diff --git a/python/docs/Makefile b/python/docs/Makefile
index 903009790ba3b52d146f1afb0673ebee584c7b9d..905e0215c20c209963f1bbfd811e21f7e05c670b 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 316d7e30bcf10267b67872545e4df4c49170de1e..c064fe500c3c0f67a6e4d76542b8369f6f49c65c 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 4008332c84d0a2c9bd2ba67ee7fc094c8e707f07..11dfcfe13ee0d7f0562e7f07d4350280398c0f26 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 d473d6b534647432d155c863e46a7c3a9f417965..b4fa8368936a48430b124e0faafa10c17d4f134e 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