Skip to content

chore: Update references from GCS buckets to new storage paths #537

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

Merged
merged 2 commits into from
May 6, 2025
Merged

chore: Update references from GCS buckets to new storage paths #537

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
cee8def
chore: Update bucket path
jstlaurent Apr 30, 2025
4621a5d
chore: Formatting
jstlaurent Apr 30, 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
6 changes: 3 additions & 3 deletions .github/workflows/test_ipu.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,9 +47,9 @@ jobs:
python -c "import poptorch"

# Download the datafiles (Total ~ 10Mb - nothing compared to the libraries)
wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/ZINC12k.csv.gz
wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Small-dataset/Tox21-7k-12-labels.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/ZINC12k.csv.gz
wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/Tox21-7k-12-labels.csv.gz
wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Small-dataset/qm9.csv.gz


# Install the IPU specific and graphium requirements
Expand Down
4 changes: 2 additions & 2 deletions docs/tutorials/feature_processing/choosing_parallelization.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,8 +64,8 @@
"# download from https://raw.githubusercontent.com/aspuru-guzik-group/chemical_vae/master/models/zinc_properties/250k_rndm_zinc_drugs_clean_3.csv\n",
"# data = pd.read_csv(\"/home/hadim/250k_rndm_zinc_drugs_clean_3.csv\", usecols=[\"smiles\"])\n",
"\n",
"# download from https://storage.googleapis.com/graphium-public/datasets/QM9/norm_qm9.csv\n",
"data = pd.read_csv(\"https://storage.googleapis.com/graphium-public/datasets/QM9/norm_qm9.csv\", usecols=[\"smiles\"])"
"# download from https://storage.valencelabs.com/graphium/datasets/QM9/norm_qm9.csv\n",
"data = pd.read_csv(\"https://storage.valencelabs.com/graphium/datasets/QM9/norm_qm9.csv\", usecols=[\"smiles\"])"
]
},
{
Expand Down
4 changes: 2 additions & 2 deletions docs/tutorials/feature_processing/timing_parallel.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,8 +65,8 @@
"# download from https://raw.githubusercontent.com/aspuru-guzik-group/chemical_vae/master/models/zinc_properties/250k_rndm_zinc_drugs_clean_3.csv\n",
"# data = pd.read_csv(\"/home/hadim/250k_rndm_zinc_drugs_clean_3.csv\", usecols=[\"smiles\"])\n",
"\n",
"# download from https://storage.googleapis.com/graphium-public/datasets/QM9/norm_qm9.csv\n",
"data = pd.read_csv(\"https://storage.googleapis.com/graphium-public/datasets/QM9/norm_qm9.csv\", usecols=[\"smiles\"])"
"# download from https://storage.valencelabs.com/graphium/datasets/QM9/norm_qm9.csv\n",
"data = pd.read_csv(\"https://storage.valencelabs.com/graphium/datasets/QM9/norm_qm9.csv\", usecols=[\"smiles\"])"
]
},
{
Expand Down
6 changes: 3 additions & 3 deletions expts/configs/config_gps_10M_pcqm4m.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,12 +66,12 @@ datamodule:
df: null
task_level: "graph"
df_path: ~/scratch/data/graphium/data/PCQM4M/pcqm4mv2-20k.csv
# wget https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv
# or set path as https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv directly
# wget https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv
# or set path as https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv directly
smiles_col: "cxsmiles"
label_cols: ["homo_lumo_gap"]
# sample_size: 30000 # use sample_size for test
# splits_path: graphium/data/PCQM4M/split_dict_v2.pt # Download with `wget https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/split_dict_v2.pt`
# splits_path: graphium/data/PCQM4M/split_dict_v2.pt # Download with `wget https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/split_dict_v2.pt`
split_val: 0.1
split_test: 0.1

Expand Down
6 changes: 3 additions & 3 deletions expts/configs/config_gps_10M_pcqm4m_mod.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,12 +15,12 @@ datamodule:
df: null
task_level: "graph"
df_path: ~/scratch/data/graphium/data/PCQM4M/pcqm4mv2-20k.csv
# wget https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv
# or set path as https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv directly
# wget https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv
# or set path as https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv directly
smiles_col: "cxsmiles"
label_cols: ["homo_lumo_gap"]
# sample_size: 30000 # use sample_size for test
# splits_path: graphium/data/PCQM4Mv2/split_dict.pt # Download with `wget https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/split_dict.pt`
# splits_path: graphium/data/PCQM4Mv2/split_dict.pt # Download with `wget https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/split_dict.pt`
split_val: 0.1
split_test: 0.1

