import numpy as np
import pandas as pd
# make a 1million x 10 dataframe with nans interspersed
arr = np.random.randn(int(1e6))
cols = {f'column_{i}': arr for i in range(10)}
df = pd.DataFrame(cols)
df.tail()
%time df.to_feather('test_df.feather')
%time df.to_csv('test_df.gzip.csv', compression='gzip')