Pandas string operations

gistfile1.txt

from string import ascii_letters

import timeit

import numpy as np
import pandas as pd

letters = [
    "".join(np.random.choice(list(ascii_letters), 10, replace=True))
    for x in range(1000000)
]

df = pd.DataFrame({"a": letters})


def vectorized_approach(df):
    # df["a"] = df["a"].str.lower()
    df["a"].str.lower()


def non_vectorized(items):
    [item.lower() for item in items]


if __name__ == "__main__":
    print(
        "Vectorized approach",
        timeit.timeit(
            "vectorized_approach(df)",
            setup="from __main__ import vectorized_approach, df",
            number=100,
        ),
    )

    print(
        "Non vectorized approach",
        timeit.timeit(
            "non_vectorized(letters)",
            setup="from __main__ import non_vectorized, letters",
            number=100,
        ),
    )