The goal of this project is to create a product to highlight the prediction algorithm that I have built and to provide an interface that can be accessed by others.

Click here to use the app.

• The text file data is from https://d396qusza40orc.cloudfront.net/dsscapstone/dataset/Coursera-SwiftKey.zip.
• I remove the URLs, special characters, punctuations, numbers, excess whitespace and stopwords and transfer the text to lower case.
• The data is separated into tokens as bigram, trigram and quadgram.
• For speeding up the deployment of app, I upload those three cleaned datasets to server.

• Algorithm matches the given words into N-grams cases.
• If nothing matches, less given words will be used. And algorithm then try to match N-grams again.
• If nothing matches single given word, the algorithm will just return a word “the”.

• Type in the “Enter here” box
• Read the prediction results on the right area