You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by gu...@apache.org on 2018/01/28 01:33:14 UTC
spark git commit: [SPARK-23248][PYTHON][EXAMPLES] Relocate module
docstrings to the top in PySpark examples
Repository: spark
Updated Branches:
refs/heads/master 3227d14fe -> b8c32dc57
[SPARK-23248][PYTHON][EXAMPLES] Relocate module docstrings to the top in PySpark examples
## What changes were proposed in this pull request?
This PR proposes to relocate the docstrings in modules of examples to the top. Seems these are mistakes. So, for example, the below codes
```python
>>> help(aft_survival_regression)
```
shows the module docstrings for examples as below:
**Before**
```
Help on module aft_survival_regression:
NAME
aft_survival_regression
...
DESCRIPTION
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
...
(END)
```
**After**
```
Help on module aft_survival_regression:
NAME
aft_survival_regression
...
DESCRIPTION
An example demonstrating aft survival regression.
Run with:
bin/spark-submit examples/src/main/python/ml/aft_survival_regression.py
(END)
```
## How was this patch tested?
Manually checked.
Author: hyukjinkwon <gu...@gmail.com>
Closes #20416 from HyukjinKwon/module-docstring-example.
Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/b8c32dc5
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/b8c32dc5
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/b8c32dc5
Branch: refs/heads/master
Commit: b8c32dc57368e49baaacf660b7e8836eedab2df7
Parents: 3227d14
Author: hyukjinkwon <gu...@gmail.com>
Authored: Sun Jan 28 10:33:06 2018 +0900
Committer: hyukjinkwon <gu...@gmail.com>
Committed: Sun Jan 28 10:33:06 2018 +0900
----------------------------------------------------------------------
examples/src/main/python/avro_inputformat.py | 14 +++++++-------
.../src/main/python/ml/aft_survival_regression.py | 11 +++++------
.../src/main/python/ml/bisecting_k_means_example.py | 11 +++++------
.../ml/bucketed_random_projection_lsh_example.py | 12 +++++-------
.../src/main/python/ml/chi_square_test_example.py | 10 +++++-----
examples/src/main/python/ml/correlation_example.py | 10 +++++-----
examples/src/main/python/ml/cross_validator.py | 15 +++++++--------
examples/src/main/python/ml/fpgrowth_example.py | 9 ++++-----
.../src/main/python/ml/gaussian_mixture_example.py | 11 +++++------
.../ml/generalized_linear_regression_example.py | 11 +++++------
examples/src/main/python/ml/imputer_example.py | 9 ++++-----
.../main/python/ml/isotonic_regression_example.py | 9 +++------
examples/src/main/python/ml/kmeans_example.py | 15 +++++++--------
examples/src/main/python/ml/lda_example.py | 12 +++++-------
.../python/ml/logistic_regression_summary_example.py | 11 +++++------
examples/src/main/python/ml/min_hash_lsh_example.py | 12 +++++-------
examples/src/main/python/ml/one_vs_rest_example.py | 13 ++++++-------
.../src/main/python/ml/train_validation_split.py | 13 ++++++-------
examples/src/main/python/parquet_inputformat.py | 12 ++++++------
examples/src/main/python/sql/basic.py | 11 +++++------
examples/src/main/python/sql/datasource.py | 11 +++++------
examples/src/main/python/sql/hive.py | 11 +++++------
22 files changed, 115 insertions(+), 138 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/avro_inputformat.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/avro_inputformat.py b/examples/src/main/python/avro_inputformat.py
