% tensorflow_version 2.x
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>')  # oov stands for out of vocabulary
tokenizer.fit_on_texts(sentences)
word_index = tokenizer.word_index

sequences = tokenizer.texts_to_sequences(sentences)

padded = pad_sequences(sequences, padding='post', maxlen=8)  #  padding='post' ==> padding after the sentence

print(word_index)
print(sequences)
print(padded)

test_data = [
             'I really love my dog',
             'My dog loves my manatees'
]
test_seq = tokenizer.texts_to_sequences(test_data)
print(test_seq)

!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)

% tensorflow_version 2.x

!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
# Convert it to a Python list and paste it here
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])

#Expected output
# 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.


tokenizer = Tokenizer(oov_token='<OOV>')
tokenizer.fit_on_texts(sentences)
word_index = tokenizer.word_index
print(word_index)
# Expected output
# 29714


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

# Expected output
# [  96  176 1158 ...    0    0    0]
# (2225, 2442)


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)

# Expected Output
# [[4], [2], [1], [1], [5], [3], [3], [1], [1], [5], [5], [2], [2], [3], [1], [2], [3], [1], [2], [4], [4], [4], [1], [1], [4], [1], [5], [4], [3], [5], [3], [4], [5], [5], [2], [3], [4], [5], [3], [2], [3], [1], [2], [1], [4], [5], [3], [3], [3], [2], [1], [3], [2], [2], [1], [3], [2], [1], [1], [2], [2], [1], [2], [1], [2], [4], [2], [5], [4], [2], [3], [2], [3], [1], [2], [4], [2], [1], [1], [2], [2], [1], [3], [2], [5], [3], [3], [2], [5], [2], [1], [1], [3], [1], [3], [1], [2], [1], [2], [5], [5], [1], [2], [3], [3], [4], [1], [5], [1], [4], [2], [5], [1], [5], [1], [5], [5], [3], [1], [1], [5], [3], [2], [4], [2], [2], [4], [1], [3], [1], [4], [5], [1], [2], [2], [4], [5], [4], [1], [2], [2], [2], [4], [1], [4], [2], [1], [5], [1], [4], [1], [4], [3], [2], [4], [5], [1], [2], [3], [2], [5], [3], [3], [5], [3], [2], [5], [3], [3], [5], [3], [1], [2], [3], [3], [2], [5], [1], [2], [2], [1], [4], [1], [4], [4], [1], [2], [1], [3], [5], [3], [2], [3], [2], [4], [3], [5], [3], [4], [2], [1], [2], [1], [4], [5], [2], [3], [3], [5], [1], [5], [3], [1], [5], [1], [1], [5], [1], [3], [3], [5], [4], [1], [3], [2], [5], [4], [1], [4], [1], [5], [3], [1], [5], [4], [2], [4], [2], [2], [4], [2], [1], [2], [1], [2], [1], [5], [2], [2], [5], [1], [1], [3], [4], [3], [3], [3], [4], [1], [4], [3], [2], [4], [5], [4], [1], [1], [2], [2], [3], [2], [4], [1], [5], [1], [3], [4], [5], [2], [1], [5], [1], [4], [3], [4], [2], [2], [3], [3], [1], [2], [4], [5], [3], [4], [2], [5], [1], [5], [1], [5], [3], [2], [1], [2], [1], [1], [5], [1], [3], [3], [2], [5], [4], [2], [1], [2], [5], [2], [2], [2], [3], [2], [3], [5], [5], [2], [1], [2], [3], [2], [4], [5], [2], [1], [1], [5], [2], [2], [3], [4], [5], [4], [3], [2], [1], [3], [2], [5], [4], [5], [4], [3], [1], [5], [2], [3], [2], [2], [3], [1], [4], [2], [2], [5], [5], [4], [1], [2], [5], [4], [4], [5], [5], [5], [3], [1], [3], [4], [2], [5], [3], [2], [5], [3], [3], [1], [1], [2], [3], [5], [2], [1], [2], [2], [1], [2], [3], [3], [3], [1], [4], [4], [2], [4], [1], [5], [2], [3], [2], [5], [2], [3], [5], [3], [2], [4], [2], [1], [1], [2], [1], [1], [5], [1], [1], [1], [4], [2], [2], [2], [3], [1], [1], [2], [4], [2], [3], [1], [3], [4], [2], [1], [5], [2], [3], [4], [2], [1], [2], [3], [2], [2], [1], [5], [4], [3], [4], [2], [1], [2], [5], [4], [4], [2], [1], [1], [5], [3], [3], [3], [1], [3], [4], [4], [5], [3], [4], [5], [2], [1], [1], [4], [2], [1], [1], [3], [1], [1], [2], [1], [5], [4], [3], [1], [3], [4], [2], [2], [2], [4], [2], [2], [1], [1], [1], [1], [2], [4], [5], [1], [1], [4], [2], [4], [5], [3], [1], [2], [3], [2], [4], [4], [3], [4], [2], [1], [2], [5], [1], [3], [5], [1], [1], [3], [4], [5], [4], [1], [3], [2], [5], [3], [2], [5], [1], [1], [4], [3], [5], [3], [5], [3], [4], [3], [5], [1], [2], [1], [5], [1], [5], [4], [2], [1], [3], [5], [3], [5], [5], [5], [3], [5], [4], [3], [4], [4], [1], [1], [4], [4], [1], [5], [5], [1], [4], [5], [1], [1], [4], [2], [3], [4], [2], [1], [5], [1], [5], [3], [4], [5], [5], [2], [5], [5], [1], [4], [4], [3], [1], [4], [1], [3], [3], [5], [4], [2], [4], [4], [4], [2], [3], [3], [1], [4], [2], [2], [5], [5], [1], [4], [2], [4], [5], [1], [4], [3], [4], [3], [2], [3], [3], [2], [1], [4], [1], [4], [3], [5], [4], [1], [5], [4], [1], [3], [5], [1], [4], [1], [1], [3], [5], [2], [3], [5], [2], [2], [4], [2], [5], [4], [1], [4], [3], [4], [3], [2], [3], [5], [1], [2], [2], [2], [5], [1], [2], [5], [5], [1], [5], [3], [3], [3], [1], [1], [1], [4], [3], [1], [3], [3], [4], [3], [1], [2], [5], [1], [2], [2], [4], [2], [5], [5], [5], [2], [5], [5], [3], [4], [2], [1], [4], [1], [1], [3], [2], [1], [4], [2], [1], [4], [1], [1], [5], [1], [2], [1], [2], [4], [3], [4], [2], [1], [1], [2], [2], [2], [2], [3], [1], [2], [4], [2], [1], [3], [2], [4], [2], [1], [2], [3], [5], [1], [2], [3], [2], [5], [2], [2], [2], [1], [3], [5], [1], [3], [1], [3], [3], [2], [2], [1], [4], [5], [1], [5], [2], [2], [2], [4], [1], [4], [3], [4], [4], [4], [1], [4], [4], [5], [5], [4], [1], [5], [4], [1], [1], [2], [5], [4], [2], [1], [2], [3], [2], [5], [4], [2], [3], [2], [4], [1], [2], [5], [2], [3], [1], [5], [3], [1], [2], [1], [3], [3], [1], [5], [5], [2], [2], [1], [4], [4], [1], [5], [4], [4], [2], [1], [5], [4], [1], [1], [2], [5], [2], [2], [2], [5], [1], [5], [4], [4], [4], [3], [4], [4], [5], [5], [1], [1], [3], [2], [5], [1], [3], [5], [4], [3], [4], [4], [2], [5], [3], [4], [3], [3], [1], [3], [3], [5], [4], [1], [3], [1], [5], [3], [2], [2], [3], [1], [1], [1], [5], [4], [4], [2], [5], [1], [3], [4], [3], [5], [4], [4], [2], [2], [1], [2], [2], [4], [3], [5], [2], [2], [2], [2], [2], [4], [1], [3], [4], [4], [2], [2], [5], [3], [5], [1], [4], [1], [5], [1], [4], [1], [2], [1], [3], [3], [5], [2], [1], [3], [3], [1], [5], [3], [2], [4], [1], [2], [2], [2], [5], [5], [4], [4], [2], [2], [5], [1], [2], [5], [4], [4], [2], [2], [1], [1], [1], [3], [3], [1], [3], [1], [2], [5], [1], [4], [5], [1], [1], [2], [2], [4], [4], [1], [5], [