Natural language processing in tensorflow

from tensorflow.keras.preprocessing.text import Tokenizer

sentences = [
    'i love my dog',
    'I, love my cat',
    'You love my dog!'
]

tokenizer = Tokenizer(num_words = 100)
tokenizer.fit_on_texts(sentences)
word_index = tokenizer.word_index
print(word_index)

{'love': 1, 'my': 2, 'i': 3, 'dog': 4, 'cat': 5, 'you': 6}

import tensorflow as tf
from tensorflow import keras

from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

sentences = [
    'I love my dog',
    'I love my cat',
    'You love my dog!',
    'Do you think my dog is amazing?'
]

tokenizer = Tokenizer(num_words = 100, oov_token="<OOV>")
tokenizer.fit_on_texts(sentences)
word_index = tokenizer.word_index

sequences = tokenizer.texts_to_sequences(sentences)

padded = pad_sequences(sequences, maxlen=5)
print("\nWord Index = " , word_index)
print("\nSequences = " , sequences)
print("\nPadded Sequences:")
print(padded)


# Try with words that the tokenizer wasn't fit to
test_data = [
    'i really love my dog',
    'my dog loves my manatee'
]

test_seq = tokenizer.texts_to_sequences(test_data)
print("\nTest Sequence = ", test_seq)

padded = pad_sequences(test_seq, maxlen=10)
print("\nPadded Test Sequence: ")
print(padded)

Word Index =  {'<OOV>': 1, 'my': 2, 'love': 3, 'dog': 4, 'i': 5, 'you': 6, 'cat': 7, 'do': 8, 'think': 9, 'is': 10, 'amazing': 11}

Sequences =  [[5, 3, 2, 4], [5, 3, 2, 7], [6, 3, 2, 4], [8, 6, 9, 2, 4, 10, 11]]

Padded Sequences:
[[ 0  5  3  2  4]
 [ 0  5  3  2  7]
 [ 0  6  3  2  4]
 [ 9  2  4 10 11]]

Test Sequence =  [[5, 1, 3, 2, 4], [2, 4, 1, 2, 1]]

Padded Test Sequence: 
[[0 0 0 0 0 5 1 3 2 4]
 [0 0 0 0 0 2 4 1 2 1]]

!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/sarcasm.json \
    -O /tmp/sarcasm.json
  
import json

with open("/tmp/sarcasm.json", 'r') as f:
    datastore = json.load(f)


sentences = [] 
labels = []
urls = []
for item in datastore:
    sentences.append(item['headline'])
    labels.append(item['is_sarcastic'])
    urls.append(item['article_link'])



from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
tokenizer = Tokenizer(oov_token="<OOV>")
tokenizer.fit_on_texts(sentences)

word_index = tokenizer.word_index
print(len(word_index))
print(word_index)
sequences = tokenizer.texts_to_sequences(sentences)
padded = pad_sequences(sequences, padding='post')
print(padded[0])
print(padded.shape)

29657
{'<OOV>': 1, 'to': 2, 'of': 3, 'the': 4, 'in': 5, 'for': 6, 'a': 7, 'on': 8, 'and': 9, 'with': 10, 'is': 11, 'new': 12, 'trump': 13, 'man': 14, 'from': 15, 'at': 16, 'about': 17, 'you': 18, 'this': 19, 'by': 20, 'after': 21, ........."writin'": 29647, "'easy": 29648, 'drywall': 29649, 'blowhole': 29650, "zimbabwe's": 29651, 'gonzalez': 29652, 'breached': 29653, "'basic'": 29654, 'hikes': 29655, 'gourmet': 29656, 'foodie': 29657}  #Too long, results truncated.
[  308 15115   679  3337  2298    48   382  2576 15116     6  2577  8434
     0     0     0     0     0     0     0     0     0     0     0     0
     0     0     0     0     0     0     0     0     0     0     0     0
     0     0     0     0]
(26709, 40)

