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

use all available cores in fit

Browse Source 
adapt pre-commit to python 3.8
This commit is contained in:
Ricardo Montañana Gómez 2020-11-10 14:12:00 +01:00
parent 8f7cbc9091
commit 7a49d672df
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
4 changed files with 36 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
.pre-commit-config.yaml
View File

@ -5,7 +5,7 @@ repos:
- id: black
language_version: python3.8
- repo: https://gitlab.com/pycqa/flake8
rev: 3.7.9
rev: 3.8.3
hooks:
- id: flake8
- repo: https://github.com/pre-commit/mirrors-mypy
@ -17,6 +17,11 @@ repos:
hooks:
- id: unittest
name: unittest
entry: python -m unittest discover
entry: python -m coverage run -m unittest discover
language: system
pass_filenames: false
- id: coverage
name: coverage
entry: python -m coverage report -m --fail-under=100
language: system
pass_filenames: false

18
notebooks/wine_iris.ipynb
View File

@ -21,7 +21,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
@ -32,7 +32,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
@ -40,14 +40,14 @@
"clf = {}\n",
"clf[\"stree\"] = Stree(random_state=random_state, max_depth=5)\n",
"clf[\"stree\"].set_params(**dict(splitter=\"best\", kernel=\"linear\", max_features=\"auto\"))\n",
"clf[\"odte\"] = Odte(base_estimator=clf[\"stree\"], random_state=random_state, n_estimators=n_estimators, max_features=.8)\n",
"clf[\"odte\"] = Odte(n_jobs=-1, base_estimator=clf[\"stree\"], random_state=random_state, n_estimators=n_estimators, max_features=.8)\n",
"clf[\"adaboost\"] = AdaBoostClassifier(base_estimator=clf[\"stree\"], n_estimators=n_estimators, random_state=random_state, algorithm=\"SAMME\")\n",
"clf[\"bagging\"] = BaggingClassifier(base_estimator=clf[\"stree\"], n_estimators=n_estimators)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 14,
"metadata": {
"tags": []
},
@ -55,7 +55,7 @@
{
"output_type": "stream",
"name": "stdout",
"text": "****************************** Results for wine ******************************\nTraining stree...\nScore: 94.444 in 0.19 seconds\nTraining odte...\nScore: 100.000 in 3.43 seconds\nTraining adaboost...\nScore: 94.444 in 0.76 seconds\nTraining bagging...\nScore: 100.000 in 3.27 seconds\n"
"text": "****************************** Results for wine ******************************\nTraining stree...\nScore: 94.444 in 0.18 seconds\nTraining odte...\nScore: 100.000 in 1.33 seconds\nTraining adaboost...\nScore: 94.444 in 0.62 seconds\nTraining bagging...\nScore: 100.000 in 2.88 seconds\n"
}
],
"source": [
@ -87,7 +87,7 @@
"n_estimators = 10\n",
"clf = {}\n",
"clf[\"stree\"] = Stree(random_state=random_state, max_depth=3)\n",
"clf[\"odte\"] = Odte(random_state=random_state, n_estimators=n_estimators, max_features=1.0)\n",
"clf[\"odte\"] = Odte(n_jobs=-1, random_state=random_state, n_estimators=n_estimators, max_features=1.0)\n",
"clf[\"adaboost\"] = AdaBoostClassifier(base_estimator=clf[\"stree\"], n_estimators=n_estimators, random_state=random_state, algorithm=\"SAMME\")\n",
"clf[\"bagging\"] = BaggingClassifier(base_estimator=clf[\"stree\"], n_estimators=n_estimators)"
]
@ -102,7 +102,7 @@
{
"output_type": "stream",
"name": "stdout",
"text": "****************************** Results for iris ******************************\nTraining stree...\nScore: 100.000 in 0.02 seconds\nTraining odte...\nScore: 100.000 in 0.15 seconds\nTraining adaboost...\nScore: 83.333 in 0.01 seconds\nTraining bagging...\nScore: 96.667 in 0.13 seconds\n"
"text": "****************************** Results for iris ******************************\nTraining stree...\nScore: 100.000 in 0.02 seconds\nTraining odte...\nScore: 100.000 in 0.12 seconds\nTraining adaboost...\nScore: 83.333 in 0.01 seconds\nTraining bagging...\nScore: 100.000 in 0.13 seconds\n"
}
],
"source": [
@ -124,7 +124,7 @@
{
"output_type": "stream",
"name": "stdout",
"text": "{'fit_time': array([0.23599219, 0.22772503, 0.21689606, 0.20017815, 0.22257805]), 'score_time': array([0.01378369, 0.01322389, 0.0125649 , 0.01751685, 0.01062703]), 'test_score': array([1. , 1. , 1. , 0.93333333, 1. ]), 'train_score': array([0.98333333, 0.96666667, 0.99166667, 0.99166667, 0.975 ])}\n98.667 +- 0.027\n"
"text": "{'fit_time': array([0.22121811, 0.21985221, 0.19185114, 0.19187999, 0.20067477]), 'score_time': array([0.01268458, 0.01461887, 0.01160598, 0.01308703, 0.01070738]), 'test_score': array([1. , 1. , 1. , 0.93333333, 1. ]), 'train_score': array([0.98333333, 0.96666667, 0.99166667, 0.99166667, 0.975 ])}\n98.667 +- 0.027\n"
}
],
"source": [
@ -143,7 +143,7 @@
{
"output_type": "stream",
"name": "stdout",
"text": "{'fit_time': array([0.02912688, 0.05858397, 0.06724691, 0.02860498, 0.03802919]), 'score_time': array([0.0024271 , 0.0022819 , 0.00219584, 0.00195408, 0.00342584]), 'test_score': array([1. , 0.93333333, 0.93333333, 0.93333333, 0.96666667]), 'train_score': array([0.93333333, 0.96666667, 0.96666667, 0.96666667, 0.95 ])}\n95.333 +- 0.027\n"
"text": "{'fit_time': array([0.02130818, 0.02036786, 0.02829814, 0.02326989, 0.03807497]), 'score_time': array([0.00140715, 0.00173712, 0.00199389, 0.00132608, 0.00199199]), 'test_score': array([1. , 0.93333333, 0.93333333, 0.93333333, 0.96666667]), 'train_score': array([0.93333333, 0.96666667, 0.96666667, 0.96666667, 0.95 ])}\n95.333 +- 0.027\n"
}
],
"source": [

