Manually Setup Data Science Tools (DSTools) on Windows 10

dstools-setup-on-windows-10.md

dstools

Windows Data Science Tools

Directory Structure

DSTools\bin
DSTools\src

Source Files

• Java 1.8-202 - https://www.oracle.com/java/technologies/javase/javase8-archive-downloads.html
• Winpython 3.10.9 - https://github.com/winpython/winpython/releases/download/5.3.20221233/Winpython64-3.10.9.0.exe
• Spark 3.2.3 (Hadoop 3.2) - https://dlcdn.apache.org/spark/spark-3.2.3/spark-3.2.3-bin-hadoop3.2.tgz
• Scala 2.13 - https://downloads.lightbend.com/scala/2.13.0/scala-2.13.0.zip
• R 4.2.1 - https://cran.microsoft.com/snapshot/2022-10-15/bin/windows/base/R-4.2.1-win.exe
• Git 2.39.2 - https://github.com/git-for-windows/git/releases/download/v2.39.2.windows.1/PortableGit-2.39.2-64-bit.7z.exe

dstools.cmd

@echo off
rem DSTools Environment Setup

set DSTOOLSDIR=F:\DSTools

rem java
if exist %DSTOOLSDIR%\bin\jdk\bin\javac.exe set JAVA_HOME=%DSTOOLSDIR%\bin\jdk
if exist %DSTOOLSDIR%\bin\jdk\bin\javac.exe set JDK_HOME=%DSTOOLSDIR%\bin\jdk
if exist %DSTOOLSDIR%\bin\jdk\bin\javac.exe set JRE_HOME=%DSTOOLSDIR%\bin\jdk\jre
if exist %DSTOOLSDIR%\bin\jdk\bin\javac.exe set CLASSPATH=.;%JDK_HOME%\lib;%JRE_HOME%\lib
if exist %DSTOOLSDIR%\bin\jdk\bin\javac.exe set PATH=%JAVA_HOME%\bin;%PATH%

rem scala
set SCALA_HOME=%DSTOOLSDIR%\bin\scala

rem spark
set SPARK_HOME=%DSTOOLSDIR%\bin\spark
set HADOOP_HOME=%SPARK_HOME%

rem R & git
rem set PATH=%SPARK_HOME%\bin;%SCALA_HOME%\bin;%DSTOOLSDIR%\bin\R\bin\x64;%DSTOOLSDIR%\bin\winpython\scripts;%PATH%
set PATH=%SPARK_HOME%\bin;%SCALA_HOME%\bin;%DSTOOLSDIR%\bin\R\bin\x64;%DSTOOLSDIR%\bin\git;;%DSTOOLSDIR%\bin\git\bin;%PATH%

rem winpython
%DSTOOLSDIR%\bin\winpython\scripts\env.bat