[
https://issues.apache.org/jira/browse/SPARK-19134?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hyukjin Kwon updated SPARK-19134:
---------------------------------
Description:
*binary_classification_metrics_example.py*
{code}
./bin/spark-submit
examples/src/main/python/mllib/binary_classification_metrics_example.py
{code}
{code}
File
".../spark/examples/src/main/python/mllib/binary_classification_metrics_example.py",
line 39, in <lambda>
.rdd.map(lambda row: LabeledPoint(row[0], row[1]))
File ".../spark/python/pyspark/mllib/regression.py", line 54, in __init__
self.features = _convert_to_vector(features)
File ".../spark/python/pyspark/mllib/linalg/__init__.py", line 80, in
_convert_to_vector
raise TypeError("Cannot convert type %s into Vector" % type(l))
TypeError: Cannot convert type <class 'pyspark.ml.linalg.SparseVector'> into
Vector
{code}
*status_api_demo.py*
{code}
PYSPARK_PYTHON=python3 ./bin/spark-submit
examples/src/main/python/status_api_demo.py
{code}
{code}
Traceback (most recent call last):
File ".../spark/examples/src/main/python/status_api_demo.py", line 22, in
<module>
import Queue
ImportError: No module named 'Queue'
{code}
*bisecting_k_means_example.py*
{code}
./bin/spark-submit examples/src/main/python/mllib/bisecting_k_means_example.py
{code}
{code}
Traceback (most recent call last):
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/examples/src/main/python/mllib/bisecting_k_means_example.py",
line 46, in <module>
model.save(sc, path)
AttributeError: 'BisectingKMeansModel' object has no attribute 'save'
{code}
*elementwise_product_example.py*
{code}
./bin/spark-submit examples/src/main/python/mllib/elementwise_product_example.py
{code}
{code}
Traceback (most recent call last):
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/examples/src/main/python/mllib/elementwise_product_example.py",
line 48, in <module>
for each in transformedData2.collect():
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/python/pyspark/mllib/linalg/__init__.py",
line 478, in __getattr__
return getattr(self.array, item)
AttributeError: 'numpy.ndarray' object has no attribute 'collect'
{code}
*hive.py*
{code}
./bin/spark-submit examples/src/main/python/sql/hive.py
{code}
{code}
Traceback (most recent call last):
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/examples/src/main/python/sql/hive.py",
line 47, in <module>
spark.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING
hive")
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/python/lib/pyspark.zip/pyspark/sql/session.py",
line 541, in sql
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py",
line 1133, in __call__
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/python/lib/pyspark.zip/pyspark/sql/utils.py",
line 69, in deco
pyspark.sql.utils.AnalysisException:
'org.apache.hadoop.hive.ql.metadata.HiveException:
MetaException(message:java.lang.IllegalArgumentException:
java.net.URISyntaxException: Relative path in absolute URI:
file:./spark-warehouse);'
{code}
**SparkHiveExample**
{code}
./bin/run-example sql.hive.SparkHiveExample
{code}
{code}
Exception in thread "main" org.apache.hadoop.hive.ql.metadata.HiveException:
Unable to alter table. java.lang.IllegalArgumentException:
java.net.URISyntaxException: Relative path in absolute URI:
file:./spark-warehouse
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:498)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at
org.apache.spark.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:722)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply$mcV$sp(HiveClientImpl.scala:686)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply(HiveClientImpl.scala:686)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply(HiveClientImpl.scala:686)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$withHiveState$1.apply(HiveClientImpl.scala:283)
at
org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:230)
at
org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:229)
at
org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:272)
at
org.apache.spark.sql.hive.client.HiveClientImpl.loadTable(HiveClientImpl.scala:685)
{code}
**JavaSparkHiveExample**
{code}
