# 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'
#
# # 使用loompy连接loom文件
# with loompy.connect(file_path) as ds:
#
#     # 打印所有的列属性（column attributes, 即细胞元数据）
#     print("\nColumn:")
#     for key, val in ds.ca.items():
#         print(f"{key}: {val}")
#
#     # 打印所有的行属性（row attributes, 即基因元数据）
#     print("\nRow:")
#     for key, val in ds.ra.items():
#         print(f"{key}: {val}")
#
#     # 打印矩阵的一部分（例如，前5个基因和前5个细胞的表达量）
#     print("\nData matrix:")
#     matrix_slice = ds[:, :5]  # 获取所有基因在前5个细胞中的表达量
#     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])