In [1]:
import glob
import unicodedata
import string

def findFiles(path): return glob.glob(path)

print(findFiles('data/names/*.txt'))

all_letters = string.ascii_letters + " .,;'"
n_letters = len(all_letters)

# 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'
        and c in all_letters
    )

print(unicodeToAscii('Ślusàrski'))

# Build the category_lines dictionary, a list of names per language
category_lines = {}
all_categories = []

# Read a file and split into lines
def readLines(filename):
    lines = open(filename, encoding='utf-8').read().strip().split('\n')
    return [unicodeToAscii(line) for line in lines]

for filename in findFiles('data/names/*.txt'):
    category = filename.split('/')[-1].split('.')[0]
    all_categories.append(category)
    lines = readLines(filename)
    category_lines[category] = lines

n_categories = len(all_categories)
print(n_categories)


['data/names/Czech.txt', 'data/names/German.txt', 'data/names/Arabic.txt', 'data/names/Japanese.txt', 'data/names/Chinese.txt', 'data/names/Vietnamese.txt', 'data/names/Russian.txt', 'data/names/French.txt', 'data/names/Irish.txt', 'data/names/English.txt', 'data/names/Spanish.txt', 'data/names/Greek.txt', 'data/names/Italian.txt', 'data/names/Portuguese.txt', 'data/names/Scottish.txt', 'data/names/Dutch.txt', 'data/names/Korean.txt', 'data/names/Polish.txt']
Slusarski
18

In [2]:
import torch

# Find letter index from all_letters, e.g. "a" = 0
def letterToIndex(letter):
    return all_letters.find(letter)

# Just for demonstration, turn a letter into a <1 x n_letters> Tensor
def letterToTensor(letter):
    tensor = torch.zeros(1, n_letters)
    tensor[0][letterToIndex(letter)] = 1
    return tensor

# Turn a line into a <line_length x 1 x n_letters>,
# or an array of one-hot letter vectors
def lineToTensor(line):
    tensor = torch.zeros(len(line), 1, n_letters)
    for li, letter in enumerate(line):
        tensor[li][0][letterToIndex(letter)] = 1
    return tensor

print(letterToTensor('J'))

print(lineToTensor('Jones').size())



Columns 0 to 12 
    0     0     0     0     0     0     0     0     0     0     0     0     0

Columns 13 to 25 
    0     0     0     0     0     0     0     0     0     0     0     0     0

Columns 26 to 38 
    0     0     0     0     0     0     0     0     0     1     0     0     0

Columns 39 to 51 
    0     0     0     0     0     0     0     0     0     0     0     0     0

Columns 52 to 56 
    0     0     0     0     0
[torch.FloatTensor of size 1x57]

torch.Size([5, 1, 57])

In [3]:
import torch.nn as nn
from torch.autograd import Variable

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size
        self.i2h = nn.Linear(input_size + hidden_size, hidden_size)
        self.i2o = nn.Linear(input_size + hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)

    def forward(self, input, hidden):
        combined = torch.cat((input, hidden), 1)
        hidden = self.i2h(combined)
        output = self.i2o(combined)
        output = self.softmax(output)
        return output, hidden

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

n_hidden = 128
rnn = RNN(n_letters, n_hidden, n_categories)

In [5]:
input = Variable(lineToTensor('Albert'))
hidden = Variable(torch.zeros(1, n_hidden))

output, next_hidden = rnn(input[0], hidden)
print(output)


Variable containing:

Columns 0 to 9 
-2.8819 -2.8384 -2.8839 -2.8680 -2.9061 -2.9383 -2.9151 -2.7883 -2.9839 -2.8460

Columns 10 to 17 
-2.9795 -2.8679 -2.8784 -2.8306 -2.9763 -2.9056 -2.8571 -2.9056
[torch.FloatTensor of size 1x18]


In [6]:
def categoryFromOutput(output):
    top_n, top_i = output.data.topk(1) # Tensor out of Variable with .data
    category_i = top_i[0][0]
    return all_categories[category_i], category_i

print(categoryFromOutput(output))


('French', 7)

In [7]:
import random

def randomChoice(l):
    return l[random.randint(0, len(l) - 1)]

def randomTrainingExample():
    category = randomChoice(all_categories)
    line = randomChoice(category_lines[category])
    category_tensor = Variable(torch.LongTensor([all_categories.index(category)]))
    line_tensor = Variable(lineToTensor(line))
    return category, line, category_tensor, line_tensor

for i in range(10):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    print('category =', category, '/ line =', line)


category = Dutch / line = Teunissen
category = Chinese / line = Chew
category = Polish / line = Jaskolski
category = French / line = Albert
category = Irish / line = Murchadh
category = French / line = Degarmo
category = Italian / line = Genovese
category = Chinese / line = Chai
category = Irish / line = Cathan
category = German / line = Weigand

