import random import string import numpy as np import pandas as pd np.random.seed = 42 def get_random_string(length): letters = string.ascii_lowercase return ''.join(random.choice(letters) for i in range(length)) df_size = 5_000_000 df = pd.DataFrame({ 'num_1': np.random.rand(df_size), 'num_2': np.random.rand(df_size), 'num_3': np.random.rand(df_size), 'num_4': np.random.rand(df_size), 'num_5': np.random.rand(df_size), 'str_1': [get_random_string(length=32) for x in range(df_size)], 'str_2': [get_random_string(length=128) for x in range(df_size)] })