knnor_data_prep.py

from sklearn.datasets import load_breast_cancer
import numpy as np
import collections

from knnor import data_augment

dataset = load_breast_cancer()

(unique, counts) = np.unique(dataset['target'], return_counts=True)

print('Unique values of the target variable', unique)
print('Counts of the target variable :', counts)

X=dataset["data"]
y=dataset["target"]

print("Original shape=",X.shape,y.shape)
elements_count = collections.Counter(y)
# printing the element and the frequency
print("Original distribution:")
for key, value in elements_count.items():
    print(f"{key}: {value}")