10
odte/Odte.py
View File

@ -25,6 +25,7 @@ from stree import Stree
class Odte(BaseEnsemble, ClassifierMixin): # type: ignore
def __init__(
self,
# n_jobs = -1 to use all available cores
n_jobs: int = 1,
base_estimator: BaseEstimator = None,
random_state: int = 0,
@ -38,7 +39,8 @@ class Odte(BaseEnsemble, ClassifierMixin): # type: ignore
else base_estimator
)
super().__init__(
base_estimator=base_estimator, n_estimators=n_estimators,
base_estimator=base_estimator,
n_estimators=n_estimators,
)
self.n_jobs = n_jobs
self.n_estimators = n_estimators
@ -48,7 +50,7 @@ class Odte(BaseEnsemble, ClassifierMixin): # type: ignore
def _initialize_random(self) -> np.random.mtrand.RandomState:
if self.random_state is None:
self.random_state = random.randint(0, sys.maxint)
self.random_state = random.randint(0, sys.maxsize)
return np.random.mtrand._rand
return np.random.RandomState(self.random_state)
@ -84,9 +86,7 @@ class Odte(BaseEnsemble, ClassifierMixin): # type: ignore
self.estimators_: List[BaseEstimator] = []
self.subspaces_: List[Tuple[int, ...]] = []
result = self._train(X, y, sample_weight)
self.estimators_, self.subspaces_ = tuple( # type: ignore
zip(*result)
)
self.estimators_, self.subspaces_ = tuple(zip(*result)) # type: ignore
return self
@staticmethod

20
odte/tests/Odte_tests.py
View File

@ -57,7 +57,7 @@ class Odte_test(unittest.TestCase):
computed = box.randint(0, 1000, 3)
self.assertListEqual(expected, computed.tolist())
# test None
tclf = Odte()
tclf = Odte(random_state=None)
box = tclf._initialize_random()
computed = box.randint(101, 1000, 3)
for value in computed.tolist():
@ -83,7 +83,7 @@ class Odte_test(unittest.TestCase):
warnings.filterwarnings("ignore", category=ConvergenceWarning)
warnings.filterwarnings("ignore", category=RuntimeWarning)
X, y = [[1, 2], [5, 6], [9, 10], [16, 17]], [0, 1, 1, 2]
expected = [0, 1, 1, 1]
expected = [0, 1, 1, 2]
tclf = Odte(
random_state=self._random_state, n_estimators=10, n_jobs=-1
)
@ -102,9 +102,15 @@ class Odte_test(unittest.TestCase):
X, y = load_dataset(self._random_state)
expected = y
tclf = Odte(
random_state=self._random_state, max_features=1.0, max_samples=0.1,
random_state=self._random_state,
max_features=1.0,
max_samples=0.1,
)
tclf.set_params(
**dict(
base_estimator__kernel="linear",
)
)
tclf.set_params(**dict(base_estimator__kernel="linear",))
computed = tclf.fit(X, y).predict(X)
self.assertListEqual(expected[:27].tolist(), computed[:27].tolist())
@ -134,7 +140,11 @@ class Odte_test(unittest.TestCase):
max_features=max_features,
n_estimators=10,
)
tclf.set_params(**dict(base_estimator__splitter=splitter,))
tclf.set_params(
**dict(
base_estimator__splitter=splitter,
)
)
expected = results.pop(0)
computed = tclf.fit(X, y).score(X, y)
self.assertAlmostEqual(expected, computed)