Extracting and segregating on geographic locations

Question

I have list of strings like this:

["Ola, Uber's India rival, invests $100M in scooter rental startup Vogo","Chattanooga startup Bellhops Moving raises over $31 million in latest", "Boston biotech Entrada launches with $59M to tackle deadly disease"]

I want to identify strings like India, Boston, Chattanooga which is either city, town, country, state or continent from the list of strings and segregate them as per the region.

I am not able to find a proper path or way to achieve this particular output. Any suggestions will be much helpful.

my suggestion is to use Spacy and NER – backtrack Dec 23 '18 at 07:17 — backtrack, Dec 23 '18 at 07:17

score 2 · Accepted Answer · answered Dec 23 '18 at 08:27

You need to use GeoText library. You can install it by typing the following in your command prompt cmd of your windows.

pip install https://github.com/elyase/geotext/archive/master.zip

Once installed, you can extract cities and countries.

from geotext import GeoText
your_list=["Ola, Uber's India rival, invests $100M in scooter rental startup Vogo","Chattanooga startup Bellhops Moving raises over $31 million in latest", "Boston biotech Entrada launches with $59M to tackle deadly disease"]
complete_string=','.join(map(str,your_list) ) # converting the list 'your_list' to string
locations=GeoText(complete_string)
locations.countries
    ['India']
locations.cities
    ['Chattanooga', 'Boston']

score 0 · Answer 2 · answered Dec 23 '18 at 07:52

0

For detecting countries and cities you might use geotext: https://pypi.org/project/geotext/

answered Dec 23 '18 at 07:52

Daweo

31,313
3
12
25

Extracting and segregating on geographic locations

2 Answers2