Improve linting

.pylintrc

@@ -32,13 +32,14 @@ callbacks=cb_,_cb
 bad-functions=map,filter
 
 # Good variable names which should always be accepted, separated by a comma
-# x, y, X, Y - vector maxtrix of features and labels.
+# x, y, X, Y, Z - vector maxtrix of features and labels.
 # P, p - probability distribution
 # qs - query strategry
 # w, W - weight vector
 # N - number of instances
 # T, K - number of iterations
-good-names=i,j,k,_,X,Y,x,y,P,p,qs,w,W,N,T,K
+# up, down - numerator and denominator of the fraction
+good-names=i,j,k,_,X,Y,Z,x,y,P,p,qs,w,W,N,T,K,up,down
 
 # Regular expression matching correct attribute names
 attr-rgx=[a-z_][a-z0-9_]{2,30}$

docs/.readthedocs.yaml

@@ -0,0 +1,22 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# We recommend specifying your dependencies to enable reproducible builds:
+# https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+python:
+  install:
+  - requirements: docs/rtd-requirements.txt

libact/base/interfaces.py

@@ -36,7 +36,6 @@ def update(self, entry_id, label):
         label : float
             The label of the queried sample.
         """
-        pass
 
     def _get_scores(self):
         """Return the score used for making query, the larger the better. Read-only.
@@ -48,7 +47,6 @@ def _get_scores(self):
         (ask_id, scores): list of tuple (int, float)
             The index of the next unlabeled sample to be queried and the score assigned.
         """
-        pass
 
     @abstractmethod
     def make_query(self):
@@ -61,7 +59,6 @@ def make_query(self):
         ask_id : int
             The index of the next unlabeled sample to be queried and labeled.
         """
-        pass
 
 
 class Labeler(with_metaclass(ABCMeta, object)):
@@ -84,7 +81,6 @@ def label(self, feature):
         label : int
             The class label of the queried feature.
         """
-        pass
 
 
 class Model(with_metaclass(ABCMeta, object)):
@@ -108,7 +104,6 @@ def train(self, dataset, *args, **kwargs):
         self : object
             Returns self.
         """
-        pass
 
     @abstractmethod
     def predict(self, feature, *args, **kwargs):
@@ -124,7 +119,6 @@ def predict(self, feature, *args, **kwargs):
         y_pred : array-like, shape (n_samples,)
             The class labels for samples in the feature array.
         """
-        pass
 
     @abstractmethod
     def score(self, testing_dataset, *args, **kwargs):
@@ -141,7 +135,6 @@ def score(self, testing_dataset, *args, **kwargs):
         score : float
             Mean accuracy of self.predict(X) wrt. y.
         """
-        pass
 
 
 class MultilabelModel(Model):
@@ -150,7 +143,6 @@ class MultilabelModel(Model):
     A Model returns a multilabel-predicting function for future samples after
     trained on a training dataset.
     """
-    pass
 
 
 class ContinuousModel(Model):
@@ -183,7 +175,6 @@ def predict_real(self, feature, *args, **kwargs):
             Each entry is the confidence scores per (sample, class)
             combination.
         """
-        pass
 
 
 class ProbabilisticModel(ContinuousModel):
@@ -210,4 +201,3 @@ def predict_proba(self, feature, *args, **kwargs):
         X : array-like, shape (n_samples, n_classes)
             Each entry is the prabablity estimate for each class.
         """
-        pass

libact/base/tests/test_dataset.py

@@ -75,7 +75,7 @@ def test_get_labeled_entries(self):
 
     def test_get_unlabeled_entries(self):
         dataset = self.setup_dataset()
-        idx, X = dataset.get_unlabeled_entries()
+        _, X = dataset.get_unlabeled_entries()
         self.assertTrue(np.array_equal(X[0], np.array([6, 7, 8])))
         self.assertTrue(np.array_equal(X[1], np.array([12, 13, 14])))
 

libact/labelers/__init__.py

@@ -5,6 +5,6 @@
 from .ideal_labeler import IdealLabeler
 try:
     from .interactive_labeler import InteractiveLabeler
-except ImportError:
+except ImportError as import_error:
     raise ImportError("Error importing matplotlib."
-                      "InteractiveLabeler not supported.")
+                      "InteractiveLabeler not supported.") from import_error

libact/labelers/ideal_labeler.py

@@ -20,7 +20,8 @@ class IdealLabeler(Labeler):
 
     """
 
-    def __init__(self, dataset, **kwargs):
+    def __init__(self, dataset):
+        super().__init__()
         X, y = dataset.get_entries()
         # make sure the input dataset is fully labeled
         assert (np.array(y) != np.array(None)).all()
@@ -29,7 +30,7 @@ def __init__(self, dataset, **kwargs):
 
