Python 3.13 tests

.github/workflows/pytest_duckdb.yml

@@ -15,7 +15,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12", "3.13"]
     name: Run tests with Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
@@ -35,7 +35,7 @@ jobs:
 
       - name: Run tests with coverage
         run: |
-          poetry add pytest-cov
+          poetry add "pytest-cov>=5.0.0"
           poetry run pytest -v --durations=0 -m "duckdb_only or core" --cov=splink --cov-report=xml --cov-report=term tests/
 
       - name: Upload coverage report

.github/workflows/pytest_postgres.yml

@@ -29,7 +29,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12", "3.13"]
     name: Run tests with Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4

.github/workflows/pytest_sqlite.yml

@@ -15,7 +15,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12", "3.13"]
     name: Run tests with Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4

docs/api_docs/comparison_level_library.md

@@ -18,9 +18,9 @@ tags:
         - "!^create_sql$"  # Exclude the create_sql method
 
 
-## AbsoluteDateDifferenceAtThresholds
+## AbsoluteDateDifferenceLevel
 
-An alias of [AbsoluteTimeDifferenceAtThresholds](./comparison_level_library.html#splink.comparison_level_library.AbsoluteTimeDifferenceLevel).
+An alias of [AbsoluteTimeDifferenceLevel](./comparison_level_library.html#splink.comparison_level_library.AbsoluteTimeDifferenceLevel).
 
 ## Configuring comparisons
 

docs/topic_guides/splink_fundamentals/backends/backends.md

@@ -95,31 +95,31 @@ Once you have initialised the `linker` object, there is no difference in the sub
     ```python
     from splink import Linker, DuckDBAPI
 
-    linker = Linker(your_args. DuckDBAPI)
+    linker = Linker(df, settings, db_api=DuckDBAPI(...))
     ```
 
 === ":simple-apachespark: Spark"
 
     ```python
     from splink import Linker, SparkAPI
 
-    linker = Linker(your_args. SparkAPI)
+    linker = Linker(df, settings, db_api=SparkAPI(...))
     ```
 
 === ":simple-amazonaws: Athena"
 
     ```python
     from splink import Linker, AthenaAPI
 
-    linker = Linker(your_args. AthenaAPI)
+    linker = Linker(df, settings, db_api=AthenaAPI(...))
     ```
 
 === ":simple-sqlite: SQLite"
 
     ```python
     from splink import Linker, SQLiteAPI
 
-    linker = Linker(your_args. SQLiteAPI)
+    linker = Linker(df, settings, db_api=SQLiteAPI(...))
 
     ```
 
@@ -128,7 +128,7 @@ Once you have initialised the `linker` object, there is no difference in the sub
     ```python
     from splink import Linker, PostgresAPI
 
-    linker = Linker(your_args. PostgresAPI)
+    linker = Linker(df, settings, db_api=PostgresAPI(...))
 
     ```
 

pyproject.toml

@@ -12,7 +12,10 @@ readme = "README.md"
 python = ">=3.8.0,<4.0.0"
 jsonschema = ">=3.2"
 # 1.3.5 is the last version supporting py 3.7.1
-pandas = ">1.3.5"
+pandas = [
+     { version = ">1.3.5", python = "<3.13" },
+     { version = ">=2.2.3", python = ">=3.13" }
+]
 duckdb = ">=0.9.2"
 sqlglot = ">=13.0.0"
 altair = "^5.0.1"
@@ -57,7 +60,10 @@ ruff = "^0.4.2"
 [tool.poetry.group.testing.dependencies]
 # pin to reduce dependencies
 pytest = ">=7.3"
-pyarrow = ">=7.0.0"
+pyarrow = [
+    { version = ">=7.0.0", python = "<3.13" },
+    { version = ">=18.0.0", python = ">=3.13" }
+]
 networkx = ">=2.5.1"
 rapidfuzz = ">=2.0.3"
 

splink/internals/charts.py

@@ -3,26 +3,17 @@
 import json
 import math
 import os
-from typing import TYPE_CHECKING, Any, Dict, Union
+from typing import Any, Dict, Union
 
 import numpy as np
 import pandas as pd
+from altair import Chart, SchemaBase
 
 from splink.internals.misc import read_resource
 from splink.internals.waterfall_chart import records_to_waterfall_data
 
-altair_installed = True
-
-try:
-    import altair as alt
-except ImportError:
-    altair_installed = False
-
-if TYPE_CHECKING:
-    import altair as alt
-
 # type alias:
-ChartReturnType = Union[Dict[Any, Any], alt.core.SchemaBase]
+ChartReturnType = Union[Dict[Any, Any], SchemaBase]
 
 
 def load_chart_definition(filename):
@@ -42,13 +33,8 @@ def _load_external_libs():
 def altair_or_json(
     chart_dict: dict[Any, Any], as_dict: bool = False
 ) -> ChartReturnType:
-    if altair_installed:
-        if not as_dict:
-            try:
-                return alt.Chart.from_dict(chart_dict)
-
-            except ModuleNotFoundError:
-                return chart_dict
+    if not as_dict:
+        return Chart.from_dict(chart_dict)
 
     return chart_dict
 

splink/internals/cluster_studio.py

@@ -233,7 +233,7 @@ def _get_cluster_id_of_each_size(
     where row_num <= {rows_per_partition}
     """
 
-    pipeline.enqueue_sql(sql, "__splink__cluster_count_row_numbered")
+    pipeline.enqueue_sql(sql, "__splink__cluster_count_row_numbered_2")
     df_cluster_sample_with_size = linker._db_api.sql_pipeline_to_splink_dataframe(
         pipeline
     )

splink/internals/connected_components.py

@@ -445,7 +445,7 @@ def solve_connected_components(
         where node_id in
             (select node_id from {prev_representatives_thinned.templated_name})
         """
-        pipeline.enqueue_sql(sql, "__splink__df_neighbours_filtered")
+        pipeline.enqueue_sql(sql, f"__splink__df_neighbours_filtered_{iteration}")
         filtered_neighbours_thinned = db_api.sql_pipeline_to_splink_dataframe(pipeline)
         filtered_neighbours.drop_table_from_database_and_remove_from_cache()
         filtered_neighbours = filtered_neighbours_thinned