Training


In [9]:
criterion = nn.NLLLoss()
learning_rate = 0.005 # If you set this too high, it might explode. If too low, it might not learn

def train(category_tensor, line_tensor):
    hidden = rnn.initHidden()

    rnn.zero_grad()

    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)

    loss = criterion(output, category_tensor)
    loss.backward()

    # Add parameters' gradients to their values, multiplied by learning rate
    for p in rnn.parameters():
        p.data.add_(-learning_rate, p.grad.data)

    return output, loss.data[0]

In [10]:
import time
import math

n_iters = 100000
print_every = 5000
plot_every = 1000



# Keep track of losses for plotting
current_loss = 0
all_losses = []

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

start = time.time()

for iter in range(1, n_iters + 1):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output, loss = train(category_tensor, line_tensor)
    current_loss += loss

    # Print iter number, loss, name and guess
    if iter % print_every == 0:
        guess, guess_i = categoryFromOutput(output)
        correct = '✓' if guess == category else '✗ (%s)' % category
        print('%d %d%% (%s) %.4f %s / %s %s' % (iter, iter / n_iters * 100, timeSince(start), loss, line, guess, correct))

    # Add current loss avg to list of losses
    if iter % plot_every == 0:
        all_losses.append(current_loss / plot_every)
        current_loss = 0


5000 5% (0m 5s) 2.8540 Orritt / Japanese ✗ (English)
10000 10% (0m 9s) 2.2451 Borde / Portuguese ✗ (French)
15000 15% (0m 14s) 2.8439 Hardy / Spanish ✗ (French)
20000 20% (0m 19s) 3.5542 Lathan / Arabic ✗ (English)
25000 25% (0m 23s) 2.6605 Santos / Arabic ✗ (Portuguese)
30000 30% (0m 28s) 2.0455 Feldt / English ✗ (German)
35000 35% (0m 32s) 0.7162 Kaminski / Polish ✓
40000 40% (0m 37s) 1.4398 Reijnder / German ✗ (Dutch)
45000 45% (0m 41s) 3.3753 Pavlu / Spanish ✗ (Czech)
50000 50% (0m 46s) 0.3058 Okamoto / Japanese ✓
55000 55% (0m 51s) 3.1177 Del bosque / French ✗ (Spanish)
60000 60% (0m 55s) 0.3264 Kawachi / Japanese ✓
65000 65% (1m 0s) 0.5377 Tojo / Japanese ✓
70000 70% (1m 5s) 0.1211 Trieu / Vietnamese ✓
75000 75% (1m 9s) 1.2198 Wasem / Arabic ✓
80000 80% (1m 14s) 1.9996 Palomo / Japanese ✗ (Spanish)
85000 85% (1m 18s) 0.8518 Ho / Vietnamese ✓
90000 90% (1m 23s) 1.8049 Kim / Korean ✗ (Vietnamese)
95000 95% (1m 27s) 1.7311 Bureau / Spanish ✗ (French)
100000 100% (1m 32s) 1.7969 Sciarra / Portuguese ✗ (Italian)

In [14]:
%matplotlib inline
import matplotlib.pyplot as plt
import matplotlib.ticker as ticker

plt.figure()
plt.plot(all_losses)
plt.show()


Evaluating the Results


In [15]:
# Keep track of correct guesses in a confusion matrix
confusion = torch.zeros(n_categories, n_categories)
n_confusion = 10000

# Just return an output given a line
def evaluate(line_tensor):
    hidden = rnn.initHidden()

    for i in range(line_tensor.size()[0]):
        output, hidden = rnn(line_tensor[i], hidden)

    return output

# Go through a bunch of examples and record which are correctly guessed
for i in range(n_confusion):
    category, line, category_tensor, line_tensor = randomTrainingExample()
    output = evaluate(line_tensor)
    guess, guess_i = categoryFromOutput(output)
    category_i = all_categories.index(category)
    confusion[category_i][guess_i] += 1

# Normalize by dividing every row by its sum
for i in range(n_categories):
    confusion[i] = confusion[i] / confusion[i].sum()

# Set up plot
fig = plt.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(confusion.numpy())
fig.colorbar(cax)

# Set up axes
ax.set_xticklabels([''] + all_categories, rotation=90)
ax.set_yticklabels([''] + all_categories)

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

# sphinx_gallery_thumbnail_number = 2
plt.show()



In [ ]: