In this project we are using the book The Picture of Dorian Gray by Oscar Wilde as a dataset.
- first we will have a text corpus as a dataset.
- we will do NLP preprocessing for text data and create a vocabulary of tokenized words
- we will take first 4 words of va sequence as an input ( independent variables ) and the 5th word as output ( depenedent variable)
- then we will train a neural network (LSTM) on the data
- finally we will predict our model with random sequences
- tensorflow
- numpy
- pickle
- os