My take on the Mahout and Myrrix recommendation algorithms

MahoutWhereas BestComparator has his own recommendation engine based on user profiling, behavior analysis and analysis of product specs, I recently wanted to explore the possibilities of the famous recommendation engine built inside Mahout.

First of all, Mahout is a set of machine learning algorithms which leverage the Hadoop environment, providing powerful and scalable algorithms. One of its main target is the recommendation algorithms also known as taste collaborative filtering.

Recommendation algorithms have been made famous by websites such as Amazon, Youtube or Netflix. They use it to make suggestions based on what you bought, watched or liked.

Myrrix

MyrrixOne of the author of Taste/Mahout recommender engine, Sean Owen decided to give the engine a more formal structure by building Myrrix.

Myrrix is a recommendation engine based on Mahout. It offers an out of the box configuration for a recommendation engine accessible with a Rest API. The good to know are:

  • Scalable as Mahout and Hadoop are scalable, using computing parallelization and a distributed file system
  • Runs an optimized version of Taste (currently Taste 3)
  • Runs in real time
  • Can be efficient even with a relatively small amount of data

Recommendation process

The first thing you want to do is to feed your model (ie. Your algorithm) with current observed data. The models aggregates users, items and the associations between them. These associations are called preferences and are qualified by their value, describing the strength of the association between the user and the item.

Feeding the engine means pushing every observed associations with the user id, the item id and the strength. You are simply giving the engine your current taste graph, linking users to items via their tastes.

When your engine is fed, you have to ask it to refresh. Thus it will re-analyze the given graph and compute an actualized, and thus better, model. This may take some time, but Myrrix has the ability to continue answer your requests during this time.

Finally, with your shinny model you can ask questions and get recommendations. Here are the main queries:

  • Recommend to a user
  • Recommend to a group of users
  • Recommend to an anonymous user
  • Recommend similar items
  • Estimate the strength of the preference between an user and an item

With such a panel of tools you can easily guess that answering the question “What item users like me also liked?” becomes accessible.

Consuming Myrrix from PHP

PHPIn order to integrate Myrrix results to my recommendation engine, I had to build a PHP Myrrix client. I decided to use the Guzzle library that provides a really neat way of building a PHP client for Rest APIs. You can download my library on the open source Github Project: https://github.com/michelsalib/bcc-myrrix.

After installing the library, you can write some very fancy code:

// Get a client
$this->client = MyrrixClient::factory(array(
    'hostname' => 'localhost',
    'port'     => 8080,
));

// Put a user/item assocation, here use #101 as an association of strength 0.5 with item #1000
$command = $this->client->getCommand('PostPref', array(
    'userID' => 101,
    'itemID' => 1000,
    'value'  => (string)0.5,
));
$this->client->execute($command);

// Refresh the index
$command = $this->client->getCommand('Refresh');
$this->client->execute($command);

// Get a recommendation for user #101
$command = $this->client->getCommand('GetRecommendation', array(
    'userID' => 101,
));
$recommendation = $this->client->execute($command)->json();

Here we instantiate a Myrrix client hosted on the localhost on port 8080. We put into the model a preference of 0.5 between the user #101 and the item #1000. We then ask the model to refresh. Finally we get a recommendation for the user #101. The recommendation result is an array of item id with their estimated strength for the given user.

The library is pretty straight forward and help you leverage in a very simple way all the powerfulness of the Myrrix engine from PHP.

I also made a Symfony Bundle that helps you get the client from the dependency container, and offers a cleaner configuration process: https://github.com/michelsalib/BCCMyrrixBundle.

Don’t hesitate to get the code, install it and test it. I would be very happy to get contributions, feedbacks or feature requests.

Advertisements

The BCCEnumerableUtility is out

The BCCEnumerableUtility is out

One of the most frustrating things you may encounter as a PHP developer is definitely the lack of clarity and consistency of many of the core array and string manipulation functions.

What goes wrong

Let’s take for example the function that checks if a string contains another string. You might want to use strstr but you should use strpos for performance purpose. You already noticed the lack of clarity in the name of the functions, and the fact that whatever you do, the better way of dealing with strings in php is never straightforward.
You may also know that the case insensitive equivalents of these function adds an i in the middle of their names (stristr, stripos). Again, this is not very explicit. Finally, some functions does not respect the same format, such as str_split or str_replace.

And the same matters occur with the array functions.

As you may know, I also have a .NET background, especially in C#. One of the thing I like is the way they deal with this issue. First of all, strings and arrays are objects… They also have the IEnumerable interface that is implemented by everything that is an enumeration of items (strings are enumeration of characters). They added a bunch a generic methods that extends the IEnumerable interface to provide clear and powerful functionalities. So whenever you have something that is enumerable you leverage automatically tens of filtering, ordering, transformation and manipulation functions.

I really miss IEnumerable when I am using PHP.

The BCCEnumerableUtility

When PHP5.4 came out, I saw in traits a way to port IEnumerable from C# to PHP.

So I mimicked the C# interface and made the Enumerable trait, with the Collection and String classes that leverage the trait.

Let’s avoid taking too much, here is an example with the Collection class that leverage the trait:

select(function($item) { return $item*$item; })->average();

// filter the even numbers and then order
$values->where(function($item) { return $item%2 == 0; })->orderBy();

The Enumerable trait comes with a bunch of nice functions that you can discover on the BBCEnumerableUtility Github repository.

The String class

The library also provides a String class that adds some string dedicated functions:

replace('world', 'pineapple') // replace world by pineapple
->toUpper() // to upper case
->skip(6) // skip the 6 first letters
->takeWhile(function($char) { $char != '!'; }); // take the rest while the char is different from '!'

echo $string; // PINEAPPLE

I know many people won’t like the idea of a String class, so I provide a StringUtility helper that gives you access to all the functionality with static calls:

<?php
use BCCEnumerableUtilityStringUtility;

$string = 'Hello world!';

$string = StringUtility::replace ($string, 'world', 'pineapple'); // replace world by pineapple
$string = StringUtility::toUpper ($string); // to upper case
$string = StringUtility::skip ($string, 6); // skip the 6 first letters
$string = StringUtility::takeWhile($string, function($char) { $char != '!'; }); // take the rest while the char is different from '!'

echo $string; // PINEAPPLE

Wrap up

The BCCEnumerableUtility library will help you manipulate strings and arrays more easily.

As usual, I published this library on Github. I welcome remarks, bugs and contributions 🙂