From 3d1988c5584013d8706b1db2423b00ed49d500b0 Mon Sep 17 00:00:00 2001
From: Michael Kamprath <michael@kamprath.net>
Date: Sun, 27 Oct 2019 12:23:43 -0700
Subject: [PATCH] added same code for QFS

---
 ...-numbers.ipynb => prime-numbers-qfs.ipynb} | 39 ++++++++++++++++---
 1 file changed, 33 insertions(+), 6 deletions(-)
 rename jupyter-notebooks/prime-numbers/{prime-numbers.ipynb => prime-numbers-qfs.ipynb} (74%)

diff --git a/jupyter-notebooks/prime-numbers/prime-numbers.ipynb b/jupyter-notebooks/prime-numbers/prime-numbers-qfs.ipynb
similarity index 74%
rename from jupyter-notebooks/prime-numbers/prime-numbers.ipynb
rename to jupyter-notebooks/prime-numbers/prime-numbers-qfs.ipynb
index 477340c..451e33a 100644
--- a/jupyter-notebooks/prime-numbers/prime-numbers.ipynb
+++ b/jupyter-notebooks/prime-numbers/prime-numbers-qfs.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -17,16 +17,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "MAX_VALUE = 1000000000"
+    "MAX_VALUE = 10000000"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -69,7 +69,34 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "values.filter(F.col('is_prime')).count()"
+    "values.repartition(50).write.parquet('qfs:///test/prime-numbers', mode='overwrite')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = spark.read.parquet('qfs:///test/prime-numbers')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.count()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.filter(F.col('is_prime')).count()"
    ]
   },
   {
@@ -78,7 +105,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "values.filter(F.col('is_prime')).agg(F.max('value')).collect()"
+    "df.filter(F.col('is_prime')).agg(F.max('value').alias('max_prime')).collect()[0].max_prime"
    ]
   },
   {