Capstone_Presentation

The objective of this project was to use all the skills in the previous 9 courses to create a text prediction application. this included the following major steps

• Clean and tidy up a large data set
• Create a text corpus to use in NLP
• Tokenize the corpus via Ngrams
• Use the tokenized Ngrams to create a prediction algorithm for the next word based on given input
• Create Shiny App to use the algorithm

This App takes a user input and predicts the next word based on the last word used in the set

the algorithm works as follows:

Taking a users input > create a string > parse out the last word > match last word to a data set of ngrams > suggest the most frequently used next word in the ngram set

• 1. Enter text
• 2. Press Predict

• Predict more than one word after the given phrase
• Remove profanities from suggestions

THANKS. THE END