diff options
Diffstat (limited to 'python')
| -rw-r--r-- | python/pyspark/sql.py | 18 |
1 files changed, 14 insertions, 4 deletions
diff --git a/python/pyspark/sql.py b/python/pyspark/sql.py index 0e8b398fc6..014ac1791c 100644 --- a/python/pyspark/sql.py +++ b/python/pyspark/sql.py @@ -807,14 +807,14 @@ def _create_converter(dataType): return if isinstance(obj, tuple): - if hasattr(obj, "fields"): - d = dict(zip(obj.fields, obj)) - if hasattr(obj, "__FIELDS__"): + if hasattr(obj, "_fields"): + d = dict(zip(obj._fields, obj)) + elif hasattr(obj, "__FIELDS__"): d = dict(zip(obj.__FIELDS__, obj)) elif all(isinstance(x, tuple) and len(x) == 2 for x in obj): d = dict(obj) else: - raise ValueError("unexpected tuple: %s" % obj) + raise ValueError("unexpected tuple: %s" % str(obj)) elif isinstance(obj, dict): d = obj @@ -1327,6 +1327,16 @@ class SQLContext(object): >>> srdd = sqlCtx.inferSchema(nestedRdd2) >>> srdd.collect() [Row(f1=[[1, 2], [2, 3]], f2=[1, 2]), ..., f2=[2, 3])] + + >>> from collections import namedtuple + >>> CustomRow = namedtuple('CustomRow', 'field1 field2') + >>> rdd = sc.parallelize( + ... [CustomRow(field1=1, field2="row1"), + ... CustomRow(field1=2, field2="row2"), + ... CustomRow(field1=3, field2="row3")]) + >>> srdd = sqlCtx.inferSchema(rdd) + >>> srdd.collect()[0] + Row(field1=1, field2=u'row1') """ if isinstance(rdd, SchemaRDD): |