[英]How to extract the boundary values from k-nearest neighbors predict
.predict
,為sklearn.neighbors.KNeighborsClassifier()
import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
from sklearn.neighbors import KNeighborsClassifier
import seaborn as sns
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
# prepare data
iris = load_iris()
X = iris.data
y = iris.target
df = pd.DataFrame(X, columns=iris.feature_names)
df['label'] = y
species_map = dict(zip(range(3), iris.target_names))
df['species'] = df.label.map(species_map)
df = df.reindex(['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)', 'species', 'label'], axis=1)
# instantiate model
knn = KNeighborsClassifier(n_neighbors=6)
# predict for 'petal length (cm)' and 'petal width (cm)'
knn.fit(df.iloc[:, 2:4], df.label)
h = .02 # step size in the mesh
# create colormap for the contour plot
cmap_light = ListedColormap(list(sns.color_palette('pastel', n_colors=3)))
# Plot the decision boundary.
# For that, we will assign a color to each point in the mesh [x_min, x_max]x[y_min, y_max].
x_min, x_max = df['petal length (cm)'].min() - 1, df['petal length (cm)'].max() + 1
y_min, y_max = df['petal width (cm)'].min() - 1, df['petal width (cm)'].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()]).reshape(xx.shape)
# create plot
fig, ax = plt.subplots()
# add data points
sns.scatterplot(data=df, x='petal length (cm)', y='petal width (cm)', hue='species', ax=ax, edgecolor='k')
# add decision boundary countour map
ax.contourf(xx, yy, Z, cmap=cmap_light, alpha=0.4)
# legend
lgd = plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left')
plt.show()
plt.contour(xx, yy, Z, cmap=plt.cm.Paired)
contourf
或pcolormesh
圖中有顏色的解決方案。np.diff
沿兩個軸Z
的.predict
結果。 這個想法是,每當結果發生變化時,這就是一個決策邊界。
.diff
從自身中減去Z
,然后移動 1。mask
,使用np.diff(Z) != 0
mask
從xx
和yy
選擇合適的x
和y
# use diff to create a mask
mask = np.diff(Z, axis=1) != 0
mask2 = np.diff(Z, axis=0) != 0
# apply mask against xx and yy
xd = np.concatenate((xx[:, 1:][mask], xx[1:, :][mask2]))
yd = np.concatenate((yy[:, 1:][mask], yy[1:, :][mask2]))
# plot just the decision boundary
fig, ax = plt.subplots()
sns.scatterplot(x=xd, y=yd, color='k', edgecolor='k', s=5, ax=ax, label='decision boundary')
plt.show()
fig, ax = plt.subplots()
sns.scatterplot(data=df, x='petal length (cm)', y='petal width (cm)', hue='species', ax=ax, edgecolor='k')
sns.scatterplot(x=xd, y=yd, color='k', edgecolor='k', s=5, ax=ax, label='decision boundary')
lgd = plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left')
xd
和yd
正確覆蓋plt.contourf
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.