diff --git a/README.md b/README.md index a83f7ab40..758af2cf2 100644 --- a/README.md +++ b/README.md @@ -5,7 +5,6 @@ --- -[![Run on Gradient](https://assets.paperspace.io/img/gradient-badge.svg)](https://ipu.dev/sdGggS) [![PyPI](https://img.shields.io/pypi/v/graphium)](https://pypi.org/project/graphium/) [![Conda](https://img.shields.io/conda/v/conda-forge/graphium?label=conda&color=success)](https://anaconda.org/conda-forge/graphium) [![PyPI - Downloads](https://img.shields.io/pypi/dm/graphium)](https://pypi.org/project/graphium/) @@ -34,10 +33,6 @@ A deep learning library focused on graph representation learning for real-world Visit https://graphium-docs.datamol.io/. -[![Run on Gradient](https://assets.paperspace.io/img/gradient-badge.svg)](https://ipu.dev/sdGggS) - -You can try running Graphium on Graphcore IPUs for free on Gradient by clicking on the button above. - ## Installation for developers ### For CPU and GPU developers diff --git a/download_datasets.sh b/download_datasets.sh new file mode 100755 index 000000000..90159cc39 --- /dev/null +++ b/download_datasets.sh @@ -0,0 +1,33 @@ +#!/bin/bash + +# Function to download dataset +download_dataset() { + local dataset_url=$1 + local dataset_path=$2 + + # Create directory if it does not exist + mkdir -p $(dirname "${dataset_path}") + + # Download the dataset + wget -O "${dataset_path}" "${dataset_url}" +} + +# L1000_VCAP +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/LINCS_L1000_VCAP_0-4.csv.gz" "graphium/data/neurips2023/large-dataset/LINCS_L1000_VCAP_0-2_th2.csv.gz" +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/l1000_vcap_random_splits.pt" "graphium/data/neurips2023/large-dataset/l1000_vcap_random_splits.pt" + +# l1000_MCF7 +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/LINCS_L1000_MCF7_0-4.csv.gz" "graphium/data/neurips2023/large-dataset/LINCS_L1000_MCF7_0-2_th2.csv.gz" +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/l1000_mcf7_random_splits.pt" "graphium/data/neurips2023/large-dataset/l1000_mcf7_random_splits.pt" + +# PCBA_1328 +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/PCBA_1328_1564k.parquet" "graphium/data/neurips2023/large-dataset/PCBA_1328_1564k.parquet" +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/pcba_1328_random_splits.pt" "graphium/data/neurips2023/large-dataset/pcba_1328_random_splits.pt" + +# PCQM4M_G25 +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet" "graphium/data/neurips2023/large-dataset/PCQM4M_G25_N4.parquet" +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt" "graphium/data/neurips2023/large-dataset/pcqm4m_g25_n4_random_splits.pt" + +# PCQM4M_N4 +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/PCQM4M_G25_N4.parquet" "graphium/data/neurips2023/large-dataset/PCQM4M_G25_N4.parquet" +download_dataset "https://storage.googleapis.com/graphium-public/datasets/neurips_2023/Large-dataset/pcqm4m_g25_n4_random_splits.pt" "graphium/data/neurips2023/large-dataset/pcqm4m_g25_n4_random_splits.pt"