diff options
| author | Holden Karau <holden@us.ibm.com> | 2016-04-14 09:42:15 +0100 |
|---|---|---|
| committer | Sean Owen <sowen@cloudera.com> | 2016-04-14 09:42:15 +0100 |
| commit | 478af2f45595913c9b8f560d13e8d88447486f99 (patch) | |
| tree | 0c078a5b722da4df50339dae6eacd18e3d2bd2cb /python/pyspark | |
| parent | b4819404a65f9b97c1f8deb1fcb8419969831574 (diff) | |
| download | spark-478af2f45595913c9b8f560d13e8d88447486f99.tar.gz spark-478af2f45595913c9b8f560d13e8d88447486f99.tar.bz2 spark-478af2f45595913c9b8f560d13e8d88447486f99.zip | |
[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.
Diffstat (limited to 'python/pyspark')
| -rw-r--r-- | python/pyspark/ml/regression.py | 2 | ||||
| -rw-r--r-- | python/pyspark/sql/context.py | 2 | ||||
| -rw-r--r-- | python/pyspark/sql/dataframe.py | 2 |
3 files changed, 3 insertions, 3 deletions
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 |