!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/bbc-text.csv \
    -O /tmp/bbc-text.csv
    
import csv
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

#Stopwords list from https://github.com/Yoast/YoastSEO.js/blob/develop/src/config/stopwords.js
stopwords = [ "a", "about", "above", "after", "again", "against", "all", "am", "an", "and", "any", "are", "as", "at", "be", "because", "been", "before", "being", "below", "between", "both", "but", "by", "could", "did", "do", "does", "doing", "down", "during", "each", "few", "for", "from", "further", "had", "has", "have", "having", "he", "he'd", "he'll", "he's", "her", "here", "here's", "hers", "herself", "him", "himself", "his", "how", "how's", "i", "i'd", "i'll", "i'm", "i've", "if", "in", "into", "is", "it", "it's", "its", "itself", "let's", "me", "more", "most", "my", "myself", "nor", "of", "on", "once", "only", "or", "other", "ought", "our", "ours", "ourselves", "out", "over", "own", "same", "she", "she'd", "she'll", "she's", "should", "so", "some", "such", "than", "that", "that's", "the", "their", "theirs", "them", "themselves", "then", "there", "there's", "these", "they", "they'd", "they'll", "they're", "they've", "this", "those", "through", "to", "too", "under", "until", "up", "very", "was", "we", "we'd", "we'll", "we're", "we've", "were", "what", "what's", "when", "when's", "where", "where's", "which", "while", "who", "who's", "whom", "why", "why's", "with", "would", "you", "you'd", "you'll", "you're", "you've", "your", "yours", "yourself", "yourselves" ]

sentences = []
labels = []
with open("/tmp/bbc-text.csv", 'r') as csvfile:
    reader = csv.reader(csvfile, delimiter=',')
    next(reader)
    for row in reader:
        labels.append(row[0])
        sentence = row[1]
        for word in stopwords:
            token = " " + word + " "
            sentence = sentence.replace(token, " ")
            sentence = sentence.replace("  ", " ")
        sentences.append(sentence)


print(len(sentences))
print(sentences[0])

tokenizer = Tokenizer(oov_token="<OOV>")
tokenizer.fit_on_texts(sentences)
word_index = tokenizer.word_index
print(len(word_index))

sequences = tokenizer.texts_to_sequences(sentences)
padded = pad_sequences(sequences, padding='post')
print(padded[0])
print(padded.shape)

label_tokenizer = Tokenizer()
label_tokenizer.fit_on_texts(labels)
label_word_index = label_tokenizer.word_index
label_seq = label_tokenizer.texts_to_sequences(labels)
print(label_seq)
print(label_word_index)

import tensorflow as tf
print(tf.__version__)

# !pip install -q tensorflow-datasets

import tensorflow_datasets as tfds
imdb, info = tfds.load("imdb_reviews", with_info=True, as_supervised=True)

import numpy as np

train_data, test_data = imdb['train'], imdb['test']

training_sentences = []
training_labels = []

testing_sentences = []
testing_labels = []

# str(s.tonumpy()) is needed in Python3 instead of just s.numpy()
for s,l in train_data:
  training_sentences.append(s.numpy().decode('utf8'))
  training_labels.append(l.numpy())
  
for s,l in test_data:
  testing_sentences.append(s.numpy().decode('utf8'))
  testing_labels.append(l.numpy())
  
training_labels_final = np.array(training_labels)
testing_labels_final = np.array(testing_labels)

vocab_size = 10000
embedding_dim = 16
max_length = 120
trunc_type='post'
oov_tok = "<OOV>"


from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

tokenizer = Tokenizer(num_words = vocab_size, oov_token=oov_tok)
tokenizer.fit_on_texts(training_sentences)
word_index = tokenizer.word_index
sequences = tokenizer.texts_to_sequences(training_sentences)
padded = pad_sequences(sequences,maxlen=max_length, truncating=trunc_type)

testing_sequences = tokenizer.texts_to_sequences(testing_sentences)
testing_padded = pad_sequences(testing_sequences,maxlen=max_length)

reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])

def decode_review(text):
    return ' '.join([reverse_word_index.get(i, '?') for i in text])

print(decode_review(padded[3]))
print(training_sentences[3])

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(6, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
model.summary()

num_epochs = 10
model.fit(padded, training_labels_final, epochs=num_epochs, validation_data=(testing_padded, testing_labels_final))

e = model.layers[0]
weights = e.get_weights()[0]
print(weights.shape) # shape: (vocab_size, embedding_dim)

import io

out_v = io.open('vecs.tsv', 'w', encoding='utf-8')
out_m = io.open('meta.tsv', 'w', encoding='utf-8')
for word_num in range(1, vocab_size):
  word = reverse_word_index[word_num]
  embeddings = weights[word_num]
  out_m.write(word + "\n")
  out_v.write('\t'.join([str(x) for x in embeddings]) + "\n")
out_v.close()
out_m.close()

try:
  from google.colab import files
except ImportError:
  pass
else:
  files.download('vecs.tsv')
  files.download('meta.tsv')
  
sentence = "I really think this is amazing. honest."
sequence = tokenizer.texts_to_sequences([sentence])
print(sequence)

