seq2seq.py

# -*- coding: utf-8 -*-

from __future__ import unicode_literals, print_function, division
from io import open
import unicodedata
import string
import re
import random
import sys

import torch
import torch.nn as nn
from torch import optim
import torch.nn.functional as F

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if torch.cuda.is_available():
    print("Using GPU...")
else:
    print("Using CPU...")

######################################################################
# Loading data files
# ==================

SOS_token = 0
EOS_token = 1


class Lang:
    def __init__(self, name):
        self.name = name
        self.word2index = {}
        #self.word2count = {}
        self.index2word = {0: "SOS", 1: "EOS"}
        self.n_words = 2  # Count SOS and EOS

    def addSentence(self, sentence):
        for word in sentence.split(' '):
            self.addWord(word)

    def addWord(self, word):
        if word not in self.word2index:
            self.word2index[word] = self.n_words
            #self.word2count[word] = 1
            self.index2word[self.n_words] = word
            self.n_words += 1
        # else:
        #     self.word2count[word] += 1


######################################################################
# The files are all in Unicode, to simplify we will turn Unicode
# characters to ASCII, make everything lowercase, and trim most
# punctuation.

def unicodeToAscii(s):
    return ''.join(
        c for c in unicodedata.normalize('NFD', s)
        if unicodedata.category(c) != 'Mn'
    )

# Lowercase, trim, and remove non-letter characters


def normalizeString(s):
    s = unicodeToAscii(s.lower().strip())
    s = re.sub(r"([.!?])", r" \1", s)
    s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)
    return s


######################################################################

#first parameter is language in, second is language out
#reverse=False assumes you are translating from english to spanish
#call with reverse=True when translating spanish to english
def readLangs(lang_in, lang_out):
    print("Reading lines...")

    # Read the file and split into lines
    spLines = open('trimmedSpanish.txt', encoding='utf-8').\
        read().strip().split('\n')
    enLines = open('trimmedEnglish.txt', encoding='utf-8').\
        read().strip().split('\n')

    # Split every line into pairs and normalize
    #assume english to spanish
    pairs = []
    for i in range(len(spLines)):
        pairs.append([normalizeString(enLines[i]), normalizeString(spLines[i])])

    #check if spanish was input lang
    #if it was then we need to reverse the pairs we just made
    if lang_in == "Spanish":
        pairs = [list(reversed(p)) for p in pairs]

    #create language objs for input and output lang
    input_lang = Lang(lang_in)
    output_lang = Lang(lang_out)

    return input_lang, output_lang, pairs


#######################
###### TRIM DATA ######
#######################

MAX_LENGTH = 10


def filterPair(p):
    return len(p[0].split(' ')) < MAX_LENGTH and \
        len(p[1].split(' ')) < MAX_LENGTH 


def filterPairs(pairs):
    return [pair for pair in pairs if filterPair(pair)]


######################################################################
# The full process for preparing the data is:
#
# -  Read text file and split into lines, split lines into pairs
# -  Normalize text, filter by length and content
# -  Make word lists from sentences in pairs
#

def prepareData(lang1, lang2):
    input_lang, output_lang, pairs = readLangs(lang1, lang2)
    print("Read %s sentence pairs" % len(pairs))
    pairs = filterPairs(pairs)
    print("Trimmed to %s sentence pairs" % len(pairs))
    print("Counting words...")
    for pair in pairs:
        input_lang.addSentence(pair[0])
        output_lang.addSentence(pair[1])
    print("Counted words:")
    print(input_lang.name, input_lang.n_words)
    print(output_lang.name, output_lang.n_words)
    return input_lang, output_lang, pairs



######################################################################
# The Seq2Seq Model
# =================
#
# A Recurrent Neural Network, or RNN, is a network that operates on a
# sequence and uses its own output as input for subsequent steps.
#
# A Sequence to Sequence network, or Encoder Decoder network, is a model
# consisting of two RNNs called the encoder and decoder. The encoder reads
# an input sequence and outputs a single vector, and the decoder reads
# that vector to produce an output sequence.
#


######################################################################
# The Encoder
# -----------
#
# The encoder of a seq2seq network is a RNN that outputs some value for
# every word from the input sentence. For every input word the encoder
# outputs a vector and a hidden state, and uses the hidden state for the
# next input word.
#