index 4422f9e..6286ba6 100644
--- a/examples/src/main/python/avro_inputformat.py
+++ b/examples/src/main/python/avro_inputformat.py
@@ -15,13 +15,6 @@
# limitations under the License.
#
-from __future__ import print_function
-
-import sys
-
-from functools import reduce
-from pyspark.sql import SparkSession
-
"""
Read data file users.avro in local Spark distro:
@@ -50,6 +43,13 @@ $ ./bin/spark-submit --driver-class-path /path/to/example/jar \
{u'favorite_color': None, u'name': u'Alyssa'}
{u'favorite_color': u'red', u'name': u'Ben'}
"""
+from __future__ import print_function
+
+import sys
+
+from functools import reduce
+from pyspark.sql import SparkSession
+
if __name__ == "__main__":
if len(sys.argv) != 2 and len(sys.argv) != 3:
print("""
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/aft_survival_regression.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/aft_survival_regression.py b/examples/src/main/python/ml/aft_survival_regression.py
index 2f0ca99..0a71f76 100644
--- a/examples/src/main/python/ml/aft_survival_regression.py
+++ b/examples/src/main/python/ml/aft_survival_regression.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+An example demonstrating aft survival regression.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/aft_survival_regression.py
+"""
from __future__ import print_function
# $example on$
@@ -23,12 +28,6 @@ from pyspark.ml.linalg import Vectors
# $example off$
from pyspark.sql import SparkSession
-"""
-An example demonstrating aft survival regression.
-Run with:
- bin/spark-submit examples/src/main/python/ml/aft_survival_regression.py
-"""
-
if __name__ == "__main__":
spark = SparkSession \
.builder \
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/bisecting_k_means_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/bisecting_k_means_example.py b/examples/src/main/python/ml/bisecting_k_means_example.py
index 1263cb5..7842d20 100644
--- a/examples/src/main/python/ml/bisecting_k_means_example.py
+++ b/examples/src/main/python/ml/bisecting_k_means_example.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+An example demonstrating bisecting k-means clustering.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/bisecting_k_means_example.py
+"""
from __future__ import print_function
# $example on$
@@ -22,12 +27,6 @@ from pyspark.ml.clustering import BisectingKMeans
# $example off$
from pyspark.sql import SparkSession
-"""
-An example demonstrating bisecting k-means clustering.
-Run with:
- bin/spark-submit examples/src/main/python/ml/bisecting_k_means_example.py
-"""
-
if __name__ == "__main__":
spark = SparkSession\
.builder\
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/bucketed_random_projection_lsh_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/bucketed_random_projection_lsh_example.py b/examples/src/main/python/ml/bucketed_random_projection_lsh_example.py
index 1b7a458..610176e 100644
--- a/examples/src/main/python/ml/bucketed_random_projection_lsh_example.py
+++ b/examples/src/main/python/ml/bucketed_random_projection_lsh_example.py
@@ -15,7 +15,11 @@
# limitations under the License.
#
-
+"""
+An example demonstrating BucketedRandomProjectionLSH.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/bucketed_random_projection_lsh_example.py
+"""
from __future__ import print_function
# $example on$
@@ -25,12 +29,6 @@ from pyspark.sql.functions import col
# $example off$
from pyspark.sql import SparkSession
-"""
-An example demonstrating BucketedRandomProjectionLSH.
-Run with:
- bin/spark-submit examples/src/main/python/ml/bucketed_random_projection_lsh_example.py
-"""
-
if __name__ == "__main__":
spark = SparkSession \
.builder \
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/chi_square_test_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/chi_square_test_example.py b/examples/src/main/python/ml/chi_square_test_example.py
index 8f25318..2af7e68 100644
--- a/examples/src/main/python/ml/chi_square_test_example.py
+++ b/examples/src/main/python/ml/chi_square_test_example.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+An example for Chi-square hypothesis testing.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/chi_square_test_example.py
+"""
from __future__ import print_function
from pyspark.sql import SparkSession
@@ -23,11 +28,6 @@ from pyspark.ml.linalg import Vectors
from pyspark.ml.stat import ChiSquareTest
# $example off$
-"""
-An example for Chi-square hypothesis testing.