"""Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/github/lmoroney/dlaicourse/blob/master/TensorFlow%20In%20Practice/Course%203%20-%20NLP/Course%203%20-%20Week%202%20-%20Lesson%202.ipynb
"""

#@title Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""<a href="https://colab.research.google.com/github/lmoroney/dlaicourse/blob/master/TensorFlow%20In%20Practice/Course%203%20-%20NLP/Course%203%20-%20Week%202%20-%20Lesson%202.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>"""

# Commented out IPython magic to ensure Python compatibility.
# Run this to ensure TensorFlow 2.x is used
try:
  # %tensorflow_version only exists in Colab.
#   %tensorflow_version 2.x
except Exception:
  pass

import json
import tensorflow as tf

from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

vocab_size = 10000
embedding_dim = 16
max_length = 100
trunc_type='post'
padding_type='post'
oov_tok = "<OOV>"
training_size = 20000

!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/sarcasm.json \
    -O /tmp/sarcasm.json

with open("/tmp/sarcasm.json", 'r') as f:
    datastore = json.load(f)

sentences = []
labels = []

for item in datastore:
    sentences.append(item['headline'])
    labels.append(item['is_sarcastic'])

training_sentences = sentences[0:training_size]
testing_sentences = sentences[training_size:]
training_labels = labels[0:training_size]
testing_labels = labels[training_size:]

tokenizer = Tokenizer(num_words=vocab_size, oov_token=oov_tok)
tokenizer.fit_on_texts(training_sentences)

word_index = tokenizer.word_index

training_sequences = tokenizer.texts_to_sequences(training_sentences)
training_padded = pad_sequences(training_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

testing_sequences = tokenizer.texts_to_sequences(testing_sentences)
testing_padded = pad_sequences(testing_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

# Need this block to get it to work with TensorFlow 2.x
import numpy as np
training_padded = np.array(training_padded)
training_labels = np.array(training_labels)
testing_padded = np.array(testing_padded)
testing_labels = np.array(testing_labels)

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),
    tf.keras.layers.GlobalAveragePooling1D(),
    tf.keras.layers.Dense(24, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])

model.summary()

num_epochs = 30
history = model.fit(training_padded, training_labels, epochs=num_epochs, validation_data=(testing_padded, testing_labels), verbose=2)

import matplotlib.pyplot as plt


def plot_graphs(history, string):
  plt.plot(history.history[string])
  plt.plot(history.history['val_'+string])
  plt.xlabel("Epochs")
  plt.ylabel(string)
  plt.legend([string, 'val_'+string])
  plt.show()
  
plot_graphs(history, "accuracy")
plot_graphs(history, "loss")

reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])

def decode_sentence(text):
    return ' '.join([reverse_word_index.get(i, '?') for i in text])

print(decode_sentence(training_padded[0]))
print(training_sentences[2])
print(labels[2])

e = model.layers[0]
weights = e.get_weights()[0]
print(weights.shape) # shape: (vocab_size, embedding_dim)

import io

out_v = io.open('vecs.tsv', 'w', encoding='utf-8')
out_m = io.open('meta.tsv', 'w', encoding='utf-8')
for word_num in range(1, vocab_size):
  word = reverse_word_index[word_num]
  embeddings = weights[word_num]
  out_m.write(word + "\n")
  out_v.write('\t'.join([str(x) for x in embeddings]) + "\n")
out_v.close()
out_m.close()

try:
  from google.colab import files
except ImportError:
  pass
else:
  files.download('vecs.tsv')
  files.download('meta.tsv')

sentence = ["granny starting to fear spiders in the garden might be real", "game of thrones season finale showing this sunday night"]
sequences = tokenizer.texts_to_sequences(sentence)
padded = pad_sequences(sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)
print(model.predict(padded))

