Add Python 3.9, 3.10, 3.11 Support and Fix Compilation Issues (#194)

* 1. Modified _hintsvm.pyx and successfully compiled the source code
2. Modified README.md (changed the order of installing dependencies && changed the installation method)

* Updated plot.py

* Removed unnecessary  comment in libact/query_strategies/tests/test_density_weighted_meta.py

* Update README.md and revert unnecessary changes

* Update README.md and libact/base/dataset.py
Current Status: 2 of the tests fail and 1 throws an error

* Fix the NearestNeighbors error in libact/query_strategies/multilabel/cost_sensitive_reference_pair_encoding.py

* Update test cases and specify module versions in requirements.txt

* Update `unittest` and `coverage` usage

Resolve the [Deprecate test command](pypa/setuptools#1684) in `setuptools`.

* Update .gitignore

* Restore plot.py

* Update dataset.py

* Update density_weighted_meta.py

* Update density_weighted_uncertainty_sampling.py

* Update setup.py

* Add support for Python 3.9 and 3.11

* Update README.md

* Update requirements.txt

* Update GitHub workflows

---------

Co-authored-by: Poy <[email protected]>

Author: CoolJosh0221

.github/workflows/tests.yml

@@ -9,8 +9,10 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-latest, macos-latest]
-        python-version: [2.7, 3.6, 3.7, 3.8, 3.9]
+        # os: [ubuntu-latest, macos-latest]
+        # python-version: [2.7, 3.6, 3.7, 3.8, 3.9]
+        os: [ubuntu-22.04]
+        python-version: [3.9, 3.10, 3.11]
 
     steps:
       - uses: actions/checkout@v2

.gitignore

@@ -61,3 +61,5 @@ target/
 examples/australian.txt
 examples/diabetes.txt
 examples/heart.txt
+
+libact/query_strategies/_hintsvm.c

README.md

@@ -21,16 +21,17 @@ Comments and questions on the package is welcomed at `libact-users@googlegroups.
 
 # Basic Dependencies
 
-* Python 2.7, 3.3, 3.4, 3.5, 3.6
+* Python 3.9, 3.10, 3.11
+  * _Note._ We will soon release Python 2.7, 3.3, 3.4, 3.5, and 3.6 installations in the new branch.
 
-* Python dependencies
+* Debian (>= 7) / Ubuntu (>= 14.04)
 ```
-pip install -r requirements.txt
+sudo apt-get install build-essential gfortran libatlas-base-dev liblapacke-dev python3-dev
 ```
 
-* Debian (>= 7) / Ubuntu (>= 14.04)
+* Python dependencies
 ```
-sudo apt-get install build-essential gfortran libatlas-base-dev liblapacke-dev python3-dev
+pip install -r requirements.txt
 ```
 
 * Arch
@@ -66,9 +67,10 @@ python setup.py install --user
 ```
 
 To build and install from souce for all users on Unix/Linux:
+
+**(This is the recommended method for Python 3.10 users)**
 ```
-python setup.py build
-sudo python setup.py install
+pip install -e .
 ```
 
 ## Installation Options
@@ -120,7 +122,7 @@ Available examples:
 To run the test suite:
 
 ```
-python setup.py test
+python -m unittest -v
 ```
 
 To run pylint, install pylint through ```pip install pylint``` and run the following command in root directory:
@@ -132,8 +134,8 @@ pylint libact
 To measure the test code coverage, install coverage through ```pip install coverage``` and run the following commands in root directory:
 
