Corrections for CDH4 release and CDH5.

- updates CDH4 dependencies to final release (beta artifacts are no long available)
- remove use of CASE as variable name, since it became a reserved word in CDH5
- corrects error in gephi generation; corrected xml validates according to gephi xmlschema
- update pom version to reflect change

pom.xml

@@ -4,27 +4,28 @@
 
   <groupId>com.cloudera.science</groupId>
   <artifactId>ades</artifactId>
-  <version>0.1.0</version>
+  <version>0.2.0</version>
   <packaging>jar</packaging>
 
   <name>ades</name>
 
   <properties>
     <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
+    <hadoop.version>2.0.0-mr1-cdh4.0.0</hadoop.version>
   </properties>
 
   <dependencies>
     <dependency>
       <groupId>org.apache.hadoop</groupId>
       <artifactId>hadoop-core</artifactId>
-      <version>0.23.1-mr1-cdh4.0.0b2</version>
+      <version>${hadoop.version}</version>
       <scope>provided</scope>
     </dependency>
 
     <dependency>
       <groupId>org.apache.hadoop</groupId>
       <artifactId>hadoop-client</artifactId>
-      <version>0.23.1-mr1-cdh4.0.0b2</version>
+      <version>${hadoop.version}</version>
       <scope>provided</scope>
     </dependency>
 

src/main/pig/step1_join_drugs_reactions.pig

@@ -43,7 +43,7 @@ drugs = LOAD 'aers/drugs' USING PigStorage('$') AS (
     vbm: long, route: chararray, dose_vbm: chararray, dechal: chararray, rechal: chararray,
     lot: long, exp_dt: chararray, nda: long);
 demos = LOAD 'aers/demos' USING PigStorage('$') AS (
-    isr: long, case: int, if_cod: chararray, foll_seq: chararray, image: chararray,
+    isr: long, case_id: int, if_cod: chararray, foll_seq: chararray, image: chararray,
     event_dt: chararray, mfr_dt: chararray, fda_dt: chararray, rept_code: chararray,
     mfr_num: chararray, mfr_sndr: chararray, age: long, age_code: chararray,
     gender: chararray, e_sub: chararray, weight: long, wt_code: chararray,
@@ -70,8 +70,8 @@ demos = FILTER demos BY age_code == 'YR' and (gender == 'M' or gender == 'F') an
  * For simplicity, we simply choose the minimum ISR number for each case identifier
  * as the representative report for that patient.
  */
-demos_by_case = GROUP demos BY case;
-selected = FOREACH demos_by_case GENERATE MIN(demos.isr) as isr;
+demos_by_case_id = GROUP demos BY case_id;
+selected = FOREACH demos_by_case_id GENERATE MIN(demos.isr) as isr;
 
 /**
  * Now we filter the demographics data to only include the reports that we selected

src/main/python/gephi.py

@@ -44,7 +44,7 @@
  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://www.gexf.net/1.2draft http://www.gexf.net/1.2draft/gexf.xsd"
  version="1.2">
-  <meta lastmodifieddate="20111012">
+  <meta lastmodifieddate="2011-10-12">
     <creator>Cloudera</creator>
     <description>A network of drug-drug relationships</description>
   </meta>