# -*- coding: utf-8 -*-
"""Course 3 - Week 2 - Lesson 3.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/github/lmoroney/dlaicourse/blob/master/TensorFlow%20In%20Practice/Course%203%20-%20NLP/Course%203%20-%20Week%202%20-%20Lesson%203.ipynb
"""

#@title Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""<a href="https://colab.research.google.com/github/lmoroney/dlaicourse/blob/master/TensorFlow%20In%20Practice/Course%203%20-%20NLP/Course%203%20-%20Week%202%20-%20Lesson%203.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>"""

# NOTE: PLEASE MAKE SURE YOU ARE RUNNING THIS IN A PYTHON3 ENVIRONMENT

import tensorflow as tf
print(tf.__version__)

# Double check TF 2.0x is installed. If you ran the above block, there was a 
# 'reset all runtimes' button at the bottom that you needed to press
import tensorflow as tf
print(tf.__version__)

# If the import fails, run this
# !pip install -q tensorflow-datasets

import tensorflow_datasets as tfds
imdb, info = tfds.load("imdb_reviews/subwords8k", with_info=True, as_supervised=True)

train_data, test_data = imdb['train'], imdb['test']

tokenizer = info.features['text'].encoder

print(tokenizer.subwords)

sample_string = 'TensorFlow, from basics to mastery'

tokenized_string = tokenizer.encode(sample_string)
print ('Tokenized string is {}'.format(tokenized_string))

original_string = tokenizer.decode(tokenized_string)
print ('The original string: {}'.format(original_string))

for ts in tokenized_string:
  print ('{} ----> {}'.format(ts, tokenizer.decode([ts])))

BUFFER_SIZE = 10000
BATCH_SIZE = 64

train_dataset = train_data.shuffle(BUFFER_SIZE)
train_dataset = train_dataset.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(train_dataset))
test_dataset = test_data.padded_batch(BATCH_SIZE, tf.compat.v1.data.get_output_shapes(test_data))

embedding_dim = 64
model = tf.keras.Sequential([
    tf.keras.layers.Embedding(tokenizer.vocab_size, embedding_dim),
    tf.keras.layers.GlobalAveragePooling1D(),
    tf.keras.layers.Dense(6, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.summary()

num_epochs = 10

model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])

history = model.fit(train_dataset, epochs=num_epochs, validation_data=test_dataset)

import matplotlib.pyplot as plt


def plot_graphs(history, string):
  plt.plot(history.history[string])
  plt.plot(history.history['val_'+string])
  plt.xlabel("Epochs")
  plt.ylabel(string)
  plt.legend([string, 'val_'+string])
  plt.show()
  
plot_graphs(history, "accuracy")
plot_graphs(history, "loss")

e = model.layers[0]
weights = e.get_weights()[0]
print(weights.shape) # shape: (vocab_size, embedding_dim)

import io

out_v = io.open('vecs.tsv', 'w', encoding='utf-8')
out_m = io.open('meta.tsv', 'w', encoding='utf-8')
for word_num in range(1, tokenizer.vocab_size):
  word = tokenizer.decode([word_num])
  embeddings = weights[word_num]
  out_m.write(word + "\n")
  out_v.write('\t'.join([str(x) for x in embeddings]) + "\n")
out_v.close()
out_m.close()


try:
  from google.colab import files
except ImportError:
  pass
else:
  files.download('vecs.tsv')
  files.download('meta.tsv')

# -*- coding: utf-8 -*-
"""Course 3 - Week 2 - Exercise - Question.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/github/lmoroney/dlaicourse/blob/master/TensorFlow%20In%20Practice/Course%203%20-%20NLP/Course%203%20-%20Week%202%20-%20Exercise%20-%20Question.ipynb
"""

#@title Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""<a href="https://colab.research.google.com/github/lmoroney/dlaicourse/blob/master/TensorFlow%20In%20Practice/Course%203%20-%20NLP/Course%203%20-%20Week%202%20-%20Exercise%20-%20Question.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>"""

import csv
import tensorflow as tf
import numpy as np
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences

