Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion mlquantify/neighbors/__init__.py
Original file line number Diff line number Diff line change
@@ -1,5 +1,8 @@
from ._classes import (
PWK,
)
from ._classification import (
PWKCLF,
)

__all__ = ["PWK"]
__all__ = ["PWK", "PWKCLF"]
36 changes: 24 additions & 12 deletions mlquantify/neighbors/_classification.py
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@

import numpy as np
from sklearn.base import BaseEstimator, ClassifierMixin
from sklearn.neighbors import NearestNeighbors



class PWKCLF:
class PWKCLF(ClassifierMixin, BaseEstimator):
r"""Probabilistic Weighted k-Nearest Neighbor Classifier (PWKCLF).

A weighted k-nearest neighbor classifier that assigns class probabilities to
Expand Down Expand Up @@ -61,16 +62,18 @@ def __init__(self,
p=2,
metric_params=None,
n_jobs=None):
# Only store the constructor arguments here. ``get_params`` reads them
# back by name, and ``sklearn.base.clone`` rebuilds the estimator from
# them -- so every argument must survive as an attribute of the same
# name, and no work may happen before ``fit``.
self.alpha = alpha
self.n_neighbors = n_neighbors

self.nbrs = NearestNeighbors(n_neighbors=n_neighbors,
algorithm=algorithm,
leaf_size=leaf_size,
metric=metric,
p=p,
metric_params=metric_params,
n_jobs=n_jobs)
self.algorithm = algorithm
self.metric = metric
self.leaf_size = leaf_size
self.p = p
self.metric_params = metric_params
self.n_jobs = n_jobs

self.classes_ = None
self.class_to_index = None
Expand All @@ -95,9 +98,18 @@ def fit(self, X, y):
The fitted instance.
"""
n_samples = X.shape[0]
if n_samples < self.n_neighbors:
self.nbrs.set_params(n_neighbors=n_samples)

# Built here, not in ``__init__``: a scikit-learn estimator must do no
# work before ``fit``, and the neighbour count depends on the training
# set when it is smaller than ``n_neighbors``.
self.nbrs = NearestNeighbors(
n_neighbors=min(self.n_neighbors, n_samples),
algorithm=self.algorithm,
leaf_size=self.leaf_size,
metric=self.metric,
p=self.p,
metric_params=self.metric_params,
n_jobs=self.n_jobs)

self.y_train = y

unique_classes, class_counts = np.unique(y, return_counts=True)
Expand Down
64 changes: 64 additions & 0 deletions tests/test_neighbors.py
Original file line number Diff line number Diff line change
Expand Up @@ -39,3 +39,67 @@ def test_pwk_params(binary_dataset):

# Test high neighbors count
q = PWK(n_neighbors=len(X) - 1).fit(X, y)


# --------------------------------------------------------------------------
# PWKCLF as a scikit-learn estimator
#
# Both of these were broken: ``PWKCLF`` was not exported, and it had no
# ``get_params``, so ``sklearn.base.clone`` refused it. Together that meant a
# user could not build "PWK with count adjustment" out of the two pieces this
# library already ships -- ``ACC`` clones its estimator for cross-validation.
# --------------------------------------------------------------------------

def test_pwkclf_is_exported():
from mlquantify.neighbors import PWKCLF # noqa: F401

import mlquantify.neighbors as mod

assert "PWKCLF" in mod.__all__


def test_pwkclf_get_params_round_trips():
from sklearn.base import clone

from mlquantify.neighbors import PWKCLF

clf = PWKCLF(alpha=2.0, n_neighbors=7, metric="manhattan", leaf_size=17)
params = clf.get_params()
assert params["alpha"] == 2.0
assert params["n_neighbors"] == 7
assert params["metric"] == "manhattan"
assert params["leaf_size"] == 17

copia = clone(clf)
assert copia is not clf
assert copia.get_params() == params


def test_pwkclf_fits_after_clone(binary_dataset):
from sklearn.base import clone

from mlquantify.neighbors import PWKCLF

X, y = binary_dataset
clf = clone(PWKCLF(n_neighbors=5))
clf.fit(X, y)
rotulos = clf.predict(X)
assert rotulos.shape == (X.shape[0],)
assert set(np.unique(rotulos)).issubset(set(np.unique(y)))


def test_pwkclf_works_as_estimator_of_acc(binary_dataset):
"""O conserto que importa: montar PWK com ajuste de contagem."""
from mlquantify.counting import ACC
from mlquantify.neighbors import PWKCLF

X, y = binary_dataset
q = ACC(estimator=PWKCLF(n_neighbors=5), cv=3)
q.fit(X, y)
_assert_valid_prevalence_dict(q.predict(X), n_classes=2)


def _assert_valid_prevalence_dict(prevalence, n_classes):
if isinstance(prevalence, dict):
prevalence = np.asarray([prevalence[k] for k in sorted(prevalence)])
_assert_valid_prevalence(prevalence, n_classes)
Loading