RandomBinaryProjectionSearcher: distance type considered (#230)

gyrdym · web-flow · commit 8aa109f7508d · 2022-05-16T23:51:16.000+03:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,15 @@
 # Changelog
 
+## 16.13.0
+- `RandomBinaryProjectionSearcher`:
+    - Distance type considered
+- `ml_algo` export file:
+    - Distance type exported
+    - DType exported
+- `kd_tree` export file:
+    - Distance type exported
+    - DType exported
+
 ## 16.12.1
 - Corrected link to `RandomBinaryProjectionSearcher` class in README.md
 
diff --git a/e2e/decision_tree_classifier/decision_tree_classifier_test.dart b/e2e/decision_tree_classifier/decision_tree_classifier_test.dart
@@ -1,6 +1,5 @@
 import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:ml_preprocessing/ml_preprocessing.dart';
 import 'package:test/test.dart';
diff --git a/e2e/kd_tree/kd_tree_serialization_test.dart b/e2e/kd_tree/kd_tree_serialization_test.dart
@@ -2,7 +2,6 @@ import 'dart:convert';
 import 'dart:io';
 
 import 'package:ml_algo/ml_algo.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:test/test.dart';
 
diff --git a/e2e/kd_tree/kd_tree_test.dart b/e2e/kd_tree/kd_tree_test.dart
@@ -1,6 +1,5 @@
 import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:test/test.dart';
 
diff --git a/e2e/knn_classifier/knn_classifier_serialization_test.dart b/e2e/knn_classifier/knn_classifier_serialization_test.dart
@@ -1,8 +1,6 @@
 import 'dart:io';
 
 import 'package:ml_algo/ml_algo.dart';
-import 'package:ml_linalg/distance.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:test/test.dart';
 
 void main() {
diff --git a/e2e/knn_classifier/knn_classifier_test.dart b/e2e/knn_classifier/knn_classifier_test.dart
@@ -1,6 +1,5 @@
 import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:ml_preprocessing/ml_preprocessing.dart';
 import 'package:test/test.dart';
diff --git a/e2e/knn_regressor/knn_regressor_test.dart b/e2e/knn_regressor/knn_regressor_test.dart
@@ -1,6 +1,5 @@
 import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:ml_preprocessing/ml_preprocessing.dart';
 import 'package:test/test.dart';
diff --git a/e2e/lasso_regressor/lasso_regressor_test.dart b/e2e/lasso_regressor/lasso_regressor_test.dart
@@ -1,6 +1,5 @@
 import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:test/test.dart';
 
diff --git a/e2e/linear_regressor/linear_regressor_test.dart b/e2e/linear_regressor/linear_regressor_test.dart
@@ -1,6 +1,5 @@
 import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:test/test.dart';
 
diff --git a/e2e/logistic_regressor/logistic_regressor_serialization_test.dart b/e2e/logistic_regressor/logistic_regressor_serialization_test.dart
@@ -1,7 +1,6 @@
 import 'dart:io';
 
 import 'package:ml_algo/ml_algo.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:test/test.dart';
 
 void main() {
diff --git a/e2e/logistic_regressor/logistic_regressor_test.dart b/e2e/logistic_regressor/logistic_regressor_test.dart
@@ -1,6 +1,5 @@
 import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:test/test.dart';
 
diff --git a/e2e/random_binary_projection_searcher/random_binary_projection_searcher_serialization_test.dart b/e2e/random_binary_projection_searcher/random_binary_projection_searcher_serialization_test.dart
@@ -1,7 +1,6 @@
 import 'dart:io';
 
 import 'package:ml_algo/ml_algo.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:test/test.dart';
 
diff --git a/e2e/sgd_regressor/sgd_regressor_test.dart b/e2e/sgd_regressor/sgd_regressor_test.dart
@@ -1,6 +1,5 @@
 import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:test/test.dart';
 
diff --git a/e2e/softmax_regressor/softmax_regressor_serialization_test.dart b/e2e/softmax_regressor/softmax_regressor_serialization_test.dart
@@ -1,7 +1,6 @@
 import 'dart:io';
 
 import 'package:ml_algo/ml_algo.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:test/test.dart';
 