!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/bbc-text.csv \
    -O /tmp/bbc-text.csv

vocab_size =10000  # YOUR CODE HERE
embedding_dim = 16 # YOUR CODE HERE
max_length = 120 # YOUR CODE HERE
trunc_type = 'post' # YOUR CODE HERE
padding_type = 'post'# YOUR CODE HERE
oov_tok = "<OOV>" # YOUR CODE HERE
training_portion = .8

sentences = []
labels = []
stopwords = [ "a", "about", "above", "after", "again", "against", "all", "am", "an", "and", "any", "are", "as", "at", "be", "because", "been", "before", "being", "below", "between", "both", "but", "by", "could", "did", "do", "does", "doing", "down", "during", "each", "few", "for", "from", "further", "had", "has", "have", "having", "he", "he'd", "he'll", "he's", "her", "here", "here's", "hers", "herself", "him", "himself", "his", "how", "how's", "i", "i'd", "i'll", "i'm", "i've", "if", "in", "into", "is", "it", "it's", "its", "itself", "let's", "me", "more", "most", "my", "myself", "nor", "of", "on", "once", "only", "or", "other", "ought", "our", "ours", "ourselves", "out", "over", "own", "same", "she", "she'd", "she'll", "she's", "should", "so", "some", "such", "than", "that", "that's", "the", "their", "theirs", "them", "themselves", "then", "there", "there's", "these", "they", "they'd", "they'll", "they're", "they've", "this", "those", "through", "to", "too", "under", "until", "up", "very", "was", "we", "we'd", "we'll", "we're", "we've", "were", "what", "what's", "when", "when's", "where", "where's", "which", "while", "who", "who's", "whom", "why", "why's", "with", "would", "you", "you'd", "you'll", "you're", "you've", "your", "yours", "yourself", "yourselves" ]
print(len(stopwords))
# Expected Output
# 153

with open("/tmp/bbc-text.csv", 'r') as csvfile:
    reader = csv.reader(csvfile, delimiter=',')
    next(reader)
    for row in reader:
        labels.append(row[0])
        sentence = row[1]
        for word in stopwords:
            token = " " + word + " "
            sentence = sentence.replace(token, " ")
            sentence = sentence.replace("  ", " ")
        sentences.append(sentence)


    
print(len(labels))
print(len(sentences))
print(sentences[0])
# Expected Output
# 2225
# 2225
# tv future hands viewers home theatre systems  plasma high-definition tvs  digital video recorders moving living room  way people watch tv will radically different five years  time.  according expert panel gathered annual consumer electronics show las vegas discuss new technologies will impact one favourite pastimes. us leading trend  programmes content will delivered viewers via home networks  cable  satellite  telecoms companies  broadband service providers front rooms portable devices.  one talked-about technologies ces digital personal video recorders (dvr pvr). set-top boxes  like us s tivo uk s sky+ system  allow people record  store  play  pause forward wind tv programmes want.  essentially  technology allows much personalised tv. also built-in high-definition tv sets  big business japan us  slower take off europe lack high-definition programming. not can people forward wind adverts  can also forget abiding network channel schedules  putting together a-la-carte entertainment. us networks cable satellite companies worried means terms advertising revenues well  brand identity  viewer loyalty channels. although us leads technology moment  also concern raised europe  particularly growing uptake services like sky+.  happens today  will see nine months years  time uk   adam hume  bbc broadcast s futurologist told bbc news website. likes bbc  no issues lost advertising revenue yet. pressing issue moment commercial uk broadcasters  brand loyalty important everyone.  will talking content brands rather network brands   said tim hanlon  brand communications firm starcom mediavest.  reality broadband connections  anybody can producer content.  added:  challenge now hard promote programme much choice.   means  said stacey jolna  senior vice president tv guide tv group  way people find content want watch simplified tv viewers. means networks  us terms  channels take leaf google s book search engine future  instead scheduler help people find want watch. kind channel model might work younger ipod generation used taking control gadgets play them. might not suit everyone  panel recognised. older generations comfortable familiar schedules channel brands know getting. perhaps not want much choice put hands  mr hanlon suggested.  end  kids just diapers pushing buttons already - everything possible available   said mr hanlon.  ultimately  consumer will tell market want.   50 000 new gadgets technologies showcased ces  many enhancing tv-watching experience. high-definition tv sets everywhere many new models lcd (liquid crystal display) tvs launched dvr capability built  instead external boxes. one example launched show humax s 26-inch lcd tv 80-hour tivo dvr dvd recorder. one us s biggest satellite tv companies  directtv  even launched branded dvr show 100-hours recording capability  instant replay  search function. set can pause rewind tv 90 hours. microsoft chief bill gates announced pre-show keynote speech partnership tivo  called tivotogo  means people can play recorded programmes windows pcs mobile devices. reflect increasing trend freeing multimedia people can watch want  want.

