Presentation to accompany the Shiny App: https://jmcastagnetto.shinyapps.io/predict-child-height. This was done as part of the course project for the Coursera class "Developing Data Products", July 2015 session.
I am currently reading the book "Machine Learning with R" by Brent Lantz, and also want to learn more about the caret package, so I decided to replicate the SPAM/HAM classification example from the chapter 4 of the book using caret instead of the e1071 package used in the text. Also, instead of using as comparison the number of false positives, I decided to use the sensitivity and specificity as criteria to evaluate the prediction models. Another difference is that I used the calculated models on a (different) second dataset to test their prediction performance.
A reproduction of the cancer example from the chapter 3 of the book "Machine Learning with R", using the caret package for estimating the kNN models.
Ejemplo simple de uso del API del servicio del Portal de Datos Abiertos de Lima Metropolitana, extrayendo las posiciones georefenciadas de los paraderos del corredor TGA (rutas troncales y alimentadoras), y luego poniendo los datos en un mapa.
Analysis of the NOAA NCDC data set provided in the "Reproducible Research" course (Coursera, August 2014)
A simple document showing the use of XML to get data from an HTML table, dplyr for data manipulation, lubridate for some simple date mangling, and ggplot2 and googleVis to generate nice charts (interactive in the case of googleVis)