Blog Archives

Using R to refine the search result of www.finn.no

December 12, 2012
By
Using R to refine the search result of www.finn.no

www.finn.no is the most popular website in Norway. It supplies a lot of features, such as booking flight tickets, finding job, renting and sales of houses, cars and other properties, etc. I just have some experience with it. I sold and bought cars, apartment and some other stuff. It’s very convenient. But just one thing I feel not convenient:...

Read more »

Rename photos’ names according to shooting time in a batch mode.

October 17, 2012
By

For some reason, you want to know the shooting time of your photos. Generally, shooting time can be found as Date modified, if you didn’t made a lot of change to your photos. But, we often make change to our photos, such like copy them from a place to another, edit using Photoshop, Picasa, etc., and then, the Date...

Read more »

Generate simple HTML slides using deck.js and markdown

August 29, 2012
By

RStudio and knitr are an excellent conbination for generating dynamic reports. But in this blog, I will show you how to generate HTML-style presentaion using R only.OK, I confess that we still need something else: deck.js and markdown and R.utils. ...

Read more »

Facts About R Packages (2)

August 29, 2012
By

R Packages All Well maintained?There are so many R packages, can they all be trusted? or are they well maintained? To answer this question, we just need to take a look of their archive histories. If a package has many versions, we can take that as th...

Read more »

Facts About R Packages (1)

August 29, 2012
By

R Packages growth CurveWhy R is so popular? There are a lot of reasons, such as: easy to learn and convenient to use, active community, open source, etc. Another important reason is the numerous contributed packages. Up to yesterday, there are 4033 R...

Read more »

Generate Quasi-Poisson Distribution Random Variable

August 29, 2012
By

Most of regression methods assume that response variables follow some exponential distribution families, e.g. Guassian, Poisson, Gamma, etc. However, this assumption was frequently violated in real world by, for example, zero-inflated overdispersion problem. A number of methods were developed to deal with such problem, and among them, Quasi-Poisson and Negative Binomial are the most popular methods perhaps due to that...

Read more »

Generate simple HTML slides using deck.js and markdown

June 19, 2012
By

RStudio and knitr are an excellent conbination for generating dynamic reports. But in this blog, I will show you how to generate HTML-style presentaion using R only.OK, I confess that we still need something else: deck.js and markdown and R.utils....

Read more »

Facts About R Packages (2)

June 6, 2012
By

R Packages All Well maintained?There are so many R packages, can they all be trusted? or are they well maintained? To answer this question, we just need to take a look of their archive histories. If a package has many versions, we can take that as the authors spent a lot of time to make their packages perfect, these...

Read more »

Facts About R Packages (1)

June 6, 2012
By

R Packages growth CurveWhy R is so popular? There are a lot of reasons, such as: easy to learn and convenient to use, active community, open source, etc. Another important reason is the numerous contributed packages. Up to yesterday, there are 3854 R packages on CRAN.The following figure shows the growth curve of R package:

Generate Quasi-Poisson Distribution Variable

June 4, 2012
By

Most of regression methods assume that the response variables follow some exponential distribution families, e.g. Guassian, Poisson, Gamma, etc. However, this assumption was frequently violated in real world data by, for example, zero-inflated overdispersion problem. A number of methods were developed to deal with such problem, and among them, Quasi-Poisson and Negative Binomial are the most popular methods perhaps due...

Read more »