cf nn

neuralnet

# nh = dimension of hidden linear layer
# p1 = dropout1
# p2 = dropout2

class EmbeddingNet(nn.Module):
    def __init__(self, n_users, _n_movies, nh = 10, p1 = 0.05, p2= 0.5):
        super().__init__()
        (self.u, self.m, self.ub, self.mb) = [get_emb(*o) for o in [
            (n_users, n_factors), (n_movies, n_factors),
            (n_users,1), (n_movies,1)
        ]]
        
        self.lin1 = nn.Linear(n_factors*2, nh)  # bias is True by default
        self.lin2 = nn.Linear(nh, 1)
        self.drop1 = nn.Dropout(p = p1)
        self.drop2 = nn.Dropout(p = p2)
    
    def forward(self, cats, conts): # forward pass i.e.  dot product of vector from movie embedding matrixx
                                    # and vector from user embeddings matrix
        
        # torch.cat : concatenates both embedding matrix to make more columns, same rows i.e. n_factors*2, n : rows
        # u(users) is doing lookup for indexed mentioned in users
        # users has indexes to lookup in embedding matrix. 
        
        users,movies = cats[:,0],cats[:,1]
        u2,m2 = self.u(users) , self.m(movies)
       
        x = self.drop1(torch.cat([u2,m2], 1)) # drop initialized weights
        x = self.drop2(F.relu(self.lin1(x))) # drop 1st linear + nonlinear wt
        r = F.sigmoid(self.lin2(x)) * (max_rating - min_rating) + min_rating               
        return r