#### NOTEBOOK DESCRIPTION

from datetime import datetime

NOTEBOOK_TITLE = 'taruma_udemy_autoencoders'
NOTEBOOK_VERSION = '1.0.0'
NOTEBOOK_DATE = 1 # Set 1, if you want add date classifier

NOTEBOOK_NAME = "{}_{}".format(
    NOTEBOOK_TITLE, 
    NOTEBOOK_VERSION.replace('.','_')
)
PROJECT_NAME = "{}_{}{}".format(
    NOTEBOOK_TITLE, 
    NOTEBOOK_VERSION.replace('.','_'), 
    "_" + datetime.utcnow().strftime("%Y%m%d_%H%M") if NOTEBOOK_DATE else ""
)

print(f"Nama Notebook: {NOTEBOOK_NAME}")
print(f"Nama Proyek: {PROJECT_NAME}")

#### System Version
import sys, torch
print("versi python: {}".format(sys.version))
print("versi pytorch: {}".format(torch.__version__))

#### Load Notebook Extensions
%load_ext google.colab.data_table

#### Download dataset
# ref: https://grouplens.org/datasets/movielens/
!wget -O autoencoders.zip "https://sds-platform-private.s3-us-east-2.amazonaws.com/uploads/P16-AutoEncoders.zip"
!unzip autoencoders.zip

# Karena ada file .zip dalam direktori, harus diekstrak lagi.
# ref: https://askubuntu.com/q/399951
# ref: https://unix.stackexchange.com/q/12902
!find AutoEncoders -type f -name '*.zip' -exec unzip -d AutoEncoders {} \;

#### Atur dataset path
DATASET_DIRECTORY = 'AutoEncoders/'

def showdata(dataframe):
    print('Dataframe Size: {}'.format(dataframe.shape))
    return dataframe

# 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

movies = pd.read_csv(DATASET_DIRECTORY + 'ml-1m/movies.dat', sep='::', header=None, engine='python', encoding='latin-1')
showdata(movies).head(10)

users = pd.read_csv(DATASET_DIRECTORY + 'ml-1m/users.dat', sep='::', header=None, engine='python', encoding='latin-1')
showdata(users).head(10)

ratings = pd.read_csv(DATASET_DIRECTORY + 'ml-1m/ratings.dat', sep='::', header=None, engine='python', encoding='latin-1')
showdata(ratings).head(10)

# Preparing the training set and the test set
training_set = pd.read_csv(DATASET_DIRECTORY + 'ml-100k/u1.base', delimiter='\t')
training_set = np.array(training_set, dtype='int')
test_set = pd.read_csv(DATASET_DIRECTORY + '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])))

# 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)

training_set

# Creating the architecture of the Neural Network
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)
        return x
sae = SAE()
criterion = nn.MSELoss()
optimizer = optim.RMSprop(sae.parameters(), lr = 0.01, weight_decay = 0.5)

# Training the SAE
nb_epoch = 200
for epoch in range(1, nb_epoch + 1):
    train_loss = 0
    s = 0.
    for id_user in range(nb_users):
        input = Variable(training_set[id_user]).unsqueeze(0)
        target = input.clone()
        if torch.sum(target.data > 0) > 0:
            output = sae(input)
            target.require_grad = False
            output[target == 0] = 0
            loss = criterion(output, target)
            mean_corrector = nb_movies/float(torch.sum(target.data > 0) + 1e-10)
            loss.backward()
            train_loss += np.sqrt(loss.item()*mean_corrector)
            s += 1.
            optimizer.step()
    print('epoch: '+str(epoch)+' loss: '+str(train_loss/s))

# Testing the SAE
test_loss = 0
s = 0.
for id_user in range(nb_users):
    input = Variable(training_set[id_user]).unsqueeze(0)
    target = Variable(test_set[id_user]).unsqueeze(0)
    if torch.sum(target.data > 0) > 0:
        output = sae(input)
        target.require_grad = False
        output[target == 0] = 0
        loss = criterion(output, target)
        mean_corrector = nb_movies/float(torch.sum(target.data > 0) + 1e-10)
        test_loss += np.sqrt(loss.item()*mean_corrector)
        s += 1.
print('test loss: '+str(test_loss/s))