神经网络：实现感知机算法-python

主要原理：

f(x) = sign(w*x + b)

损失函数 L(w, b) = -\Sigma{y_{i}(w*x_{i} + b)}

随即梯度下降法 Stochastic Gradient Descent

随机抽取一个误分类点使其梯度下降。

$w = w + \eta y_{i}x_{i}$

$b = b + \eta y_{i}$

当实例点被误分类，即位于分离超平面的错误侧，则调整w, b的值，使分离超平面向该无分类点的一侧移动，直至误分类点被正确分类

拿出iris数据集中两个分类的数据和[sepal length，sepal width]作为特征

方法一：perception

导入所需要的库

import pandas as pd
import numpy as np
from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
%matplotlib inline

加载数据

# load data
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)
df['label'] = iris.target

#
df.columns = ['sepal length', 'sepal width', 'petal length', 'petal width', 'label']
df.label.value_counts()

#将原始数据的前两个维度提取出来作为特征向量，最后一个维度提取出来作为目标

data = np.array(df.iloc[:100, [0, 1, -1]])
X, y = data[:,:-1], data[:,-1]
#将标签记作-1和1
y = np.array([1 if i == 1 else -1 for i in y])

Perceptron

# 数据线性可分，二分类数据
# 此处为一元一次线性方程
class Model:
    def __init__(self):
        self.w = np.ones(len(data[0])-1, dtype=np.float32)
        self.b = 0
        self.l_rate = 0.1
        # self.data = data
    
    #定义感知机的模型
    def sign(self, x, w, b):
        y = np.dot(x, w) + b
        return y
    
    # 随机梯度下降法
    def fit(self, X_train, y_train):
        is_wrong = False
        while not is_wrong:
            is_wrong = True
            for i in range(len(X_train)):
                if y_train[i] * self.sign(X_train[i],self.w,self.b) < 0:
                    self.w = self.w + self.l_rate*np.dot(X_train[i],y_train[i])
                    self.b = self.b + self.l_rate*y_train[i]
                    is_wrong = False
                    break
        
        return 'Perceptron Model!'
        
    def score(self):
        pass

perceptron = Model()
perceptron.fit(X, y)

画图

fig = plt.figure()
x_points = np.linspace(4, 7,10)

#画出分类线及样本点的散状图
y_= -(perceptron.b+perceptron.w[0]*x_points)/perceptron.w[1]
plt.plot(x_points,y_)


right = plt.scatter(X[:,0][y==1],X[:,1][y==1])
false = plt.scatter(X[:,0][y==-1],X[:,1][y==-1],marker='^')


plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend([right,false],['0','1'])
plt.show()

结果：

 方法二：使用scikit-learn实现Perceptron

from sklearn.linear_model import Perceptron
from sklearn.metrics import f1_score, classification_report

clf = Perceptron(random_state=10)
clf.fit(X, y)

# Weights assigned to the features.
print(clf.coef_)

# 截距 Constants in decision function.
print(clf.intercept_)

predictions=clf.predict(X)
print(classification_report(y,predictions))

y_ = -(clf.coef_[0][0]*x_ponits + clf.intercept_)/clf.coef_[0][1] 
x_points = np.linspace(4, 7, 10)
print(x_points)
print(y_)

#x_ponits = np.arange(4,8)# 4,5,6,7
x_points = [4,5,6,7]
y_ = -(clf.coef_[0][0]*x_ponits + clf.intercept_)/clf.coef_[0][1] 
#画分类超平面
plt.plot(x_points, y_)

plt.plot(data[:50,0],data[:50,1],'bo',color='blue',label='0')
plt.plot(data[50:100,0],data[50:100,1],'bo',color='orange',label='1')
#画出训练样本点的散状图，蓝色一类，红色一类

plt.xlabel('sepal length')
plt.ylabel('sepal width')
plt.legend()

结果：