使用 KNearestNeighbors 绘制 Iris 数据集的决策边界的问题

Question

我正在尝试 plot 为 Iris 数据集的 Scikit-learn 中的 KNeighborsClassifier 的决策边界。 但是，我得到的图表对我来说没有多大意义。

我希望深蓝色和浅蓝色线 go 之间的边界在我在图片上绘制的绿线的方向上。

我用来生成它的代码可以在下面找到。 它的灵感来自于VotingClassifier 的决策边界 Plot 。

我错过了什么或不理解什么？

# -*- coding: utf-8 -*-
"""
Created on Sat May 30 14:22:05 2020

@author: KamKam

Plotting the decision boundaries for KNearestNeighbours.
"""
# Import required modules.
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.neighbors import KNeighborsClassifier
import numpy as np
from matplotlib.colors import ListedColormap

n_neighbors = [1, 3, 9]

# Load the iris dataset.
iris = datasets.load_iris()
X = iris.data[:, 2:4] # Slice features to only contain 
y = iris.target


# Set up the data such that it can be inserting into one plot.
# Count the number of each target that are in the dataset.
ylen = y.shape[0]
unique, counts = np.unique(y, return_counts=True)

# Create empty arrays for each of the targets. We only require them to have 2
# features because we are only plotting in 2D.
X0 = np.zeros((counts[0], 2))
X1 = np.zeros((counts[1], 2))
X2 = np.zeros((counts[2], 2))

countX0, countX1, countX2 = 0, 0, 0 #Initialize place holder for interating
# though and adding data to the X arrays.
# Insert data into to newly created arrays.
for i in range(ylen):
    if y[i] == 0:
        X0[countX0, :] = X[i, :]
        countX0 += 1
    elif y[i] == 1:
        X1[countX1, :] = X[i, :]
        countX1 += 1
    else:
        X2[countX2, :] = X[i, :]
        countX2 += 1

h = 0.02 # Step size of the mesh.
plotCount = 0 # Counter for each of the plots that we will be creating.

# Create colour maps.
cmap_light = ListedColormap(['orange', 'cyan', 'cornflowerblue'])
cmap_bold = ListedColormap(['darkorange', 'c', 'darkblue'])

# Initialize plotting. Close all the currently open plots, initialize the 
# figure and subplot commands
plt.close('all')
fig, axs = plt.subplots(1, 3)
axs = axs.ravel()

for j in n_neighbors:
    # Create the instance od Neighbours classifier and fit the data.
    knn = KNeighborsClassifier(n_neighbors=j)
    knn.fit(X, y)

    # Plot the decision boundary. For that, we will assign a color for each
    # point in the mesh [x_min, x_max]x[y_min, y_max]
    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), 
                         np.arange(y_min, y_max, h))
    Z = knn.predict(np.c_[xx.ravel(), yy.ravel()])

    # Put the result into a color plot
    Z = Z.reshape(xx.shape)
    axs[plotCount].pcolormesh(xx, yy, Z, cmap=cmap_bold)

    # Plot the training points.
    axs[plotCount].scatter(X0[:,0], X0[:,1], c='k', marker='o', 
                           label=iris.target_names[0])
    axs[plotCount].scatter(X1[:,0], X1[:,1], c='r', marker='o', 
                           label=iris.target_names[1])
    axs[plotCount].scatter(X1[:,0], X2[:,1], c='y', marker='o', 
                           label=iris.target_names[2])
    axs[plotCount].set_xlabel('Petal Width')
    axs[plotCount].set_ylabel('Petal Length')
    axs[plotCount].legend()
    axs[plotCount].set_title('n_neighbours = ' + str(j))
    plotCount += 1

fig.suptitle('Petal Width vs Length')
plt.show()

Answer 1

arrays X0、X1 和 X2 的引入似乎使事情变得过于复杂，并且很难将代码变成 Pythonic。

Python中应该避免的一些事情：

• 多余的变量plotCount仅用于遍历轴，可以省略并替换为for j, ax in zip(n_neighbors, axs) 。
• X0 , X1和 ``X2 的内容can be obtained directly via X[:, 0][y == y_val], X[:, 1][y == y_val]` 直接获得，此外还可以轻松编写散点图在一个循环中。 您可以在此文档中阅读有关 numpy 高级索引的更多信息。

import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.neighbors import KNeighborsClassifier
import numpy as np
from matplotlib.colors import ListedColormap

n_neighbors = [1, 3, 9]

# Load the iris dataset.
iris = datasets.load_iris()
X = iris.data[:, 2:4]  # Slice features to only contain
y = iris.target

# Set up the data such that it can be inserting into one plot.
# Count the number of each target that are in the dataset.
ylen = y.shape[0]
unique, counts = np.unique(y, return_counts=True)

h = 0.02  # Step size of the mesh.

# Create colour maps.
#cmap_light = ListedColormap(['orange', 'cyan', 'cornflowerblue'])
cmap_bold = ListedColormap(['darkorange', 'c', 'darkblue'])

# Initialize plotting. Close all the currently open plots, initialize the
# figure and subplot commands
plt.close('all')
fig, axs = plt.subplots(1, 3)
axs = axs.ravel()

for j, ax in zip(n_neighbors, axs):
    # Create the instance od Neighbours classifier and fit the data.
    knn = KNeighborsClassifier(n_neighbors=j)
    knn.fit(X, y)

    # Plot the decision boundary. For that, we will assign a color for each
    # point in the mesh [x_min, x_max]x[y_min, y_max]
    x_min, x_max = X[:, 0].min() - h, X[:, 0].max() + h
    y_min, y_max = X[:, 1].min() - h, X[:, 1].max() + h
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))
    Z = knn.predict(np.c_[xx.ravel(), yy.ravel()])

    # Put the result into a color plot
    Z = Z.reshape(xx.shape)
    ax.pcolormesh(xx, yy, Z, cmap=cmap_bold)

    # Plot the training points.
    for y_val, (color, name) in enumerate(zip(['k', 'r', 'y'], iris.target_names)):
        ax.scatter(X[:, 0][y == y_val], X[:, 1][y == y_val], c=color, marker='o', label=name)

    ax.set_xlabel('Petal Width')
    ax.set_ylabel('Petal Length')
    ax.legend()
    ax.set_title(f'n_neighbours = {j}')

fig.suptitle('Petal Width vs Length')
plt.show()