[sklearn-snippets] skl-learn snippets #python #sklearn

svm-demo.py

import numpy as np
import matplotlib.pyplot as plt
import ipywidgets as widget

from sklearn.datasets import make_blobs
from sklearn.svm import SVC

def plot_svc_decision_function(model, ax=None, plot_support=True):
    """Plot the decision function for a 2D SVC"""
    ax = ax or plt.gca()
    xlim = ax.get_xlim()
    ylim = ax.get_ylim()
    
    # create grid to evaluate model
    x = np.linspace(xlim[0], xlim[1], 30)
    y = np.linspace(ylim[0], ylim[1], 30)
    Y, X = np.meshgrid(y, x)

    # vstack将数据垂直放置，类似于append，在T一下，得到的数据类似
    # xy = np.array([(i, j) for i in x for j in y])
    xy = np.vstack([X.ravel(), Y.ravel()]).T

    # contour的计算需要P转化为row*col的格式，所以还需要reshape回来
    P = model.decision_function(xy).reshape(X.shape)
    
    # plot decision boundary and margins
    ax.contour(X, Y, P, colors='k', 
               levels=[-1, 0, 1], alpha=0.5,
               linestyles=['--', '-', '--'])
    
    # plot support vectors
    # support_vectors_中记录的是SVM训练得到的分界点
    # facecolors记录点的中心颜色，linecolors记录点的边界颜色，这里只保持边界颜色
    if plot_support:
        ax.scatter(model.support_vectors_[:, 0],
                   model.support_vectors_[:, 1],
                   s=300, linewidth=1, facecolors='none');
    ax.set_xlim(xlim)
    ax.set_ylim(ylim)

# @note 神器，ipywidgets的interact可以提供简单的UI空间，进而控制计算过程
# 这里可以根据[10, 200, 10]选择数据来看不同的N情况下，decision boundary的变化情况
@widget.interact(N=(10, 200, 10), ax=widget.fixed(None))
def plot_svm(N=10, ax=None):
    X, y = make_blobs(n_samples=200, centers=2,
                      random_state=0, cluster_std=0.60)
    X = X[:N]
    y = y[:N]
    model = SVC(kernel='linear', C=1E10)
    model.fit(X, y)
    
    ax = ax or plt.gca()
    ax.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='autumn')
    ax.set_xlim(-1, 4)
    ax.set_ylim(-1, 6)
    plot_svc_decision_function(model, ax)