Removing duplicate objects
Assume that you want to construct a predictive model in order to select donors that are most likely to respond on a letter. The population of the basetable should contain donors that have an adress available, and that have privacy settings that allow to send them a letter.
All candidate donors are given in a dataframe donors with three columns: the donor_id, a flag address that is 1 if the address is available and 0 otherwise, and a flag letter_allowed that is 1 if one can send this donor a letter and 0 otherwise.
In this exercise you will construct a set with the donors that should go in the population.
Deze oefening maakt deel uit van de cursus
Intermediate Predictive Analytics in Python
Oefeninstructies
- Create a dataframe
donors_populationonly containing observations that have address available and for which a letter is allowed. - Create a list containing the donor ids in
donors_population. - Construct the final population and then numbers of donors in it.
Praktische interactieve oefening
Probeer deze oefening eens door deze voorbeeldcode in te vullen.
# Create a dataframe donors_population
donors_population = ____[(____["____"] == ____) & (____["____"] == ____)]
# Create a list of donor IDs
population_list = ____(____["____"])
# Select unique donors in population_list
population = ____(____)
print(len(population))