import os
import urllib.request
import scanpy as sc


def collect_data():

    os.makedirs("celldreamer/data/raw", exist_ok=True)
    
    # Source: https://scanpy-tutorials.readthedocs.io/en/latest/integrating-data-using-ingest.html
    url = "https://www.dropbox.com/s/qj1jlm9w10wmt0u/pancreas.h5ad?dl=1"
    save_path = "celldreamer/data/raw/panc8_raw.h5ad"
    
    urllib.request.urlretrieve(url, save_path)

    adata = sc.read(save_path)
    print(f"{adata.shape[0]} cells x {adata.shape[1]} genes")