Moving task_specific_args to tasks config level

Author: luis-mueller

expts/hydra-configs/architecture/toymix.yaml

@@ -81,48 +81,6 @@ datamodule:
     processed_graph_data_path: "../datacache/neurips2023-small/"
     num_workers: 30 # -1 to use all
     persistent_workers: False
-    task_specific_args:
-      qm9:
-        df: null
-        df_path: ${constants.data_dir}/qm9.csv.gz
-        # wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9.csv.gz
-        # or set path as the URL directly
-        smiles_col: "smiles"
-        label_cols: ["A", "B", "C", "mu", "alpha", "homo", "lumo", "gap", "r2", "zpve", "u0", "u298", "h298", "g298", "cv", "u0_atom", "u298_atom", "h298_atom", "g298_atom"]
-        # sample_size: 2000 # use sample_size for test
-        splits_path: ${constants.data_dir}/qm9_random_splits.pt  # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
-        seed: ${constants.seed} #*seed
-        task_level: graph
-        label_normalization:
-          normalize_val_test: True
-          method: "normal"
-
-      tox21:
-        df: null
-        df_path: ${constants.data_dir}/Tox21-7k-12-labels.csv.gz
-        # wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21-7k-12-labels.csv.gz
-        # or set path as the URL directly
-        smiles_col: "smiles"
-        label_cols: ["NR-AR", "NR-AR-LBD", "NR-AhR", "NR-Aromatase", "NR-ER", "NR-ER-LBD", "NR-PPAR-gamma", "SR-ARE", "SR-ATAD5", "SR-HSE", "SR-MMP", "SR-p53"]
-        # sample_size: 2000 # use sample_size for test
-        splits_path: ${constants.data_dir}/Tox21_random_splits.pt  # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt`
-        seed: ${constants.seed}
-        task_level: graph
-
-      zinc:
-        df: null
-        df_path: ${constants.data_dir}/ZINC12k.csv.gz
-        # wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k.csv.gz
-        # or set path as the URL directly
-        smiles_col: "smiles"
-        label_cols: ["SA", "logp", "score"]
-        # sample_size: 2000 # use sample_size for test
-        splits_path: ${constants.data_dir}/ZINC12k_random_splits.pt  # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
-        seed: ${constants.seed}
-        task_level: graph
-        label_normalization:
-          normalize_val_test: True
-          method: "normal"
     featurization:
       atom_property_list_onehot: [atomic-number, group, period, total-valence]
       atom_property_list_float: [degree, formal-charge, radical-electron, aromatic, in-ring]

expts/hydra-configs/tasks/toymix.yaml

@@ -90,4 +90,49 @@ metrics:
       multitask_handling: mean-per-label
       average: micro
       threshold_kwargs: *threshold_05
-  zinc: *qm9_metrics
+  zinc: *qm9_metrics
+
+datamodule:
+  args:
+    task_specific_args:
+      qm9:
+        df: null
+        df_path: ${constants.data_dir}/qm9.csv.gz
+        # wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9.csv.gz
+        # or set path as the URL directly
+        smiles_col: "smiles"
+        label_cols: ["A", "B", "C", "mu", "alpha", "homo", "lumo", "gap", "r2", "zpve", "u0", "u298", "h298", "g298", "cv", "u0_atom", "u298_atom", "h298_atom", "g298_atom"]
+        # sample_size: 2000 # use sample_size for test
+        splits_path: ${constants.data_dir}/qm9_random_splits.pt  # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
+        seed: ${constants.seed} #*seed
+        task_level: graph
+        label_normalization:
+          normalize_val_test: True
+          method: "normal"
+
+      tox21:
+        df: null
+        df_path: ${constants.data_dir}/Tox21-7k-12-labels.csv.gz
+        # wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21-7k-12-labels.csv.gz
+        # or set path as the URL directly
+        smiles_col: "smiles"
+        label_cols: ["NR-AR", "NR-AR-LBD", "NR-AhR", "NR-Aromatase", "NR-ER", "NR-ER-LBD", "NR-PPAR-gamma", "SR-ARE", "SR-ATAD5", "SR-HSE", "SR-MMP", "SR-p53"]
+        # sample_size: 2000 # use sample_size for test
+        splits_path: ${constants.data_dir}/Tox21_random_splits.pt  # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt`
+        seed: ${constants.seed}
+        task_level: graph
+
+      zinc:
+        df: null
+        df_path: ${constants.data_dir}/ZINC12k.csv.gz
+        # wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k.csv.gz
+        # or set path as the URL directly
+        smiles_col: "smiles"
+        label_cols: ["SA", "logp", "score"]
+        # sample_size: 2000 # use sample_size for test
+        splits_path: ${constants.data_dir}/ZINC12k_random_splits.pt  # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
+        seed: ${constants.seed}
+        task_level: graph
+        label_normalization:
+          normalize_val_test: True
+          method: "normal"