AI Poem Generator trained on Shakespeares work

Introduction

Importing the Packages

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
from tensorflow.keras import regularizers
import tensorflow.keras.utils as ku 
import numpy as np 

Importing the Data

For the purpose of this model, I’ve used the sonnets.txt file from Laurence Moroney’s blog. You can download it as well by using the code below

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")

The Tokenizer

tokenizer = Tokenizer()

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

Creating Input Sentences

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)

Padding the 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'))

Creating Predictors and the Labels

predictors, label = input_sequences[:,:-1],input_sequences[:,-1]
label = ku.to_categorical(label, num_classes=total_words)

Creating the Actual Model

model = Sequential()
model.add(Embedding(total_words, 100, input_length=max_sequence_len-1))
model.add(Bidirectional(LSTM(150, return_sequences = True)))
model.add(Dropout(0.2))
model.add(LSTM(100))
model.add(Dense(total_words/2, activation='relu', kernel_regularizer=regularizers.l2(0.01)))
model.add(Dense(total_words, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())

Analyzing the Model

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

import matplotlib.pyplot as plt
acc = history.history['accuracy']
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()

Actually generating the poem!!

seed_text = "Help me Saurav Maheshkar, 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)

End Notes

If you do end up using the code kindly write your poem in the comments section.