跟着Leo机器学习实战：sklearn之model_selection

源地址

https://scikit-learn.org/stable/modules/cross_validation.html

函数导图

3.1. Cross-validation: evaluating estimator performance

3.1.1. Computing cross-validated metrics

from sklearn.model_selection import cross_val_score
clf = svm.SVC(kernel='linear', C=1)
scores = cross_val_score(clf, X, y, cv=5)
scores

from sklearn.model_selection import ShuffleSplit
n_samples = X.shape[0]
cv = ShuffleSplit(n_splits=5, test_size=0.3, random_state=0)
cross_val_score(clf, X, y, cv=cv)

from sklearn.model_selection import cross_validate
from sklearn.metrics import recall_score
scoring = ['precision_macro', 'recall_macro']
clf = svm.SVC(kernel='linear', C=1, random_state=0)
scores = cross_validate(clf, X, y, scoring=scoring)
sorted(scores.keys())

scores['test_recall_macro']

3.1.2. Cross validation iterators

3.1.2.1.1. K-fold

import numpy as np
from sklearn.model_selection import KFold

X = ["a", "b", "c", "d"]
kf = KFold(n_splits=2)
for train, test in kf.split(X):
    print("%s %s" % (train, test))

3.1.2.1.2. Repeated K-Fold

import numpy as np
from sklearn.model_selection import RepeatedKFold
X = np.array([[1, 2], [3, 4], [1, 2], [3, 4]])
random_state = 12883823
rkf = RepeatedKFold(n_splits=2, n_repeats=2, random_state=random_state)
for train, test in rkf.split(X):
    print("%s %s" % (train, test))

3.1.2.1.3. Leave One Out (LOO)

from sklearn.model_selection import LeaveOneOut

X = [1, 2, 3, 4]
loo = LeaveOneOut()
for train, test in loo.split(X):
    print("%s %s" % (train, test))

3.1.2.1.4. Leave P Out (LPO)

from sklearn.model_selection import LeavePOut

X = np.ones(4)
lpo = LeavePOut(p=2)
for train, test in lpo.split(X):
    print("%s %s" % (train, test))

3.1.2.2.1. Stratified k-fold

from sklearn.model_selection import StratifiedKFold, KFold
import numpy as np
X, y = np.ones((50, 1)), np.hstack(([0] * 45, [1] * 5))
skf = StratifiedKFold(n_splits=3)
for train, test in skf.split(X, y):
    print('train -  {}   |   test -  {}'.format(
        np.bincount(y[train]), np.bincount(y[test])))



kf = KFold(n_splits=3)
for train, test in kf.split(X, y):
    print('train -  {}   |   test -  {}'.format(
        np.bincount(y[train]), np.bincount(y[test])))

3.1.2.3.1. Group k-fold

from sklearn.model_selection import GroupKFold

X = [0.1, 0.2, 2.2, 2.4, 2.3, 4.55, 5.8, 8.8, 9, 10]
y = ["a", "b", "b", "b", "c", "c", "c", "d", "d", "d"]
groups = [1, 1, 1, 2, 2, 2, 3, 3, 3, 3]

gkf = GroupKFold(n_splits=3)
for train, test in gkf.split(X, y, groups=groups):
    print("%s %s" % (train, test))

3.1.2.3.2. Leave One Group Out

from sklearn.model_selection import LeaveOneGroupOut

X = [1, 5, 10, 50, 60, 70, 80]
y = [0, 1, 1, 2, 2, 2, 2]
groups = [1, 1, 2, 2, 3, 3, 3]
logo = LeaveOneGroupOut()
for train, test in logo.split(X, y, groups=groups):
    print("%s %s" % (train, test))

3.1.2.3.3. Leave P Groups Out

from sklearn.model_selection import LeavePGroupsOut

X = np.arange(6)
y = [1, 1, 1, 2, 2, 2]
groups = [1, 1, 2, 2, 3, 3]
lpgo = LeavePGroupsOut(n_groups=2)
for train, test in lpgo.split(X, y, groups=groups):
    print("%s %s" % (train, test))

3.1.2.3.4. Group Shuffle Split

from sklearn.model_selection import GroupShuffleSplit

X = [0.1, 0.2, 2.2, 2.4, 2.3, 4.55, 5.8, 0.001]
y = ["a", "b", "b", "b", "c", "c", "c", "a"]
groups = [1, 1, 2, 2, 3, 3, 4, 4]
gss = GroupShuffleSplit(n_splits=4, test_size=0.5, random_state=0)
for train, test in gss.split(X, y, groups=groups):
    print("%s %s" % (train, test))

3.1.2.5.1. Time Series Split

from sklearn.model_selection import TimeSeriesSplit

X = np.array([[1, 2], [3, 4], [1, 2], [3, 4], [1, 2], [3, 4]])
y = np.array([1, 2, 3, 4, 5, 6])
tscv = TimeSeriesSplit(n_splits=3)
print(tscv)

for train, test in tscv.split(X):
    print("%s %s" % (train, test))