Expand Down
10 changes: 5 additions & 5 deletions expts/configs/config_mpnn_10M_b3lyp.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,8 +67,8 @@ datamodule:
df: null
task_level: "graph"
df_path: graphium/data/b3lyp/b3lyp_mini.parquet #graphium/data/b3lyp/b3lyp_mini.parquet
# wget https://storage.googleapis.com/graphium-public/datasets/b3lyp/b3lyp_mini.parquet
# or set path as https://storage.googleapis.com/graphium-public/datasets/b3lyp/b3lyp_mini.parquet directly
# wget https://storage.valencelabs.com/graphium/datasets/b3lyp/b3lyp_mini.parquet
# or set path as https://storage.valencelabs.com/graphium/datasets/b3lyp/b3lyp_mini.parquet directly
smiles_col: "smiles"
label_cols: ["beta_gap"]
# sample_size: 30000 # use sample_size for test
Expand All @@ -78,12 +78,12 @@ datamodule:
df: null
task_level: "graph"
df_path: graphium/data/b3lyp/b3lyp_mini.parquet #graphium/data/b3lyp/b3lyp_mini.parquet
# wget https://storage.googleapis.com/graphium-public/datasets/b3lyp/b3lyp_mini.parquet
# or set path as https://storage.googleapis.com/graphium-public/datasets/b3lyp/b3lyp_mini.parquet directly
# wget https://storage.valencelabs.com/graphium/datasets/b3lyp/b3lyp_mini.parquet
# or set path as https://storage.valencelabs.com/graphium/datasets/b3lyp/b3lyp_mini.parquet directly
smiles_col: "smiles"
label_cols: ["alpha_gap"]
# sample_size: 30000 # use sample_size for test
# splits_path: graphium/data/PCQM4M/split_dict_v2.pt # Download with `wget https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/split_dict_v2.pt`
# splits_path: graphium/data/PCQM4M/split_dict_v2.pt # Download with `wget https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/split_dict_v2.pt`
split_val: 0.1
split_test: 0.1

