Data Science Capstone

This Capstone project is part of a 10 course certification, which I strongly recommend as it strengths your skills and teach you in deep detail:

This is the link of the course: Data Science track by Johns Hopkins University on Coursera.

The goal of this exercise is to create a product to highlight the prediction algorithm that you have built and to provide an interface that can be accessed by others. For this project you must submit:

A Shiny app that takes as input a phrase (multiple words) in a text box input and outputs a prediction of the next word.

A slide deck consisting of no more than 5 slides created with R Studio Presenter pitching the algorithm and app as if you were presenting to your boss or an investor.

The data is from a corpus called Coursera Cappstone.

The data consist from three txt files: Twitter, Blog and News. At the end I used RWeka library.

I used a random sample of 90% from the raw data to build the final model.

Other libraries used to compare ngrams, to process graphs and build the Milestone:

• library(dplyr)
• library(ggplot2)
• library™
• library(NLP)
• library(stringi)
• library(stringr)
• library(kableExtra)
• library(tidytext)
• library(RColorBrewer)
• library(plotly)

The Milestone Report you can find it here: Milestone Report

The tokenization I made:

• Remove non-english characters
• Remove white spaces
• Remove URL and mail
• Convert all words to lowercase
• Remove english stopwords
• Remove punctuation marks
• Convert to Latin encoding to remove lines with non-English words

Once the data is cleaned, I used for the n-gram: unigram, bigram, trigram, and quadgrams. The data was saved in RData file to read in the server.R code, and again I pre-process the data with all filtering as in the previous step. I filtered the data with these n-gram and on the ui.R I gave format, I added a Shiny theme.

You can find the app here: Shiny App The Milestone Report you can find it here: Milestone Report