#

class EncoderRNN(nn.Module):
    def __init__(self, input_size, hidden_size):
        super(EncoderRNN, self).__init__()
        self.hidden_size = hidden_size

        self.embedding = nn.Embedding(input_size, hidden_size)
        self.gru = nn.GRU(hidden_size, hidden_size)
        self.gru2 = nn.GRU(hidden_size, hidden_size)

    def forward(self, input, hidden):
        embedded = self.embedding(input).view(1, 1, -1)
        output = embedded
        output, hidden = self.gru(output, hidden)
        output, hidden = self.gru2(output, hidden)
        return output, hidden

    def initHidden(self):
        return torch.zeros(1, 1, self.hidden_size, device=device)

######################################################################
# The Decoder
# -----------
#
# The decoder is another RNN that takes the encoder output vector(s) and
# outputs a sequence of words to create the translation.
#


######################################################################
# Simple Decoder
# ^^^^^^^^^^^^^^
#
# In the simplest seq2seq decoder we use only last output of the encoder.
# This last output is sometimes called the *context vector* as it encodes
# context from the entire sequence. This context vector is used as the
# initial hidden state of the decoder.
#
# At every step of decoding, the decoder is given an input token and
# hidden state. The initial input token is the start-of-string ``<SOS>``
# token, and the first hidden state is the context vector (the encoder's
# last hidden state).


class DecoderRNN(nn.Module):
    def __init__(self, hidden_size, output_size):
        super(DecoderRNN, self).__init__()
        self.hidden_size = hidden_size

        self.embedding = nn.Embedding(output_size, hidden_size)
        self.gru = nn.GRU(hidden_size, hidden_size)
        self.gru2 = nn.GRU(hidden_size, hidden_size)
        self.out = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)

    def forward(self, input, hidden):
        output = self.embedding(input).view(1, 1, -1)
        output = F.relu(output)
        output, hidden = self.gru(output, hidden)
        output, hidden = self.gru2(output, hidden)
        output = self.softmax(self.out(output[0]))
        return output, hidden

    def initHidden(self):
        return torch.zeros(1, 1, self.hidden_size, device=device)



######################################################################
# Attention Decoder
# ^^^^^^^^^^^^^^^^^
#
# If only the context vector is passed betweeen the encoder and decoder,
# that single vector carries the burden of encoding the entire sentence.
#
# Attention allows the decoder network to "focus" on a different part of
# the encoder's outputs for every step of the decoder's own outputs. First
# we calculate a set of *attention weights*. These will be multiplied by
# the encoder output vectors to create a weighted combination. The result
# (called ``attn_applied`` in the code) should contain information about
# that specific part of the input sequence, and thus help the decoder
# choose the right output words.
#
# Calculating the attention weights is done with another feed-forward
# layer ``attn``, using the decoder's input and hidden state as inputs.
# Because there are sentences of all sizes in the training data, to
# actually create and train this layer we have to choose a maximum
# sentence length (input length, for encoder outputs) that it can apply
# to. Sentences of the maximum length will use all the attention weights,
# while shorter sentences will only use the first few.
#
#

class AttnDecoderRNN(nn.Module):
    def __init__(self, hidden_size, output_size, dropout_p=0.1, max_length=MAX_LENGTH):
        super(AttnDecoderRNN, self).__init__()
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.dropout_p = dropout_p
        self.max_length = max_length

        self.embedding = nn.Embedding(self.output_size, self.hidden_size)
        self.attn = nn.Linear(self.hidden_size * 2, self.max_length)
        self.attn_combine = nn.Linear(self.hidden_size * 2, self.hidden_size)
        self.dropout = nn.Dropout(self.dropout_p)
        self.gru = nn.GRU(self.hidden_size, self.hidden_size)
        self.gru2 = nn.GRU(self.hidden_size, self.hidden_size)
        self.out = nn.Linear(self.hidden_size, self.output_size)

    def forward(self, input, hidden, encoder_outputs):
        embedded = self.embedding(input).view(1, 1, -1)
        embedded = self.dropout(embedded)

        attn_weights = F.softmax(
            self.attn(torch.cat((embedded[0], hidden[0]), 1)), dim=1)
        attn_applied = torch.bmm(attn_weights.unsqueeze(0),
                                 encoder_outputs.unsqueeze(0))

        output = torch.cat((embedded[0], attn_applied[0]), 1)
        output = self.attn_combine(output).unsqueeze(0)

        output = F.relu(output)
        output, hidden = self.gru(output, hidden)
        output, hidden = self.gru2(output, hidden)

        output = F.log_softmax(self.out(output[0]), dim=1)
        return output, hidden, attn_weights

    def initHidden(self):
        return torch.zeros(1, 1, self.hidden_size, device=device)