 ```
-coverage run --source libact --omit */tests/* setup.py test
-coverage report
+python -m coverage run --source libact --omit */tests/* -m unittest
+python -m coverage report
 ```
 
 # Citing

libact/base/dataset.py

@@ -39,7 +39,7 @@ def __init__(self, X=None, y=None):
             X = np.array(X)
 
         if y is None: y = []
-        y = np.array(y)
+        y = np.array(y, dtype=object)
 
         self._X = X
         self._y = y
@@ -218,7 +218,7 @@ def labeled_uniform_sample(self, sample_size, replace=True):
         sample_size
         """
         idx = np.random.choice(np.where(self.get_labeled_mask())[0],
-                               size=sample_size, replace=replace )
+                               size=sample_size, replace=replace)
         return Dataset(self._X[idx], self._y[idx])
 
 

libact/query_strategies/_hintsvm.pyx

@@ -1,9 +1,9 @@
 #defining NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION
 
-import  numpy as np
+import numpy as np
 cimport numpy as np
 from libc.stdlib cimport free
-cimport _hintsvm
+from . cimport _hintsvm
 
 cdef extern from *:
     ctypedef struct svm_parameter:

libact/query_strategies/density_weighted_meta.py

@@ -86,13 +86,12 @@ def __init__(self, dataset, base_query_strategy, similarity_metric=None,
         else:
             self.clustering_method = KMeans(
                 n_clusters=5, random_state=self.random_state_)
-        
+
         if similarity_metric is not None:
             self.similarity_metric = similarity_metric
         else:
             self.similarity_metric = cosine_similarity
 
-
     @inherit_docstring_from(QueryStrategy)
     def update(self, entry_id, label):
         pass
@@ -104,7 +103,7 @@ def _get_scores(self):
         scores = self.base_query_strategy._get_scores()
         _, X_pool = dataset.get_unlabeled_entries()
         unlabeled_entry_ids, base_scores = zip(*scores)
-        
+
         self.clustering_method.fit(X)
         pool_cluster = self.clustering_method.predict(X_pool)
         cluster_center = self.clustering_method.cluster_centers_
@@ -128,4 +127,4 @@ def make_query(self):
         unlabeled_entry_ids, scores = zip(*self._get_scores())
         ask_id = self.random_state_.choice(np.where(scores == np.max(scores))[0])
 
-        return unlabeled_entry_ids[ask_id]
+        return unlabeled_entry_ids[ask_id]

libact/query_strategies/density_weighted_uncertainty_sampling.py

@@ -153,6 +153,7 @@ def make_query(self):
 
         return unlabeled_entry_ids[ask_id]
 
+
 class DensityWeightedLogisticRegression(object):
     """Density Weighted Logistic Regression
 

libact/query_strategies/multilabel/cost_sensitive_reference_pair_encoding.py

@@ -73,7 +73,8 @@ class CostSensitiveReferencePairEncoding(QueryStrategy):
 
     def __init__(self, dataset, scoring_fn, model, base_model, n_models=100,
                  n_jobs=1, random_state=None):
-        super(CostSensitiveReferencePairEncoding, self).__init__(dataset=dataset)
+        super(CostSensitiveReferencePairEncoding,
+              self).__init__(dataset=dataset)
 
         self.model_ = model
         self.csrpe_ = CSRPE(scoring_fn=scoring_fn, base_clf=base_model,
@@ -94,12 +95,12 @@ def make_query(self):
         Z = self.csrpe_.predicted_code(X_pool)
         predZ = self.csrpe_.encode(predY)
 
-        dist = paired_distances(Z, predZ, metric=hamming) # z1 z2
-        dist2 = self.csrpe_.predict_dist(X_pool) # z1 zt
-        #dist3 = self.csrpe.distance(predZ) # z2 zt
+        dist = paired_distances(Z, predZ, metric=hamming)  # z1 z2
+        dist2 = self.csrpe_.predict_dist(X_pool)  # z1 zt
+        # dist3 = self.csrpe.distance(predZ) # z2 zt
 
         dist = dist + dist2
-        #dist = dist + dist3
+        # dist = dist + dist3
 
         ask_id = self.random_state_.choice(
             np.where(np.isclose(dist, np.max(dist)))[0])
@@ -127,8 +128,10 @@ def train(self, X, y):
         self.n_samples = np.shape(X)[0]
         self.n_labels = np.shape(y)[1]
 
-        score0 = self.scoring_fn(y, np.tile(self.rep_label[0], (self.n_samples, 1)))
-        score1 = self.scoring_fn(y, np.tile(self.rep_label[1], (self.n_samples, 1)))
+        score0 = self.scoring_fn(y, np.tile(
+            self.rep_label[0], (self.n_samples, 1)))
+        score1 = self.scoring_fn(y, np.tile(
+            self.rep_label[1], (self.n_samples, 1)))
         lbl = (((score1 - score0) > 0) + 0.0)
 
         weight = np.abs(score1 - score0)
@@ -153,8 +156,8 @@ def __init__(self, scoring_fn, base_clf, n_clfs, n_jobs,
                  metric='euclidean', random_state=None):
         self.scoring_fn = scoring_fn
         self.base_clf = base_clf
-        self.nn_ = NearestNeighbors(1, algorithm='ball_tree',
-                metric=metric, n_jobs=n_jobs)
+        self.nn_ = NearestNeighbors(n_neighbors=1, algorithm='ball_tree',
+                                    metric=metric, n_jobs=n_jobs)
         self.n_clfs = n_clfs
         self.random_state_ = seed_random_state(random_state)
 
@@ -224,4 +227,4 @@ def predict_dist(self, X):
         encoded = self.predicted_code(X)
         dist, _ = self.nn_.kneighbors(encoded, 1, return_distance=True)
         dist = dist.reshape(-1)
-        return dist
+        return dist

libact/query_strategies/tests/test_density_weighted_meta.py

@@ -24,7 +24,8 @@ def setUp(self):
         self.quota = 10
 
     def test_density_weighted_meta_uncertainty_lc(self):
-        trn_ds = Dataset(self.X[:20], np.concatenate([self.y[:6], [None] * 14]))
+        trn_ds = Dataset(self.X[:20], np.concatenate(
+            [self.y[:6], [None] * 14]))
         base_qs = UncertaintySampling(
             trn_ds, method='lc',
             model=LogisticRegression(solver='liblinear', multi_class="ovr"))
@@ -37,7 +38,8 @@ def test_density_weighted_meta_uncertainty_lc(self):
             beta=1.0, random_state=1126)
         model = LogisticRegression(solver='liblinear', multi_class="ovr")
         qseq = run_qs(trn_ds, qs, self.y, self.quota)
-        assert_array_equal(qseq, np.array([13, 18,  9, 12,  8, 16, 10, 19, 15, 17]))
+        assert_array_equal(qseq, np.array(
+            [18, 13,  9, 12,  8, 16, 10, 19, 15,  7]))
 
 
 if __name__ == '__main__':

libact/query_strategies/tests/test_realdata.py

@@ -153,7 +153,7 @@ def test_DensityWeightedUncertaintySampling(self):
         qs = DWUS(trn_ds, random_state=1126)
         qseq = run_qs(trn_ds, qs, self.y, self.quota)
         assert_array_equal(
-            qseq, np.array([30, 179, 104, 186, 28, 65, 142, 62, 257, 221]))
+            qseq, np.array([257, 220, 179,  84, 208,  70, 245,  62,  50,  69]))
 
 
 if __name__ == '__main__':