tomelm

ruby|ruby ⇒ ruby sample.rb lookup --business-id=tropisueño-san-francisco-3
Found business with id yelp-san-francisco:
{
  "categories": [
    {
      "alias": "localflavor",
      "title": "Local Flavor"
    },
    {
      "alias": "massmedia",

tomelm

{
    "location": {
        "city": "some_city",
        "state": "ABC"
    }
}

tomelm

require 'date'
require 'nokogiri'
require 'rest-client'
require 'reverse_markdown'

# Match [caption <stuff>]...[/caption] tags
# example: http://rubular.com/r/r2FH3QSOpL
CAPTION_REGEX = /\[caption.*\](?=.*\[)|\[\/caption\]/

tomelm

# clf = sklearn.linear_model.LogisticRegression
# significant_terms = set of terms appearing more than n times in training
def classify(left_name, right_name):
    """
    Classifies names using delta term analysis.
    :return:
        A tuple (p_is_duplicate, exact_match_rare_terms, one_side_rare_terms).

        * p_is_duplicate is the score from the log-linear classifier. It's
          probably the most relevant signal.

tomelm

# -*- coding: utf-8 -*-
import itertools
import re
import urlparse
 
import boto
import warc
 
from boto.s3.key import Key
from gzipstream import GzipStreamFile

tomelm

require 'aws-sdk'
require 'json'

REGION = 'us-west-2'
QUEUE_NAME = 'c0wl-cloudtrail'

s3  = Aws::S3::Client.new(region: REGION)
sqs = Aws::SQS::Client.new(region: REGION)

queue_url = sqs.get_queue_url(queue_name: QUEUE_NAME).queue_url

tomelm

{
  "query" : "cheap restaurants",
  "language" : "en",
  "queryAnnotations" : [ 
    {
      "type" : "RawTokenQueryAnnotation",
      "offset" : 0,
      "length" : 5,
      "queryText" : "cheap"
    },

tomelm

with mock.patch("%s.restart_server" % module_under_test, autospec=True) as mock_restart:
    restart_servers_in_datacenter(servers, "sfo")
    mock_restart.assert_called_once()

tomelm

SELECT
    r.id as restaurant_id,
    rez_sheet.shift as shift,
    start AT TIME ZONE r.timezone as start_time,
    "end" AT TIME ZONE r.timezone as end_time
FROM
    rez_sheet,rez_schedule rs,rez_restaurant r
WHERE
    r.id = rez_sheet.restaurant_id AND
    rs.sheet_id = rez_sheet.id;

tomelm

{
  "visit_time": "2014-10-16 09:44:57",
  "title": "Pizza New York, NY",
  "url": "http://www.yelp.com/search?find_desc=pizza&find_loc=NYC"
}