xinrong-meng commented on code in PR #48008: URL: https://github.com/apache/spark/pull/48008#discussion_r1756435393
########## python/pyspark/sql/plot/core.py: ########## @@ -0,0 +1,135 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +from typing import Any, TYPE_CHECKING, Optional, Union +from types import ModuleType +from pyspark.errors import PySparkRuntimeError, PySparkValueError +from pyspark.sql.utils import require_minimum_plotly_version + + +if TYPE_CHECKING: + from pyspark.sql import DataFrame + import pandas as pd + from plotly.graph_objs import Figure + + +class PySparkTopNPlotBase: + def get_top_n(self, sdf: "DataFrame") -> "pd.DataFrame": + from pyspark.sql import SparkSession + + session = SparkSession.getActiveSession() + if session is None: + raise PySparkRuntimeError(errorClass="NO_ACTIVE_SESSION", messageParameters=dict()) + + max_rows = int( + session.conf.get("spark.sql.pyspark.plotting.max_rows") # type: ignore[arg-type] + ) + pdf = sdf.limit(max_rows + 1).toPandas() + + self.partial = False + if len(pdf) > max_rows: + self.partial = True + pdf = pdf.iloc[:max_rows] + + return pdf + + +class PySparkSampledPlotBase: + def get_sampled(self, sdf: "DataFrame") -> "pd.DataFrame": + from pyspark.sql import SparkSession + + session = SparkSession.getActiveSession() + if session is None: + raise PySparkRuntimeError(errorClass="NO_ACTIVE_SESSION", messageParameters=dict()) + + sample_ratio = session.conf.get("spark.sql.pyspark.plotting.sample_ratio") Review Comment: Created https://issues.apache.org/jira/browse/SPARK-49607 as a placeholder :) -- 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]
