colinpollock

""" Prints the probability of a successful shot given argv[1] attempts where 
each has an argv[2] probability of success.
"""

from __future__ import division

import random
import sys

colinpollock

from __future__ import division

import itertools
import math
import pprint
import random
import sys


INF = float('inf')

colinpollock

"""Readability

[Wiki](http://en.wikipedia.org/wiki/Flesch%E2%80%93Kincaid_readability_test)

The Flesch Reading Ease Score (FRES) is
206.835 - 1.015 * (#words / #sentences) - 84.6 * (#syllables / #words)

Example:
"The Australian platypus is seemingly a hybrid of a mammal and reptilian
creature."

colinpollock

#
# http://www.elasticsearch.org/guide/reference/modules/scripting/
#

# Create the index
curl -XPOST 'http://localhost:9200/people/' -d '{
    "settings" : {
    },
    "mappings" : {
        "person" : {

colinpollock

   public static ClientConfig getClientConfig(String connectionUrl) {
        ClientConfig clientConfig = new ClientConfig();
        LinkedHashSet<String> servers = new LinkedHashSet<String>();
        servers.add(connectionUrl);
        clientConfig.getServerProperties().put(ClientConstants.SERVER_LIST, servers);
        return clientConfig;
    }

    public static JestClient getClient(String connectionUrl) {
        JestClientFactory factory = new JestClientFactory();

colinpollock

IT'S GO TIME
GIDDYUP "Hello, Newman"
YADA YADA YADA

colinpollock

IT'S GO TIME

YO YO MA isLessThan20
IT'S IN THE VAULT  @IT'S NOT A LIE IF YOU BELIEVE IT
YO YO MA n
IT'S IN THE VAULT 0
YO YO MA multiple
IT'S IN THE VAULT @IT'S NOT A LIE IF YOU BELIEVE IT

CRY CRY AGAIN isLessThan20

colinpollock

from collections import defaultdict
import random


restaurants = [
    'za', 'jake', 'spoon', 'hacienda', 'bridgetender', 'river grill', 'rosie', 'sunnyside'
]

people = ['megan', 'jan', 'todd', 'colin', 'michelle']
random.shuffle(people)

colinpollock

"""Make initial clusters of categories to bootstrap top-level categories."""

from collections import defaultdict

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans, MiniBatchKMeans

from j_util import get_rows

colinpollock

import spacy
from spacy.pipeline import EntityRuler

nlp = spacy.load("en_core_web_sm")

ruler = EntityRuler(nlp, validate=True)
ruler.add_patterns[
    {
        "label": "PHRASE",
        "pattern": [