I hereby claim:
- I am boblannon on github.
- I am boblannon (https://keybase.io/boblannon) on keybase.
- I have a public key whose fingerprint is DA32 3774 0A70 5FE1 234B E4F3 6543 90FE 7D1B 247B
To claim this, I am signing this object:
from collections import defaultdict | |
from math import log | |
from math import exp | |
import pandas as pd | |
# this is based on data in the form released here: http://corpora.uni-leipzig.de/ | |
# inv_w.txt is a table of (word_id, sentence_id, offset), which lets us create an inverted | |
# index with offset information |
from superfastmatch import client | |
import uuid | |
sfm_client = client.Client(url='http://127.0.0.1:9000/') | |
class Document(): | |
def __init__(self,title_string,content_string): | |
self.doc_id = uuid.uuid4() |
I hereby claim:
To claim this, I am signing this object:
6018211044-774 | |
6018210841-12253 | |
6018211039-10619 | |
6018211039-11153 | |
6018210827-1520 | |
02-055-000996 | |
6018261174-1333 | |
6018210841-9305 | |
6018210827-2681 | |
6018211170-8238 |
from elasticsearch import Elasticsearch | |
es = Elasticsearch(['localhost:9201',]) | |
def node_phrase_query(node_id, key_phrase): | |
qbody = {"query": | |
{ | |
"bool": { | |
"must": [ | |
{"match_phrase": {"text": key_phrase}}, | |
{"match_phrase": {"clusters": node_id}} |
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ | |
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), | |
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) | |
})(window,document,'script','//www.google-analytics.com/analytics.js','ga'); | |
ga('create', 'UA-1265484-62', 'influenceexplorer.com'); | |
ga('send', 'pageview'); | |
ga('create', 'UA-48789618-1', 'influenceexplorer.com', {'name': 'global'}); | |
ga('global.send', 'pageview'); |
import json | |
import csv | |
from io import StringIO | |
import requests | |
from lxml import etree | |
resp = requests.get('http://www.barackobama.com/contribution-disclosure/') | |
parsed = etree.parse(StringIO(resp.text), parser=etree.HTMLParser()) |
for chunk in record_chunks: | |
pool.apply_async(scoring_function, (chunk,), callback=score_queue.put) | |
pool.close() | |
pool.join() |
all_records_that_are_new_or_changed_since_your_last_import = get_all_records_that_are_new_or_changed_since_your_last_import() | |
for record in all_records_that_are_new_or_changed_since_your_last_import: | |
found = find_the_record_in_your_old_data(record) | |
if not found: | |
add_the_record(record) | |
if found: | |
change_whatever_bits_of_the_record_are_different(record) | |
all_your_existing_data = get_all_your_existing_data() |