import os.path
import csv
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
from pathlib import Path
Importing the 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 the training set and the test set
training_set = pd.read_csv(‘ml-100k/u2.base’, delimiter = ‘\t’)
training_set = np.array(training_set, dtype = ‘int’)
test_set = pd.read_csv(‘ml-100k/u2.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])))
Converting the data into an array with users in lines and movies in columns
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)
Converting the data into Torch tensors
training_set = torch.FloatTensor(training_set)
test_set = torch.FloatTensor(test_set)
class SAE(nn.Module):
def init(self, ):
super(SAE, self).init()
self.fc1 = nn.Linear(nb_movies, 20)
self.fc2 = nn.Linear(20, 10)
self.fc3 = nn.Linear(10, 20)
self.fc4 = nn.Linear(20, nb_movies)
self.activation = nn.Sigmoid()
def forward(self, x):
x = self.activation(self.fc1(x))
x = self.activation(self.fc2(x))
x = self.activation(self.fc3(x))
x = self.fc4(x)
x.view(x.size(0), -1)
return x
sae = SAE()
criterion = nn.MSELoss()
optimizer = optim.RMSprop(sae.parameters(), lr = 0.01, weight_decay = 0.5)
from pathlib import Path, PureWindowsPath
filename = Path(“D:/Movie-Recommendation-System-using-AutoEncoders-master/Movie-Recommendation-System-using-AutoEncoders-master”)
Convert path to Windows format
path_on_windows = PureWindowsPath(filename)
print(path_on_windows)
def load_checkpoint(path_on_windows):
checkpoint = torch.load(path_on_windows)
model = checkpoint[‘model’]
model.load_state_dict(checkpoint[‘state_dict’])
for parameter in model.parameters():
parameter.requires_grad = False
model.eval()
return model
model = load_checkpoint(‘checkpoint.pth’)
#print(model)
movie_dict = {3709 : ‘Sleepwalkers’,
2846 : ‘Adventures of Milo and Otis’,
3880 : ‘Ballad of Ramblin Jack’,
2971 : ‘All That Jazz’,
3951 : ‘Two Family House’,
3681 : ‘For a Few Dollars More’,
3921 : ‘Beach Party’,
3541 : ‘Third World Cop’,
2189 : ‘I Married A Strange Person’,
3687 : ‘Light Years’,
3390 : ‘Shanghai Surprise’,
2940 : ‘Gilda’,
3857 : ‘Bless the Child’,
1464 : ‘Lost Highway’,
3376 : ‘Fantastic Night-The (La Nuit Fantastique)’,
3670 : ‘Story of G.I. Joe’,
3906 : ‘Under Suspicion’,
792 : ‘Hungarian Fairy Tale’}
count = nb_users
sid = count+1
sid2 = sid-1
with open(‘ml-100k/u2.base’, mode=‘a’) as file:
writer = csv.writer(file, delimiter=’\t’, lineterminator=’\n’)
for iD in movie_dict:
#print(movie_dict[iD])
#a = int(input(‘Enter rating:’))
writer.writerow([sid,iD,4,‘888692464’])
file.close()
#nb_users = int(max(max(training_set[:,0]), max(test_set[:,0])))
training_set = pd.read_csv(‘ml-100k/u2.base’, delimiter = ‘\t’)
training_set = np.array(training_set, dtype = ‘int’)
training_set = convert(training_set)
training_set = torch.FloatTensor(training_set)
sid = 954
input = Variable(training_set[sid]).unsqueeze(0)
output = model(input)
lol = output.detach().numpy()
loll = lol[0]
for i in loll:
if(i>4):
print(100,’:’,round(i))
The above is my code for recommender system using autoencoder. While running the code, I am getting the following error:
RuntimeError: size mismatch, m1: [1 x 3951], m2: [1682 x 20] at C:\w\1\s\windows\pytorch\aten\src\TH/generic/THTensorMath.cpp:136