 void main() {
diff --git a/e2e/softmax_regressor/softmax_regressor_test.dart b/e2e/softmax_regressor/softmax_regressor_test.dart
@@ -1,6 +1,5 @@
 import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:ml_preprocessing/ml_preprocessing.dart';
 import 'package:test/test.dart';
diff --git a/lib/kd_tree.dart b/lib/kd_tree.dart
@@ -1 +1,3 @@
 export 'package:ml_algo/src/retrieval/kd_tree/kd_tree.dart';
+export 'package:ml_linalg/distance.dart';
+export 'package:ml_linalg/dtype.dart';
diff --git a/lib/ml_algo.dart b/lib/ml_algo.dart
@@ -16,3 +16,5 @@ export 'package:ml_algo/src/retrieval/kd_tree/kd_tree.dart';
 export 'package:ml_algo/src/retrieval/kd_tree/kd_tree_split_strategy.dart';
 export 'package:ml_algo/src/retrieval/random_binary_projection_searcher/random_binary_projection_searcher.dart';
 export 'package:ml_algo/src/tree_trainer/tree_assessor/tree_assessor_type.dart';
+export 'package:ml_linalg/distance.dart';
+export 'package:ml_linalg/dtype.dart';
diff --git a/lib/src/retrieval/random_binary_projection_searcher/random_binary_projection_searcher.dart b/lib/src/retrieval/random_binary_projection_searcher/random_binary_projection_searcher.dart
@@ -3,6 +3,7 @@ import 'package:ml_algo/src/retrieval/neighbour.dart';
 import 'package:ml_algo/src/retrieval/random_binary_projection_searcher/helpers/create_random_binary_projection_searcher.dart';
 import 'package:ml_algo/src/retrieval/random_binary_projection_searcher/random_binary_projection_searcher_impl.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
+import 'package:ml_linalg/distance.dart';
 import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/matrix.dart';
 import 'package:ml_linalg/vector.dart';
@@ -186,8 +187,18 @@ abstract class RandomBinaryProjectionSearcher with SerializableMixin {
   /// ```
   Matrix get points;
 
-  /// Accepts a [point] and finds it's [k] nearest neighbours. The search is
-  /// performed along bins in [searchRadius] (in bits) from the [point]'s bin.
+  /// Accepts a [point] and finds it's [k] nearest neighbours using [distance]
+  /// type. The search is performed along all bins in [searchRadius] (in bits) from
+  /// the [point]'s bin index.
+  ///
+  /// For example, if [searchRadius] is 2, and the [point]'s bin index is 9
+  /// (1001 in binary), it means that all bins with indices in binary:
+  ///
+  /// - 0001, 1101, 1011, 1000 (1 altered bit on 1st, 2nd, 3rd and 4th position)
+  /// - 0101, 0010, 0110, 0000, 1100, 1011 (2 altered bits on positions (0,1), (0, 2), (1,2), (0,3), (1,3) and (2,3))
+  ///
+  /// will be examined (if such indices exists of course).
+  ///
   /// The greater [searchRadius] is, the more bins will be examined by the algorithm.
   ///
   /// A neighbour is represented by an index in the [points] matrix and the
@@ -223,5 +234,6 @@ abstract class RandomBinaryProjectionSearcher with SerializableMixin {
   ///   // To access a neighbour, refer to `searcher.points` by the neighbour index
   /// }
   /// ```
-  Iterable<Neighbour> query(Vector point, int k, int searchRadius);
+  Iterable<Neighbour> query(Vector point, int k, int searchRadius,
+      {Distance distance = Distance.euclidean});
 }
diff --git a/lib/src/retrieval/random_binary_projection_searcher/random_binary_projection_searcher_impl.dart b/lib/src/retrieval/random_binary_projection_searcher/random_binary_projection_searcher_impl.dart
@@ -67,7 +67,8 @@ class RandomBinaryProjectionSearcherImpl
   final int schemaVersion;
 
   @override
-  Iterable<Neighbour> query(Vector point, int k, int searchRadius) {
+  Iterable<Neighbour> query(Vector point, int k, int searchRadius,
+      {Distance distance = Distance.euclidean}) {
     final pointAsMatrix = Matrix.fromRows([point], dtype: points.dtype);
     final queryBits =
         getBinaryRepresentation(pointAsMatrix, randomVectors).toVector();
@@ -95,9 +96,9 @@ class RandomBinaryProjectionSearcherImpl
       }
     }
 
