Last active
August 29, 2015 14:06
-
-
Save alexwoolford/4e667be8827bcb61145e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# The csv dataset was downloaded from http://data.denvergov.org/dataset/city-and-county-of-denver-crime | |
import pandas as pd | |
from elasticsearch import Elasticsearch | |
import json | |
data = pd.read_csv('/Users/awoolford/Downloads/crime.csv') | |
es = Elasticsearch() | |
# ignore 400 cause by IndexAlreadyExistsException when creating an index | |
es.indices.create(index='crime-index', ignore=400) | |
for id, record in enumerate(json.loads(data.to_json(orient='records'))): | |
doc = dict() | |
for key, value in record.iteritems(): | |
try: | |
doc[key.encode('utf-8')] = value.encode('utf-8') | |
except: | |
doc[key.encode('utf-8')] = value | |
doc['LOCATION'] = [doc['GEO_LON'], doc['GEO_LAT']] | |
es.index(index="crimes-index", doc_type='crime', id=id, body=doc) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment