xinrong-meng commented on code in PR #37635:
URL: https://github.com/apache/spark/pull/37635#discussion_r954114300
##########
python/pyspark/sql/types.py:
##########
@@ -2256,11 +2260,47 @@ def convert(self, obj: datetime.timedelta,
gateway_client: GatewayClient) -> Jav
)
+class NumpyScalarConverter:
+ def can_convert(self, obj: Any) -> bool:
+ return has_numpy and isinstance(obj, np.generic)
+
+ def convert(self, obj: "np.generic", gateway_client: GatewayClient) -> Any:
+ return obj.item()
+
+
+class NumpyArrayConverter:
+ def can_convert(self, obj: Any) -> bool:
+ return has_numpy and isinstance(obj, np.ndarray)
+
+ def convert(self, obj: "np.ndarray", gateway_client: GatewayClient) ->
JavaObject:
+ from pyspark import SparkContext
+
+ gateway = SparkContext._gateway
+ assert gateway is not None
+
+ plist = obj.tolist()
+ ptpe = type(plist[0]) if len(plist) > 0 else float
+ tpe_dict = {
+ int: gateway.jvm.int,
+ float: gateway.jvm.double,
+ bool: gateway.jvm.boolean,
+ str: gateway.jvm.String,
+ }
+ jarr = gateway.new_array(tpe_dict[ptpe], len(plist))
Review Comment:
The Java type of the array is required in order to create a Java array. So
`tpe_dict` is created to map Python types to Java types.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