Expand Down
6 changes: 3 additions & 3 deletions expts/configs/config_mpnn_pcqm4m.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,12 +15,12 @@ datamodule:
df: null
task_level: "graph"
df_path: graphium/data/PCQM4M/pcqm4mv2-20k.csv
# wget https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv
# or set path as https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv directly
# wget https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv
# or set path as https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2-20k.csv directly
smiles_col: "cxsmiles"
label_cols: ["homo_lumo_gap"]
# sample_size: 6000 # use sample_size for test
splits_path: graphium/data/PCQM4Mv2/split_dict_v2.pt # Download with `wget https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/split_dict_v2.pt`
splits_path: graphium/data/PCQM4Mv2/split_dict_v2.pt # Download with `wget https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/split_dict_v2.pt`
# graphium/data/PCQM4Mv2/split_dict.pt
# graphium/data/PCQM4Mv2/pcqm4m_split.csv
split_names: ["train", "valid", "test-dev"]
Expand Down
4 changes: 2 additions & 2 deletions expts/hydra-configs/tasks/loss_metrics_datamodule/l1000_mcf7.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,12 +38,12 @@ datamodule:
l1000_mcf7:
df: null
df_path: ../data/graphium/large-dataset/LINCS_L1000_MCF7_0-2_th2.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/LINCS_L1000_MCF7_0-4.csv.gz
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/LINCS_L1000_MCF7_0-4.csv.gz
# or set path as the URL directly
smiles_col: "SMILES"
label_cols: geneID-* # geneID-* means all columns starting with "geneID-"
# sample_size: 2000 # use sample_size for test
task_level: graph
splits_path: ../data/graphium/large-dataset/l1000_mcf7_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/l1000_mcf7_random_splits.pt`
splits_path: ../data/graphium/large-dataset/l1000_mcf7_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/l1000_mcf7_random_splits.pt`
# split_names: [train, val, test_seen]
epoch_sampling_fraction: 1.0
4 changes: 2 additions & 2 deletions expts/hydra-configs/tasks/loss_metrics_datamodule/l1000_vcap.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,12 +38,12 @@ datamodule:
l1000_vcap:
df: null
df_path: ../data/graphium/large-dataset/LINCS_L1000_VCAP_0-2_th2.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/LINCS_L1000_VCAP_0-4.csv.gz
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/LINCS_L1000_VCAP_0-4.csv.gz
# or set path as the URL directly
smiles_col: "SMILES"
label_cols: geneID-* # geneID-* means all columns starting with "geneID-"
# sample_size: 2000 # use sample_size for test
task_level: graph
splits_path: ../data/graphium/large-dataset/l1000_vcap_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/l1000_vcap_random_splits.pt`
splits_path: ../data/graphium/large-dataset/l1000_vcap_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/l1000_vcap_random_splits.pt`
# split_names: [train, val, test_seen]
epoch_sampling_fraction: 1.0
20 changes: 10 additions & 10 deletions expts/hydra-configs/tasks/loss_metrics_datamodule/largemix.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,52 +85,52 @@ datamodule:
l1000_vcap:
df: null
df_path: ../data/graphium/large-dataset/LINCS_L1000_VCAP_0-2_th2.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/LINCS_L1000_VCAP_0-4.csv.gz
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/LINCS_L1000_VCAP_0-4.csv.gz
# or set path as the URL directly
smiles_col: "SMILES"
label_cols: geneID-* # geneID-* means all columns starting with "geneID-"
# sample_size: 2000 # use sample_size for test
task_level: graph
splits_path: ../data/graphium/large-dataset/l1000_vcap_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/l1000_vcap_random_splits.pt`
splits_path: ../data/graphium/large-dataset/l1000_vcap_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/l1000_vcap_random_splits.pt`
# split_names: [train, val, test_seen]
epoch_sampling_fraction: 1.0

l1000_mcf7:
df: null
df_path: ../data/graphium/large-dataset/LINCS_L1000_MCF7_0-2_th2.csv.gz
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/LINCS_L1000_MCF7_0-4.csv.gz
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/LINCS_L1000_MCF7_0-4.csv.gz
# or set path as the URL directly
smiles_col: "SMILES"
label_cols: geneID-* # geneID-* means all columns starting with "geneID-"
# sample_size: 2000 # use sample_size for test
task_level: graph
splits_path: ../data/graphium/large-dataset/l1000_mcf7_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/l1000_mcf7_random_splits.pt`
splits_path: ../data/graphium/large-dataset/l1000_mcf7_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/l1000_mcf7_random_splits.pt`
# split_names: [train, val, test_seen]
epoch_sampling_fraction: 1.0

pcba_1328:
df: null
df_path: ../data/graphium/large-dataset/PCBA_1328_1564k.parquet
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/PCBA_1328_1564k.parquet
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/PCBA_1328_1564k.parquet
# or set path as the URL directly
smiles_col: "SMILES"
label_cols: assayID-* # assayID-* means all columns starting with "assayID-"
# sample_size: 2000 # use sample_size for test
task_level: graph
splits_path: ../data/graphium/large-dataset/pcba_1328_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/pcba_1328_random_splits.pt`
splits_path: ../data/graphium/large-dataset/pcba_1328_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/pcba_1328_random_splits.pt`
# split_names: [train, val, test_seen]
epoch_sampling_fraction: 1.0

