From f09826cb9bf04fca566ed6f438f681f6d0000e3d Mon Sep 17 00:00:00 2001 From: Xinrong Meng Date: Fri, 6 Sep 2024 15:03:55 +0800 Subject: [PATCH 1/3] clarify sample_ratio --- python/pyspark/pandas/config.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/python/pyspark/pandas/config.py b/python/pyspark/pandas/config.py index bfa88253dc6f..e56e5f5a3f34 100644 --- a/python/pyspark/pandas/config.py +++ b/python/pyspark/pandas/config.py @@ -287,7 +287,8 @@ def validate(self, v: Any) -> None: doc=( "'plotting.sample_ratio' sets the proportion of data that will be plotted for sample-" "based plots such as `plot.line` and `plot.area`. " - "This option defaults to 'plotting.max_rows' option." + "If not set, it is derived from ‘plotting.max_rows’, by calculating the ratio of " + "'plotting.max_rows' to the total dataset size." ), default=None, types=(float, type(None)), From 82282f1854451d3d2e5f19d6a24c9e9639a499ed Mon Sep 17 00:00:00 2001 From: Xinrong Meng Date: Fri, 6 Sep 2024 15:15:35 +0800 Subject: [PATCH 2/3] fix --- python/pyspark/pandas/config.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/pyspark/pandas/config.py b/python/pyspark/pandas/config.py index e56e5f5a3f34..3e68e8e18574 100644 --- a/python/pyspark/pandas/config.py +++ b/python/pyspark/pandas/config.py @@ -287,7 +287,7 @@ def validate(self, v: Any) -> None: doc=( "'plotting.sample_ratio' sets the proportion of data that will be plotted for sample-" "based plots such as `plot.line` and `plot.area`. " - "If not set, it is derived from ‘plotting.max_rows’, by calculating the ratio of " + "If not set, it is derived from 'plotting.max_rows', by calculating the ratio of " "'plotting.max_rows' to the total dataset size." ), default=None, From 2c51f7fa15a85149bab55b36fbe3a8bef0d69f44 Mon Sep 17 00:00:00 2001 From: Xinrong Meng Date: Fri, 6 Sep 2024 15:16:59 +0800 Subject: [PATCH 3/3] avoid dataset --- python/pyspark/pandas/config.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/pyspark/pandas/config.py b/python/pyspark/pandas/config.py index 3e68e8e18574..6ed4adf21ff4 100644 --- a/python/pyspark/pandas/config.py +++ b/python/pyspark/pandas/config.py @@ -288,7 +288,7 @@ def validate(self, v: Any) -> None: "'plotting.sample_ratio' sets the proportion of data that will be plotted for sample-" "based plots such as `plot.line` and `plot.area`. " "If not set, it is derived from 'plotting.max_rows', by calculating the ratio of " - "'plotting.max_rows' to the total dataset size." + "'plotting.max_rows' to the total data size." ), default=None, types=(float, type(None)),