HyukjinKwon commented on a change in pull request #34931:
URL: https://github.com/apache/spark/pull/34931#discussion_r773636875
##########
File path: python/pyspark/pandas/frame.py
##########
@@ -8809,16 +8814,30 @@ def describe(self, percentiles: Optional[List[float]] =
None) -> "DataFrame":
max 3.0
Name: numeric1, dtype: float64
"""
- exprs = []
- column_labels = []
+ psser_numeric: List[Series] = []
+ psser_string: List[Series] = []
+ psser_timestamp: List[Series] = []
+ spark_data_types: List[DataType] = []
+ column_labels: Optional[List[Label]] = []
+ column_names: List[str] = []
for label in self._internal.column_labels:
psser = self._psser_for(label)
- if isinstance(psser.spark.data_type, NumericType):
- exprs.append(psser._dtype_op.nan_to_null(psser).spark.column)
+ spark_data_type = psser.spark.data_type
+ if isinstance(spark_data_type, NumericType):
+ psser_numeric.append(psser)
column_labels.append(label)
-
- if len(exprs) == 0:
- raise ValueError("Cannot describe a DataFrame without columns")
+ spark_data_types.append(spark_data_type)
+ elif isinstance(spark_data_type, TimestampType):
Review comment:
We can do this:
```suggestion
elif isinstance(spark_data_type, (TimestampType,
TimestampNTZType)):
```
--
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]
