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

• Evil evil update

  This update took me quite a bit more time than I initially expected. Anyway, I have done some refactoring work to the original code, and thought it would be nice to document the changes. Overall, most of the changes involved the refactoring of function names. I am not sure if this would stick, but I am quite satisfied for now.

  (more…)

• Dragon Curve

  I really don’t know how to start explaining what is a Dragon Curve. However, I find it is interesting enough after finding out that there’s actually a fixed pattern of occurrence. Therefore I spent some time writing a series of scripts to plot the generated fractal into a graph. What I didn’t expect is, the series get really complicated after a while.

  (more…)

• My Collection of Common Javascript Functions – Part 1

  After coded enough Javascript few months back, I found that there are a couple of functions that I kept re-using in different projects. Therefore I took some time to refactor them and re-arrange them into a single file. The common code that I keep reusing even today consists of functions that does prototypical inheritance, scope maintenance, some jquery stuff, google maps api stuff and some general ajax application related code.

  (more…)

• Linting a libsvm-formatted data

  While working on a text classification task, I spent quite some time preparing the training set for a given document collection. The project is supposed to be a pure golang implementation, so after some quick searching I found some libraries that are either a wrapper to libsvm, or a re-implementation. So I happily started to prepare my training set in the libsvm format.

  (more…)

• Protobuf and dask

  While JSON is a fine data-interchange format, however it does have some limitations. It is well-known for its simplicity, that even a non-programmer can easily compose a JSON file (but humanity will surprise you IRL). Therefore, it is found almost everywhere, from numerous web APIs, to geospatial data (GeoJSON), and even semantic web (RDF/JSON).

  (more…)