######################################################################
#
# Training
# ========
#
# Preparing Training Data
# -----------------------
#
# To train, for each pair we will need an input tensor (indexes of the
# words in the input sentence) and target tensor (indexes of the words in
# the target sentence). While creating these vectors we will append the
# EOS token to both sequences.
#

def indexesFromSentence(lang, sentence):
    return [lang.word2index[word] for word in sentence.split(' ')]


def tensorFromSentence(lang, sentence):
    indexes = indexesFromSentence(lang, sentence)
    indexes.append(EOS_token)
    return torch.tensor(indexes, dtype=torch.long, device=device).view(-1, 1)


def tensorsFromPair(pair):
    input_tensor = tensorFromSentence(input_lang, pair[0])
    target_tensor = tensorFromSentence(output_lang, pair[1])
    return (input_tensor, target_tensor)


######################################################################
# Training the Model
# ------------------
#
# To train we run the input sentence through the encoder, and keep track
# of every output and the latest hidden state. Then the decoder is given
# the ``<SOS>`` token as its first input, and the last hidden state of the
# encoder as its first hidden state.
#
#

teacher_forcing_ratio = 0.5


def train(input_tensor, target_tensor, encoder, decoder, encoder_optimizer, decoder_optimizer, criterion, max_length=MAX_LENGTH):
    encoder_hidden = encoder.initHidden()

    encoder_optimizer.zero_grad()
    decoder_optimizer.zero_grad()

    input_length = input_tensor.size(0)
    target_length = target_tensor.size(0)

    encoder_outputs = torch.zeros(max_length, encoder.hidden_size, device=device)

    loss = 0

    for ei in range(input_length):
        encoder_output, encoder_hidden = encoder(
            input_tensor[ei], encoder_hidden)
        encoder_outputs[ei] = encoder_output[0, 0]

    decoder_input = torch.tensor([[SOS_token]], device=device)

    decoder_hidden = encoder_hidden

    use_teacher_forcing = True if random.random() < teacher_forcing_ratio else False

    if use_teacher_forcing:
        # Teacher forcing: Feed the target as the next input
        for di in range(target_length):
            decoder_output, decoder_hidden, decoder_attention = decoder(
                decoder_input, decoder_hidden, encoder_outputs)
            loss += criterion(decoder_output, target_tensor[di])
            decoder_input = target_tensor[di]  # Teacher forcing

    else:
        # Without teacher forcing: use its own predictions as the next input
        for di in range(target_length):
            decoder_output, decoder_hidden, decoder_attention = decoder(
                decoder_input, decoder_hidden, encoder_outputs)
            #topk(1) returns the top element as: values=tensor (topv), indices=tensor (topi)
            #only topi is used 
            topv, topi = decoder_output.topk(1)
            decoder_input = topi.squeeze().detach()  # detach from history as input

            loss += criterion(decoder_output, target_tensor[di])
            if decoder_input.item() == EOS_token:
                break

    loss.backward()

    encoder_optimizer.step()
    decoder_optimizer.step()

    return loss.item() / target_length


######################################################################
# This is a helper function to print time elapsed and estimated time
# remaining given the current time and progress %.
#

import time
import math


def asMinutes(s):
    m = math.floor(s / 60)
    s -= m * 60
    return '%dm %ds' % (m, s)


def timeSince(since, percent):
    now = time.time()
    s = now - since
    es = s / (percent)
    rs = es - s
    return '%s (- %s)' % (asMinutes(s), asMinutes(rs))


######################################################################
# The whole training process looks like this:
#
# -  Start a timer
# -  Initialize optimizers and criterion
# -  Create set of training pairs
# -  Start empty losses array for plotting
#
# Then we call ``train`` many times and occasionally print the progress (%
# of examples, time so far, estimated time) and average loss.
#

def trainEpoch(encoder, decoder, print_every=1000, plot_every=100, learning_rate=0.01):
    start = time.time()
    plot_losses = []
    print_loss_total = 0  # Reset every print_every
    plot_loss_total = 0  # Reset every plot_every

    encoder_optimizer = optim.SGD(encoder.parameters(), lr=learning_rate)
    decoder_optimizer = optim.SGD(decoder.parameters(), lr=learning_rate)
    criterion = nn.NLLLoss()

    for iter in range(1, len(pairs) + 1):
        training_pair = tensorsFromPair(pairs[iter - 1])
        input_tensor = training_pair[0]
        target_tensor = training_pair[1]

        loss = train(input_tensor, target_tensor, encoder,
                     decoder, encoder_optimizer, decoder_optimizer, criterion)
        print_loss_total += loss
        plot_loss_total += loss

        if iter % print_every == 0:
            print_loss_avg = print_loss_total / print_every
            print_loss_total = 0
            print('%s (%d %d%%) %.4f' % (timeSince(start, iter / (len(pairs) + 1)),
                                         iter, iter / (len(pairs) + 1) * 100, print_loss_avg))

        if iter % plot_every == 0:
            plot_loss_avg = plot_loss_total / plot_every
            plot_losses.append(plot_loss_avg)
            plot_loss_total = 0

    showPlot(plot_losses)


