From c4083037d751166641b8faec1dbf17b2a8d5d35a Mon Sep 17 00:00:00 2001 From: Robin Linacre Date: Wed, 22 Mar 2023 14:00:19 +0000 Subject: [PATCH 1/2] fix clustering in issue 1136 --- splink/spark/spark_linker.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/splink/spark/spark_linker.py b/splink/spark/spark_linker.py index 932f3c4cde..da89b53fb5 100644 --- a/splink/spark/spark_linker.py +++ b/splink/spark/spark_linker.py @@ -331,7 +331,7 @@ def _break_lineage_and_repartition(self, spark_df, templated_name, physical_name r"__splink__df_concat_with_tf", r"__splink__df_predict", r"__splink__df_tf_.+", - r"__splink__df_representatives", + r"__splink__df_representatives.+", r"__splink__df_neighbours", r"__splink__df_connected_components_df", ] From 1f95830bf82c3e10de898a49af678838d5fda732 Mon Sep 17 00:00:00 2001 From: Robin Linacre Date: Wed, 22 Mar 2023 14:01:57 +0000 Subject: [PATCH 2/2] bump version --- pyproject.toml | 2 +- splink/__init__.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index e7aae1729c..d5fc2320d3 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "splink" -version = "3.7.0" +version = "3.7.1" description = "Fast probabilistic data linkage at scale" authors = ["Robin Linacre ", "Sam Lindsay", "Theodore Manassis", "Tom Hepworth", "Andy Bond"] license = "MIT" diff --git a/splink/__init__.py b/splink/__init__.py index 762969eed5..8429f8cfd1 100644 --- a/splink/__init__.py +++ b/splink/__init__.py @@ -1 +1 @@ -__version__ = "3.7.0" +__version__ = "3.7.1"