From 2113e885b3d54078942e533ffbdeaa01aa3e40c0 Mon Sep 17 00:00:00 2001
From: Max O'Cull <max.ocull@protonmail.com>
Date: Sat, 20 Apr 2019 22:07:35 -0400
Subject: [PATCH] fix varchar and group by

---
 p4/src/main/java/cs448/Project4.java | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/p4/src/main/java/cs448/Project4.java b/p4/src/main/java/cs448/Project4.java
index 2e78af0..c4be7bf 100644
--- a/p4/src/main/java/cs448/Project4.java
+++ b/p4/src/main/java/cs448/Project4.java
@@ -133,7 +133,7 @@ public class Project4 {
         ratingDF.createOrReplaceTempView("Rating");
 
         // Compute the result.
-        Dataset<Row> resultDF = spark.sql("SELECT DISTINCT STR(m.movieId) FROM Movie m, Rating r, User u WHERE m.movieId = r.movieId AND r.userId = u.userId AND u.occupation = " +
+        Dataset<Row> resultDF = spark.sql("SELECT DISTINCT CONVERT(varchar(10), m.movieId) FROM Movie m, Rating r, User u WHERE m.movieId = r.movieId AND r.userId = u.userId AND u.occupation = " +
                 conf.q3Occupation + " AND r.rating = " + conf.q3Rating);
         resultDF.show();
         resultDF.write().text(CS448Utils.resolveUri(conf.outPath, "query-3"));
@@ -175,7 +175,7 @@ public class Project4 {
         // "SELECT m.title, r.average FROM Movie m, (SELECT AVG(r.rating) as average FROM Rating r, User u WHERE r.userId = u.userId AND u.age = " + conf.q4Age + ") r, User u WHERE m.movieId = r.movieId AND r.userId = u.userId AND u.age = " +
         // conf.q4Age);
         Dataset<Row> resultDF = spark.sql(
-                "SELECT m.title, AVG(r.rating) FROM Movie m, Rating r, User u WHERE m.movieId = r.movieId AND r.userId = u.userId AND u.age = " + conf.q4Age + " GROUP BY r.movieId");
+                "SELECT m.title, AVG(r.rating) FROM Movie m, Rating r, User u WHERE m.movieId = r.movieId AND r.userId = u.userId AND u.age = " + conf.q4Age + " GROUP BY m.title");
         resultDF.show();
         resultDF.write().text(CS448Utils.resolveUri(conf.outPath, "query-4"));