xinrong-databricks commented on code in PR #36793:
URL: https://github.com/apache/spark/pull/36793#discussion_r895206894
##########
python/pyspark/sql/session.py:
##########
@@ -952,12 +953,29 @@ def createDataFrame( # type: ignore[misc]
schema = [x.encode("utf-8") if not isinstance(x, str) else x for x
in schema]
try:
- import pandas
+ import pandas as pd
has_pandas = True
except Exception:
has_pandas = False
- if has_pandas and isinstance(data, pandas.DataFrame):
+
+ try:
+ import numpy as np
+
+ has_numpy = True
+ except Exception:
+ has_numpy = False
+
+ if has_numpy and isinstance(data, np.ndarray):
+ from pyspark.sql.pandas.utils import require_minimum_pandas_version
+
+ require_minimum_pandas_version()
+ if data.ndim not in [1, 2]:
+ raise ValueError("NumPy array input should be of 1 or 2
dimensions.")
+ column_names = ["value"] if data.ndim == 1 else ["_1", "_2"]
+ data = pd.DataFrame(data, columns=column_names)
Review Comment:
Yes, since pandas extends numpy dtypes.
--
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]