pcqm4m_g25:
df: null
df_path: ../data/graphium/large-dataset/PCQM4M_G25_N4.parquet
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet
# or set path as the URL directly
smiles_col: "ordered_smiles"
label_cols: graph_* # graph_* means all columns starting with "graph_"
# sample_size: 2000 # use sample_size for test
task_level: graph
splits_path: ../data/graphium/large-dataset/pcqm4m_g25_n4_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt`
splits_path: ../data/graphium/large-dataset/pcqm4m_g25_n4_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt`
# split_names: [train, val, test_seen]
label_normalization:
normalize_val_test: True
Expand All @@ -140,13 +140,13 @@ datamodule:
pcqm4m_n4:
df: null
df_path: ../data/graphium/large-dataset/PCQM4M_G25_N4.parquet
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet
# or set path as the URL directly
smiles_col: "ordered_smiles"
label_cols: node_* # node_* means all columns starting with "node_"
# sample_size: 2000 # use sample_size for test
task_level: node
splits_path: ../data/graphium/large-dataset/pcqm4m_g25_n4_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt`
splits_path: ../data/graphium/large-dataset/pcqm4m_g25_n4_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt`
# split_names: [train, val, test_seen]
seed: 42
label_normalization:
Expand Down
4 changes: 2 additions & 2 deletions expts/hydra-configs/tasks/loss_metrics_datamodule/pcba_1328.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,12 +30,12 @@ datamodule:
pcba_1328:
df: null
df_path: ../data/graphium/large-dataset/PCBA_1328_1564k.parquet
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/PCBA_1328_1564k.parquet
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/PCBA_1328_1564k.parquet
# or set path as the URL directly
smiles_col: "SMILES"
label_cols: assayID-* # assayID-* means all columns starting with "assayID-"
# sample_size: 2000 # use sample_size for test
task_level: graph
splits_path: ../data/graphium/large-dataset/pcba_1328_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/pcba_1328_random_splits.pt`
splits_path: ../data/graphium/large-dataset/pcba_1328_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/pcba_1328_random_splits.pt`
# split_names: [train, val, test_seen]
epoch_sampling_fraction: 1.0
6 changes: 3 additions & 3 deletions expts/hydra-configs/tasks/loss_metrics_datamodule/pcqm4m.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,12 +32,12 @@ datamodule:
df: null
task_level: "graph"
df_path: graphium/data/PCQM4M/pcqm4mv2.csv
# wget https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2.csv
# or set path as https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2.csv directly
# wget https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2.csv
# or set path as https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/pcqm4mv2.csv directly
smiles_col: "cxsmiles"
label_cols: ["homo_lumo_gap"]
# sample_size: 8000 # use sample_size for test
splits_path: graphium/data/PCQM4M/split_dict_v2.pt # Download with `wget https://storage.googleapis.com/datasets-public-research/PCQM4M/cxsmiles/split_dict_v2.pt`
splits_path: graphium/data/PCQM4M/split_dict_v2.pt # Download with `wget https://storage.valencelabs.com/datasets-public-research/PCQM4M/cxsmiles/split_dict_v2.pt`
split_names: ["train", "valid", "test-dev"]
# graphium/data/PCQM4Mv2/split_dict.pt
# graphium/data/PCQM4Mv2/pcqm4m_split.csv
Expand Down
4 changes: 2 additions & 2 deletions expts/hydra-configs/tasks/loss_metrics_datamodule/pcqm4m_g25.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,13 +32,13 @@ datamodule:
pcqm4m_g25:
df: null
df_path: ../data/graphium/large-dataset/PCQM4M_G25_N4.parquet
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet
# or set path as the URL directly
smiles_col: "ordered_smiles"
label_cols: graph_* # graph_* means all columns starting with "graph_"
# sample_size: 2000 # use sample_size for test
task_level: graph
splits_path: ../data/graphium/large-dataset/pcqm4m_g25_n4_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt`
splits_path: ../data/graphium/large-dataset/pcqm4m_g25_n4_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt`
# split_names: [train, val, test_seen]
label_normalization:
normalize_val_test: True
Expand Down
4 changes: 2 additions & 2 deletions expts/hydra-configs/tasks/loss_metrics_datamodule/pcqm4m_n4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,13 +30,13 @@ datamodule:
pcqm4m_n4:
df: null
df_path: ../data/graphium/large-dataset/PCQM4M_G25_N4.parquet
# wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet
# wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet
# or set path as the URL directly
smiles_col: "ordered_smiles"
label_cols: node_* # node_* means all columns starting with "node_"
# sample_size: 2000 # use sample_size for test
task_level: node
splits_path: ../data/graphium/large-dataset/pcqm4m_g25_n4_random_splits.pt # Download with `wget https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt`
splits_path: ../data/graphium/large-dataset/pcqm4m_g25_n4_random_splits.pt # Download with `wget https://storage.valencelabs.com/graphium/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt`
# split_names: [train, val, test_seen]
seed: 42
label_normalization:
Expand Down
Loading
Loading