-Run with:
- bin/spark-submit examples/src/main/python/ml/chi_square_test_example.py
-"""
if __name__ == "__main__":
spark = SparkSession \
.builder \
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/correlation_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/correlation_example.py b/examples/src/main/python/ml/correlation_example.py
index 0a9d30d..1f4e402 100644
--- a/examples/src/main/python/ml/correlation_example.py
+++ b/examples/src/main/python/ml/correlation_example.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+An example for computing correlation matrix.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/correlation_example.py
+"""
from __future__ import print_function
# $example on$
@@ -23,11 +28,6 @@ from pyspark.ml.stat import Correlation
# $example off$
from pyspark.sql import SparkSession
-"""
-An example for computing correlation matrix.
-Run with:
- bin/spark-submit examples/src/main/python/ml/correlation_example.py
-"""
if __name__ == "__main__":
spark = SparkSession \
.builder \
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/cross_validator.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/cross_validator.py b/examples/src/main/python/ml/cross_validator.py
index db70543..6256d11 100644
--- a/examples/src/main/python/ml/cross_validator.py
+++ b/examples/src/main/python/ml/cross_validator.py
@@ -15,6 +15,13 @@
# limitations under the License.
#
+"""
+A simple example demonstrating model selection using CrossValidator.
+This example also demonstrates how Pipelines are Estimators.
+Run with:
+
+ bin/spark-submit examples/src/main/python/ml/cross_validator.py
+"""
from __future__ import print_function
# $example on$
@@ -26,14 +33,6 @@ from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
# $example off$
from pyspark.sql import SparkSession
-"""
-A simple example demonstrating model selection using CrossValidator.
-This example also demonstrates how Pipelines are Estimators.
-Run with:
-
- bin/spark-submit examples/src/main/python/ml/cross_validator.py
-"""
-
if __name__ == "__main__":
spark = SparkSession\
.builder\
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/fpgrowth_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/fpgrowth_example.py b/examples/src/main/python/ml/fpgrowth_example.py
index c92c3c2..39092e6 100644
--- a/examples/src/main/python/ml/fpgrowth_example.py
+++ b/examples/src/main/python/ml/fpgrowth_example.py
@@ -15,16 +15,15 @@
# limitations under the License.
#
-# $example on$
-from pyspark.ml.fpm import FPGrowth
-# $example off$
-from pyspark.sql import SparkSession
-
"""
An example demonstrating FPGrowth.
Run with:
bin/spark-submit examples/src/main/python/ml/fpgrowth_example.py
"""
+# $example on$
+from pyspark.ml.fpm import FPGrowth
+# $example off$
+from pyspark.sql import SparkSession
if __name__ == "__main__":
spark = SparkSession\
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/gaussian_mixture_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/gaussian_mixture_example.py b/examples/src/main/python/ml/gaussian_mixture_example.py
index e4a0d31..4938a90 100644
--- a/examples/src/main/python/ml/gaussian_mixture_example.py
+++ b/examples/src/main/python/ml/gaussian_mixture_example.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+A simple example demonstrating Gaussian Mixture Model (GMM).
+Run with:
+ bin/spark-submit examples/src/main/python/ml/gaussian_mixture_example.py
+"""
from __future__ import print_function
# $example on$
@@ -22,12 +27,6 @@ from pyspark.ml.clustering import GaussianMixture
# $example off$
from pyspark.sql import SparkSession
-"""
-A simple example demonstrating Gaussian Mixture Model (GMM).
-Run with:
- bin/spark-submit examples/src/main/python/ml/gaussian_mixture_example.py
-"""
-
if __name__ == "__main__":
spark = SparkSession\
.builder\
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/generalized_linear_regression_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/generalized_linear_regression_example.py b/examples/src/main/python/ml/generalized_linear_regression_example.py
index 796752a..a52f465 100644
--- a/examples/src/main/python/ml/generalized_linear_regression_example.py
+++ b/examples/src/main/python/ml/generalized_linear_regression_example.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+An example demonstrating generalized linear regression.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/generalized_linear_regression_example.py
+"""
from __future__ import print_function
from pyspark.sql import SparkSession
@@ -22,12 +27,6 @@ from pyspark.sql import SparkSession
from pyspark.ml.regression import GeneralizedLinearRegression
# $example off$
-"""
-An example demonstrating generalized linear regression.
