Improved quality based on Codacy report #153

Author: dpuenteramirez

instance_selection/_CNN.py

@@ -3,14 +3,24 @@
 # @Filename:    CNN.py
 # @Author:      Daniel Puente Ramírez
 # @Time:        19/11/21 07:13
-# @Version:     3.0
+# @Version:     4.0
 
 import numpy as np
 import pandas as pd
 
 from .utils import transform, delete_multiple_element
 
 
+def check_store(store, sample, store_classes):
+    euc = []
+    for s in store:
+        euc.append(np.linalg.norm(s - sample))
+    euc = np.array(euc)
+    euc_nn = np.amin(euc)
+    index_nn = np.ravel(np.where(euc == euc_nn))
+    return store_classes[index_nn[0]]
+
+
 class CNN:
 
     def __init__(self):
@@ -51,13 +61,7 @@ def filter(self, samples, y):
         handbag = []
 
         for sample_class, sample in zip(samples.target, samples.data):
-            euc = []
-            for s in store:
-                euc.append(np.linalg.norm(s - sample))
-            euc = np.array(euc)
-            euc_nn = np.amin(euc)
-            index_nn = np.ravel(np.where(euc == euc_nn))
-            nn_class = store_classes[index_nn[0]]
+            nn_class = check_store(store, sample, store_classes)
 
             if nn_class == sample_class:
                 handbag.append((sample_class, sample))
@@ -71,13 +75,7 @@ def filter(self, samples, y):
             indexes = []
             for index, s2 in enumerate(handbag):
                 sample_class, sample = s2
-                euc = []
-                for s in store:
-                    euc.append(np.linalg.norm(s - sample))
-                euc = np.array(euc)
-                euc_nn = np.amin(euc)
-                index_nn = np.ravel(np.where(euc == euc_nn))
-                nn_class = store_classes[index_nn[0]]
+                nn_class = check_store(store, sample, store_classes)
                 if nn_class != sample_class:
                     store.append(sample)
                     store_classes.append(sample_class)

instance_selection/_ENN.py

@@ -3,7 +3,7 @@
 # @Filename:    ENN.py
 # @Author:      Daniel Puente Ramírez
 # @Time:        16/11/21 17:14
-# @Version:     5.0
+# @Version:     6.0
 
 import numpy as np
 import pandas as pd
@@ -18,6 +18,20 @@ def __init__(self, nearest_neighbors=3, power_parameter=2):
         self.power_parameter = power_parameter
         self.x_attr = None
 
+    def neighs(self, s_samples, s_targets, index, removed):
+        x_sample = s_samples[index - removed]
+        x_target = s_targets[index - removed]
+        knn = NearestNeighbors(n_jobs=-1,
+                               n_neighbors=self.nearest_neighbors, p=2)
+        samples_not_x = s_samples[:index - removed] + s_samples[
+                                                      index - removed + 1:]
+        targets_not_x = s_targets[:index - removed] + s_targets[
+                                                      index - removed + 1:]
+        knn.fit(samples_not_x)
+        _, neigh_ind = knn.kneighbors([x_sample])
+
+        return x_sample, x_target, targets_not_x, samples_not_x, neigh_ind
+
     def filter(self, samples, y):
         """
         Wilson, D. L. (1972). Asymptotic properties of nearest neighbor rules
@@ -42,17 +56,8 @@ def filter(self, samples, y):
         removed = 0
 
         for index in range(size):
-            x_sample = s_samples[index - removed]
-            x_target = s_targets[index - removed]
-            knn = NearestNeighbors(
-                n_jobs=1, n_neighbors=self.nearest_neighbors,
-                p=self.power_parameter)
-            samples_not_x = s_samples[:index - removed] + s_samples[
-                                                          index - removed + 1:]
-            targets_not_x = s_targets[:index - removed] + s_targets[
-                                                          index - removed + 1:]
-            knn.fit(samples_not_x)
-            _, neigh_ind = knn.kneighbors([x_sample])
+            _, x_target, targets_not_x, samples_not_x, neigh_ind = self.neighs(
+                s_samples, s_targets, index, removed)
             y_targets = np.ravel(
                 np.array([targets_not_x[x] for x in neigh_ind[0]])).astype(int)
             count = np.bincount(y_targets)
@@ -94,16 +99,8 @@ def filter_original_complete(self, original, original_y, complete,
         removed = 0
 
         for index in range(size):
-            x_sample = s_samples[index - removed]
-            x_target = s_targets[index - removed]
-            knn = NearestNeighbors(n_jobs=-1,
-                                   n_neighbors=self.nearest_neighbors, p=2)
-            samples_not_x = s_samples[:index - removed] + s_samples[
-                                                          index - removed + 1:]
-            targets_not_x = s_targets[:index - removed] + s_targets[
-                                                          index - removed + 1:]
-            knn.fit(samples_not_x)
-            _, neigh_ind = knn.kneighbors([x_sample])
+            x_sample, x_target, targets_not_x, samples_not_x, neigh_ind = \
+                self.neighs(s_samples, s_targets, index, removed)
             y_targets = [targets_not_x[x] for x in neigh_ind[0]]
             count = np.bincount(y_targets)
             max_class = np.where(count == np.amax(count))[0][0]

instance_selection/_LocalSets.py

@@ -96,7 +96,7 @@ def filter(self, instances, labels):
                 s_samples.append(instances[index])
                 s_labels.append(labels[index])
 
-        x = pd.DataFrame(s_samples)
+        x = pd.DataFrame(s_samples, columns=names)
         y = pd.DataFrame(s_labels)
         return x, y