Doctorado-ML/odte
1
1
Fork 0
mirror of https://github.com/Doctorado-ML/Odte.git synced 2025-07-11 08:12:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix np.random initialization

Browse Source
This commit is contained in:
Ricardo Montañana Gómez 2022-02-23 12:02:59 +01:00
parent cd7c7f3938
commit 3766886190
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
2 changed files with 40 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
odte/Odte.py
View File

@ -16,6 +16,7 @@ from sklearn.utils.multiclass import ( # type: ignore
check_classification_targets, check_classification_targets,
) )
from sklearn.base import clone, BaseEstimator, ClassifierMixin # type: ignore from sklearn.base import clone, BaseEstimator, ClassifierMixin # type: ignore
from sklearn.utils import check_random_state
from sklearn.ensemble import BaseEnsemble # type: ignore from sklearn.ensemble import BaseEnsemble # type: ignore
from sklearn.utils.validation import ( # type: ignore from sklearn.utils.validation import ( # type: ignore
check_is_fitted, check_is_fitted,
@ -31,7 +32,6 @@ def _parallel_build_tree(
X: np.ndarray, X: np.ndarray,
y: np.ndarray, y: np.ndarray,
weights: np.ndarray, weights: np.ndarray,
random_box: np.random.mtrand.RandomState,
random_seed: int, random_seed: int,
boot_samples: int, boot_samples: int,
max_features: int, max_features: int,
@ -43,6 +43,7 @@ def _parallel_build_tree(
clf.set_params(**hyperparams_) clf.set_params(**hyperparams_)
n_samples = X.shape[0] n_samples = X.shape[0]
# bootstrap # bootstrap
random_box = check_random_state(random_seed)
indices = random_box.randint(0, n_samples, boot_samples) indices = random_box.randint(0, n_samples, boot_samples)
# update weights with the chosen samples # update weights with the chosen samples
weights_update = np.bincount(indices, minlength=n_samples) weights_update = np.bincount(indices, minlength=n_samples)
@ -83,12 +84,6 @@ class Odte(BaseEnsemble, ClassifierMixin):
def version() -> str: def version() -> str:
return __version__ return __version__
def _initialize_random(self) -> np.random.mtrand.RandomState:
if self.random_state is None:
self.random_state = random.randint(0, sys.maxsize)
return np.random.mtrand._rand
return np.random.RandomState(self.random_state)
def _validate_estimator(self) -> None: def _validate_estimator(self) -> None:
"""Check the estimator and set the base_estimator_ attribute.""" """Check the estimator and set the base_estimator_ attribute."""
super()._validate_estimator( super()._validate_estimator(
@ -141,7 +136,7 @@ class Odte(BaseEnsemble, ClassifierMixin):
def _train( def _train(
self, X: np.ndarray, y: np.ndarray, weights: np.ndarray self, X: np.ndarray, y: np.ndarray, weights: np.ndarray
) -> Tuple[List[BaseEstimator], List[Tuple[int, ...]]]: ) -> Tuple[List[BaseEstimator], List[Tuple[int, ...]]]:
random_box = self._initialize_random() # np.random.RandomState(seed)
n_samples = X.shape[0] n_samples = X.shape[0]
boot_samples = self._get_bootstrap_n_samples(n_samples) boot_samples = self._get_bootstrap_n_samples(n_samples)
estimator = [] estimator = []
@ -153,17 +148,13 @@ class Odte(BaseEnsemble, ClassifierMixin):
X, X,
y, y,
weights, weights,
random_box,
random_seed, random_seed,
boot_samples, boot_samples,
self.max_features_, self.max_features_,
self.be_hyperparams, self.be_hyperparams,
) )
for random_seed, i in zip( for i, random_seed in enumerate(
range( range(self.random_state, self.random_state + self.n_estimators)
self.random_state, self.random_state + self.n_estimators
),
range(self.n_estimators),
) )
) )

