upd README.md, refactor

README.md

@@ -1,6 +1,6 @@
 # Neighbours
 
-Weighted kNN classifier implementation based on random projection forest.
+Weighted kNN classifier and Nadaraya-Watson kernel regressor implementation based on random projection forest.
 
 ### Classifier description
 
@@ -19,13 +19,22 @@ Built-in distance metrics:
 
 Custom distance metrics and smoothing kernels are supported.
 
+Demo: `demo/regressor_demo.py`
+
+### Regressor description
+
+Nadaraya-Watson kernel regressor is implemented.
+
+Demo: `demo/classifier_demo.py`
+
 ### Neighbors search algorithm
 
 Random projection forest is used to search for neighbours.
 
 RP trees are built by recursive binary splits of space by selected hyperplanes.
 
-On each step algorithm chooses two random objects from train set and calculates a hyperplane symmetrically separating these two objects in feature space.
+On each step algorithm chooses two random objects from the train set
+and calculates a hyperplane symmetrically separating these two objects in feature space.
 Such hyperplanes become splitting nodes of an RP tree.
 
 Each resulting subset is split again if it contains more than `m` (hyperparameter) objects. 
@@ -52,6 +61,7 @@ Since nodes are organized into a tree, we can perform search by evaluating the e
 Import the package, for example, as
 
 ```python
+
 import neighbours as ns
 ```
 
@@ -84,4 +94,4 @@ The only third-party dependency is `numpy`.
 
 ### License
 
-This project is licensed under [the MIT License](https://raw.githubusercontent.com/hashlag/neighbours/main/LICENSE)
+This project is licensed under [the MIT License](https://raw.githubusercontent.com/hashlag/neighbours/main/LICENSE).

demo/classifier_demo.py

@@ -1,7 +1,3 @@
-import sys
-
-sys.path.append("../")
-
 import neighbours as ns
 
 import numpy as np

demo/regressor_demo.py

@@ -1,6 +1,6 @@
-import matplotlib.pyplot as plt
 import neighbours as ns
 
+import matplotlib.pyplot as plt
 import numpy as np
 import random
 import math

src/neighbours/classifier.py

@@ -28,7 +28,7 @@ class KNNClassifier:
         """
 
         self.features = features
-        self.forest = RPTForest(features, trees_count, rpt_m)
+        self.forest = RPForest(features, trees_count, rpt_m)
         self.classes = None
         self.classes_count = classes_count
 

src/neighbours/regressor.py

@@ -26,7 +26,7 @@ class KNNRegressor:
         """
 
         self.features = features
-        self.forest = RPTForest(features, trees_count, rpt_m)
+        self.forest = RPForest(features, trees_count, rpt_m)
         self.targets = None
 
     def load(self, points, targets):

src/neighbours/rp_neighbours.py

@@ -48,7 +48,7 @@ class LeafNode:
     """
 
     def __init__(self, ixs):
-        """Creates new LeafNode with given set of point indexes
+        """Creates new LeafNode with a given set of point indexes
 
         :param ixs: list of point indexes
         """
@@ -56,8 +56,8 @@ class LeafNode:
         self.indexes = set(ixs)
 
 
-class RPTForest:
-    """Forest of random projection trees
+class RPForest:
+    """Random projection forest
 
     Attributes:
         features: number of features in each sample
@@ -68,7 +68,7 @@ class RPTForest:
     """
 
     def __init__(self, features, trees_count, m):
-        """Creates new random projection tree forest
+        """Creates new random projection forest
 
         :param features: number of features in each sample
         :param trees_count: number of trees in the forest