205 lines
6.2 KiB
Plaintext
205 lines
6.2 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Importing the libraries\n",
|
|
"import numpy as np\n",
|
|
"import pandas as pd\n",
|
|
"import torch\n",
|
|
"import torch.nn.parallel\n",
|
|
"import torch.utils.data"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Importing the dataset\n",
|
|
"movies = pd.read_csv('ml-1m/movies.dat', sep = '::', header = None, engine = 'python', encoding = 'latin-1')\n",
|
|
"users = pd.read_csv('ml-1m/users.dat', sep = '::', header = None, engine = 'python', encoding = 'latin-1')\n",
|
|
"ratings = pd.read_csv('ml-1m/ratings.dat', sep = '::', header = None, engine = 'python', encoding = 'latin-1')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Preparing the training set and the test set\n",
|
|
"training_set = pd.read_csv('ml-100k/u1.base', delimiter = '\\t')\n",
|
|
"training_set = np.array(training_set, dtype = 'int')\n",
|
|
"test_set = pd.read_csv('ml-100k/u1.test', delimiter = '\\t')\n",
|
|
"test_set = np.array(test_set, dtype = 'int')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Getting the number of users and movies\n",
|
|
"nb_users = int(max(max(training_set[:,0]), max(test_set[:,0])))\n",
|
|
"nb_movies = int(max(max(training_set[:,1]), max(test_set[:,1])))\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Converting the data into an array with users in lines and movies in columns\n",
|
|
"def convert(data):\n",
|
|
" new_data = []\n",
|
|
" for id_users in range(1, nb_users + 1):\n",
|
|
" id_movies = data[:,1][data[:,0] == id_users]\n",
|
|
" id_ratings = data[:,2][data[:,0] == id_users]\n",
|
|
" ratings = np.zeros(nb_movies)\n",
|
|
" ratings[id_movies - 1] = id_ratings\n",
|
|
" new_data.append(list(ratings))\n",
|
|
" return new_data\n",
|
|
"training_set = convert(training_set)\n",
|
|
"test_set = convert(test_set)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Converting the data into Torch tensors\n",
|
|
"training_set = torch.FloatTensor(training_set)\n",
|
|
"test_set = torch.FloatTensor(test_set)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Converting the ratings into binary ratings 1 (Liked) or 0 (Not Liked)\n",
|
|
"training_set[training_set == 0] = -1\n",
|
|
"training_set[training_set == 1] = 0\n",
|
|
"training_set[training_set == 2] = 0\n",
|
|
"training_set[training_set >= 3] = 1\n",
|
|
"test_set[test_set == 0] = -1\n",
|
|
"test_set[test_set == 1] = 0\n",
|
|
"test_set[test_set == 2] = 0\n",
|
|
"test_set[test_set >= 3] = 1"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Creating the architecture of the Neural Network\n",
|
|
"class RBM():\n",
|
|
" def __init__(self, nv, nh):\n",
|
|
" self.W = torch.randn(nh, nv)\n",
|
|
" self.a = torch.randn(1, nh)\n",
|
|
" self.b = torch.randn(1, nv)\n",
|
|
" def sample_h(self, x):\n",
|
|
" wx = torch.mm(x, self.W.t())\n",
|
|
" activation = wx + self.a.expand_as(wx)\n",
|
|
" p_h_given_v = torch.sigmoid(activation)\n",
|
|
" return p_h_given_v, torch.bernoulli(p_h_given_v)\n",
|
|
" def sample_v(self, y):\n",
|
|
" wy = torch.mm(y, self.W)\n",
|
|
" activation = wy + self.b.expand_as(wy)\n",
|
|
" p_v_given_h = torch.sigmoid(activation)\n",
|
|
" return p_v_given_h, torch.bernoulli(p_v_given_h)\n",
|
|
" def train(self, v0, vk, ph0, phk):\n",
|
|
" # self.W += torch.mm(v0.t(), ph0) - torch.mm(vk.t(), phk)\n",
|
|
" self.W += torch.mm(ph0, v0) - torch.mm(phk, vk)\n",
|
|
" self.b += torch.sum((v0 - vk), 0)\n",
|
|
" self.a += torch.sum((ph0 - phk), 0)\n",
|
|
"nv = len(training_set[0])\n",
|
|
"nh = 100\n",
|
|
"batch_size = 100\n",
|
|
"rbm = RBM(nv, nh)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Training the RBM\n",
|
|
"nb_epoch = 10\n",
|
|
"for epoch in range(1, nb_epoch + 1):\n",
|
|
" train_loss = 0\n",
|
|
" s = 0.\n",
|
|
" for id_user in range(0, nb_users - batch_size, batch_size):\n",
|
|
" vk = training_set[id_user:id_user+batch_size]\n",
|
|
" v0 = training_set[id_user:id_user+batch_size]\n",
|
|
" ph0,_ = rbm.sample_h(v0)\n",
|
|
" for k in range(10):\n",
|
|
" _,hk = rbm.sample_h(vk)\n",
|
|
" _,vk = rbm.sample_v(hk)\n",
|
|
" vk[v0<0] = v0[v0<0]\n",
|
|
" phk,_ = rbm.sample_h(vk)\n",
|
|
" rbm.train(v0, vk, ph0, phk)\n",
|
|
" train_loss += torch.mean(torch.abs(v0[v0>=0] - vk[v0>=0]))\n",
|
|
" s += 1.\n",
|
|
" print('epoch: '+str(epoch)+' loss: '+str(train_loss/s))\n",
|
|
" \n",
|
|
"rbm.W += torch.mm(ph0, v0) - torch.mm(phk, vk)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Testing the RBM\n",
|
|
"test_loss = 0\n",
|
|
"s = 0.\n",
|
|
"for id_user in range(nb_users):\n",
|
|
" v = training_set[id_user:id_user+1]\n",
|
|
" vt = test_set[id_user:id_user+1]\n",
|
|
" if len(vt[vt>=0]) > 0:\n",
|
|
" _,h = rbm.sample_h(v)\n",
|
|
" _,v = rbm.sample_v(h)\n",
|
|
" test_loss += torch.mean(torch.abs(vt[vt>=0] - v[vt>=0]))\n",
|
|
" s += 1.\n",
|
|
"print('test loss: '+str(test_loss/s))"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.6.10"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|