swifter_pandas_apply_with_vectorization_dask_multiprocessing.py

1import pandas as pd
2import swifter
3
4def filter_func(x):
5    return x > 5
6
7df = pd.DataFrame({'x': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
8                   'y': [11, 12, 13, 14, 15, 16, 17, 18, 19, 20]})
9
10# runs on a pandas series
11df['x2'] = df['x'].swifter.apply(lambda x: x**2)
12
13# runs on a pandas dataframe
14df['h'] = df.swifter.apply(lambda x: x['x'] + x['y'], axis=1)
15
16# runs on a pandas groupby
17df.groupby('x2').swifter.apply(lambda x: x.sum())