util_model.py

from __future__ import unicode_literals, print_function, division
from smutil import *
from io import open
import unicodedata
import string
import re
import random
import os

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


SOS_token = 0
EOS_token = 1
MAX_LENGTH = 10


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


# Turn a Unicode string to plain ASCII, thanks to
# http://stackoverflow.com/a/518232/2809427
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


def readLangs(lang1, lang2, dirData, reverse=False):
    print("Reading lines...")

    # Read the file and split into lines
    lines = (
        open(dirData + "/%s-%s.txt" % (lang1, lang2), encoding="utf-8")
        .read()
        .strip()
        .split("\n")
    )

    # Split every line into pairs and normalize
    pairs = [[normalizeString(s) for s in l.split("\t")] for l in lines]

    # Reverse pairs, make Lang instances
    if reverse:
        pairs = [list(reversed(p)) for p in pairs]
        input_lang = Lang(lang2)
        output_lang = Lang(lang1)
    else:
        input_lang = Lang(lang1)
        output_lang = Lang(lang2)

    return input_lang, output_lang, pairs


eng_prefixes = (
    "i am ",
    "i m ",
    "he is",
    "he s ",
    "she is",
    "she s",
    "you are",
    "you re ",
    "we are",
    "we re ",
    "they are",
    "they re ",
)


def filterPair(p):
    return (
        len(p[0].split(" ")) < MAX_LENGTH
        and len(p[1].split(" ")) < MAX_LENGTH
        and p[1].startswith(eng_prefixes)
    )


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


def prepareData(lang1, lang2, dirData, reverse=False):
    input_lang, output_lang, pairs = readLangs(lang1, lang2, dirData, reverse)
    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


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


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


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


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

        self.embedding = nn.Embedding(input_size, hidden_size)
        self.gru = 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)
        return output, hidden

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


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.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 = self.softmax(self.out(output[0]))
        return output, hidden

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


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.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 = 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)