./bin/run-example sql.hive.JavaSparkHiveExample
{code}
{code}
Exception in thread "main" org.apache.hadoop.hive.ql.metadata.HiveException:
Unable to alter table. java.lang.IllegalArgumentException:
java.net.URISyntaxException: Relative path in absolute URI:
file:./spark-warehouse
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:498)
at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at
org.apache.spark.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:722)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply$mcV$sp(HiveClientImpl.scala:686)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply(HiveClientImpl.scala:686)
at
org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply(HiveClientImpl.scala:686)
{code}
was:
*binary_classification_metrics_example.py*
{code}
./bin/spark-submit
examples/src/main/python/mllib/binary_classification_metrics_example.py
{code}
{code}
File
".../spark/examples/src/main/python/mllib/binary_classification_metrics_example.py",
line 39, in <lambda>
.rdd.map(lambda row: LabeledPoint(row[0], row[1]))
File ".../spark/python/pyspark/mllib/regression.py", line 54, in __init__
self.features = _convert_to_vector(features)
File ".../spark/python/pyspark/mllib/linalg/__init__.py", line 80, in
_convert_to_vector
raise TypeError("Cannot convert type %s into Vector" % type(l))
TypeError: Cannot convert type <class 'pyspark.ml.linalg.SparseVector'> into
Vector
{code}
*status_api_demo.py*
{code}
PYSPARK_PYTHON=python3 ./bin/spark-submit
examples/src/main/python/status_api_demo.py
{code}
{code}
Traceback (most recent call last):
File ".../spark/examples/src/main/python/status_api_demo.py", line 22, in
<module>
import Queue
ImportError: No module named 'Queue'
{code}
*bisecting_k_means_example.py*
{code}
./bin/spark-submit examples/src/main/python/mllib/bisecting_k_means_example.py
{code}
{code}
Traceback (most recent call last):
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/examples/src/main/python/mllib/bisecting_k_means_example.py",
line 46, in <module>
model.save(sc, path)
AttributeError: 'BisectingKMeansModel' object has no attribute 'save'
{code}
*elementwise_product_example.py*
{code}
./bin/spark-submit examples/src/main/python/mllib/elementwise_product_example.py
{code}
{code}
Traceback (most recent call last):
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/examples/src/main/python/mllib/elementwise_product_example.py",
line 48, in <module>
for each in transformedData2.collect():
File
"/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/python/pyspark/mllib/linalg/__init__.py",
line 478, in __getattr__
return getattr(self.array, item)
AttributeError: 'numpy.ndarray' object has no attribute 'collect'
{code}
> Fix several Python mllib and status api examples not working
> ------------------------------------------------------------
>
> Key: SPARK-19134
> URL: https://issues.apache.org/jira/browse/SPARK-19134
> Project: Spark
> Issue Type: Bug
> Components: MLlib, PySpark
> Reporter: Hyukjin Kwon
> Priority: Minor
>
> *binary_classification_metrics_example.py*
> {code}
> ./bin/spark-submit
> examples/src/main/python/mllib/binary_classification_metrics_example.py
> {code}
> {code}
> File
> ".../spark/examples/src/main/python/mllib/binary_classification_metrics_example.py",
> line 39, in <lambda>
> .rdd.map(lambda row: LabeledPoint(row[0], row[1]))
> File ".../spark/python/pyspark/mllib/regression.py", line 54, in __init__
> self.features = _convert_to_vector(features)
> File ".../spark/python/pyspark/mllib/linalg/__init__.py", line 80, in
> _convert_to_vector
> raise TypeError("Cannot convert type %s into Vector" % type(l))
> TypeError: Cannot convert type <class 'pyspark.ml.linalg.SparseVector'> into
> Vector
> {code}
> *status_api_demo.py*
> {code}
> PYSPARK_PYTHON=python3 ./bin/spark-submit
> examples/src/main/python/status_api_demo.py
> {code}
> {code}
> Traceback (most recent call last):
> File ".../spark/examples/src/main/python/status_api_demo.py", line 22, in
> <module>
> import Queue
> ImportError: No module named 'Queue'
> {code}
> *bisecting_k_means_example.py*
> {code}
> ./bin/spark-submit examples/src/main/python/mllib/bisecting_k_means_example.py
> {code}