1], [5], [1], [5], [3], [5], [5], [4], [5], [2], [2], [3], [1], [3], [4], [2], [3], [1], [3], [1], [5], [1], [3], [1], [1], [4], [5], [1], [3], [1], [1], [2], [4], [5], [3], [4], [5], [3], [5], [3], [5], [5], [4], [5], [3], [5], [5], [4], [4], [1], [1], [5], [5], [4], [5], [3], [4], [5], [2], [4], [1], [2], [5], [5], [4], [5], [4], [2], [5], [1], [5], [2], [1], [2], [1], [3], [4], [5], [3], [2], [5], [5], [3], [2], [5], [1], [3], [1], [2], [2], [2], [2], [2], [5], [4], [1], [5], [5], [2], [1], [4], [4], [5], [1], [2], [3], [2], [3], [2], [2], [5], [3], [2], [2], [4], [3], [1], [4], [5], [3], [2], [2], [1], [5], [3], [4], [2], [2], [3], [2], [1], [5], [1], [5], [4], [3], [2], [2], [4], [2], [2], [1], [2], [4], [5], [3], [2], [3], [2], [1], [4], [2], [3], [5], [4], [2], [5], [1], [3], [3], [1], [3], [2], [4], [5], [1], [1], [4], [2], [1], [5], [4], [1], [3], [1], [2], [2], [2], [3], [5], [1], [3], [4], [2], [2], [4], [5], [5], [4], [4], [1], [1], [5], [4], [5], [1], [3], [4], [2], [1], [5], [2], [2], [5], [1], [2], [1], [4], [3], [3], [4], [5], [3], [5], [2], [2], [3], [1], [4], [1], [1], [1], [3], [2], [1], [2], [4], [1], [2], [2], [1], [3], [4], [1], [2], [4], [1], [1], [2], [2], [2], [2], [3], [5], [4], [2], [2], [1], [2], [5], [2], [5], [1], [3], [2], [2], [4], [5], [2], [2], [2], [3], [2], [3], [4], [5], [3], [5], [1], [4], [3], [2], [4], [1], [2], [2], [5], [4], [2], [2], [1], [1], [5], [1], [3], [1], [2], [1], [2], [3], [3], [2], [3], [4], [5], [1], [2], [5], [1], [3], [3], [4], [5], [2], [3], [3], [1], [4], [2], [1], [5], [1], [5], [1], [2], [1], [3], [5], [4], [2], [1], [3], [4], [1], [5], [2], [1], [5], [1], [4], [1], [4], [3], [1], [2], [5], [4], [4], [3], [4], [5], [4], [1], [2], [4], [2], [5], [1], [4], [3], [3], [3], [3], [5], [5], [5], [2], [3], [3], [1], [1], [4], [1], [3], [2], [2], [4], [1], [4], [2], [4], [3], [3], [1], [2], [3], [1], [2], [4], [2], [2], [5], [5], [1], [2], [4], [4], [3], [2], [3], [1], [5], [5], [3], [3], [2], [2], [4], [4], [1], [1], [3], [4], [1], [4], [2], [1], [2], [3], [1], [5], [2], [4], [3], [5], [4], [2], [1], [5], [4], [4], [5], [3], [4], [5], [1], [5], [1], [1], [1], [3], [4], [1], [2], [1], [1], [2], [4], [1], [2], [5], [3], [4], [1], [3], [4], [5], [3], [1], [3], [4], [2], [5], [1], [3], [2], [4], [4], [4], [3], [2], [1], [3], [5], [4], [5], [1], [4], [2], [3], [5], [4], [3], [1], [1], [2], [5], [2], [2], [3], [2], [2], [3], [4], [5], [3], [5], [5], [2], [3], [1], [3], [5], [1], [5], [3], [5], [5], [5], [2], [1], [3], [1], [5], [4], [4], [2], [3], [5], [2], [1], [2], [3], [3], [2], [1], [4], [4], [4], [2], [3], [3], [2], [1], [1], [5], [2], [1], [1], [3], [3], [3], [5], [3], [2], [4], [2], [3], [5], [5], [2], [1], [3], [5], [1], [5], [3], [3], [2], [3], [1], [5], [5], [4], [4], [4], [4], [3], [4], [2], [4], [1], [1], [5], [2], [4], [5], [2], [4], [1], [4], [5], [5], [3], [3], [1], [2], [2], [4], [5], [1], [3], [2], [4], [5], [3], [1], [5], [3], [3], [4], [1], [3], [2], [3], [5], [4], [1], [3], [5], [5], [2], [1], [4], [4], [1], [5], [4], [3], [4], [1], [3], [3], [1], [5], [1], [3], [1], [4], [5], [1], [5], [