train_size = int(len(labels) * training_portion)

train_sentences = sentences[0:train_size]
train_labels = labels[0:train_size]

validation_sentences = sentences[train_size:]
validation_labels = labels[train_size:]

print(train_size)
print(len(train_sentences))
print(len(train_labels))
print(len(validation_sentences))
print(len(validation_labels))

# Expected output (if training_portion=.8)
# 1780
# 1780
# 1780
# 445
# 445

tokenizer = Tokenizer(num_words=vocab_size, oov_token=oov_tok)
tokenizer.fit_on_texts(train_sentences)
word_index = tokenizer.word_index

train_sequences = tokenizer.texts_to_sequences(train_sentences)
train_padded = pad_sequences(train_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

print(len(train_sequences[0]))
print(len(train_padded[0]))

print(len(train_sequences[1]))
print(len(train_padded[1]))

print(len(train_sequences[10]))
print(len(train_padded[10]))

# Expected Ouput
# 449
# 120
# 200
# 120
# 192
# 120

validation_sequences = tokenizer.texts_to_sequences(validation_sentences)
validation_padded = pad_sequences(validation_sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

print(len(validation_sequences))
print(validation_padded.shape)

# Expected output
# 445
# (445, 120)

import numpy as np
label_tokenizer = Tokenizer()
label_tokenizer.fit_on_texts(labels)

training_label_seq = np.array(label_tokenizer.texts_to_sequences(train_labels))
validation_label_seq = np.array(label_tokenizer.texts_to_sequences(validation_labels))

print(training_label_seq[0])
print(training_label_seq[1])
print(training_label_seq[2])
print(training_label_seq.shape)

print(validation_label_seq[0])
print(validation_label_seq[1])
print(validation_label_seq[2])
print(validation_label_seq.shape)

# Expected output
# [4]
# [2]
# [1]
# (1780, 1)
# [5]
# [4]
# [3]
# (445, 1)

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),
    tf.keras.layers.GlobalAveragePooling1D(),
    tf.keras.layers.Dense(24, activation='relu'),
    tf.keras.layers.Dense(6, activation='sigmoid')
])
model.compile(loss='sparse_categorical_crossentropy',optimizer='adam',metrics=['accuracy'])
model.summary()

# Expected Output
# Layer (type)                 Output Shape              Param #   
# =================================================================
# embedding (Embedding)        (None, 120, 16)           16000     
# _________________________________________________________________
# global_average_pooling1d (Gl (None, 16)                0         
# _________________________________________________________________
# dense (Dense)                (None, 24)                408       
# _________________________________________________________________
# dense_1 (Dense)              (None, 6)                 150       
# =================================================================
# Total params: 16,558
# Trainable params: 16,558
# Non-trainable params: 0

num_epochs = 30
history = model.fit(train_padded, training_label_seq, epochs=num_epochs, validation_data=(validation_padded, validation_label_seq), verbose=2)

import matplotlib.pyplot as plt


def plot_graphs(history, string):
  plt.plot(history.history[string])
  plt.plot(history.history['val_'+string])
  plt.xlabel("Epochs")
  plt.ylabel(string)
  plt.legend([string, 'val_'+string])
  plt.show()
  
plot_graphs(history, "accuracy")
plot_graphs(history, "loss")

reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])

def decode_sentence(text):
    return ' '.join([reverse_word_index.get(i, '?') for i in text])

e = model.layers[0]
weights = e.get_weights()[0]
print(weights.shape) # shape: (vocab_size, embedding_dim)

# Expected output
# (1000, 16)

import io

out_v = io.open('vecs.tsv', 'w', encoding='utf-8')
out_m = io.open('meta.tsv', 'w', encoding='utf-8')
for word_num in range(1, vocab_size):
  word = reverse_word_index[word_num]
  embeddings = weights[word_num]
  out_m.write(word + "\n")
  out_v.write('\t'.join([str(x) for x in embeddings]) + "\n")
out_v.close()
out_m.close()

try:
  from google.colab import files
except ImportError:
  pass
else:
  files.download('vecs.tsv')
  files.download('meta.tsv')