dkincaid

library(RJSONIO)
library(ggplot2)

api.uri <- "http://api.infochimps.com/"
acs.topline <- "social/demographics/us_census/topline/search?"
api.key <- "apikey=xxxxxxxxxx" # replace the x's with your Infochimps API key

radius <- 10000  # in meters
lat <- 44.768202
long <- -91.491603

dkincaid

geocode = function(location) {
  library(RJSONIO)
  api.uri = "http://api.infochimps.com/"
  geocode.uri = "geo/utils/geolocate?"
  api.key = "apikey=xxxxxxxxxxxx"

  print(location)
  uri = paste(api.uri, geocode.uri, api.key, "&f.address_text=", location, sep="")
  raw.data = readLines(uri, warn="F")
  results = fromJSON(raw.data)

dkincaid

(defn standard-tokenizer [text]
  "Uses the Lucene StandardTokenizer to tokenize the given text. Returns a vector containing
the tokens."
  (let [analyzer (StandardAnalyzer. Version/LUCENE_31)
        tokenstream (.tokenStream analyzer "field" (StringReader. text))
        termatt (.addAttribute tokenstream TermAttribute)
        terms []]
    (while (.incrementToken tokenstream)
      (print (.term termatt)))))

dkincaid

(ns transaction.queries
  (:use [cascalog.api])
  (:require [cascalog.ops :as c]
            [cascalog.tap :as tap]
            [cascalog.workflow :as w])
  (:import [com.google.common.hash Hashing]
           [org.joda.time.format DateTimeFormat]
           [cascading.scheme.hadoop TextDelimited])
  (:gen-class))

dkincaid

@Test
public void changeNameTest() {
  MutableClass original_name = new MutableClass("my name");
  MutableClass expected_name = original_name;

  NameFilter filter = new NameFilter();
  MutableClass new_name = filter.changeName(original_name,
                                            "new name");

  assertEquals(new_name, expected_name);

dkincaid

@Test
public void changeNameTest() {
  MutableClass original_name = new MutableClass("my name");
  MutableClass expected_name = new MutableClass("my name");

  NameFilter filter = new NameFilter();
  MutableClass new_name = filter.changeName(original_name,
                                            "new name");

  assertEquals(new_name, expected_name);

dkincaid

public MutableClass changeName(MutableClass oldNameClass, String newName) {
  MutableClass newNameClass = new MutableClass();
  newNameClass = oldNameClass;
  newNameClass.setName(newName);

  return newNameClass;
}

dkincaid

/* If I execute only the clientQuery or only the emailQuery by themselves everything works right.
   I set breakpoints inside the ExtractClientEdgeFields() and ExtractClientId() functions and they
   are called with only the Data objects with the correct property types.
   
   However, if I execute this query as it is shown here then only one of the two functions is called
   with all of the Data objects from both taps. */
public static Subquery clientEmail(String pailPath) {
  PailTap clientEdgeTap = clientEdgeTap(pailPath);
  PailTap clientTap = petOwnerTap(pailPath);

dkincaid

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

dkincaid

grammar MinRtf ;

document : (control | text )+ ;

text : TEXT ;

control : KEYWORD INT? SPACE? ;

KEYWORD : '\\' (ASCIILETTER)+ ;