# import scanpy as sc
#
# file_path = '/scDifformer/data/240412_test/raw_h5ad/zheng68k_fold0_test.h5ad'
#
# adata = sc.read_h5ad(file_path)
# adata[:3, :3].to_df().to_excel('/scDifformer/data/240412_test/data_info/h5ad_info.xlsx')




# import loompy
#
# file_path = '/scDifformer/data/240412_test/looms/zheng68k_fold0_test.loom'
#
# # Use loompy to connect to the loom file
# with loompy.connect(file_path) as ds:
#
#     # Print all column attributes (cell metadata)
#     print("\nColumn:")
#     for key, val in ds.ca.items():
#         print(f"{key}: {val}")
#
#     # Print all row attributes (gene metadata)
#     print("\nRow:")
#     for key, val in ds.ra.items():
#         print(f"{key}: {val}")
#
#     # Print part of the matrix (e.g., expression of first 5 genes and first 5 cells)
#     print("\nData matrix:")
#     matrix_slice = ds[:, :5]  # Expression of all genes in the first 5 cells
#     print(matrix_slice)

# import pickle
#
# file_path = '/scDifformer/data/240412_test/material/gene_median_dictionary.pkl'
#
# with open(file_path, 'rb') as file:
#     data = pickle.load(file)
#
# print(data)


# import pickle
#
# file_path = '/scDifformer/data/240412_test/material/token_dictionary.pkl'
#
# with open(file_path, 'rb') as file:
#     data = pickle.load(file)
#
# print(data)


from datasets import load_from_disk

file_path = '/scDifformer/data/240412_test/output_directory_run/geneformer_run.dataset'

ds = load_from_disk(file_path)
print(ds[:3])