First commit

This commit is contained in:
Ricardo Montañana Gómez 2020-06-12 22:45:58 +02:00
parent eae2eaf663
commit 872914dca7
Signed by: rmontanana
GPG Key ID: 46064262FD9A7ADE
12 changed files with 314 additions and 0 deletions

14
.coveragerc Normal file
View File

@ -0,0 +1,14 @@
[run]
branch = True
source = odte
[report]
exclude_lines =
if self.debug:
pragma: no cover
raise NotImplementedError
if __name__ == .__main__.:
ignore_errors = True
omit =
odte/tests/*
odte/__init__.py

10
.pre-commit-config.yaml Normal file
View File

@ -0,0 +1,10 @@
repos:
- repo: https://github.com/ambv/black
rev: stable
hooks:
- id: black
language_version: python3.7
- repo: https://gitlab.com/pycqa/flake8
rev: 3.7.9
hooks:
- id: flake8

15
.vscode/launch.json vendored Normal file
View File

@ -0,0 +1,15 @@
{
// Use IntelliSense para saber los atributos posibles.
// Mantenga el puntero para ver las descripciones de los existentes atributos.
// Para más información, visite: https://go.microsoft.com/fwlink/?linkid=830387
"version": "0.2.0",
"configurations": [
{
"name": "Python: Archivo actual",
"type": "python",
"request": "launch",
"program": "${file}",
"console": "integratedTerminal"
}
]
}

18
.vscode/settings.json vendored Normal file
View File

@ -0,0 +1,18 @@
{
"python.testing.unittestArgs": [
],
"python.testing.pytestEnabled": false,
"python.testing.nosetestsEnabled": false,
"python.testing.unittestEnabled": true,
"python.pythonPath": "/Users/rmontanana/.virtualenvs/general/bin/python",
"python.linting.flake8Enabled": true,
"python.linting.enabled": true,
"editor.rulers": [
80,
100
],
"python.linting.pylintEnabled": false,
"restructuredtext.confPath": "${workspaceFolder}/docs/source"
}

12
codecov.yml Normal file
View File

@ -0,0 +1,12 @@
overage:
status:
project:
default:
target: 90%
comment:
layout: "reach, diff, flags, files"
behavior: default
require_changes: false
require_base: yes
require_head: yes
branches: null

152
odte/Odte.py Normal file
View File

@ -0,0 +1,152 @@
"""
__author__ = "Ricardo Montañana Gómez"
__copyright__ = "Copyright 2020, Ricardo Montañana Gómez"
__license__ = "MIT"
__version__ = "0.1"
Build a forest of oblique trees based on STree
"""
import numpy as np
from sklearn.utils import check_consistent_length
from sklearn.metrics._classification import _weighted_sum, _check_targets
from sklearn.utils.multiclass import check_classification_targets
from sklearn.base import BaseEstimator, ClassifierMixin
from sklearn.utils.validation import (
check_X_y,
check_array,
check_is_fitted,
_check_sample_weight,
)
from stree import Stree
class Odte(BaseEstimator, ClassifierMixin):
def __init__(
self,
random_state: int = None,
C: int = 1,
n_estimators: int = 100,
max_iter: int = 1000,
max_depth: int = None,
min_samples_split: int = 0,
bootstrap: bool = True,
split_criteria: str = "min_distance",
tol: float = 1e-4,
gamma="scale",
degree: int = 3,
kernel: str = "linear",
max_features="auto",
max_samples=None,
):
self.n_estimators = n_estimators
self.bootstrap = bootstrap
self.random_state = random_state
self.max_features = max_features
self.max_samples = max_samples
self.estimator_params = dict(
C=C,
random_state=random_state,
min_samples_split=min_samples_split,
max_depth=max_depth,
split_criteria=split_criteria,
kernel=kernel,
max_iter=max_iter,
tol=tol,
degree=degree,
gamma=gamma,
)
def _initialize_random(self) -> np.random.mtrand.RandomState:
if self.random_state is None:
return np.random.mtrand._rand
else:
return np.random.RandomState(self.random_state)
def _initialize_sample_weight(
self, sample_weight: np.array, n_samples: int
) -> np.array:
if sample_weight is None:
return np.ones((n_samples,), dtype=np.float64)
else:
return sample_weight.copy()
def fit(
self, X: np.array, y: np.array, sample_weight: np.array = None
) -> "Odte":
# Check parameters are Ok.
if self.n_estimators < 10:
raise ValueError(
f"n_estimators must be greater than 9... got (n_estimators=\
{self.n_estimators:f})"
)
# the rest of parameters are checked in estimator
check_classification_targets(y)
X, y = check_X_y(X, y)
sample_weight = _check_sample_weight(sample_weight, X)
check_classification_targets(y)
# Initialize computed parameters
self.classes_, y = np.unique(y, return_inverse=True)
self.n_classes_ = self.classes_.shape[0]
self.estimators_ = []
self._train(X, y, sample_weight)
def _train(
self, X: np.array, y: np.array, sample_weight: np.array
) -> "Odte":
random_box = self._initialize_random()
n_samples = X.shape[0]
weights = self._initialize_sample_weight(sample_weight, n_samples)
boot_samples = self._get_bootstrap_n_samples(n_samples)
for _ in range(self.n_estimators):
# Build clf
clf = Stree().set_params(**self.estimator_params)
self.estimators_.append(clf)
# bootstrap
indices = random_box.randint(0, n_samples, boot_samples)
# update weights with the chosen samples
weights_update = np.bincount(indices, minlength=n_samples)
current_weights = weights * weights_update
# train the classifier
clf.fit(X[indices, :], y[indices, :], current_weights[indices, :])
def _get_bootstrap_n_samples(self, n_samples) -> int:
if self.max_samples is None:
return n_samples
if type(self.max_samples) == int:
if not (1 <= self.max_samples <= n_samples):
message = f"max_samples should be in the range 1 to \
{n_samples} but got {self.max_samples}"
raise ValueError(message)
return self.max_samples
if type(self.max_samples) == float:
if not (0 < self.max_samples < 1):
message = f"max_samples should be in the range (0, 1)\
but got {self.max_samples}"
raise ValueError(message)
return int(round(self.max_samples * n_samples))
raise ValueError(
f"Expected values int, float but got \
{type(self.max_samples)}"
)
def predict(self, X: np.array):
# todo
check_is_fitted(self, ["estimators_"])
# Input validation
X = check_array(X)
def score(
self, X: np.array, y: np.array, sample_weight: np.array
) -> float:
# todo
check_is_fitted(self, ["estimators_"])
check_classification_targets(y)
X, y = check_X_y(X, y)
y_pred = self.predict(X).reshape(y.shape)
# Compute accuracy for each possible representation
y_type, y_true, y_pred = _check_targets(y, y_pred)
check_consistent_length(y_true, y_pred, sample_weight)
score = y_true == y_pred
return _weighted_sum(score, sample_weight, normalize=True)

