Taken from Stephanie Wang's gist: https://gist.github.com/stephanie-wang/7400fd3b50bef0c8ce2d5b29f58c2530#file-pyspark_on_ray-py

modin_on_ray.py

import ray
# Modin defaults to backing Ray’s object store with disk.
# Start Ray before importing modin to use shared memory instead.
ray.init()

import modin.pandas as pd
import numpy as np

frame_data = np.random.randint(0, 100, size=(2**10, 2**8))
df = pd.DataFrame(frame_data)
print(df.head(10))