Add PySpark README and run scripts.

core/src/main/scala/spark/SparkContext.scala

@@ -113,7 +113,7 @@ class SparkContext(
   // Environment variables to pass to our executors
   private[spark] val executorEnvs = HashMap[String, String]()
   for (key <- Seq("SPARK_MEM", "SPARK_CLASSPATH", "SPARK_LIBRARY_PATH", "SPARK_JAVA_OPTS",
-       "SPARK_TESTING")) {
+       "SPARK_TESTING", "PYTHONPATH")) {
     val value = System.getenv(key)
     if (value != null) {
       executorEnvs(key) = value

pyspark/README

+# PySpark
+
+PySpark is a Python API for Spark.
+
+PySpark jobs are writen in Python and executed using a standard Python
+interpreter; this supports modules that use Python C extensions.  The
+API is based on the Spark Scala API and uses regular Python functions
+and lambdas to support user-defined functions.  PySpark supports
+interactive use through a standard Python interpreter; it can
+automatically serialize closures and ship them to worker processes.
+
+PySpark is built on top of the Spark Java API.  Data is uniformly
+represented as serialized Python objects and stored in Spark Java
+processes, which communicate with PySpark worker processes over pipes.
+
+## Features
+
+PySpark supports most of the Spark API, including broadcast variables.
+RDDs are dynamically typed and can hold any Python object.
+
+PySpark does not support:
+
+- Special functions on RDDs of doubles
+- Accumulators
+
+## Examples and Documentation
+
+The PySpark source contains docstrings and doctests that document its
+API.  The public classes are in `context.py` and `rdd.py`.
+
+The `pyspark/pyspark/examples` directory contains a few complete
+examples.
+
+## Installing PySpark
+
+PySpark requires a development version of Py4J, a Python library for
+interacting with Java processes.  It can be installed from
+https://github.com/bartdag/py4j; make sure to install a version that
+contains at least the commits through 3dbf380d3d.
+
+PySpark uses the `PYTHONPATH` environment variable to search for Python
+classes; Py4J should be on this path, along with any libraries used by
+PySpark programs.  `PYTHONPATH` will be automatically shipped to worker
+machines, but the files that it points to must be present on each
+machine.
+
+PySpark requires the Spark assembly JAR, which can be created by running
+`sbt/sbt assembly` in the Spark directory.
+
+Additionally, `SPARK_HOME` should be set to the location of the Spark
+package.
+
+## Running PySpark
+
+The easiest way to run PySpark is to use the `run-pyspark` and
+`pyspark-shell` scripts, which are included in the `pyspark` directory.
+These scripts automatically load the `spark-conf.sh` file, set
+`SPARK_HOME`, and add the `pyspark` package to the `PYTHONPATH`.

pyspark/pyspark-shell

+#!/bin/sh
+FWDIR="`dirname $0`"
+exec $FWDIR/run-pyspark $FWDIR/pyspark/shell.py "$@"

pyspark/pyspark/context.py

@@ -18,14 +18,13 @@ class SparkContext(object):
     asPickle = jvm.spark.api.python.PythonRDD.asPickle
     arrayAsPickle = jvm.spark.api.python.PythonRDD.arrayAsPickle
 
-    def __init__(self, master, name, defaultParallelism=None,
-                 pythonExec='python'):
+    def __init__(self, master, name, defaultParallelism=None):
         self.master = master
         self.name = name
         self._jsc = self.jvm.JavaSparkContext(master, name)
         self.defaultParallelism = \
             defaultParallelism or self._jsc.sc().defaultParallelism()
-        self.pythonExec = pythonExec
+        self.pythonExec = os.environ.get("PYSPARK_PYTHON_EXEC", 'python')
         # Broadcast's __reduce__ method stores Broadcast instances here.
         # This allows other code to determine which Broadcast instances have
         # been pickled, so it can determine which Java broadcast objects to

pyspark/pyspark/examples/wordcount.py

+import sys
+from operator import add
+from pyspark.context import SparkContext
+
+if __name__ == "__main__":
+    if len(sys.argv) < 3:
+        print >> sys.stderr, \
+            "Usage: PythonWordCount <master> <file>"
+        exit(-1)
+    sc = SparkContext(sys.argv[1], "PythonWordCount")
+    lines = sc.textFile(sys.argv[2], 1)
+    counts = lines.flatMap(lambda x: x.split(' ')) \
+                  .map(lambda x: (x, 1)) \
+                  .reduceByKey(add)
+    output = counts.collect()
+    for (word, count) in output:
+        print "%s : %i" % (word, count)

pyspark/pyspark/shell.py

+"""
+An interactive shell.
+"""
+import code
+import sys
+
+from pyspark.context import SparkContext
+
+
+def main(master='local'):
+    sc = SparkContext(master, 'PySparkShell')
+    print "Spark context available as sc."
+    code.interact(local={'sc': sc})
+
+
+if __name__ == '__main__':
+    if len(sys.argv) > 1:
+        master = sys.argv[1]
+    else:
+        master = 'local'
+    main(master)

pyspark/run-pyspark

+#!/bin/bash
+
+# Figure out where the Scala framework is installed
+FWDIR="$(cd `dirname $0`; cd ../; pwd)"
+
+# Export this as SPARK_HOME
+export SPARK_HOME="$FWDIR"
+
+# Load environment variables from conf/spark-env.sh, if it exists
+if [ -e $FWDIR/conf/spark-env.sh ] ; then
+  . $FWDIR/conf/spark-env.sh
+fi
+
+# Figure out which Python executable to use
+if [ -z "$PYSPARK_PYTHON" ] ; then
+  PYSPARK_PYTHON="python"
+fi
+export PYSPARK_PYTHON
+
+# Add the PySpark classes to the Python path:
+export PYTHONPATH=$SPARK_HOME/pyspark/:$PYTHONPATH
+
+exec "$PYSPARK_PYTHON" "$@"