因子分解机——代码

利用矩阵，梯度下降算法实现的因子分解机
 

import numpy as np

LEARNING_RATE = 0.95
REGULARIZATION_COEFFICIENT = 0.000001
STEP_THRESHOLD = 300
K = 6

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

class factorizationMachine:
    #x: a sample in train_set
    #cross_v: it is a two-dimensional numpy, whose shape is (k,n).And n is sample's feature number.
    def __init__(self, w0, linear_w, cross_v):
        self.w0 = w0
        self.linear_w = linear_w
        self.cross_v = cross_v

    #def pi_map(self, i):
    
    def inference(self, x):
        return self.w0 + self.linear_w.dot(x) + np.sum((self.cross_v.dot(x))**2) - np.sum((self.cross_v**2).dot(x**2))
    
    def loss(self, y, x):
        # y_ is predicted value, y is real value
        y_ = self.inference(x)
        #L2 regularization