2], [2], [5], [5], [5], [4], [1], [2], [2], [3], [3], [2], [3], [5], [1], [1], [4], [3], [1], [2], [1], [2], [4], [1], [1], [2], [5], [1], [1], [4], [1], [2], [3], [2], [5], [4], [5], [3], [2], [5], [3], [5], [3], [3], [2], [1], [1], [1], [4], [4], [1], [3], [5], [4], [1], [5], [2], [5], [3], [2], [1], [4], [2], [1], [3], [2], [5], [5], [5], [3], [5], [3], [5], [1], [5], [1], [3], [3], [2], [3], [4], [1], [4], [1], [2], [3], [4], [5], [5], [3], [5], [3], [1], [1], [3], [2], [4], [1], [3], [3], [5], [1], [3], [3], [2], [4], [4], [2], [4], [1], [1], [2], [3], [2], [4], [1], [4], [3], [5], [1], [2], [1], [5], [4], [4], [1], [3], [1], [2], [1], [2], [1], [1], [5], [5], [2], [4], [4], [2], [4], [2], [2], [1], [1], [3], [1], [4], [1], [4], [1], [1], [2], [2], [4], [1], [2], [4], [4], [3], [1], [2], [5], [5], [4], [3], [1], [1], [4], [2], [4], [5], [5], [3], [3], [2], [5], [1], [5], [5], [2], [1], [3], [4], [2], [1], [5], [4], [3], [3], [1], [1], [2], [2], [2], [2], [2], [5], [2], [3], [3], [4], [4], [5], [3], [5], [2], [3], [1], [1], [2], [4], [2], [4], [1], [2], [2], [3], [1], [1], [3], [3], [5], [5], [3], [2], [3], [3], [2], [4], [3], [3], [3], [3], [3], [5], [5], [4], [3], [1], [3], [1], [4], [1], [1], [1], [5], [4], [5], [4], [1], [4], [1], [1], [5], [5], [2], [5], [5], [3], [2], [1], [4], [4], [3], [2], [1], [2], [5], [1], [3], [5], [1], [1], [2], [3], [4], [4], [2], [2], [1], [3], [5], [1], [1], [3], [5], [4], [1], [5], [2], [3], [1], [3], [4], [5], [1], [3], [2], [5], [3], [5], [3], [1], [3], [2], [2], [3], [2], [4], [1], [2], [5], [2], [1], [1], [5], [4], [3], [4], [3], [3], [1], [1], [1], [2], [4], [5], [2], [1], [2], [1], [2], [4], [2], [2], [2], [2], [1], [1], [1], [2], [2], [5], [2], [2], [2], [1], [1], [1], [4], [2], [1], [1], [1], [2], [5], [4], [4], [4], [3], [2], [2], [4], [2], [4], [1], [1], [3], [3], [3], [1], [1], [3], [3], [4], [2], [1], [1], [1], [1], [2], [1], [2], [2], [2], [2], [1], [3], [1], [4], [4], [1], [4], [2], [5], [2], [1], [2], [4], [4], [3], [5], [2], [5], [2], [4], [3], [5], [3], [5], [5], [4], [2], [4], [4], [2], [3], [1], [5], [2], [3], [5], [2], [4], [1], [4], [3], [1], [3], [2], [3], [3], [2], [2], [2], [4], [3], [2], [3], [2], [5], [3], [1], [3], [3], [1], [5], [4], [4], [2], [4], [1], [2], [2], [3], [1], [4], [4], [4], [1], [5], [1], [3], [2], [3], [3], [5], [4], [2], [4], [1], [5], [5], [1], [2], [5], [4], [4], [1], [5], [2], [3], [3], [3], [4], [4], [2], [3], [2], [3], [3], [5], [1], [4], [2], [4], [5], [4], [4], [1], [3], [1], [1], [3], [5], [5], [2], [3], [3], [1], [2], [2], [4], [2], [4], [4], [1], [2], [3], [1], [2], [2], [1], [4], [1], [4], [5], [1], [1], [5], [2], [4], [1], [1], [3], [4], [2], [3], [1], [1], [3], [5], [4], [4], [4], [2], [1], [5], [5], [4], [2], [3], [4], [1], [1], [4], [4], [3], [2], [1], [5], [5], [1], [5], [4], [4], [2], [2], [2], [1], [1], [4], [1], [2], [4], [2], [2], [1], [2], [3], [2], [2], [4], [2], [4], [3], [4], [5], [3], [4], [5], [1], [3], [5], [2], [4], [2], [4], [5], [4], [1], [2], [2], [3], [5], [3], [1]]
# {'sport': 1, 'business': 2, 'politics': 3, 'tech': 4, 'entertainment': 5}

