! wget http: // www.manythings.org / anki / fra - eng.zip

! unzip -q fra-eng.zip -d /content/french-eng

In [1]:

--2020-02-04 06:43:40-- http://www.manythings.org/anki/fra-eng.zip (http://www.manythings.org/anki/fra-eng.zip)

Resolving www.manythings.org (www.manythings.org). 104.24.109.196,

104.24.108.196, 2606:4700:3037::6818:6cc4, ...

Connecting to www.manythings.org (www.manythings.org)|104.24.109.196

|:80. connected.

HTTP request sent, awaiting response... 200 OK Length: 5939832 (5.7M) [application/zip] Saving to: ‘fra-eng.zip’

fra-eng.zip 100%[===================>] 5.66M 7.67MB/s i

n 0.7s

2020-02-04 06:43:41 (7.67 MB/s) - ‘fra-eng.zip’ saved [5939832/593983

2]

error: -fn or any combination of -c, -l, -p, -t, -u and -v options i nvalid

UnZip 6.00 of 20 April 2009, by Debian. Original by Info-ZIP.

Usage: unzip [-Z] [-opts[modifiers]] file[.zip] [list] [-x xlist] [-d exdir]

Default action is to extract files in list, except those in xlist, to exdir;

file[.zip] may be a wildcard. -Z => ZipInfo mode ("unzip -Z" for u sage).

-p extract files to pipe, no messages -l list files (short fo rmat)

-f freshen existing files, create none -t test compressed arch ive data

-u update files, create if necessary -z display archive comm ent only

-v list verbosely/show version info -T timestamp archive to latest

-x exclude files that follow (in xlist) -d extract files into e xdir

modifiers:

-n never overwrite existing files -q quiet mode (-qq => q uieter)

-o overwrite files WITHOUT prompting -a auto-convert any tex t files

-j junk paths (do not make directories) -aa treat ALL files as t ext

-U use escapes for all non-ASCII Unicode -UU ignore any Unicode f ields

-C match filenames case-insensitively -L make (some) names lo wercase

-X restore UID/GID info -V retain VMS version n umbers

-K keep setuid/setgid/tacky permissions -M pipe through "more" pager

-O CHARSET specify a character encoding for DOS, Windows and OS/2 archives

-I CHARSET specify a character encoding for UNIX and other archive

s

See "unzip -hh" or unzip.txt for more help. Examples:

unzip data1 -x joe => extract all files except joe from zipfile d ata1.zip

unzip -p foo | more => send contents of foo.zip via pipe into prog ram more

unzip -fo foo ReadMe => quietly replace existing ReadMe if archive file newer

#importing libraries

from   future import print_function

from keras.models import Model

from keras.layers import Input, LSTM, Dense

import numpy as np

In [2]:

batch_s = 64 # Batch size for training.

epochs = 100 # Number of epochs to train for.

latent_dimension = 256 # Latent dimensionality of the encoding space.

number_samples = 10000 # Number of samples to train on. # Path to the data txt file on disk.

data_path = '/content/french-eng/fra.txt'

In [0]:

In [0]:

# Vectorize the data. input_texts = [] target_texts = [] input_characters = set() target_characters = set()

with open(data_path, 'r', encoding='utf-8') as f: lines = f.read().split('\n')

for line in lines[: min(number_samples, len(lines) - 1)]: input_text, target_text, _ = line.split('\t')

# We use "tab" as the "start sequence" character

# for the targets, and "\n" as "end sequence" character. target_text = '\t' + target_text + '\n' input_texts.append(input_text) target_texts.append(target_text)

for char in input_text:

if char not in input_characters: input_characters.add(char)

for char in target_text:

if char not in target_characters: target_characters.add(char)

input_characters = sorted(list(input_characters)) target_characters = sorted( list(target_characters)) num_encoder_tokens = len(input_characters) num_decoder_tokens = len(target_characters)

max_encoder_seq_length = max([len(txt) for txt in input_texts]) max_decoder_seq_length = max([len(txt) for txt in target_texts])

print('Number of samples:', len(input_texts)) print( 'Number of unique input tokens:', num_encoder_tokens)

print('Number of unique output tokens:', num_decoder_tokens) print( 'Max sequence length for inputs:', max_encoder_seq_length) print('Max sequence length for outputs:', max_decoder_seq_length)

In [8]:

Number of samples: 10000

Number of unique input tokens: 70 Number of unique output tokens: 93 Max sequence length for inputs: 16 Max sequence length for outputs: 59

input_token_index = dict(

[(char, i) for i, char in enumerate(input_characters)]) target_token_index = dict(

