感知机

最新推荐文章于 2025-03-07 21:58:16 发布

vct26

最新推荐文章于 2025-03-07 21:58:16 发布

阅读量101

点赞数 1

CC 4.0 BY-SA版权

本文链接：https://blog.csdn.net/segfes/article/details/103638738

本文介绍了一种使用Python实现的感知机算法，并展示了如何通过matplotlib库来可视化决策边界。通过加载Iris数据集和自动生成的数据点，感知机模型被训练以分类数据，并通过决策区域的绘制来直观展示分类效果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

# -*- coding: utf-8 -*-
import numpy as np
from sklearn.datasets import load_iris
from sklearn.datasets import make_blobs
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
#%%
def plot_decision_regions(model, X, y, resolution=0.02):
    "param resolution:分辨率"
    # initialization colors map
    colors = ['red', 'blue']
    markers = ['o', 'x']
    cmap = ListedColormap(colors[:len(np.unique(y))])

    # plot the decision regions
    x1_max, x1_min = max(X[:, 0]) + 1, min(X[:, 0]) - 1
    x2_max, x2_min = max(X[:, 1]) + 1, min(X[:, 1]) - 1
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
                           np.arange(x2_min, x2_max, resolution))
    Z = model.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())

    # plot class samples
    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1],
                    alpha=0.8, c=cmap(idx),
                    marker=markers[idx], label=cl)
    plt.show()
    #%%
class PerceptronBase(object):
    def __init__(self, eta=0.1, n_iter=50):
        self.eta = eta
        self.n_iter = n_iter

    def fit(self, X, y):
        self.w = np.zeros(X.shape[1])
        self.b = 0
        self.errors_ = []
        
        for epo in range(self.n_iter):
            errors = 0
            for xi, yi in zip(X, y):
                update = self.eta * (yi - self.predict(xi))
                self.w += update * xi
                self.b += update
                errors += int(update != 0.0)
            if errors == 0:
                break
            self.errors_.append(errors)
        print('Finish training after {} epoch !!'.format(epo))

    def sign(self, xi):
        return np.dot(xi, self.w) + self.b

    def predict(self, xi):
        return np.where(self.sign(xi) > 0.0, 1, -1)

#%%
iris = load_iris()
X = iris.data[:100, [0, 2]] 
y = iris.target[:100]

#%%
X, y = make_blobs(n_samples=1000, centers=2)

    #%%
y = np.where(y == 1, 1, -1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
ppn = PerceptronBase(eta=0.9, n_iter=100)
ppn.fit(X_train, y_train)
plot_decision_regions(ppn, X_train, y_train.reshape(-1,))