downstream_flip_sec_str") # ProtT5
 def main(cfg) -> None:
     logging.info("\n\n************* Finetune config ****************")
-    logging.info(f'\n{OmegaConf.to_yaml(cfg)}')
+    logging.info(f"\n{OmegaConf.to_yaml(cfg)}")
 
     if cfg.do_training:
         logging.info("************** Starting Training ***********")
@@ -90,5 +87,5 @@ def main(cfg) -> None:
         preprocessor.prepare_all_datasets(output_dir=cfg.model.data.preprocessed_data_path)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

examples/advanced/bionemo/downstream/scl/jobs/fedavg_scl_finetune_esm2nv/app2/custom/downstream_flip.py

@@ -13,16 +13,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nemo.core.config import hydra_runner
-from nemo.utils import logging
-from omegaconf.omegaconf import OmegaConf
-
 from bionemo.data import FLIPPreprocess
 from bionemo.data.metrics import accuracy, mse, per_token_accuracy
 from bionemo.model.protein.downstream import FineTuneProteinModel
-from bionemo.model.utils import (
-    setup_trainer,
-)
+from bionemo.model.utils import setup_trainer
+from nemo.core.config import hydra_runner
+from nemo.utils import logging
+from omegaconf.omegaconf import OmegaConf
 
 # (0): import nvflare lightning api
 import nvflare.client.lightning as flare
@@ -32,7 +29,7 @@
 # @hydra_runner(config_path="../prott5nv/conf", config_name="downstream_flip_sec_str") # ProtT5
 def main(cfg) -> None:
     logging.info("\n\n************* Finetune config ****************")
-    logging.info(f'\n{OmegaConf.to_yaml(cfg)}')
+    logging.info(f"\n{OmegaConf.to_yaml(cfg)}")
 
     if cfg.do_training:
         logging.info("************** Starting Training ***********")
@@ -90,5 +87,5 @@ def main(cfg) -> None:
         preprocessor.prepare_all_datasets(output_dir=cfg.model.data.preprocessed_data_path)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

examples/advanced/bionemo/downstream/scl/jobs/fedavg_scl_finetune_esm2nv/app3/custom/downstream_flip.py

@@ -13,16 +13,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nemo.core.config import hydra_runner
-from nemo.utils import logging
-from omegaconf.omegaconf import OmegaConf
-
 from bionemo.data import FLIPPreprocess
 from bionemo.data.metrics import accuracy, mse, per_token_accuracy
 from bionemo.model.protein.downstream import FineTuneProteinModel
-from bionemo.model.utils import (
-    setup_trainer,
-)
+from bionemo.model.utils import setup_trainer
+from nemo.core.config import hydra_runner
+from nemo.utils import logging
+from omegaconf.omegaconf import OmegaConf
 
 # (0): import nvflare lightning api
 import nvflare.client.lightning as flare
@@ -32,7 +29,7 @@
 # @hydra_runner(config_path="../prott5nv/conf", config_name="downstream_flip_sec_str") # ProtT5
 def main(cfg) -> None:
     logging.info("\n\n************* Finetune config ****************")
-    logging.info(f'\n{OmegaConf.to_yaml(cfg)}')
+    logging.info(f"\n{OmegaConf.to_yaml(cfg)}")
 
     if cfg.do_training:
         logging.info("************** Starting Training ***********")
@@ -90,5 +87,5 @@ def main(cfg) -> None:
         preprocessor.prepare_all_datasets(output_dir=cfg.model.data.preprocessed_data_path)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()

examples/advanced/bionemo/downstream/scl/jobs/local_scl_finetune_esm2nv/app1/custom/downstream_flip.py

@@ -13,16 +13,13 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nemo.core.config import hydra_runner
-from nemo.utils import logging
-from omegaconf.omegaconf import OmegaConf
-
 from bionemo.data import FLIPPreprocess
 from bionemo.data.metrics import accuracy, mse, per_token_accuracy
 from bionemo.model.protein.downstream import FineTuneProteinModel
-from bionemo.model.utils import (
-    setup_trainer,
-)
+from bionemo.model.utils import setup_trainer
+from nemo.core.config import hydra_runner
+from nemo.utils import logging
+from omegaconf.omegaconf import OmegaConf
 
 # (0): import nvflare lightning api
 import nvflare.client.lightning as flare
@@ -32,7 +29,7 @@
 # @hydra_runner(config_path="../prott5nv/conf", config_name="downstream_flip_sec_str") # ProtT5
 def main(cfg) -> None:
     logging.info("\n\n************* Finetune config ****************")
-    logging.info(f'\n{OmegaConf.to_yaml(cfg)}')
+    logging.info(f"\n{OmegaConf.to_yaml(cfg)}")
 
     if cfg.do_training:
         logging.info("************** Starting Training ***********")
@@ -90,5 +87,5 @@ def main(cfg) -> None:
         preprocessor.prepare_all_datasets(output_dir=cfg.model.data.preprocessed_data_path)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     main()