-Run with:
- bin/spark-submit examples/src/main/python/ml/generalized_linear_regression_example.py
-"""
-
if __name__ == "__main__":
spark = SparkSession\
.builder\
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/imputer_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/imputer_example.py b/examples/src/main/python/ml/imputer_example.py
index b8437f8..9ba0147 100644
--- a/examples/src/main/python/ml/imputer_example.py
+++ b/examples/src/main/python/ml/imputer_example.py
@@ -15,16 +15,15 @@
# limitations under the License.
#
-# $example on$
-from pyspark.ml.feature import Imputer
-# $example off$
-from pyspark.sql import SparkSession
-
"""
An example demonstrating Imputer.
Run with:
bin/spark-submit examples/src/main/python/ml/imputer_example.py
"""
+# $example on$
+from pyspark.ml.feature import Imputer
+# $example off$
+from pyspark.sql import SparkSession
if __name__ == "__main__":
spark = SparkSession\
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/isotonic_regression_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/isotonic_regression_example.py b/examples/src/main/python/ml/isotonic_regression_example.py
index 6ae15f1..89cba9d 100644
--- a/examples/src/main/python/ml/isotonic_regression_example.py
+++ b/examples/src/main/python/ml/isotonic_regression_example.py
@@ -17,6 +17,9 @@
"""
Isotonic Regression Example.
+
+Run with:
+ bin/spark-submit examples/src/main/python/ml/isotonic_regression_example.py
"""
from __future__ import print_function
@@ -25,12 +28,6 @@ from pyspark.ml.regression import IsotonicRegression
# $example off$
from pyspark.sql import SparkSession
-"""
-An example demonstrating isotonic regression.
-Run with:
- bin/spark-submit examples/src/main/python/ml/isotonic_regression_example.py
-"""
-
if __name__ == "__main__":
spark = SparkSession\
.builder\
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/kmeans_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/kmeans_example.py b/examples/src/main/python/ml/kmeans_example.py
index 5f77843..80a878a 100644
--- a/examples/src/main/python/ml/kmeans_example.py
+++ b/examples/src/main/python/ml/kmeans_example.py
@@ -15,6 +15,13 @@
# limitations under the License.
#
+"""
+An example demonstrating k-means clustering.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/kmeans_example.py
+
+This example requires NumPy (http://www.numpy.org/).
+"""
from __future__ import print_function
# $example on$
@@ -24,14 +31,6 @@ from pyspark.ml.evaluation import ClusteringEvaluator
from pyspark.sql import SparkSession
-"""
-An example demonstrating k-means clustering.
-Run with:
- bin/spark-submit examples/src/main/python/ml/kmeans_example.py
-
-This example requires NumPy (http://www.numpy.org/).
-"""
-
if __name__ == "__main__":
spark = SparkSession\
.builder\
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/lda_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/lda_example.py b/examples/src/main/python/ml/lda_example.py
index a8b346f..97d1a04 100644
--- a/examples/src/main/python/ml/lda_example.py
+++ b/examples/src/main/python/ml/lda_example.py
@@ -15,7 +15,11 @@
# limitations under the License.
#
-
+"""
+An example demonstrating LDA.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/lda_example.py
+"""
from __future__ import print_function
# $example on$
@@ -23,12 +27,6 @@ from pyspark.ml.clustering import LDA
# $example off$
from pyspark.sql import SparkSession
-"""
-An example demonstrating LDA.
