因子分解机

https://blog.csdn.net/songbinxu/article/details/79662665

https://blog.csdn.net/google19890102/article/details/45532745

https://blog.csdn.net/jediael_lu/article/details/77772565

https://blog.csdn.net/asd136912/article/details/78318563

# -*- coding: utf-8 -*-
import pandas as pd
from math import exp
import numpy as np
from random import normalvariate
from sklearn import datasets

path = 'D:/ml_project/minist/'


def sigmoid(x): return 1.0 / (1 + exp(-x))

def stocGradAscent(dataMatrix, classLabels, k, iteration):  
    #dataMatrix用的是mat, classLabels是列表  
    m, n = np.shape(dataMatrix)  
    alpha = 0.01  
    #初始化参数  
    w = np.zeros((n, 1))#其中n是特征的个数  
    w_0 = 0.  
    v = normalvariate(0, 0.2) * np.ones((n, k))  
      
    for it in range(iteration):  
        print("第{}次迭代...".format(it))
        for x in range(m):#随机优化，对每一个样本而言的  
            inter_1 = dataMatrix[x] * v  
            inter_2 = np.multiply(dataMatrix[x], dataMatrix[x]) * np.multiply(v, v)#multiply对应元素相乘  
            #完成交叉项  
            interaction = sum(np.multiply(inter_1, inter_1) - inter_2) / 2.  
              
            p = w_0 + dataMatrix[x] * w + interaction#计算预测的输出  
          
            loss = sigmoid(classLabels[x] * p[0, 0]) - 1  
            print(loss)
          
            w_0 = w_0 - alpha * loss * classLabels[x]  
              
            for i in range(n):  
                if dataMatrix[x, i] != 0:  
                    w[i, 0] = w[i, 0] - alpha * loss * classLabels[x] * dataMatrix[x, i]  
                    for j in range(k):  
                        v[i, j] = v[i, j] - alpha * loss * classLabels[x] * (dataMatrix[x, i] * inter_1[0, j] - v[i, j] * dataMatrix[x, i] * dataMatrix[x, i])  
    return w_0, w, v  

def getAccuracy(dataMatrix, classLabels, w_0, w, v):  
    m, n = np.shape(dataMatrix)  
    allItem = 0  
    error = 0  
    result = []  
    for x in range(m):  
        allItem += 1  
        inter_1 = dataMatrix[x] * v  
        inter_2 = np.multiply(dataMatrix[x], dataMatrix[x]) * np.multiply(v, v)#multiply对应元素相乘  
        #完成交叉项  
        interaction = sum(np.multiply(inter_1, inter_1) - inter_2) / 2.  
        p = w_0 + dataMatrix[x] * w + interaction#计算预测的输出  
          
        pre = sigmoid(p[0, 0])  
          
        result.append(pre)  
          
        if pre < 0.5 and classLabels[x] == 1.0:  
            error += 1  
        elif pre >= 0.5 and classLabels[x] == -1.0:  
            error += 1  
        else:  
            continue      
    return result, float(error) / allItem  
          

if __name__ == '__main__':
    train = datasets.load_diabetes()
    
    train_X = np.mat(train['data'])
    train_y = train['target']
    train_y[train_y <= 180] = -1
    train_y[train_y > 180] = 1
    
    w_0, w, v = stocGradAscent(train_X, train_y, 5, 200)
    
    result, acc = getAccuracy(train_X, train_y, w_0, w, v)