-    final queue = createQueue(point, Distance.euclidean);
+    final queue = createQueue(point, distance);
 
-    search(point, candidateIndices, queue, k, Distance.euclidean);
+    search(point, candidateIndices, queue, k, distance);
 
     return queue.toList().reversed;
   }
diff --git a/pubspec.yaml b/pubspec.yaml
@@ -1,6 +1,6 @@
 name: ml_algo
 description: Machine learning algorithms, Machine learning models performance evaluation functionality
-version: 16.12.1
+version: 16.13.0
 homepage: https://github.com/gyrdym/ml_algo
 
 environment:
diff --git a/test/classifier/knn_classifier/knn_classifier_test.dart b/test/classifier/knn_classifier/knn_classifier_test.dart
@@ -3,8 +3,6 @@ import 'package:ml_algo/src/classifier/knn_classifier/_injector.dart';
 import 'package:ml_algo/src/classifier/knn_classifier/knn_classifier_factory.dart';
 import 'package:ml_algo/src/di/injector.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/distance.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:mockito/mockito.dart';
 import 'package:test/test.dart';
 
diff --git a/test/classifier/logistic_regressor/unit_test/logistic_regressor_test.dart b/test/classifier/logistic_regressor/unit_test/logistic_regressor_test.dart
@@ -8,7 +8,6 @@ import 'package:ml_algo/src/di/injector.dart';
 import 'package:ml_algo/src/linear_optimizer/linear_optimizer_factory.dart';
 import 'package:ml_algo/src/link_function/link_function.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/matrix.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:mockito/mockito.dart';
diff --git a/test/classifier/softmax_regressor/unit_test/softmax_regressor_factory_impl_test.dart b/test/classifier/softmax_regressor/unit_test/softmax_regressor_factory_impl_test.dart
@@ -3,7 +3,6 @@ import 'package:ml_algo/src/classifier/softmax_regressor/_injector.dart';
 import 'package:ml_algo/src/classifier/softmax_regressor/softmax_regressor_factory.dart';
 import 'package:ml_algo/src/di/injector.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/matrix.dart';
 import 'package:mockito/mockito.dart';
 import 'package:test/test.dart';
diff --git a/test/regressor/knn_regressor/knn_regressor_test.dart b/test/regressor/knn_regressor/knn_regressor_test.dart
@@ -2,8 +2,6 @@ import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_algo/src/regressor/knn_regressor/_injector.dart';
 import 'package:ml_algo/src/regressor/knn_regressor/knn_regressor_factory.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/distance.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:mockito/mockito.dart';
 import 'package:test/test.dart';
 
diff --git a/test/regressor/linear_regressor/linear_regressor_impl_test.dart b/test/regressor/linear_regressor/linear_regressor_impl_test.dart
@@ -5,7 +5,6 @@ import 'package:ml_algo/src/regressor/linear_regressor/linear_regressor_constant
 import 'package:ml_algo/src/regressor/linear_regressor/linear_regressor_factory.dart';
 import 'package:ml_algo/src/regressor/linear_regressor/linear_regressor_impl.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
-import 'package:ml_linalg/dtype.dart';
 import 'package:ml_linalg/matrix.dart';
 import 'package:ml_linalg/vector.dart';
 import 'package:mockito/mockito.dart';
diff --git a/test/retrieval/random_binary_projection_searcher/random_binary_projection_searcher_impl_test.dart b/test/retrieval/random_binary_projection_searcher/random_binary_projection_searcher_impl_test.dart
@@ -1,3 +1,4 @@
+import 'package:ml_algo/ml_algo.dart';
 import 'package:ml_algo/src/retrieval/random_binary_projection_searcher/random_binary_projection_searcher_impl.dart';
 import 'package:ml_dataframe/ml_dataframe.dart';
 import 'package:ml_linalg/vector.dart';
@@ -144,5 +145,17 @@ void main() {
 
       expect(result, hasLength(k));
     });
+
+    test('should perform knn search, k=3, searchRadius=2, distance=cosine', () {
+      final k = 3;
+      final searchRadius = 2;
+      final result = searcher.query(
+          Vector.fromList([1, 10, 11]), k, searchRadius,
+          distance: Distance.cosine);
+
+      expect(result, hasLength(k));
+      expect(result.elementAt(0).index, 5);
+      expect(result.elementAt(0).distance, 0);
+    });
   });
 }
