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

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

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

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",