You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Sandeep Singh (Jira)" <ji...@apache.org> on 2023/01/05 17:36:00 UTC
[jira] [Updated] (SPARK-41899) DataFrame.createDataFrame converting int to bigint
[ https://issues.apache.org/jira/browse/SPARK-41899?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sandeep Singh updated SPARK-41899:
----------------------------------
Description:
{code:java}
dt = datetime.date(2021, 12, 27)
# Note; number var in Python gets converted to LongType column;
# this is not supported by the function, so cast to Integer explicitly
df = self.spark.createDataFrame([Row(date=dt, add=2)], "date date, add integer")
self.assertTrue(
all(
df.select(
date_add(df.date, df.add) == datetime.date(2021, 12, 29),
date_add(df.date, "add") == datetime.date(2021, 12, 29),
date_add(df.date, 3) == datetime.date(2021, 12, 30),
).first()
)
){code}
{code:java}
Traceback (most recent call last):
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py", line 391, in test_date_add_function
).first()
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 246, in first
return self.head()
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 310, in head
rs = self.head(1)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 312, in head
return self.take(n)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 317, in take
return self.limit(num).collect()
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 1076, in collect
table = self._session.client.to_table(query)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 414, in to_table
table, _ = self._execute_and_fetch(req)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 586, in _execute_and_fetch
self._handle_error(rpc_error)
File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 625, in _handle_error
raise SparkConnectAnalysisException(
pyspark.sql.connect.client.SparkConnectAnalysisException: [DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE] Cannot resolve "date_add(date, add)" due to data type mismatch: Parameter 2 requires the ("INT" or "SMALLINT" or "TINYINT") type, however "add" has the type "BIGINT".
Plan: 'GlobalLimit 1
+- 'LocalLimit 1
+- 'Project [unresolvedalias('`==`(date_add(date#753, add#754L), 2021-12-29), None), unresolvedalias('`==`(date_add(date#753, add#754L), 2021-12-29), None), (date_add(date#753, 3) = 2021-12-30) AS (date_add(date, 3) = DATE '2021-12-30')#759]
+- Project [date#753, add#754L]
+- Project [date#749 AS date#753, add#750L AS add#754L]
+- LocalRelation [date#749, add#750L]{code}
was:
{code:java}
from pyspark.sql.functions import assert_true
df = self.spark.range(3)
self.assertEqual(
df.select(assert_true(df.id < 3)).toDF("val").collect(),
[Row(val=None), Row(val=None), Row(val=None)],
)
with self.assertRaises(Py4JJavaError) as cm:
df.select(assert_true(df.id < 2, "too big")).toDF("val").collect(){code}
{code:java}
df = self.spark.createDataFrame([(1, "1"), (2, "2"), (1, "2"), (1, "2")], ["key", "value"])
w = Window.partitionBy("value").orderBy("key")
from pyspark.sql import functions as F
sel = df.select(
df.value,
df.key,
F.max("key").over(w.rowsBetween(0, 1)),
F.min("key").over(w.rowsBetween(0, 1)),
F.count("key").over(w.rowsBetween(float("-inf"), float("inf"))),
F.row_number().over(w),
F.rank().over(w),
F.dense_rank().over(w),
F.ntile(2).over(w),
)
rs = sorted(sel.collect()){code}
> DataFrame.createDataFrame converting int to bigint
> --------------------------------------------------
>
> Key: SPARK-41899
> URL: https://issues.apache.org/jira/browse/SPARK-41899
> Project: Spark
> Issue Type: Sub-task
> Components: Connect
> Affects Versions: 3.4.0
> Reporter: Sandeep Singh
> Priority: Major
>
> {code:java}
> dt = datetime.date(2021, 12, 27)
> # Note; number var in Python gets converted to LongType column;
> # this is not supported by the function, so cast to Integer explicitly
> df = self.spark.createDataFrame([Row(date=dt, add=2)], "date date, add integer")
> self.assertTrue(
> all(
> df.select(
> date_add(df.date, df.add) == datetime.date(2021, 12, 29),
> date_add(df.date, "add") == datetime.date(2021, 12, 29),
> date_add(df.date, 3) == datetime.date(2021, 12, 30),
> ).first()
> )
> ){code}
> {code:java}
> Traceback (most recent call last):
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/tests/test_functions.py", line 391, in test_date_add_function
> ).first()
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 246, in first
> return self.head()
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 310, in head
> rs = self.head(1)
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 312, in head
> return self.take(n)
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 317, in take
> return self.limit(num).collect()
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/dataframe.py", line 1076, in collect
> table = self._session.client.to_table(query)
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 414, in to_table
> table, _ = self._execute_and_fetch(req)
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 586, in _execute_and_fetch
> self._handle_error(rpc_error)
> File "/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/client.py", line 625, in _handle_error
> raise SparkConnectAnalysisException(
> pyspark.sql.connect.client.SparkConnectAnalysisException: [DATATYPE_MISMATCH.UNEXPECTED_INPUT_TYPE] Cannot resolve "date_add(date, add)" due to data type mismatch: Parameter 2 requires the ("INT" or "SMALLINT" or "TINYINT") type, however "add" has the type "BIGINT".
> Plan: 'GlobalLimit 1
> +- 'LocalLimit 1
> +- 'Project [unresolvedalias('`==`(date_add(date#753, add#754L), 2021-12-29), None), unresolvedalias('`==`(date_add(date#753, add#754L), 2021-12-29), None), (date_add(date#753, 3) = 2021-12-30) AS (date_add(date, 3) = DATE '2021-12-30')#759]
> +- Project [date#753, add#754L]
> +- Project [date#749 AS date#753, add#750L AS add#754L]
> +- LocalRelation [date#749, add#750L]{code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org