%tensorflow_version 2.x
import tensorflow as tf
print(tf.__version__)

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(str(s.numpy()))
  training_labels.append(l.numpy())
  
for s,l in test_data:
  testing_sentences.append(str(s.numpy()))
  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()])
# change {'hello':1} to {1:'hello'}

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

print(decode_review(padded[1]))
print(training_sentences[1])

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(vocab_size, embedding_dim, input_length=max_length),
    tf.keras.layers.Flatten(),  # tf.keras.layers.GlobalAveragePooling1D()     quicker than flattern, but less accuracy than falltern
    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]  # embedding layer
weights = e.get_weights()[0]
print(weights.shape) # shape: (vocab_size, embedding_dim)  ==> (10000, 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')

%tensorflow_version 2.x

import tensorflow as tf
print(tf.__version__)

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 ('Vocabulary size: {}'.format(tokenizer.vocab_size)) # 8185

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))

# Expected Output:
# Tokenized string is [6307, 2327, 4043, 2120, 2, 48, 4249, 4429, 7, 2652, 8050]
# The original string: TensorFlow, from basics to mastery


for ts in tokenized_string:
  print ('{} ----> {}'.format(ts, tokenizer.decode([ts])))
  
# Expected Output:
# 6307 ----> Ten
# 2327 ----> sor
# 4043 ----> Fl
# 2120 ----> ow
# 2 ----> , 
# 48 ----> from 
# 4249 ----> basi
# 4429 ----> cs 
# 7 ----> to 
# 2652 ----> master
# 8050 ----> y

BUFFER_SIZE = 10000
BATCH_SIZE = 64
train_dataset = train_data.shuffle(BUFFER_SIZE)
train_dataset = train_dataset.padded_batch(BATCH_SIZE, train_dataset.output_shapes)
test_dataset = test_data.padded_batch(BATCH_SIZE, test_data.output_shapes)

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')

%tensorflow_version 2.x

from __future__ import absolute_import, division, print_function, unicode_literals

import tensorflow_datasets as tfds
import tensorflow as tf
print(tf.__version__)

# Get the data
dataset, info = tfds.load('imdb_reviews/subwords8k', with_info=True, as_supervised=True)
train_dataset, test_dataset = dataset['train'], dataset['test']


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


BUFFER_SIZE = 10000
BATCH_SIZE = 64

train_dataset = train_dataset.shuffle(BUFFER_SIZE)
train_dataset = train_dataset.padded_batch(BATCH_SIZE, train_dataset.output_shapes)
test_dataset = test_dataset.padded_batch(BATCH_SIZE, test_dataset.output_shapes)

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(tokenizer.vocab_size, 64),
    ### with Single layer LSTM
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),
    
    ### with Multi layer LSTM
    # tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64, return_sequences=True)),  # return_sequences=True ensure the outputs of LSTM match the desired inputs of next one
    # tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(32)),
    
    ### witout LSTM
    # tf.keras.layers.Flatten()),
    # tf.keras.layers.GlobalAveragePooling1D(),

    ### with 1D Convolutional Layer
    # tf.keras.layers.Conv1D(128, 5, activation='relu'),
    # tf.keras.layers.GlobalAveragePooling1D(),

    ### with GRU
    # tf.keras.layers.Bidirectional(tf.keras.layers.GRU(32)),
    
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

model.summary()

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

NUM_EPOCHS = 10
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')

%tensorflow_version 2.x
import json
import tensorflow as tf
import csv
import random
import numpy as np

from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.utils import to_categorical
from tensorflow.keras import regularizers


embedding_dim = 100
max_length = 16
trunc_type='post'
padding_type='post'
oov_tok = "<OOV>"
training_size= 16000 #Your dataset size here. Experiment using smaller values (i.e. 16000), but don't forget to train on at least 160000 to see the best effects
test_portion=.1

corpus = []



# Note that I cleaned the Stanford dataset to remove LATIN1 encoding to make it easier for Python CSV reader
# You can do that yourself with:
# iconv -f LATIN1 -t UTF8 training.1600000.processed.noemoticon.csv -o training_cleaned.csv
# I then hosted it on my site to make it easier to use in this notebook

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

num_sentences = 0

with open("/tmp/training_cleaned.csv") as csvfile:
    reader = csv.reader(csvfile, delimiter=',')
    for row in reader:
      # Your Code here. Create list items where the first item is the text, found in row[5], and the second is the label. Note that the label is a '0' or a '4' in the text. When it's the former, make
      # your label to be 0, otherwise 1. Keep a count of the number of sentences in num_sentences
      list_item=[]
      list_item.append(row[5])
      this_label=row[0]
      if this_label=='0':
          list_item.append(0)
      else:
          list_item.append(1)
      num_sentences = num_sentences + 1
      corpus.append(list_item)

print(num_sentences)
print(len(corpus))
print(corpus[1])

