From 478af2f45595913c9b8f560d13e8d88447486f99 Mon Sep 17 00:00:00 2001
From: Holden Karau <holden@us.ibm.com>
Date: Thu, 14 Apr 2016 09:42:15 +0100
Subject: [SPARK-14573][PYSPARK][BUILD] Fix PyDoc Makefile & highlighting
 issues

## What changes were proposed in this pull request?

The PyDoc Makefile used "=" rather than "?=" for setting env variables so it overwrote the user values. This ignored the environment variables we set for linting allowing warnings through. This PR also fixes the warnings that had been introduced.

## How was this patch tested?

manual local export & make

Author: Holden Karau <holden@us.ibm.com>

Closes #12336 from holdenk/SPARK-14573-fix-pydoc-makefile.
---
 python/docs/Makefile            | 8 ++++----
 python/pyspark/ml/regression.py | 2 +-
 python/pyspark/sql/context.py   | 2 +-
 python/pyspark/sql/dataframe.py | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'python')

diff --git a/python/docs/Makefile b/python/docs/Makefile
index 903009790b..905e0215c2 100644
--- a/python/docs/Makefile
+++ b/python/docs/Makefile
@@ -2,10 +2,10 @@
 #
 
 # You can set these variables from the command line.
-SPHINXOPTS    =
-SPHINXBUILD   = sphinx-build
-PAPER         =
-BUILDDIR      = _build
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+PAPER         ?=
+BUILDDIR      ?= _build
 
 export PYTHONPATH=$(realpath ..):$(realpath ../lib/py4j-0.9.2-src.zip)
 
diff --git a/python/pyspark/ml/regression.py b/python/pyspark/ml/regression.py
index 316d7e30bc..c064fe500c 100644
--- a/python/pyspark/ml/regression.py
+++ b/python/pyspark/ml/regression.py
@@ -28,7 +28,7 @@ from pyspark.sql import DataFrame
 __all__ = ['AFTSurvivalRegression', 'AFTSurvivalRegressionModel',
            'DecisionTreeRegressor', 'DecisionTreeRegressionModel',
            'GBTRegressor', 'GBTRegressionModel',
-           'GeneralizedLinearRegression', 'GeneralizedLinearRegressionModel'
+           'GeneralizedLinearRegression', 'GeneralizedLinearRegressionModel',
            'IsotonicRegression', 'IsotonicRegressionModel',
            'LinearRegression', 'LinearRegressionModel',
            'LinearRegressionSummary', 'LinearRegressionTrainingSummary',
diff --git a/python/pyspark/sql/context.py b/python/pyspark/sql/context.py
index 4008332c84..11dfcfe13e 100644
--- a/python/pyspark/sql/context.py
+++ b/python/pyspark/sql/context.py
@@ -405,7 +405,7 @@ class SQLContext(object):
         >>> sqlContext.createDataFrame(rdd, "boolean").collect() # doctest: +IGNORE_EXCEPTION_DETAIL
         Traceback (most recent call last):
             ...
-        Py4JJavaError:...
+        Py4JJavaError: ...
         """
         if isinstance(data, DataFrame):
             raise TypeError("data is already a DataFrame")
diff --git a/python/pyspark/sql/dataframe.py b/python/pyspark/sql/dataframe.py
index d473d6b534..b4fa836893 100644
--- a/python/pyspark/sql/dataframe.py
+++ b/python/pyspark/sql/dataframe.py
@@ -60,7 +60,7 @@ class DataFrame(object):
         people = sqlContext.read.parquet("...")
         department = sqlContext.read.parquet("...")
 
-        people.filter(people.age > 30).join(department, people.deptId == department.id)) \
+        people.filter(people.age > 30).join(department, people.deptId == department.id)\
           .groupBy(department.name, "gender").agg({"salary": "avg", "age": "max"})
 
     .. note:: Experimental
-- 
cgit v1.2.3