Added the mySparkBatchApp.

Author: daisukenishino2

Azure/DotNet4ApacheSpark/mySparkBatchApp/mySparkBatchApp.sln

@@ -0,0 +1,25 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 16
+VisualStudioVersion = 16.0.30717.126
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "mySparkBatchApp", "mySparkBatchApp\mySparkBatchApp.csproj", "{1C6EC355-954D-4090-812C-8A77856BE22E}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{1C6EC355-954D-4090-812C-8A77856BE22E}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{1C6EC355-954D-4090-812C-8A77856BE22E}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{1C6EC355-954D-4090-812C-8A77856BE22E}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{1C6EC355-954D-4090-812C-8A77856BE22E}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {2105A144-A409-4E75-9511-D63CA8D55072}
+	EndGlobalSection
+EndGlobal

Azure/DotNet4ApacheSpark/mySparkBatchApp/mySparkBatchApp/Program.cs

@@ -0,0 +1,69 @@
+using System;
+using Microsoft.Spark.Sql;
+using static Microsoft.Spark.Sql.Functions;
+
+namespace mySparkBatchApp
+{
+    class Program
+    {
+        static void Main(string[] args)
+        {
+            //Console.WriteLine("Hello World!");
+
+            DateTime referenceDate = new DateTime(2015, 10, 20);
+
+            if (args.Length != 1)
+            {
+                Console.Error.WriteLine(
+                    "Usage: GitHubProjects <path to projects.csv>");
+                Environment.Exit(1);
+            }
+
+            string filePath = args[0];
+
+            SparkSession spark = SparkSession
+                .Builder()
+                .AppName("GitHub and Spark Batch")
+                .GetOrCreate();
+
+            DataFrame projectsDf = spark
+                .Read()
+                .Schema("id INT, url STRING, owner_id INT, " +
+                "name STRING, descriptor STRING, language STRING, " +
+                "created_at STRING, forked_from INT, deleted STRING, " +
+                "updated_at STRING")
+                .Csv(filePath);
+
+            projectsDf.Show();
+
+            // Drop any rows with NA values
+            DataFrameNaFunctions dropEmptyProjects = projectsDf.Na();
+            DataFrame cleanedProjects = dropEmptyProjects.Drop("any");
+
+            // Remove unnecessary columns
+            cleanedProjects = cleanedProjects.Drop("id", "url", "owner_id");
+            cleanedProjects.Show();
+
+            // Average number of times each language has been forked
+            DataFrame groupedDF = cleanedProjects
+                .GroupBy("language")
+                .Agg(Avg(cleanedProjects["forked_from"]));
+
+            // Sort by most forked languages first
+            groupedDF.OrderBy(Desc("avg(forked_from)")).Show();
+
+            spark.Udf().Register<string, bool>(
+                "MyUDF",
+                (date) => DateTime.TryParse(date, out DateTime convertedDate) &&
+                    (convertedDate > referenceDate));
+
+            cleanedProjects.CreateOrReplaceTempView("dateView");
+
+            DataFrame dateDf = spark.Sql(
+                "SELECT *, MyUDF(dateView.updated_at) AS datebefore FROM dateView");
+            dateDf.Show();
+
+            spark.Stop();
+        }
+    }
+}

Azure/DotNet4ApacheSpark/mySparkBatchApp/mySparkBatchApp/mySparkBatchApp.csproj

@@ -0,0 +1,18 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>netcoreapp3.1</TargetFramework>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.Spark" Version="1.0.0" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <None Update="projects_smaller.csv">
+      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
+    </None>
+  </ItemGroup>
+
+</Project>