a-pandas-ex-multiloc 0.10

Search for multiple values in multiple columns of a Pandas DataFrame

Search for multiple values in multiple columns of a Pandas DataFrame

pip install a-pandas-ex-multiloc

from random import randrange

from a_pandas_ex_multiloc import pd_add_multiloc

import pandas as pd



pd_add_multiloc()

df = pd.DataFrame(

    [(randrange(0, 256), randrange(0, 256), randrange(0, 256)) for k in range(100000)],

    columns=["r", "g", "b"],

)







df.d_multiloc(

    column_and_values=[

        (

            "==",

            ("r", "g", "b"),

            ((166, 16, 169), (1, 0, 0), (18, 38, 64), (11, 14, 45), (11, 14, pd.NA)),

        )

    ],

)



# the same as:

# df.loc[((df['r'] == 166)&(df['g'] == 16)&(df['b'] == 169))|((df['r'] == 1)&(df['g'] == 0)&(df['b'] == 0))|((df['r'] == 18)&(df['g'] == 38)&(df['b'] == 64))|((df['r'] == 11)&(df['g'] == 14)&(df['b'] == 45))|((df['r'] == 11)&(df['g'] == 14)&(df['b'] == pd.NA))]



# NaN has to be passed as: pd.NA



df.d_multiloc(

    column_and_values=[("==", ("r", "g", "b"), ((11, 14, 45), (11, 14, pd.NA)))],

)

# the same as: df.loc[((df['r'] == 11)&(df['g'] == 14)&(df['b'] == 45))|((df['r'] == 11)&(df['g'] == 14)&(df['b'] == pd.NA))]



# not all values need to be inside each tuple

df.d_multiloc(

    column_and_values=[("==", ("r", "g", "b"), ((11, 14, 45), (11,), (16, 100)))],

)

# the same as: df.loc[((df['r'] == 11)&(df['g'] == 14)&(df['b'] == 45))|((df['r'] == 11))|((df['r'] == 16)&(df['g'] == 100))]