######################################################################
# Plotting results
# ----------------
#
# Plotting is done with matplotlib, using the array of loss values
# ``plot_losses`` saved while training.
#

import matplotlib.pyplot as plt
plt.switch_backend('agg')
import matplotlib.ticker as ticker
import numpy as np


def showPlot(points):
    plt.figure()
    fig, ax = plt.subplots()
    # this locator puts ticks at regular intervals
    loc = ticker.MultipleLocator(base=0.2)
    ax.yaxis.set_major_locator(loc)
    plt.plot(points)


######################################################################
# Evaluation
# ==========
#
# Evaluation is mostly the same as training, but there are no targets so
# we simply feed the decoder's predictions back to itself for each step.
# Every time it predicts a word we add it to the output string, and if it
# predicts the EOS token we stop there. We also store the decoder's
# attention outputs for display later.
#

def evaluate(encoder, decoder, sentence, max_length=MAX_LENGTH):
    with torch.no_grad():
        try:
            input_tensor = tensorFromSentence(input_lang, sentence)
        except KeyError:
            #print("Unknown input")
            return None,None

        #ENCODER

        input_length = input_tensor.size()[0]
        encoder_hidden = encoder.initHidden()

        encoder_outputs = torch.zeros(max_length, encoder.hidden_size, device=device)

        #encoding input sentence
        for ei in range(input_length):
            encoder_output, encoder_hidden = encoder(input_tensor[ei],
                                                     encoder_hidden)
            encoder_outputs[ei] += encoder_output[0, 0]

        #DECODER

        decoder_input = torch.tensor([[SOS_token]], device=device)  # SOS

        decoder_hidden = encoder_hidden

        decoded_words = []
        decoder_attentions = torch.zeros(max_length, max_length)

        #decoding state into output sentence
        for di in range(max_length):
            #call ATTNDecoder forward 
            decoder_output, decoder_hidden, decoder_attention = decoder(
                decoder_input, decoder_hidden, encoder_outputs)

            decoder_attentions[di] = decoder_attention.data
            #topk(1) returns the top element as: values=tensor (topv), indices=tensor (topi)
            #only topi is used 
            topv, topi = decoder_output.data.topk(1)
            if topi.item() == EOS_token:
                decoded_words.append('<EOS>')
                break
            else:
                decoded_words.append(output_lang.index2word[topi.item()])

            decoder_input = topi.squeeze().detach()

        return decoded_words, decoder_attentions[:di + 1]

def evaluateRandomly(encoder, decoder, n=10):
    for i in range(n):
        pair = random.choice(pairs)
        print('>', pair[0])
        print('=', pair[1])
        output_words, attentions = evaluate(encoder, decoder, pair[0])
        output_sentence = ' '.join(output_words)
        print('<', output_sentence)
        print('')


# execuatable stuff
print(sys.argv[1])

e2s = False
s2e = False
if sys.argv[1] == "e2s":
    #eng to spa
    e2s = True
    input_lang, output_lang, pairs = prepareData('English', 'Spanish')
elif sys.argv[1] == "s2e":
    #spa to eng
    s2e = True
    input_lang, output_lang, pairs = prepareData('Spanish', 'English')
else:
    print("please specify e2s or s2e")
    exit(1)

#eng to spa
#input_lang, output_lang, pairs = prepareData('English', 'Spanish')
#spa to eng
#input_lang, output_lang, pairs = prepareData('Spanish', 'English')
print(random.choice(pairs))

hidden_size = 512
# number of times trainEpoch(...) gets run
num_epochs = 5
# learning rates for each epoch
epoch_learning_rates = [0.01, 0.01, 0.001, 0.001, 0.001]

if __name__ == "__main__":
    encoder1 = EncoderRNN(input_lang.n_words, hidden_size).to(device)
    attn_decoder1 = AttnDecoderRNN(hidden_size, output_lang.n_words, dropout_p=0.1).to(device)
    for epoch in range(num_epochs):
    	print("Training epoch: " + str(epoch))
    	trainEpoch(encoder1, attn_decoder1, print_every=5000, learning_rate=epoch_learning_rates[epoch])
    print("Done with training! Enjoy your model(s) <3")
    torch.save(encoder1, "encoder-spa-eng-OpenSub.pt")
    torch.save(attn_decoder1, "decoder-spa-eng-OpenSub.pt")