cartesian product in pandas

Question

I have two pandas dataframes:

from pandas import DataFrame
df1 = DataFrame({\'col1\':[1,2],\'col2\':[3,4]})
df2 = DataFrame({\'col3\':[5,6]})     
         


        

Answer 1

Here is a helper function to perform a simple Cartesian product with two data frames. The internal logic handles using an internal key, and avoids mangling any columns that happen to be named "key" from either side.

import pandas as pd

def cartesian(df1, df2):
    """Determine Cartesian product of two data frames."""
    key = 'key'
    while key in df1.columns or key in df2.columns:
        key = '_' + key
    key_d = {key: 0}
    return pd.merge(
        df1.assign(**key_d), df2.assign(**key_d), on=key).drop(key, axis=1)

# Two data frames, where the first happens to have a 'key' column
df1 = pd.DataFrame({'number':[1, 2], 'key':[3, 4]})
df2 = pd.DataFrame({'digit': [5, 6]})
cartesian(df1, df2)

shows:

   number  key  digit
0       1    3      5
1       1    3      6
2       2    4      5
3       2    4      6