Skip to content

chore: Update references from GCS buckets to new storage paths #16

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

Open
jstlaurent wants to merge 1 commit into
base: main
Choose a base branch
from
Open

chore: Update references from GCS buckets to new storage paths #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
12 changes: 6 additions & 6 deletions experimental/graphium/config_small_gcn.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,12 +56,12 @@ datamodule:
qm9:
df: null
df_path: data/neurips2023/small-dataset/qm9.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/qm9_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
splits_path: data/neurips2023/small-dataset/qm9_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
seed: *seed
task_level: graph
label_normalization:
Expand All @@ -71,24 +71,24 @@ datamodule:
tox21:
df: null
df_path: data/neurips2023/small-dataset/Tox21-7k-12-labels.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21-7k-12-labels.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/Tox21_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt`
splits_path: data/neurips2023/small-dataset/Tox21_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt`
seed: *seed
task_level: graph

zinc:
df: null
df_path: data/neurips2023/small-dataset/ZINC12k.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/ZINC12k_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
splits_path: data/neurips2023/small-dataset/ZINC12k_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
seed: *seed
task_level: graph
label_normalization:
Expand Down
4 changes: 2 additions & 2 deletions experimental/graphium/config_small_gcn_qm9.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,12 +45,12 @@ datamodule:
qm9:
df: null
df_path: data/neurips2023/small-dataset/qm9.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/qm9_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
splits_path: data/neurips2023/small-dataset/qm9_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
seed: *seed
task_level: graph
label_normalization:
Expand Down
4 changes: 2 additions & 2 deletions experimental/graphium/config_small_gcn_zinc.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,12 +45,12 @@ datamodule:
zinc:
df: null
df_path: data/neurips2023/small-dataset/ZINC12k.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/ZINC12k_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
splits_path: data/neurips2023/small-dataset/ZINC12k_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
seed: *seed
task_level: graph
label_normalization:
Expand Down
12 changes: 6 additions & 6 deletions experimental/graphium/config_small_gin.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,12 +56,12 @@ datamodule:
qm9:
df: null
df_path: data/neurips2023/small-dataset/qm9.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/qm9_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
splits_path: data/neurips2023/small-dataset/qm9_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
seed: *seed
task_level: graph
label_normalization:
Expand All @@ -71,24 +71,24 @@ datamodule:
tox21:
df: null
df_path: data/neurips2023/small-dataset/Tox21-7k-12-labels.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21-7k-12-labels.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/Tox21_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt`
splits_path: data/neurips2023/small-dataset/Tox21_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt`
seed: *seed
task_level: graph

zinc:
df: null
df_path: data/neurips2023/small-dataset/ZINC12k.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/ZINC12k_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
splits_path: data/neurips2023/small-dataset/ZINC12k_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
seed: *seed
task_level: graph
label_normalization:
Expand Down
12 changes: 6 additions & 6 deletions experimental/graphium/config_small_gine.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,12 +56,12 @@ datamodule:
qm9:
df: null
df_path: data/neurips2023/small-dataset/qm9.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/qm9_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
splits_path: data/neurips2023/small-dataset/qm9_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt`
seed: *seed
task_level: graph
label_normalization:
Expand All @@ -71,24 +71,24 @@ datamodule:
tox21:
df: null
df_path: data/neurips2023/small-dataset/Tox21-7k-12-labels.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21-7k-12-labels.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/Tox21_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt`
splits_path: data/neurips2023/small-dataset/Tox21_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt`
seed: *seed
task_level: graph

zinc:
df: null
df_path: data/neurips2023/small-dataset/ZINC12k.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k.csv.gz
# wget https://storage.valencelabs.com/graphium/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: data/neurips2023/small-dataset/ZINC12k_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
splits_path: data/neurips2023/small-dataset/ZINC12k_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt`
seed: *seed
task_level: graph
label_normalization:
Expand Down
12 changes: 6 additions & 6 deletions experimental/graphium/running-multitask-ipu.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -217,13 +217,13 @@
"dataset_directory = os.getenv(\"DATASETS_DIR\")\n",
"\n",
"if not os.path.exists(dataset_directory + \"/data/neurips2023/small-dataset\"):\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9.csv.gz\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21-7k-12-labels.csv.gz\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k.csv.gz\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/qm9.csv.gz\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/Tox21-7k-12-labels.csv.gz\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/ZINC12k.csv.gz\n",
"\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/qm9_random_splits.pt\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/Tox21_random_splits.pt\n",
" !wget -P $DATASETS_DIR/data/neurips2023/small-dataset/ https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/ZINC12k_random_splits.pt\n",
" print(\"Datasets have been successfully downloaded.\")\n",
"else:\n",
" print(\"Datasets are already downloaded.\")"
Expand Down