visualize.py

"""
Created on Thu Jan 24 22:40:05 2019

@author: vijay
"""


import matplotlib.pyplot as plt
plt.switch_backend('Tkagg')
import matplotlib.ticker as ticker
import numpy as np
import wordindex as wi
from wordindex import prepareData
import wordindex as wi
import random
import torch
import config as config


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")

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.
#
MAX_LENGTH = wi.MAX_LENGTH
SOS_token = wi.SOS_token
EOS_token = wi.EOS_token
def evaluate(encoder, decoder, sentence, max_length=MAX_LENGTH):
    with torch.no_grad():
        input_tensor = wi.tensorFromSentence(wi.input_lang, sentence)
        input_length = input_tensor.size()[0]
        encoder_hidden = encoder.initHidden()

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

        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)  # SOS

        decoder_hidden = encoder_hidden

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

        for di in range(max_length):
            decoder_output, decoder_hidden, decoder_attention = decoder(
                decoder_input, decoder_hidden, encoder_outputs)
            decoder_attentions[di] = decoder_attention.data
            topv, topi = decoder_output.data.topk(1)
            if topi.item() == EOS_token:
                decoded_words.append('<EOS>')
                break
            else:
                decoded_words.append(wi.output_lang.index2word[topi.item()])

            decoder_input = topi.squeeze().detach()

        return decoded_words, decoder_attentions[:di + 1]


######################################################################
# We can evaluate random sentences from the training set and print out the
# input, target, and output to make some subjective quality judgements:
#

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


######################################################################
# Training and Evaluating
# =======================
#
# With all these helper functions in place (it looks like extra work, but
# it makes it easier to run multiple experiments) we can actually
# initialize a network and start training.
#
# Remember that the input sentences were heavily filtered. For this small
# dataset we can use relatively small networks of 256 hidden nodes and a
# single GRU layer. After about 40 minutes on a MacBook CPU we'll get some
# reasonable results.
#
# .. Note::
#    If you run this notebook you can train, interrupt the kernel,
#    evaluate, and continue training later. Comment out the lines where the
#    encoder and decoder are initialized and run ``trainIters`` again.
#



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

evaluateRandomly(config.encoder1, config.attn_decoder1)


######################################################################
# Visualizing Attention
# ---------------------
#
# A useful property of the attention mechanism is its highly interpretable
# outputs. Because it is used to weight specific encoder outputs of the
# input sequence, we can imagine looking where the network is focused most
# at each time step.
#
# You could simply run ``plt.matshow(attentions)`` to see attention output
# displayed as a matrix, with the columns being input steps and rows being
# output steps:
#

output_words, attentions = evaluate(
    config.encoder1, config.attn_decoder1, "je suis trop froid .")
plt.matshow(attentions.numpy())


######################################################################
# For a better viewing experience we will do the extra work of adding axes
# and labels:
#

def showAttention(input_sentence, output_words, attentions):
    # Set up figure with colorbar
    fig = plt.figure()
    ax = fig.add_subplot(111)
    cax = ax.matshow(attentions.numpy(), cmap='bone')
    fig.colorbar(cax)

    # Set up axes
    ax.set_xticklabels([''] + input_sentence.split(' ') +
                       ['<EOS>'], rotation=90)
    ax.set_yticklabels([''] + output_words)

    # Show label at every tick
    ax.xaxis.set_major_locator(ticker.MultipleLocator(1))
    ax.yaxis.set_major_locator(ticker.MultipleLocator(1))

    plt.show()


def evaluateAndShowAttention(input_sentence):
    output_words, attentions = evaluate(
        config.encoder1, config.attn_decoder1, input_sentence)
    print('input =', input_sentence)
    print('output =', ' '.join(output_words))
    showAttention(input_sentence, output_words, attentions)


evaluateAndShowAttention("elle a cinq ans de moins que moi .")

evaluateAndShowAttention("elle est trop petit .")

evaluateAndShowAttention("je ne crains pas de mourir .")

evaluateAndShowAttention("c est un jeune directeur plein de talent .")