Particionamiento con StratifedKFold

• Ultima modificación: 2023-02-27 | `YouTube <>`__

from sklearn.model_selection import StratifiedKFold

stratifiedKFold = StratifiedKFold(
    # --------------------------------------------------------------------------
    # Número de grupos
    n_splits=4,
    # --------------------------------------------------------------------------
    # Mezcla los datos antes de crear los grupos?
    shuffle=False,
    # --------------------------------------------------------------------------
    # Semilla del generador aleatorio
    random_state=None,
)

stratifiedKFold

StratifiedKFold(n_splits=4, random_state=None, shuffle=False)

from mymodule import plot_schema

y_classes = [0] * 16 + [1] * 4

plot_schema(stratifiedKFold, y_classes)

import numpy as np

X = np.array([[1, 2], [3, 4], [5, 6], [7, 8], [9, 10], [11, 12]])
y = np.array([0, 0, 0, 1, 1, 1])

stratifiedKFold = StratifiedKFold(
    n_splits=3,
)

for i, (train_index, test_index) in enumerate(stratifiedKFold.split(X, y)):
    print(f"Fold {i}:")
    print(f"  Train: index={train_index}")
    print(f"  Test:  index={test_index}")
    print()

Fold 0:
  Train: index=[1 2 4 5]
  Test:  index=[0 3]

Fold 1:
  Train: index=[0 2 3 5]
  Test:  index=[1 4]

Fold 2:
  Train: index=[0 1 3 4]
  Test:  index=[2 5]