scottrice10

Use extractDocs.py to parse and index the StackOverflow posts.xml file into an existing index.
 
Usage: extractDocs.py [options] file
 
Options:
  -h, --help            show this help message and exit
  -s SERVER, --server=SERVER
                        ElasticSearch Server
  -i INDEX, --index=INDEX
                        Index name to use

scottrice10

#!/usr/bin/env python2.7
import csv
from pyes import *
 
reader = csv.reader(open('npidata_20050523-20130811.csv', 'rb'))
 
conn = ES('localhost:9200', timeout=20.0)
 
counter = 0
for row in reader:

scottrice10

#!/usr/bin/env python
 
import requests
import json
 
data = []
limit = 100
offset = 740
chunks = 74
 

scottrice10

curl -XPUT 'localhost:9200/doctors_index' -d '
{
    "settings": {
        "number_of_shards": 16,
        "number_of_replicas": 0,
        "index.refresh_interval": 120,
        "analysis": {
            "analyzer": {
                "autocomplete": {
                    "type": "custom",

scottrice10

"settings" : { 
   "analysis" : {
       "filter" : {
           "blocks_filter" : {
               "type" : "word_delimiter",
               "preserve_original": "true"
           },
          "shingle":{
              "type":"shingle",
              "max_shingle_size":5,

scottrice10

curl -XPUT 'localhost:9200/doctors_index' -d '
{
    "settings": {
        "analysis": {
            "analyzer": {
                "autocomplete": {
                    "type": "custom",
                    "tokenizer": "standard",
                    "filter": ["standard", "lowercase", "kstem", "edgeNGram"]
                }

scottrice10

# all apache files need writeable permissions for this script to run
import sys, inspect, os, shutil
home = os.path.expanduser("~")
top = home + '/git'
apacheRoot = '/Library/WebServer/Documents/'

#first remind user to have proper permissions on /etc/apache2/
var = raw_input("\nScript requires that /etc/apache2/ is writeable. Running 'sudo chmod -R 777 /etc/apache2' will accomplish this. Enter 'y' to proceed.\n")
if var != 'y':
	sys.exit(0)

scottrice10

var globalTimeout = 120000;

/***************************************************************
 ** set configs for protractor tests
 **
 ***************************************************************/
exports.config = {

  //directConnect: true,

scottrice10

//Problem: variation of Josephus problem
// Take a second to imagine that you are in a room with 100 chairs arranged in a circle.
//These chairs are numbered sequentially from One to One Hundred.
//At some point in time, the person in chair #1 will be told to leave the room.
//The person in chair #2 will be skipped, and the person in chair #3 will be told to leave.
//Next to go is person in chair #6. In other words, 1 person will be skipped initially, and then 2, 3, 4.. and so on.
//This pattern of skipping will keep going around the circle until there is only one person remaining.. the survivor.
//Note that the chair is removed when the person leaves the room.
//
//Write a program to figure out which chair the survivor is sitting in.

scottrice10

[
    {
        "jmhVersion" : "1.32",
        "benchmark" : "com.rallyhealth.mongo.v13.FutureMongoCollectionBench.aggregate",
        "mode" : "thrpt",
        "threads" : 10,
        "forks" : 1,
        "jvm" : "/Users/scott.rice/.sdkman/candidates/java/8.0.292.hs-adpt/jre/bin/java",
        "jvmArgs" : [
            "-Xmx2G",