1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
|
"""
=============================================================================
Comparing Nearest Neighbors with and without Neighborhood Components Analysis
=============================================================================
An example comparing nearest neighbors classification with and without
Neighborhood Components Analysis.
It will plot the class decision boundaries given by a Nearest Neighbors
classifier when using the Euclidean distance on the original features, versus
using the Euclidean distance after the transformation learned by Neighborhood
Components Analysis. The latter aims to find a linear transformation that
maximises the (stochastic) nearest neighbor classification accuracy on the
training set.
"""
# License: BSD 3 clause
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn import datasets
from sklearn.inspection import DecisionBoundaryDisplay
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier, NeighborhoodComponentsAnalysis
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
n_neighbors = 1
dataset = datasets.load_iris()
X, y = dataset.data, dataset.target
# we only take two features. We could avoid this ugly
# slicing by using a two-dim dataset
X = X[:, [0, 2]]
X_train, X_test, y_train, y_test = train_test_split(
X, y, stratify=y, test_size=0.7, random_state=42
)
h = 0.05 # step size in the mesh
# Create color maps
cmap_light = ListedColormap(["#FFAAAA", "#AAFFAA", "#AAAAFF"])
cmap_bold = ListedColormap(["#FF0000", "#00FF00", "#0000FF"])
names = ["KNN", "NCA, KNN"]
classifiers = [
Pipeline(
[
("scaler", StandardScaler()),
("knn", KNeighborsClassifier(n_neighbors=n_neighbors)),
]
),
Pipeline(
[
("scaler", StandardScaler()),
("nca", NeighborhoodComponentsAnalysis()),
("knn", KNeighborsClassifier(n_neighbors=n_neighbors)),
]
),
]
for name, clf in zip(names, classifiers):
clf.fit(X_train, y_train)
score = clf.score(X_test, y_test)
_, ax = plt.subplots()
DecisionBoundaryDisplay.from_estimator(
clf,
X,
cmap=cmap_light,
alpha=0.8,
ax=ax,
response_method="predict",
plot_method="pcolormesh",
shading="auto",
)
# Plot also the training and testing points
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, edgecolor="k", s=20)
plt.title("{} (k = {})".format(name, n_neighbors))
plt.text(
0.9,
0.1,
"{:.2f}".format(score),
size=15,
ha="center",
va="center",
transform=plt.gca().transAxes,
)
plt.show()
|