[(char, i) for i, char in enumerate(target_characters)])

In [0]:

encoder_input_data = np.zeros(

(len(input_texts), max_encoder_seq_length, num_encoder_tokens), dtype='float32')

decoder_input_data = np.zeros(

(len(input_texts), max_decoder_seq_length, num_decoder_tokens), dtype='float32')

decoder_target_data = np.zeros(

(len(input_texts), max_decoder_seq_length, num_decoder_tokens), dtype='float32')

In [0]:

In [0]:

for i, (input_text, target_text) in enumerate(zip(input_texts, target_

for t, char in enumerate(input_text): encoder_input_data[i, t, input_token_index[char]] = 1.

encoder_input_data[i, t + 1:, input_token_index[' ']] = 1.

for t, char in enumerate(target_text):

# decoder_target_data is ahead of decoder_input_data by one ti

decoder_input_data[i, t, target_token_index[char]] = 1.

if t > 0:

# decoder_target_data will be ahead by one timestep # and will not include the start character.

decoder_target_data[i, t - 1, target_token_index[char]] = decoder_input_data[i, t + 1:, target_token_index[' ']] = 1. decoder_target_data[i, t:, target_token_index[' ']] = 1.

# Define an input sequence and process it. encoder_inputs = Input(shape=(None, num_encoder_tokens)) encoder = LSTM(latent_dimension, return_state=True)

encoder_outputs, state_h, state_c = encoder(encoder_inputs) # We discard `encoder_outputs` and only keep the states. encoder_states = [state_h, state_c]

In [12]:

decoder_inputs = Input(shape=(None, num_decoder_tokens)) # We set up our decoder to return full output sequences, # and to return internal states as well. We don't use the

# return states in the training model, but we will use them in inferen decoder_lstm = LSTM(latent_dimension, return_sequences=True, return_st decoder_outputs, _, _ = decoder_lstm(decoder_inputs,

initial_state=encoder_states) decoder_dense = Dense(num_decoder_tokens, activation='softmax') decoder_outputs = decoder_dense(decoder_outputs)

In [0]:

model = Model([encoder_inputs, decoder_inputs], decoder_outputs)

In [0]:

model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics =['accuracy'])

model.fit([encoder_input_data, decoder_input_data], decoder_target_dat batch_size=batch_s,

epochs=epochs, validation_split=0.2)

In [16]:

model.save('seq2seq.h5')

In [0]:

encoder_model = Model(encoder_inputs, encoder_states)

decoder_state_input_h = Input(shape=(latent_dim,)) decoder_state_input_c = Input(shape=(latent_dim,)) decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c] decoder_outputs, state_h, state_c = decoder_lstm(

decoder_inputs, initial_state=decoder_states_inputs) decoder_states = [state_h, state_c]

decoder_outputs = decoder_dense(decoder_outputs) decoder_model = Model(

[decoder_inputs] + decoder_states_inputs, [decoder_outputs] + decoder_states)

In [0]:

reverse_input_char_index = dict(

(i, char) for char, i in input_token_index.items()) reverse_target_char_index = dict(

(i, char) for char, i in target_token_index.items())

In [0]:

In [0]:

states_value = encoder_model.predict(input_seq)

target_seq = np.zeros((1, 1, num_decoder_tokens))

target_seq[0, 0, target_token_index['\t']] = 1.

stop_condition = False decoded_sentence = '' while not stop_condition:

output_tokens, h, c = decoder_model.predict( [target_seq] + states_value)

sampled_token_index = np.argmax(output_tokens[0, -1, :]) sampled_char = reverse_target_char_index[sampled_token_index] decoded_sentence += sampled_char

# Exit condition: either hit max length # or find stop character.

if (sampled_char == '\n' or

len(decoded_sentence) > max_decoder_seq_length): stop_condition = True

# Update the target sequence (of length 1). target_seq = np.zeros((1, 1, num_decoder_tokens)) target_seq[ 0, 0, sampled_token_index] = 1.

# Update states

states_value = [h, c]

for seq_index in range(100):

# Take one sequence (part of the training set) # for trying out decoding.

input_seq = encoder_input_data[seq_index: seq_index + 1] decoded_sentence = decode_sequence(input_seq)

print('-')

print('Input sentence:', input_texts[seq_index]) print( 'Decoded sentence:', decoded_sentence)

In [22]:

In [0]: