Before defining and feeding data into an LSTM network it is important that the data is converted into a form which can be understood by the neural network. Computers understand everything in binary code (0s and 1s) and therefore, the textual or data in string format needs to be converted into one hot encoded variables.
Tokenizing sentences
Getting ready
For understanding how one hot encoding works, visit the following links:
- https://machinelearningmastery.com/how-to-one-hot-encode-sequence-data-in-python/
- http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.OneHotEncoder.html
- https://stackoverflow.com/questions/37292872/how-can-i-one-hot-encode-in-python
- https://www.ritchieng.com/machinelearning-one-hot...
