PredictNext

For more details on this Coursera project, please visit: https://www.coursera.org/learn/data-science-project/supplement/idhGA/syllabus.

• The dataset used to build the model could be found at: https://d396qusza40orc.cloudfront.net/dsscapstone/dataset/Coursera-SwiftKey.zip.
• Only English database is used in this model, therefore only English input is supported by this Shiny.app
• The Shiny.app could be found at: https://pmeng2.shinyapps.io/PredictNext/.

• First, a samll portion of the dataset was selected to avoid taking too much time to run the model
• The selected data was cleaned by removing profanity, numbers, shapes etc.
• Use the cleaned data to build a basic n-gram model to predict the next word.

• In the shiny app page, there's a input input box for inputting phrases that you want to predict the next word
• The red sentence suggests that only English word is supported by this Shiny.app
• The predicted word will automatically change based on your input phrases

• Thank Coursera and John Hopkins University for provideing such a great series of Data Science courses
• Thank Jeff Leek, Roger Peng and Brian Caffo for their efforts in making and presenting the course contents