3
odte/__init__.py Normal file
View File

@ -0,0 +1,3 @@
from .Odte import Odte
__all__ = ["Odte"]

49
odte/tests/Odte_tests.py Normal file
View File

@ -0,0 +1,49 @@
import unittest
import numpy as np
from odte import Odte
from .utils import load_dataset
class Odte_test(unittest.TestCase):
def __init__(self, *args, **kwargs):
self._random_state = 1
super().__init__(*args, **kwargs)
def test_max_samples_bogus(self):
values = [0, 3000, 1.1, 0.0, "hi!"]
for max_samples in values:
with self.assertRaises(ValueError):
tclf = Odte(max_samples=max_samples)
tclf.fit(*load_dataset(self._random_state))
def test_get_bootstrap_nsamples(self):
expected_values = [(1, 1), (1500, 1500), (0.1, 150)]
for value, expected in expected_values:
tclf = Odte(max_samples=value)
computed = tclf._get_bootstrap_n_samples(1500)
self.assertEqual(expected, computed)
def test_initialize_sample_weight(self):
m = 5
ones = np.ones(m,)
weights = np.random.rand(m,)
expected_values = [(None, ones), (weights, weights)]
for value, expected in expected_values:
tclf = Odte()
computed = tclf._initialize_sample_weight(value, m)
self.assertListEqual(expected.tolist(), computed.tolist())
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()
box = tclf._initialize_random()
computed = box.randint(101, 1000, 3)
for value in computed.tolist():
self.assertGreaterEqual(value, 101)
self.assertLessEqual(value, 1000)

3
odte/tests/__init__.py Normal file
View File

@ -0,0 +1,3 @@
from .Odte_tests import Odte_test
__all__ = ["Odte_test"]

17
odte/tests/utils.py Normal file
View File

@ -0,0 +1,17 @@
from sklearn.datasets import make_classification
def load_dataset(random_state=0, n_classes=2):
X, y = make_classification(
n_samples=1500,
n_features=3,
n_informative=3,
n_redundant=0,
n_repeated=0,
n_classes=n_classes,
n_clusters_per_class=2,
class_sep=1.5,
flip_y=0,
random_state=random_state,
)
return X, y

16
pyproject.toml Normal file
View File

@ -0,0 +1,16 @@
[tool.black]
line-length = 79
include = '\.pyi?$'
exclude = '''
/(
\.git
| \.hg
| \.mypy_cache
| \.tox
| \.venv
| _build
| buck-out
| build
| dist
)/
'''

5
requirements.txt Normal file
View File

@ -0,0 +1,5 @@
numpy
scikit-learn
pandas
ipympl
stree