     @inherit_docstring_from(Labeler)
     def label(self, feature):
-        yy = self.y[np.where([np.array_equal(x, feature)
-                              for x in self.X])[0]]
-        ind = np.arange(len(yy))
-        return yy[np.random.choice(ind, 1)[0]]
+        labels = self.y[np.where([np.array_equal(x, feature)
+                                  for x in self.X])[0]]
+        ind = np.arange(len(labels))
+        return labels[np.random.choice(ind, 1)[0]]

libact/labelers/interactive_labeler.py

@@ -26,6 +26,7 @@ class InteractiveLabeler(Labeler):
     """
 
     def __init__(self, **kwargs):
+        super().__init__()
         self.label_name = kwargs.pop('label_name', None)
 
     @inherit_docstring_from(Labeler)

libact/models/logistic_regression.py

@@ -18,6 +18,7 @@ class LogisticRegression(ProbabilisticModel):
     """
 
     def __init__(self, *args, **kwargs):
+        super().__init__()
         self.model = sklearn.linear_model.LogisticRegression(*args, **kwargs)
 
     def train(self, dataset, *args, **kwargs):
@@ -38,4 +39,3 @@ def predict_real(self, feature, *args, **kwargs):
 
     def predict_proba(self, feature, *args, **kwargs):
         return self.model.predict_proba(feature, *args, **kwargs)
-

libact/models/perceptron.py

@@ -16,6 +16,7 @@ class Perceptron(Model):
     """
 
     def __init__(self, *args, **kwargs):
+        super().__init__()
         self.model = sklearn.linear_model.Perceptron(*args, **kwargs)
 
     def train(self, dataset, *args, **kwargs):

libact/models/sklearn_adapter.py

@@ -1,7 +1,7 @@
 """scikit-learn classifier adapter
 """
 from sklearn.base import clone
-from libact.base.interfaces import Model, ContinuousModel, ProbabilisticModel
+from libact.base.interfaces import Model, ProbabilisticModel
 
 
 class SklearnAdapter(Model):
@@ -37,6 +37,7 @@ class SklearnAdapter(Model):
     """
 
     def __init__(self, clf):
+        super().__init__()
         self._model = clf
 
     def train(self, dataset, *args, **kwargs):
@@ -50,6 +51,8 @@ def score(self, testing_dataset, *args, **kwargs):
                                 **kwargs)
 
     def clone(self):
+        """Constructs a new untrained model with the same parameters.
+        """
         return SklearnProbaAdapter(clone(self._model))
 
 
@@ -89,6 +92,7 @@ class SklearnProbaAdapter(ProbabilisticModel):
     """
 
     def __init__(self, clf):
+        super().__init__()
         self._model = clf
 
     def train(self, dataset, *args, **kwargs):
@@ -108,4 +112,6 @@ def predict_proba(self, feature, *args, **kwargs):
         return self._model.predict_proba(feature, *args, **kwargs)
 
     def clone(self):
+        """Constructs a new untrained model with the same parameters.
+        """
         return SklearnProbaAdapter(clone(self._model))

libact/models/svm.py

@@ -3,7 +3,6 @@
 An interface for scikit-learn's C-Support Vector Classifier model.
 """
 import logging
-LOGGER = logging.getLogger(__name__)
 
 import numpy as np
 import sklearn.svm
@@ -12,6 +11,9 @@
 from libact.base.interfaces import ContinuousModel
 
 
+LOGGER = logging.getLogger(__name__)
+
+
 class SVM(ContinuousModel):
 
     """C-Support Vector Machine Classifier
@@ -46,8 +48,8 @@ def predict_real(self, feature, *args, **kwargs):
         dvalue = self.model.decision_function(feature, *args, **kwargs)
         if len(np.shape(dvalue)) == 1:  # n_classes == 2
             return np.vstack((-dvalue, dvalue)).T
-        else:
-            if self.decision_function_shape != 'ovr':
-                LOGGER.warn("SVM model support only 'ovr' for multiclass"
-                            "predict_real.")
-            return dvalue
+
+        if self.decision_function_shape != 'ovr':
+            LOGGER.warning("SVM model support only 'ovr' for multiclass"
+                           "predict_real.")
+        return dvalue

libact/query_strategies/__init__.py

@@ -3,6 +3,8 @@
 """
 from __future__ import absolute_import
 
+# pylint: disable=wrong-import-position
+
 import os
 ON_RTD = os.environ.get('READTHEDOCS', None) == 'True'
 import logging

libact/query_strategies/density_weighted_uncertainty_sampling.py

@@ -154,7 +154,7 @@ def make_query(self):
         return unlabeled_entry_ids[ask_id]
 
 class DensityWeightedLogisticRegression(object):
-    """Density Weighted Logistic Regression
+    r"""Density Weighted Logistic Regression
 
     Density Weighted Logistice Regression is used in DWUS to estimate the
     probability of representing which label for each cluster.