# Expected Output:
# 1600000
# 1600000
# ["is upset that he can't update his Facebook by texting it... and might cry as a result  School today also. Blah!", 0]

sentences=[]
labels=[]
random.shuffle(corpus)
for x in range(training_size):
    sentences.append(corpus[x][0])
    labels.append(corpus[x][1])


tokenizer = Tokenizer()
tokenizer.fit_on_texts(sentences)

word_index = tokenizer.word_index
vocab_size=len(word_index)

sequences = tokenizer.texts_to_sequences(sentences)
padded = pad_sequences(sequences, maxlen=max_length, padding=padding_type, truncating=trunc_type)

split = int(test_portion * training_size)

test_sequences = padded[0:split]
training_sequences = padded[split:training_size]
test_labels = labels[0:split]
training_labels = labels[split:training_size]

print(vocab_size)
print(word_index['i'])
# Expected Output
# 138858
# 1

# Note this is the 100 dimension version of GloVe from Stanford
# I unzipped and hosted it on my site to make this notebook easier
!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/glove.6B.100d.txt \
    -O /tmp/glove.6B.100d.txt
embeddings_index = {};
with open('/tmp/glove.6B.100d.txt') as f:
    for line in f:
        values = line.split();
        word = values[0];
        coefs = np.asarray(values[1:], dtype='float32');
        embeddings_index[word] = coefs;

embeddings_matrix = np.zeros((vocab_size+1, embedding_dim));
for word, i in word_index.items():
    embedding_vector = embeddings_index.get(word);
    if embedding_vector is not None:
        embeddings_matrix[i] = embedding_vector;

print(len(embeddings_matrix))
# Expected Output
# 138859

model = tf.keras.Sequential([
    tf.keras.layers.Embedding(vocab_size+1, embedding_dim, input_length=max_length, weights=[embeddings_matrix], trainable=False),
    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1, activation='sigmoid')
])

# model = tf.keras.Sequential([
#     tf.keras.layers.Embedding(vocab_size+1, embedding_dim, input_length=max_length, weights=[embeddings_matrix], trainable=False),
#     tf.keras.layers.Dropout(0.2),
#     tf.keras.layers.Conv1D(64, 5, activation='relu'),
#     tf.keras.layers.MaxPooling1D(pool_size=4),
#     tf.keras.layers.LSTM(64),
#     tf.keras.layers.Dense(1, activation='sigmoid')
# ])

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

print(type(training_sequences),type(training_labels))
import numpy as np

num_epochs = 50
history = model.fit(training_sequences, np.array(training_labels), epochs=num_epochs, validation_data=(test_sequences, np.array(test_labels)), verbose=2)

print("Training Complete")

import matplotlib.image  as mpimg
import matplotlib.pyplot as plt

#-----------------------------------------------------------
# Retrieve a list of list results on training and test data
# sets for each training epoch
#-----------------------------------------------------------
acc=history.history['accuracy']
val_acc=history.history['val_accuracy']
loss=history.history['loss']
val_loss=history.history['val_loss']

epochs=range(len(acc)) # Get number of epochs

#------------------------------------------------
# Plot training and validation accuracy per epoch
#------------------------------------------------
plt.plot(epochs, acc, 'r')
plt.plot(epochs, val_acc, 'b')
plt.title('Training and validation accuracy')
plt.xlabel("Epochs")
plt.ylabel("Accuracy")
plt.legend(["Accuracy", "Validation Accuracy"])

plt.figure()

#------------------------------------------------
# Plot training and validation loss per epoch
#------------------------------------------------
plt.plot(epochs, loss, 'r')
plt.plot(epochs, val_loss, 'b')
plt.title('Training and validation loss')
plt.xlabel("Epochs")
plt.ylabel("Loss")
plt.legend(["Loss", "Validation Loss"])

plt.figure()


# Expected Output
# A chart where the validation loss does not increase sharply!

%tensorflow_version 2.x
import tensorflow as tf

from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.layers import Embedding, LSTM, Dense, Bidirectional
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
import numpy as np 


tokenizer = Tokenizer()

# lyrics corpus
# !wget --no-check-certificate \
#     https://storage.googleapis.com/laurencemoroney-blog.appspot.com/irish-lyrics-eof.txt \
#     -O /tmp/irish-lyrics-eof.txt

