#include "stdafx.h"
#define BUFSIZE 4096
#define VARNAME TEXT("MAHOUT_CP")
int _tmain(int argc, _TCHAR* argv[]) {
    DWORD dwLength;     LPTSTR pszBuffer;
    pszBuffer = (LPTSTR)malloc(BUFSIZE*sizeof(TCHAR));
    dwLength = GetEnvironmentVariable(VARNAME, pszBuffer, BUFSIZE);
    if (dwLength > 0) { _tprintf(TEXT("%sn"), pszBuffer); return 0; }
    return 1;
}

set SCALA_HOME=C:Progra~2scala
set SPARK_HOME=C:spark
set HADOOP_HOME=C:hadoop
set MAHOUT_HOME=C:mahout
set SPARK_SCALA_VERSION=2.10
set MASTER=local[2]
set MAHOUT_LOCAL=true
set path=%SCALA_HOME%bin;%SPARK_HOME%bin;%PATH%
cd /D %SPARK_HOME%
set SPARK_CP=%SPARK_HOME%conf;%SPARK_HOME%libxxx.jar;...other jars...
set MAHOUT_CP=%MAHOUT_HOME%libxxx.jar;...other jars...;%MAHOUT_HOME%xxx.jar;...other jars...;%SPARK_CP%;%MAHOUT_HOME%libsparkxxx.jar;%MAHOUT_HOME%libhadoopxxx.jar;%MAHOUT_HOME%srcconf;%JAVA_HOME%libtools.jar
start "master0" "%JAVA_HOME%binjava" -cp "%SPARK_CP%" -Xms1g -Xmx1g org.apache.spark.deploy.master.Master --ip localhost --port 7077 --webui-port 8082 >>out-master0.log 2>>out-master0.err
start "worker1" "%JAVA_HOME%binjava" -cp "%SPARK_CP%" -Xms1g -Xmx1g org.apache.spark.deploy.worker.Worker spark://localhost:7077 --webui-port 8083 >>out-worker1.log 2>>out-worker1.err
...you may add more workers here...
cd /D %MAHOUT_HOME%
"%JAVA_HOME%binjava" -Xmx4g -classpath "%MAHOUT_CP%" "org.apache.mahout.sparkbindings.shell.Main"

https://mahout.apache.org/users/sparkbindings/play-with-shell.html

"C:Program Files (x86)GoogleChromeApplicationchrome" --disable-web-security http://localhost:4040

mkdir C:tmphive

%HADOOP_HOME%binwinutils.exe chmod 777 /tmp/hive

%SPARK_HOME%binspark-shell

import sys
import os
spark_home = 'C:Apachespark-1.6.1'

sys.path.insert(0, os.path.join(spark_home, 'python'))
sys.path.insert(0, os.path.join(spark_home, 'pythonlibpyspark.zip'))
sys.path.insert(0, os.path.join(spark_home, 'pythonlibpy4j-0.9-src.zip'))

# Start a spark context:
sc = pyspark.SparkContext()

#
lines = sc.textFile(os.path.join(spark_home, "README.md")
pythonLines = lines.filter(lambda line: "Python" in line)
pythonLines.first()

C:UsersDesktopAsparkbin>spark-shell

C:UsersDesktopAsparkbin>pyspark

pip install findspark

import findspark
findspark.init()

from pyspark import SparkContext
from pyspark import SparkConf