-Run with:
- bin/spark-submit examples/src/main/python/ml/lda_example.py
-"""
-
if __name__ == "__main__":
spark = SparkSession \
.builder \
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/logistic_regression_summary_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/logistic_regression_summary_example.py b/examples/src/main/python/ml/logistic_regression_summary_example.py
index bd440a1..2274ff7 100644
--- a/examples/src/main/python/ml/logistic_regression_summary_example.py
+++ b/examples/src/main/python/ml/logistic_regression_summary_example.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+An example demonstrating Logistic Regression Summary.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/logistic_regression_summary_example.py
+"""
from __future__ import print_function
# $example on$
@@ -22,12 +27,6 @@ from pyspark.ml.classification import LogisticRegression
# $example off$
from pyspark.sql import SparkSession
-"""
-An example demonstrating Logistic Regression Summary.
-Run with:
- bin/spark-submit examples/src/main/python/ml/logistic_regression_summary_example.py
-"""
-
if __name__ == "__main__":
spark = SparkSession \
.builder \
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/min_hash_lsh_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/min_hash_lsh_example.py b/examples/src/main/python/ml/min_hash_lsh_example.py
index 7b1dd61..93136e6 100644
--- a/examples/src/main/python/ml/min_hash_lsh_example.py
+++ b/examples/src/main/python/ml/min_hash_lsh_example.py
@@ -15,7 +15,11 @@
# limitations under the License.
#
-
+"""
+An example demonstrating MinHashLSH.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/min_hash_lsh_example.py
+"""
from __future__ import print_function
# $example on$
@@ -25,12 +29,6 @@ from pyspark.sql.functions import col
# $example off$
from pyspark.sql import SparkSession
-"""
-An example demonstrating MinHashLSH.
-Run with:
- bin/spark-submit examples/src/main/python/ml/min_hash_lsh_example.py
-"""
-
if __name__ == "__main__":
spark = SparkSession \
.builder \
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/one_vs_rest_example.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/one_vs_rest_example.py b/examples/src/main/python/ml/one_vs_rest_example.py
index 8e00c25..956e94a 100644
--- a/examples/src/main/python/ml/one_vs_rest_example.py
+++ b/examples/src/main/python/ml/one_vs_rest_example.py
@@ -15,6 +15,12 @@
# limitations under the License.
#
+"""
+An example of Multiclass to Binary Reduction with One Vs Rest,
+using Logistic Regression as the base classifier.
+Run with:
+ bin/spark-submit examples/src/main/python/ml/one_vs_rest_example.py
+"""
from __future__ import print_function
# $example on$
@@ -23,13 +29,6 @@ from pyspark.ml.evaluation import MulticlassClassificationEvaluator
# $example off$
from pyspark.sql import SparkSession
-"""
-An example of Multiclass to Binary Reduction with One Vs Rest,
-using Logistic Regression as the base classifier.
-Run with:
- bin/spark-submit examples/src/main/python/ml/one_vs_rest_example.py
-"""
-
if __name__ == "__main__":
spark = SparkSession \
.builder \
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/ml/train_validation_split.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/ml/train_validation_split.py b/examples/src/main/python/ml/train_validation_split.py
index d104f7d..d4f9184 100644
--- a/examples/src/main/python/ml/train_validation_split.py
+++ b/examples/src/main/python/ml/train_validation_split.py
@@ -15,13 +15,6 @@
# limitations under the License.
#
-# $example on$
-from pyspark.ml.evaluation import RegressionEvaluator
-from pyspark.ml.regression import LinearRegression
-from pyspark.ml.tuning import ParamGridBuilder, TrainValidationSplit
-# $example off$
-from pyspark.sql import SparkSession
-
"""
This example demonstrates applying TrainValidationSplit to split data
and preform model selection.