# data = open('/tmp/irish-lyrics-eof.txt').read()

# test corpus
data="In the town of Athy one Jeremy Lanigan \n Battered away til he hadnt a pound. \nHis father died and made him a man again \n Left him a farm and ten acres of ground. \nHe gave a grand party for friends and relations \nWho didnt forget him when come to the wall, \nAnd if youll but listen Ill make your eyes glisten \nOf the rows and the ructions of Lanigans Ball. \nMyself to be sure got free invitation, \nFor all the nice girls and boys I might ask, \nAnd just in a minute both friends and relations \nWere dancing round merry as bees round a cask. \nJudy ODaly, that nice little milliner, \nShe tipped me a wink for to give her a call, \nAnd I soon arrived with Peggy McGilligan \nJust in time for Lanigans Ball. \nThere were lashings of punch and wine for the ladies, \nPotatoes and cakes; there was bacon and tea, \nThere were the Nolans, Dolans, OGradys \nCourting the girls and dancing away. \nSongs they went round as plenty as water, \nThe harp that once sounded in Taras old hall,\nSweet Nelly Gray and The Rat Catchers Daughter,\nAll singing together at Lanigans Ball. \nThey were doing all kinds of nonsensical polkas \nAll round the room in a whirligig. \nJulia and I, we banished their nonsense \nAnd tipped them the twist of a reel and a jig. \nAch mavrone, how the girls got all mad at me \nDanced til youd think the ceiling would fall. \nFor I spent three weeks at Brooks Academy \nLearning new steps for Lanigans Ball. \nThree long weeks I spent up in Dublin, \nThree long weeks to learn nothing at all,\n Three long weeks I spent up in Dublin, \nLearning new steps for Lanigans Ball. \nShe stepped out and I stepped in again, \nI stepped out and she stepped in again, \nShe stepped out and I stepped in again, \nLearning new steps for Lanigans Ball. \nBoys were all merry and the girls they were hearty \nAnd danced all around in couples and groups, \nTil an accident happened, young Terrance McCarthy \nPut his right leg through miss Finnertys hoops. \nPoor creature fainted and cried Meelia murther, \nCalled for her brothers and gathered them all. \nCarmody swore that hed go no further \nTil he had satisfaction at Lanigans Ball. \nIn the midst of the row miss Kerrigan fainted, \nHer cheeks at the same time as red as a rose. \nSome of the lads declared she was painted, \nShe took a small drop too much, I suppose. \nHer sweetheart, Ned Morgan, so powerful and able, \nWhen he saw his fair colleen stretched out by the wall, \nTore the left leg from under the table \nAnd smashed all the Chaneys at Lanigans Ball. \nBoys, oh boys, twas then there were runctions. \nMyself got a lick from big Phelim McHugh. \nI soon replied to his introduction \nAnd kicked up a terrible hullabaloo. \nOld Casey, the piper, was near being strangled. \nThey squeezed up his pipes, bellows, chanters and all. \nThe girls, in their ribbons, they got all entangled \nAnd that put an end to Lanigans Ball."

corpus = data.lower().split("\n")

tokenizer.fit_on_texts(corpus)
total_words = len(tokenizer.word_index) + 1

print(tokenizer.word_index) # {'and': 1, 'the': 2, 'a': 3, 'in': 4, 'all': 5, 'i': 6, 'for': 7, 'of': 8, 'lanigans': 9, 'ball': 10, 'were': 11, 'at': 12, 'to': 13, .....}
print(total_words)  # 263

input_sequences = []
for line in corpus:
	token_list = tokenizer.texts_to_sequences([line])[0] # [4, 2, 66, 8, 67, 68, 69, 70]
	for i in range(1, len(token_list)):
		n_gram_sequence = token_list[:i+1]
		input_sequences.append(n_gram_sequence)

print(input_sequences) # [[4, 2], [4, 2, 66], [4, 2, 66, 8], [4, 2, 66, 8, 67],....]

# pad sequences 
max_sequence_len = max([len(x) for x in input_sequences])
input_sequences = np.array(pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre'))

# create predictors and label
xs, labels = input_sequences[:,:-1],input_sequences[:,-1]   # last word as label, the other words are input
print(xs[0],labels[0]) # [0 0 0 0 0 0 0 0 0 4] 2
print(xs[1],labels[1]) # [0 0 0 0 0 0 0 0 4 2] 66

ys = tf.keras.utils.to_categorical(labels, num_classes=total_words)  # transfer labels into one-hot vector

print(xs.shape,ys.shape) # (453, 10) (453, 263)

print(tokenizer.word_index['in']) # 4
print(tokenizer.word_index['the']) # 2 
print(tokenizer.word_index['town']) # 66
print(tokenizer.word_index['of']) # 8
print(tokenizer.word_index['athy']) # 67
print(tokenizer.word_index['one']) # 68
print(tokenizer.word_index['jeremy']) # 69
print(tokenizer.word_index['lanigan']) # 70

print(xs[6]) 
print(ys[6])
# [ 0  0  0  4  2 66  8 67 68 69]
# [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. 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. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 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. 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. 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. 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. 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. 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. 0.
#  0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]

print(xs[5])
print(ys[5])
# [ 0  0  0  0  4  2 66  8 67 68]
# [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. 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. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 0. 1. 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. 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. 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. 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. 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. 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. 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.]

print(tokenizer.word_index) # {'and': 1, 'the': 2, 'a': 3, 'in': 4, 'all': 5, 'i': 6, 'for': 7, 'of': 8, 'lanigans': 9, 'ball': 10, ...}

  model = Sequential()
  model.add(Embedding(total_words, 64, input_length=max_sequence_len-1))
  model.add(Bidirectional(LSTM(20)))
  model.add(Dense(total_words, activation='softmax'))
  model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
  history = model.fit(xs, ys, epochs=500, verbose=1)

