import ast
from pyspark.sql.functions import udf
values = [(u'[23,4,77,890.455]',10),(u'[11,2,50,1.11]',20),(u'[10.05,1,22.04]',30)]
df = sqlContext.createDataFrame(values,['list','A'])
df.show()
+-----------------+---+
| list| A|
+-----------------+---+
|[23,4,77,890.455]| 10|
| [11,2,50,1.11]| 20|
| [10.05,1,22.04]| 30|
+-----------------+---+
# Creating a UDF to convert the string list to proper list
string_list_to_list = udf(lambda row: ast.literal_eval(row))
df = df.withColumn('list',string_list_to_list(col('list')))
df.show()
+--------------------+---+
| list| A|
+--------------------+---+
|[23, 4, 77, 890.455]| 10|
| [11, 2, 50, 1.11]| 20|
| [10.05, 1, 22.04]| 30|
+--------------------+---+
Расширение Q
, как указано в OP -
# Creating a UDF to find length of resulting list.
length_list = udf(lambda row: len(row))
df = df.withColumn('length_list',length_list(col('list')))
df.show()
+--------------------+---+-----------+
| list| A|length_list|
+--------------------+---+-----------+
|[23, 4, 77, 890.455]| 10| 4|
| [11, 2, 50, 1.11]| 20| 4|
| [10.05, 1, 22.04]| 30| 3|
+--------------------+---+-----------+