rbm

Boltzmann Machines

Importing the libraries

import numpy as np import pandas as pd import torch import torch.nn as nn import torch.nn.parallel import torch.optim as optim import torch.utils.data from torch.autograd import Variable

Importing dataset

movies = pd.read_csv('ml-1m/movies.dat', sep = '::', header = None, engine = 'python', encoding = 'latin-1') users = pd.read_csv('ml-1m/users.dat', sep = '::', header = None, engine = 'python', encoding = 'latin-1') ratings = pd.read_csv('ml-1m/ratings.dat', sep = '::', header = None, engine = 'python', encoding = 'latin-1')

Preparing training set and test set

training_set = pd.read_csv('ml-100k/u1.base', delimiter = '\t') training_set = np.array(training_set, dtype = 'int')

test_set = pd.read_csv('ml-100k/u1.test', delimiter = '\t') test_set = np.array(test_set, dtype = 'int')

Getting the number of users and movies

nb_users = int(max(max(training_set[:,0]), max(test_set[:,0]))) nb_movies = int(max(max(training_set[:,1]), max(test_set[:,1])))

def convert(data): new_data = [] for id_users in range(1, nb_users + 1): id_movies = data[:,1][data[:,0] == id_users] id_ratings = data[:,2][data[:,0] == id_users] ratings = np.zeros(nb_movies) ratings[id_movies - 1] = id_ratings new_data.append(list(ratings)) return new_data training_set = convert(training_set) test_set = convert(test_set)

#convert data to torch tensor training_set = torch.FloatTensor(training_set) test_set = torch.FloatTensor(test_set)

#convert ratings to binary 1 for like 0 dislike training_set[training_set == 0] = -1 training_set[training_set == 1] = 0 training_set[training_set == 2] = 0 training_set[training_set >=3] = 1

test_set[test_set == 0] = -1 test_set[test_set == 1] = 0 test_set[test_set == 2] = 0 test_set[test_set >=3] = 1

#creat the architecture of NN class RBM(): def init(self, nv, nh): self.W = torch.randn(nh , nv) self.a = torch.randn(1, nh) self.b = torch.randn(1, nv) def sample_h(self, x): wx = torch.mm(x, self.W.t()) activation = wx + self.a.expand_as(wx) P_h_given_v = torch.sigmoid(activation) return P_h_given_v, torch.bernoulli(P_h_given_v) def sample_v(self, y): wy = torch.mm(y, self.W) activation = wy + self.b.expand_as(wy) P_v_given_h = torch.sigmoid(activation) return P_v_given_h, torch.bernoulli(P_v_given_h) def train(self, v0, vk, ph0, phk): self.W += torch.mm(v0.t(), ph0) - torch.mm(vk.t(), phk) self.b += torch.sum((v0 - vk), 0) self.a += torch.sum((ph0 - phk), 0)