[
https://issues.apache.org/jira/browse/SPARK-41833?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sandeep Singh updated SPARK-41833:
--
Description:
{code:java}
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1117, in pyspark.sql.connect.functions.array
Failed example:
df.select(array('age', 'age').alias("arr")).collect()
Expected:
[Row(arr=[2, 2]), Row(arr=[5, 5])]
Got:
[Row(arr=array([2, 2])), Row(arr=array([5, 5]))]
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1119, in pyspark.sql.connect.functions.array
Failed example:
df.select(array([df.age, df.age]).alias("arr")).collect()
Expected:
[Row(arr=[2, 2]), Row(arr=[5, 5])]
Got:
[Row(arr=array([2, 2])), Row(arr=array([5, 5]))]
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1124, in pyspark.sql.connect.functions.array_distinct
Failed example:
df.select(array_distinct(df.data)).collect()
Expected:
[Row(array_distinct(data)=[1, 2, 3]), Row(array_distinct(data)=[4, 5])]
Got:
[Row(array_distinct(data)=array([1, 2, 3])),
Row(array_distinct(data)=array([4, 5]))]
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1135, in pyspark.sql.connect.functions.array_except
Failed example:
df.select(array_except(df.c1, df.c2)).collect()
Expected:
[Row(array_except(c1, c2)=['b'])]
Got:
[Row(array_except(c1, c2)=array(['b'], dtype=object))]
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1142, in pyspark.sql.connect.functions.array_intersect
Failed example:
df.select(array_intersect(df.c1, df.c2)).collect()
Expected:
[Row(array_intersect(c1, c2)=['a', 'c'])]
Got:
[Row(array_intersect(c1, c2)=array(['a', 'c'], dtype=object))]
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1180, in pyspark.sql.connect.functions.array_remove
Failed example:
df.select(array_remove(df.data, 1)).collect()
Expected:
[Row(array_remove(data, 1)=[2, 3]), Row(array_remove(data, 1)=[])]
Got:
[Row(array_remove(data, 1)=array([2, 3])), Row(array_remove(data,
1)=array([], dtype=int64))]
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1187, in pyspark.sql.connect.functions.array_repeat
Failed example:
df.select(array_repeat(df.data, 3).alias('r')).collect()
Expected:
[Row(r=['ab', 'ab', 'ab'])]
Got:
[Row(r=array(['ab', 'ab', 'ab'], dtype=object))]
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1204, in pyspark.sql.connect.functions.array_sort
Failed example:
df.select(array_sort(df.data).alias('r')).collect()
Expected:
[Row(r=[1, 2, 3, None]), Row(r=[1]), Row(r=[])]
Got:
[Row(r=array([ 1., 2., 3., nan])), Row(r=array([1])), Row(r=array([],
dtype=int64))]
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1207, in pyspark.sql.connect.functions.array_sort
Failed example:
df.select(array_sort(
"data",
lambda x, y: when(x.isNull() | y.isNull(), lit(0)).otherwise(length(y)
- length(x))
).alias("r")).collect()
Expected:
[Row(r=['foobar', 'foo', None, 'bar']), Row(r=['foo']), Row(r=[])]
Got:
[Row(r=array(['foobar', 'foo', None, 'bar'], dtype=object)),
Row(r=array(['foo'], dtype=object)), Row(r=array([], dtype=object))]
**
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1209, in pyspark.sql.connect.functions.array_union
Failed example:
df.select(array_union(df.c1, df.c2)).collect()
Expected:
[Row(array_union(c1, c2)=['b', 'a', 'c', 'd', 'f'])]
Got:
[Row(array_union(c1, c2)=array(['b', 'a', 'c', 'd', 'f'],
dtype=object))]{code}
was:
{code:java}
File
"/Users/s.singh/personal/spark-oss/python/pyspark/sql/connect/functions.py",
line 1117, in pyspark.sql.connect.functions.array
Failed example:
df.select(array('age', 'age').alias("arr")).collect()
Expected:
[Row(arr=[2, 2]), Row(arr=[5, 5])]
Got:
[Row(arr=array([2, 2])), Row(arr=array([5, 5]))]{code}
> DataFrame.collect() output
