Skip to main content
This is a pre-production deployment of Warehouse. Changes made here affect the production instance of PyPI (
Help us improve Python packaging - Donate today!

Python address detector

Project Description
Address Detector

How to detect if a user query might be an address and requires to launch a map answer.

Project Modules
The project implements 3 classifiers, using an a la scikit template.

The first classifier is a simple scorer classifier, based on the parsing result of the address parser libpostal (
According to how the parser manage to work, and which fields are parsed, we make a score and decide if an address or not.

The second classifier is based on the FastText classifier trained on address data. The fasttext makes an embedding of the differents address it sees and therefore when a new address is submitted if it's in a close spaceto what have been learned.
The classifier is pre-trained, and the Fasttext zip model is store within the package.

The third classifier is a voting classifier combining the results of the two previous classifiers.

Project Dependencies
####Installation of Postal:
Before you install `Postal` , make sure you have the following prerequisites:
sudo apt-get install curl autoconf automake libtool pkg-config

Then to install the C library:

git clone
cd libpostal
./configure --datadir=[...some dir with a few GB of space...]
sudo make install

# On Linux it's probably a good idea to run
sudo ldconfig
#### Installation of FastText
In order to build `fastText`, use the following:

$ git clone
$ cd fastText
$ make


0.1.0 (2017-10-25)

* First release on PyPI.
Release History

Release History

This version
History Node


History Node


History Node


History Node


History Node


History Node


Download Files

Download Files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

File Name & Checksum SHA256 Checksum Help Version File Type Upload Date
addr_detector-0.2.1.tar.gz (52.8 MB) Copy SHA256 Checksum SHA256 Source Nov 17, 2017

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting