dask_to_array.py

def to_dask_array(df):
    #  https://stackoverflow.com/questions/37444943/dask-array-from-dataframe?utm_medium=organic&utm_source=google_rich_qa&utm_campaign=google_rich_qa
    partitions = df.to_delayed()
    shapes = [part.values.shape for part in partitions]
    dtypes = partitions[0].dtypes

    results = compute(dtypes, *shapes)  # trigger computation to find shape
    dtypes, shapes = results[0], results[1:]

    chunks = [da.from_delayed(part.values, shape, dtypes) 
              for part, shape in zip(partitions, shapes)]
    return da.concatenate(chunks, axis=0)

interactions = to_dask_array(df[['user_id', 'repo_id', 'created_at']])
da.to_npy_stack('interactions', interactions)