# if use lyrics corpus, 
# Embeding output might be 100 instead of 64
# LSTM hidden units might be 150 instead of 20
# Epochs might be 500 instead of 100

import matplotlib.pyplot as plt


def plot_graphs(history, string):
  plt.plot(history.history[string])
  plt.xlabel("Epochs")
  plt.ylabel(string)
  plt.show()

plot_graphs(history, 'accuracy')

seed_text = "Laurence went to dublin"
next_words = 100
  
for _ in range(next_words):
	token_list = tokenizer.texts_to_sequences([seed_text])[0]
	token_list = pad_sequences([token_list], maxlen=max_sequence_len-1, padding='pre')
	predicted = model.predict_classes(token_list, verbose=0)
	output_word = ""
	for word, index in tokenizer.word_index.items():
		if index == predicted:
			output_word = word
			break
	seed_text += " " + output_word
print(seed_text)
# Laurence went to dublin girls they were they round all were saw gave til hall ned your glisten made relations glisten might ask glisten call old daughter hall hall glisten glisten glisten cakes farm steps steps steps new went me me a call call call call replied til mchugh mchugh ned farm til hall ned ned ask glisten was mchugh ned ned terrible hall minute glisten glisten glisten cakes farm til hall hall ned farm steps steps lanigans ball ball were ball odaly tipped were odaly gave til ned ned glisten boys boys all were hearty hearty wall hearty nelly ned farm steps steps

%tensorflow_version 2.x
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.layers import Embedding, LSTM, Dense, Dropout, Bidirectional
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
### YOUR CODE HERE
# Figure out how to import regularizers
from tensorflow.keras import regularizers
###
import tensorflow.keras.utils as ku 
import numpy as np 

tokenizer = Tokenizer()
!wget --no-check-certificate \
    https://storage.googleapis.com/laurencemoroney-blog.appspot.com/sonnets.txt \
    -O /tmp/sonnets.txt
data = open('/tmp/sonnets.txt').read()

corpus = data.lower().split("\n")


tokenizer.fit_on_texts(corpus)
total_words = len(tokenizer.word_index) + 1
print(total_words) # 3211

# create input sequences using list of tokens
input_sequences = []
for line in corpus:
	token_list = tokenizer.texts_to_sequences([line])[0]
	for i in range(1, len(token_list)):
		n_gram_sequence = token_list[:i+1]
		input_sequences.append(n_gram_sequence)


# pad sequences 
max_sequence_len = max([len(x) for x in input_sequences])
input_sequences = np.array(pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre'))

# create predictors and label
predictors, label = input_sequences[:,:-1],input_sequences[:,-1]

label = ku.to_categorical(label, num_classes=total_words)

model = Sequential()
model.add(Embedding(total_words, 120, input_length=max_sequence_len-1))
model.add(Bidirectional(LSTM(170, return_sequences = True)))
model.add(Dropout(0.2))
model.add(LSTM(130))
model.add(Dense(total_words/2, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
model.add(Dense(total_words, activation='softmax'))
# Pick an optimizer
model.compile(loss='categorical_crossentropy', optimizer='adam',metrics=['acc'])
print(model.summary())

history = model.fit(predictors, label, epochs=100, verbose=1)

import matplotlib.pyplot as plt
acc = history.history['acc']
loss = history.history['loss']

epochs = range(len(acc))

plt.plot(epochs, acc, 'b', label='Training accuracy')
plt.title('Training accuracy')

plt.figure()

plt.plot(epochs, loss, 'b', label='Training Loss')
plt.title('Training loss')
plt.legend()

plt.show()

seed_text = "Help me Obi Wan Kenobi, you're my only hope"
next_words = 100
  
for _ in range(next_words):
	token_list = tokenizer.texts_to_sequences([seed_text])[0]
	token_list = pad_sequences([token_list], maxlen=max_sequence_len-1, padding='pre')
	predicted = model.predict_classes(token_list, verbose=0)
	output_word = ""
	for word, index in tokenizer.word_index.items():
		if index == predicted:
			output_word = word
			break
	seed_text += " " + output_word
print(seed_text)
# Help me Obi Wan Kenobi, you're my only hope chase thee admiring praise lay forth me swearing thence move chest make green me shown find them find their wealth shall call not true praise spent brought of ground one rhyme in one 'will ' torn die back remains free near slain 'will ' free die die young ground light free ' live forth thee on such sort dwell die foes commend die moan ' live forth thy praise hate bright hate green die you dearer rhyme show thee thence find you done hell you done live on thee doth he have subscribes press prove one near rhyme ' die