Machine Learning

• Regression with 2-means clustering Annoy (non-scientific)

  So apparently Annoy is now splitting points by using the centroids of 2 means clustering. It is claimed that it provides better results for ANN search, however, how does this impact regression? Purely out of curiosity, I plugged a new point splitting function and generated a new set of points.

  (more…)

• Regression with Annoy (cont’d)

  After a year and half, a lot of things changed, and annoy also changed the splitting strategy too. However, I always wanted to do a proper follow up to the original post, where I compared boosting to Annoy. I still remember the reason I started that (flawed) experiment was because I found boosting easy.

  (more…)

• Quick experiment, boosting vs annoy

  While following through the Statistical Learning course, I came across this part on doing regression with boosting. Then reading through the material, and going through it makes me wonder, the same method may be adapted to Erik Bernhardsson‘s annoy algorithm.

  (more…)

• Further Hack on the Multi-Dimensional Approximate Neighbour Search

  Traversing a tree structure often involves writing a recursive function. However, Python isn’t the best language for this purpose. Therefore I started flattening the tree into a key-value dictonary structure. Logically it is still a tree, but it is physically stored as a dictionary. Therefore it is now easier to write a simple loop to traverse it.

  (more…)

• Approximate Neighbour Search in Multiple Dimensions

  In the previous post, I re-implemented Annoy in 2D with some linear algebra maths. Then I spent some time going through some tutorial on vectors, and expanded the script to handle data in 3D and more. So instead of finding gradient, the perpendicular line in the middle of two points, I construct a plane, and find the distance between it and points to construct the tree.

  (more…)

• Re-implementing Approximate Nearest Neighbour Search

  Recently I switched my search code to Annoy because the input dataset is huge (7.5mil records with 20k dictionary count). It wasn’t without issues though, however I would probably talk about it next time. In order to figure out what each parameters meant, I spent some time watching through the talk given by the author @fulhack.

  (more…)

• Random notes on Pandas and Scikit-learn

  So I first heard about Panda probably a year ago when I was in my previous job. It looked nice, but I didn’t really get the chance to use it. So practically it is a library that makes data looks like a mix of relational database table and excel sheet. It is easy to do query with it, and provides a way to process it fast if you know how to do it properly (no, I don’t, so I cheated).

  (more…)

Random Posts

• Building problock – my personal experience

  A few years ago, I was asked to build a game or simulation (alongside 2048) as a part of a job application. Being very impressed with Explorable Explanations, I implemented Conway’s Game of life with Javascript and jQuery (that was before ES6 became popular). Then I made a very simple grid maker jQuery plugin to dynamically generate a grid of divs. If you check the source code, you may realize I rely on Underscore.js a lot back then.

  (more…)

• Real Life Enterprise Class Website Development

  Recently I am involved in developing some small modules for a enterprise class website using CodeIgniter (CI). There was no restriction given on which framework should I use for the development and I chose CI as I learned a bit on it (when I was considering whether to shift my personal development project). Of course there are other reasons why I chose to learn CI, for example the superior documentation and screencasts available.

  (more…)

• Approximate Neighbour Search in Multiple Dimensions

  In the previous post, I re-implemented Annoy in 2D with some linear algebra maths. Then I spent some time going through some tutorial on vectors, and expanded the script to handle data in 3D and more. So instead of finding gradient, the perpendicular line in the middle of two points, I construct a plane, and find the distance between it and points to construct the tree.

  (more…)

• Linked Data Principle

  Semantic Web is not just about putting data on the web, but also making links to allow a person as well as a machine to explore the web of data. Links are made in the web of data connects arbitrary things together as described by RDF as opposed to links in the web of hypertext, where links connects to only web-resources. Linkage of arbitrary things then allow related things to be found while performing search.

  (more…)

• Mixing Non-array and Array in array_map()

  array_map function is a function that I use the most in my php scripts recently. However, there are times where I want to pass some non-array into it, therefore often times I have code like the snippet shown below:

  $result = array_map(
'some_callback',
array_fill(0, count($some_array), 'some_string'),
array_fill(0, count($some_array), 'some_other_string'),
$some_array
)

  It doesn’t look good IMO, as it makes the code looks complicated. Hence, after seeing how the code may vary in all different scenarios, I created some functions to clean up the array_map call as seen above. Code snippet after the jump

  (more…)