How to parse an Unstructured International Address in Python using NLP

Working with mailing addresses can be a source of all kinds of pain and suffering if you don’t have the right support systems in place. Oftentimes, customers will submit an address in a completely jumbled order, which can wreak havoc, especially when dealing with product shipping. To combat this, a little cutting edge Natural Language Processing can be used to sort out messy strings into proper addresses. This lifesaver would normally require hours of programming to set up, but I can show you how to do it in about 5 minutes. Let’s begin.

pip install cloudmersive-validate-api-client

Next we are going to make a function call for address_parse_string, which can be set up in this fashion:

from __future__ import print_function
import time
import cloudmersive_validate_api_client
from cloudmersive_validate_api_client.rest import ApiException
from pprint import pprint
# Configure API key authorization: Apikey
configuration = cloudmersive_validate_api_client.Configuration()
configuration.api_key['Apikey'] = 'YOUR_API_KEY'
# Uncomment below to setup prefix (e.g. Bearer) for API key, if needed
# configuration.api_key_prefix['Apikey'] = 'Bearer'
# create an instance of the API class
api_instance = cloudmersive_validate_api_client.AddressApi(cloudmersive_validate_api_client.ApiClient(configuration))
input = cloudmersive_validate_api_client.ParseAddressRequest() # ParseAddressRequest | Input parse request
try:
# Parse an unstructured input text string into an international, formatted address
api_response = api_instance.address_parse_string(input)
pprint(api_response)
except ApiException as e:
print("Exception when calling AddressApi->address_parse_string: %s\n" % e)

Now go ahead and drop in a garbled address to test it out. Easy.