require 'daru' shelter_data = Daru::DataFrame.from_csv '../data/animal_shelter_train.csv' shelter_data.head(3) shelter_data.shape shelter_data.delete_vectors 'DateTime', 'AnimalID', 'OutcomeSubtype' shelter_data.to_category 'OutcomeType', 'AnimalType', 'SexuponOutcome', 'Breed', 'Color' shelter_data.first 5 shelter_data['AgeuponOutcome'] = shelter_data['AgeuponOutcome(Weeks)'].cut [0, 1, 4, 52, 260, 1500], labels: [:less_than_week, :less_than_month, :less_than_year, :one_to_five_years, :more_than__five_years] shelter_data.delete_vector 'AgeuponOutcome(Weeks)' nil shelter_data['AgeuponOutcome'].frequencies.sort ascending: false shelter_data['AnimalType'].frequencies :percentage shelter_data['OutcomeType'].frequencies died = shelter_data.where shelter_data['OutcomeType'].eq('Died') died['AnimalType'].frequencies :percentage died.where(died['AnimalType'].eq 'Dog')['AgeuponOutcome'].frequencies :percentage died.where(died['AnimalType'].eq 'Cat')['AgeuponOutcome'].frequencies :percentage adopted = shelter_data.where shelter_data['OutcomeType'].eq('Adoption') adopted['AnimalType'].frequencies :percentage owner = shelter_data.where shelter_data['OutcomeType'].eq('Return_to_owner') owner['AnimalType'].frequencies :percentage