@@ -29,6 +22,12 @@ Run with:
bin/spark-submit examples/src/main/python/ml/train_validation_split.py
"""
+# $example on$
+from pyspark.ml.evaluation import RegressionEvaluator
+from pyspark.ml.regression import LinearRegression
+from pyspark.ml.tuning import ParamGridBuilder, TrainValidationSplit
+# $example off$
+from pyspark.sql import SparkSession
if __name__ == "__main__":
spark = SparkSession\
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/parquet_inputformat.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/parquet_inputformat.py b/examples/src/main/python/parquet_inputformat.py
index 52e9662..a3f86cf 100644
--- a/examples/src/main/python/parquet_inputformat.py
+++ b/examples/src/main/python/parquet_inputformat.py
@@ -15,12 +15,6 @@
# limitations under the License.
#
-from __future__ import print_function
-
-import sys
-
-from pyspark.sql import SparkSession
-
"""
Read data file users.parquet in local Spark distro:
@@ -35,6 +29,12 @@ $ ./bin/spark-submit --driver-class-path /path/to/example/jar \\
{u'favorite_color': u'red', u'name': u'Ben', u'favorite_numbers': []}
<...more log output...>
"""
+from __future__ import print_function
+
+import sys
+
+from pyspark.sql import SparkSession
+
if __name__ == "__main__":
if len(sys.argv) != 2:
print("""
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/sql/basic.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/sql/basic.py b/examples/src/main/python/sql/basic.py
index c07fa8f..c8fb25d 100644
--- a/examples/src/main/python/sql/basic.py
+++ b/examples/src/main/python/sql/basic.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+A simple example demonstrating basic Spark SQL features.
+Run with:
+ ./bin/spark-submit examples/src/main/python/sql/basic.py
+"""
from __future__ import print_function
# $example on:init_session$
@@ -30,12 +35,6 @@ from pyspark.sql import Row
from pyspark.sql.types import *
# $example off:programmatic_schema$
-"""
-A simple example demonstrating basic Spark SQL features.
-Run with:
- ./bin/spark-submit examples/src/main/python/sql/basic.py
-"""
-
def basic_df_example(spark):
# $example on:create_df$
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/sql/datasource.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/sql/datasource.py b/examples/src/main/python/sql/datasource.py
index b375fa7..d8c879d 100644
--- a/examples/src/main/python/sql/datasource.py
+++ b/examples/src/main/python/sql/datasource.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+A simple example demonstrating Spark SQL data sources.
+Run with:
+ ./bin/spark-submit examples/src/main/python/sql/datasource.py
+"""
from __future__ import print_function
from pyspark.sql import SparkSession
@@ -22,12 +27,6 @@ from pyspark.sql import SparkSession
from pyspark.sql import Row
# $example off:schema_merging$
-"""
-A simple example demonstrating Spark SQL data sources.
-Run with:
- ./bin/spark-submit examples/src/main/python/sql/datasource.py
-"""
-
def basic_datasource_example(spark):
# $example on:generic_load_save_functions$
http://git-wip-us.apache.org/repos/asf/spark/blob/b8c32dc5/examples/src/main/python/sql/hive.py
----------------------------------------------------------------------
diff --git a/examples/src/main/python/sql/hive.py b/examples/src/main/python/sql/hive.py
index 1f83a6f..33fc2df 100644
--- a/examples/src/main/python/sql/hive.py
+++ b/examples/src/main/python/sql/hive.py
@@ -15,6 +15,11 @@
# limitations under the License.
#
+"""
+A simple example demonstrating Spark SQL Hive integration.
+Run with:
+ ./bin/spark-submit examples/src/main/python/sql/hive.py
+"""
from __future__ import print_function
# $example on:spark_hive$
@@ -24,12 +29,6 @@ from pyspark.sql import SparkSession
from pyspark.sql import Row
# $example off:spark_hive$
-"""
-A simple example demonstrating Spark SQL Hive integration.
-Run with:
- ./bin/spark-submit examples/src/main/python/sql/hive.py
-"""
-
if __name__ == "__main__":
# $example on:spark_hive$
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org