# /// script # requires-python = ">=3.12" # dependencies = [ # "zarr@git+https://github.com/zarr-developers/zarr-python.git@main", # "pandas", # "pyarrow", # ] # /// # # This script automatically imports the development branch of zarr to check for issues import zarr # your reproducer code import numpy as np import pandas as pd # Number of rows and columns num_rows = 11 num_cols = 11 # Generate incrementing strings incrementing_strings = [f"S{i:05}" for i in range(1, num_rows * num_cols + 1)] npdata = np.array(incrementing_strings, dtype="str").reshape(num_rows, num_cols) df = pd.DataFrame(npdata) dfpa = df.astype("string[pyarrow]") data = df.values datapa = dfpa.values # According to numpy, the converted data is identical: assert data.dtype == datapa.dtype # dtype == 'O' assert data.shape == datapa.shape assert data.size == datapa.size assert np.all(data == datapa) # Now store both in a zarray (using the same array here but doesn't matter if I use a fresh one) store = zarr.storage.MemoryStore() # Or LocalStore, doesn't matter array = zarr.create_array( store, name="s", shape=data.shape, chunks=(10,10), fill_value="<NA>", dtype=str, ) # This works as expected array[:,:] = data zdata = array[:,:] assert np.all(zdata == data) # This doesn't array[:,:] = datapa zdata = array[:,:] print(f"written={datapa[0,:4]}") # ['S00001' 'S00002' 'S00003' 'S00004'] print(f"read={zdata[0,:4]}") # ['S00001' 'S00012' 'S00023' 'S00034'] assert np.all(zdata == datapa) # Fails