Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk.
Project description
Annoy
What is this?
Annoy (Approximate Nearest Neighbors Something Something) is a C++ library with Python bindings to search for points in space that are close to a given query point. It also creates large read-only file-based data structures that are mmapped into memory so that many processes may share the same data.
There’s a couple of other libraries to do approximate nearest neighbor search, including FLANN, etc. Other libraries may be both faster and more accurate, but there are one major difference that sets Annoy apart: it has the ability to use static files as indexes. In particular, this means you can share index across processes. Annoy also decouples creating indexes from loading them, so you can pass around indexes as files and map them into memory quickly. Another nice thing of Annoy is that it tries to minimize memory footprint so the indexes are quite small.
Why is this useful? If you want to find nearest neighbors and you have many CPU’s, you only need the RAM to fit the index once. You can also pass around and distribute static files to use in production environment, in Hadoop jobs, etc. Any process will be able to load (mmap) the index into memory and will be able to do lookups immediately.
We use it at Spotify for music recommendations. After running matrix factorization algorithms, every user/item can be represented as a vector in f-dimensional space. This library helps us search for similar users/items. We have many millions of tracks in a high-dimensional space, so memory usage is a prime concern.
Annoy was built by Erik Bernhardsson in a couple of afternoons during Hack Week.
Summary of features
Euclidean distance (squared) or cosine similarity (using the squared distance of the normalized vectors)
Works better if you don’t have too many dimensions (like <100) but seems to perform surprisingly well even up to 1,000 dimensions
Small memory usage
Lets you share memory between multiple processes
Index creation is separate from lookup (in particular you can not add more items once the tree has been created)
Native Python support
Code example
f = 40
t = AnnoyIndex(f)
for i in xrange(n):
v = []
for z in xrange(f):
v.append(random.gauss(0, 1))
t.add_item(i, v)
t.build(10) # 10 trees
t.save('test.tree')
# …
u = AnnoyIndex(f)
u.load('test.tree') # super fast, will just mmap the file
print(u.get_nns_by_item(0, 1000)) # will find the 1000 nearest neighborsRight now it only accepts integers as identifiers for items. Note that it will allocate memory for max(id)+1 items because it assumes your items are numbered 0 … n-1. If you need other id’s, you will have to keep track of a map yourself.
How does it work
Using random projections and by building up a tree. At every intermediate node in the tree, a random hyperplane is chosen, which divides the space into two subspaces.
We do this k times so that we get a forest of trees. k has to be tuned to your need, by looking at what tradeoff you have between precision and performance. In practice k should probably be on the order of dimensionality.
More info
Dirk Eddelbuettel provides an R version of Annoy.
For some interesting stats, check out Radim Řehůřek’s great blog posts comparing Annoy to a couple of other similar Python libraries:
There’s also some biased performance metrics in a blog post by me. It compares Annoy, FLANN, PANNS, and a pull request to scikit-learn.
Source code
It’s all written in C++ with a handful of ugly optimizations for performance and memory usage. You have been warned :)
The code should support Windows, thanks to thirdwing.
Discuss
Feel free to post any questions or comments to the annoy-user group. I’m @fulhack on Twitter.
Future stuff
More performance tweaks
Expose some performance/accuracy tradeoffs at query time rather than index building time
Figure what O and Y stand for in the backronym :)
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
File details
Details for the file annoy-1.0.5.tar.gz.
File metadata
- Download URL: annoy-1.0.5.tar.gz
- Upload date:
- Size: 622.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 93e4faed778c41aa16ccdabd08bafedcf123aa096bd58e118f3b9799eda07fb6 |
|
| MD5 | 6d16f6f15b6d1b3955d5fe91843cb73a |
|
| BLAKE2b-256 | 303156ad61b57600b06e4ca390cf7e6c525cf1824c33c4028909bfad975a20bd |