68
odte/tests/Odte_tests.py
View File

@ -54,20 +54,6 @@ class Odte_test(unittest.TestCase):
self.assertListEqual(expected, list(computed)) self.assertListEqual(expected, list(computed))
# print(f"{list(computed)},") # print(f"{list(computed)},")
def test_initialize_random(self):
expected = [37, 235, 908]
tclf = Odte(random_state=self._random_state)
box = tclf._initialize_random()
computed = box.randint(0, 1000, 3)
self.assertListEqual(expected, computed.tolist())
# test None
tclf = Odte(random_state=None)
box = tclf._initialize_random()
computed = box.randint(101, 1000, 3)
for value in computed.tolist():
self.assertGreaterEqual(value, 101)
self.assertLessEqual(value, 1000)
def test_bogus_max_features(self): def test_bogus_max_features(self):
values = ["duck", -0.1, 0.0] values = ["duck", -0.1, 0.0]
for max_features in values: for max_features in values:
@ -124,7 +110,7 @@ class Odte_test(unittest.TestCase):
def test_score(self): def test_score(self):
X, y = load_dataset(self._random_state) X, y = load_dataset(self._random_state)
expected = 0.9513333333333334 expected = 0.9533333333333334
tclf = Odte( tclf = Odte(
random_state=self._random_state, random_state=self._random_state,
max_features=None, max_features=None,
@ -136,19 +122,18 @@ class Odte_test(unittest.TestCase):
def test_score_splitter_max_features(self): def test_score_splitter_max_features(self):
X, y = load_dataset(self._random_state, n_features=16, n_samples=500) X, y = load_dataset(self._random_state, n_features=16, n_samples=500)
results = [ results = [
0.948, 0.958, # best auto
0.924, 0.942, # random auto
0.926, 0.932, # trandom auto
0.94, 0.95, # mutual auto
0.932, 0.944, # iwss auto
0.936, 0.946, # cfs auto
0.962, 0.97, # best None
0.962, 0.97, # random None
0.962, 0.97, # trandom None
0.962, 0.97, # mutual None
0.962, 0.97, # iwss None
0.962, 0.97, # cfs None
0.962,
] ]
random.seed(self._random_state) random.seed(self._random_state)
for max_features in ["auto", None]: for max_features in ["auto", None]:
@ -208,15 +193,32 @@ class Odte_test(unittest.TestCase):
base_estimator=Stree(), base_estimator=Stree(),
random_state=self._random_state, random_state=self._random_state,
n_estimators=3, n_estimators=3,
n_jobs=1,
) )
X, y = load_dataset(self._random_state, n_features=16, n_samples=500) X, y = load_dataset(self._random_state, n_features=16, n_samples=500)
tclf.fit(X, y) tclf.fit(X, y)
self.assertAlmostEqual(6.0, tclf.depth_) self.assertAlmostEqual(6.333333333333333, tclf.depth_)
self.assertAlmostEqual(9.333333333333334, tclf.leaves_) self.assertAlmostEqual(10.0, tclf.leaves_)
self.assertAlmostEqual(17.666666666666668, tclf.nodes_) self.assertAlmostEqual(19.0, tclf.nodes_)
nodes, leaves = tclf.nodes_leaves() nodes, leaves = tclf.nodes_leaves()
self.assertAlmostEqual(9.333333333333334, leaves) self.assertAlmostEqual(10.0, leaves)
self.assertAlmostEqual(17.666666666666668, nodes) self.assertAlmostEqual(19, nodes)
def test_nodes_leaves_depth_parallel(self):
tclf = Odte(
base_estimator=Stree(),
random_state=self._random_state,
n_estimators=3,
n_jobs=-1,
)
X, y = load_dataset(self._random_state, n_features=16, n_samples=500)
tclf.fit(X, y)
self.assertAlmostEqual(6.333333333333333, tclf.depth_)
self.assertAlmostEqual(10.0, tclf.leaves_)
self.assertAlmostEqual(19.0, tclf.nodes_)
nodes, leaves = tclf.nodes_leaves()
self.assertAlmostEqual(10.0, leaves)
self.assertAlmostEqual(19, nodes)
def test_nodes_leaves_SVC(self): def test_nodes_leaves_SVC(self):
tclf = Odte( tclf = Odte(