From 14ff3cd1ae5bcd1334c3628c81e9f354bdee6b4f Mon Sep 17 00:00:00 2001
From: Michael Kamprath <michael@kamprath.net>
Date: Sat, 27 Jun 2020 23:35:24 -0700
Subject: [PATCH] added pyarrow to support spark 3 pandas

---
 spark-qfs-swarm/worker-node/Dockerfile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/spark-qfs-swarm/worker-node/Dockerfile b/spark-qfs-swarm/worker-node/Dockerfile
index 04f74ed..acf1b99 100644
--- a/spark-qfs-swarm/worker-node/Dockerfile
+++ b/spark-qfs-swarm/worker-node/Dockerfile
@@ -99,7 +99,7 @@ RUN mkdir -p /data/spark \
 
 # add python libraries useful in PySpark
 RUN python3 -mpip install matplotlib \
-	&& pip3 install pandas seaborn
+	&& pip3 install pandas seaborn pyarrow
 
 # copy QFS and Spark configurations
 COPY ./qfs-conf/* $QFS_HOME/conf/