> {code}
> Traceback (most recent call last):
> File
> "/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/examples/src/main/python/mllib/bisecting_k_means_example.py",
> line 46, in <module>
> model.save(sc, path)
> AttributeError: 'BisectingKMeansModel' object has no attribute 'save'
> {code}
> *elementwise_product_example.py*
> {code}
> ./bin/spark-submit
> examples/src/main/python/mllib/elementwise_product_example.py
> {code}
> {code}
> Traceback (most recent call last):
> File
> "/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/examples/src/main/python/mllib/elementwise_product_example.py",
> line 48, in <module>
> for each in transformedData2.collect():
> File
> "/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/python/pyspark/mllib/linalg/__init__.py",
> line 478, in __getattr__
> return getattr(self.array, item)
> AttributeError: 'numpy.ndarray' object has no attribute 'collect'
> {code}
> *hive.py*
> {code}
> ./bin/spark-submit examples/src/main/python/sql/hive.py
> {code}
> {code}
> Traceback (most recent call last):
> File
> "/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/examples/src/main/python/sql/hive.py",
> line 47, in <module>
> spark.sql("CREATE TABLE IF NOT EXISTS src (key INT, value STRING) USING
> hive")
> File
> "/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/python/lib/pyspark.zip/pyspark/sql/session.py",
> line 541, in sql
> File
> "/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py",
> line 1133, in __call__
> File
> "/Users/hyukjinkwon/Desktop/workspace/repos/forked/spark/python/lib/pyspark.zip/pyspark/sql/utils.py",
> line 69, in deco
> pyspark.sql.utils.AnalysisException:
> 'org.apache.hadoop.hive.ql.metadata.HiveException:
> MetaException(message:java.lang.IllegalArgumentException:
> java.net.URISyntaxException: Relative path in absolute URI:
> file:./spark-warehouse);'
> {code}
> **SparkHiveExample**
> {code}
> ./bin/run-example sql.hive.SparkHiveExample
> {code}
> {code}
> Exception in thread "main" org.apache.hadoop.hive.ql.metadata.HiveException:
> Unable to alter table. java.lang.IllegalArgumentException:
> java.net.URISyntaxException: Relative path in absolute URI:
> file:./spark-warehouse
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:498)
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
> at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:497)
> at
> org.apache.spark.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:722)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply$mcV$sp(HiveClientImpl.scala:686)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply(HiveClientImpl.scala:686)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply(HiveClientImpl.scala:686)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$withHiveState$1.apply(HiveClientImpl.scala:283)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl.liftedTree1$1(HiveClientImpl.scala:230)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl.retryLocked(HiveClientImpl.scala:229)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl.withHiveState(HiveClientImpl.scala:272)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl.loadTable(HiveClientImpl.scala:685)
> {code}
> **JavaSparkHiveExample**
> {code}
> ./bin/run-example sql.hive.JavaSparkHiveExample
> {code}
> {code}
> Exception in thread "main" org.apache.hadoop.hive.ql.metadata.HiveException:
> Unable to alter table. java.lang.IllegalArgumentException:
> java.net.URISyntaxException: Relative path in absolute URI:
> file:./spark-warehouse
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:498)
> at org.apache.hadoop.hive.ql.metadata.Hive.alterTable(Hive.java:484)
> at org.apache.hadoop.hive.ql.metadata.Hive.loadTable(Hive.java:1668)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:497)
> at
> org.apache.spark.sql.hive.client.Shim_v0_14.loadTable(HiveShim.scala:722)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply$mcV$sp(HiveClientImpl.scala:686)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply(HiveClientImpl.scala:686)
> at
> org.apache.spark.sql.hive.client.HiveClientImpl$$anonfun$loadTable$1.apply(HiveClientImpl.scala:686)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
