Restrict Dask and Fix Serialization Tests (#2694)

* restrict dask in pyproject.toml

* update release notes

* fix indent

* fix tests

* update release notes

* lint

* lint

* try to remove dask

* undo

.pre-commit-config.yaml

@@ -26,7 +26,7 @@ repos:
       - id: add-trailing-comma
         name: Add trailing comma
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: 'v0.1.6'
+    rev: 'v0.3.3'
     hooks:
       - id: ruff
         types_or: [ python, pyi, jupyter ]

docs/source/release_notes.rst

@@ -3,15 +3,18 @@
 Release Notes
 -------------
 
-.. Future Release
-  ==============
+Future Release
+==============
     * Enhancements
     * Fixes
     * Changes
+        * Temporarily restrict Dask version :pr:`2694`
     * Documentation Changes
     * Testing Changes
+        * Fix serialization test to work with pytest 8.1.1 :pr:`2694`
 
-.. Thanks to the following people for contributing to this release:
+    Thanks to the following people for contributing to this release:
+    :user:`thehomebrewnerd`
 
 v1.30.0 Feb 26, 2024
 ====================
@@ -21,8 +24,8 @@ v1.30.0 Feb 26, 2024
     * Testing Changes
         * Update ``make_ecommerce_entityset`` to work without Dask (:pr:`2677`)
 
-  Thanks to the following people for contributing to this release:
-  :user:`tamargrey`, :user:`thehomebrewnerd`
+    Thanks to the following people for contributing to this release:
+    :user:`tamargrey`, :user:`thehomebrewnerd`
 
 v1.29.0 Feb 16, 2024
 ====================

featuretools/entityset/entityset.py

@@ -1115,9 +1115,9 @@ def add_last_time_indexes(self, updated_dataframes=None):
         child_cols = defaultdict(dict)
         for r in self.relationships:
             children[r._parent_dataframe_name].append(r.child_dataframe)
-            child_cols[r._parent_dataframe_name][
-                r._child_dataframe_name
-            ] = r.child_column
+            child_cols[r._parent_dataframe_name][r._child_dataframe_name] = (
+                r.child_column
+            )
 
         updated_dataframes = updated_dataframes or []
         if updated_dataframes:

featuretools/feature_base/cache.py

@@ -3,6 +3,7 @@
 
 Custom caching class, currently used for FeatureBase
 """
+
 # needed for defaultdict annotation if < python 3.9
 from __future__ import annotations
 

featuretools/feature_base/features_serializer.py

@@ -123,12 +123,12 @@ def _feature_definitions(self):
                         # being converted to strings, but integer dict values are not.
                         primitives_dict_key = str(primitive_number)
                         primitive_id_to_key[primitive_id] = primitives_dict_key
-                        self._primitives_dict[
+                        self._primitives_dict[primitives_dict_key] = (
+                            serialize_primitive(primitive)
+                        )
+                        self._features_dict[name]["arguments"]["primitive"] = (
                             primitives_dict_key
-                        ] = serialize_primitive(primitive)
-                        self._features_dict[name]["arguments"][
-                            "primitive"
-                        ] = primitives_dict_key
+                        )
                         primitive_number += 1
                     else:
                         # Primitive we have seen already - use existing primitive_id key

featuretools/tests/primitive_tests/transform_primitive_tests/test_transform_primitive.py

@@ -1,3 +1,4 @@
+import warnings
 from datetime import datetime
 
 import numpy as np
@@ -388,10 +389,10 @@ def test_week_no_deprecation_message():
         datetime(2019, 6, 17, 11, 10, 50),
         datetime(2019, 11, 30, 19, 45, 15),
     ]
-    with pytest.warns(None) as record:
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
         week = Week()
         week(dates).tolist()
-    assert not record
 
 
 def test_url_to_domain_urls():

featuretools/tests/profiling/dfs_profile.py

@@ -12,6 +12,7 @@
   - max_depth > 2 is very slow (currently)
   - stats output can be viewed online with https://nejc.saje.info/pstats-viewer.html
 """
+
 import cProfile
 from pathlib import Path
 

featuretools/tests/synthesis/test_dfs_method.py

@@ -1,3 +1,4 @@
+import warnings
 from unittest.mock import patch
 
 import composeml as cp
@@ -87,10 +88,13 @@ def test_dfs_empty_features():
             features_only=True,
         )
         assert features == []
-    with pytest.raises(AssertionError, match=error_text), patch.object(
-        DeepFeatureSynthesis,
-        "build_features",
-        return_value=[],
+    with (
+        pytest.raises(AssertionError, match=error_text),
+        patch.object(
+            DeepFeatureSynthesis,
+            "build_features",
+            return_value=[],
+        ),
     ):
         dfs(
             dataframes,
@@ -447,7 +451,8 @@ def test_warns_with_unused_primitives(es):
     assert record[0].message.args[0] == warning_text
 
     # Should not raise a warning
-    with pytest.warns(None) as record:
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
         dfs(
             entityset=es,
             target_dataframe_name="customers",
@@ -457,13 +462,12 @@ def test_warns_with_unused_primitives(es):
             features_only=True,
         )
 
-    assert not record
-
 
 def test_no_warns_with_camel_and_title_case(es):
     for trans_primitive in ["isNull", "IsNull"]:
         # Should not raise a UnusedPrimitiveWarning warning
-        with pytest.warns(None) as record:
+        with warnings.catch_warnings():
+            warnings.simplefilter("error")
             dfs(
                 entityset=es,
                 target_dataframe_name="customers",
@@ -472,11 +476,10 @@ def test_no_warns_with_camel_and_title_case(es):
                 features_only=True,
             )
 
-        assert not record
-
     for agg_primitive in ["numUnique", "NumUnique"]:
         # Should not raise a UnusedPrimitiveWarning warning
-        with pytest.warns(None) as record:
+        with warnings.catch_warnings():
+            warnings.simplefilter("error")
             dfs(
                 entityset=es,
                 target_dataframe_name="customers",
@@ -485,11 +488,10 @@ def test_no_warns_with_camel_and_title_case(es):
                 features_only=True,
             )
 
-        assert not record
-
 
 def test_does_not_warn_with_stacking_feature(pd_es):
-    with pytest.warns(None) as record:
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
         dfs(
             entityset=pd_es,
             target_dataframe_name="régions",
@@ -501,8 +503,6 @@ def test_does_not_warn_with_stacking_feature(pd_es):
             features_only=True,
         )
 
-    assert not record
-
 
 def test_warns_with_unused_where_primitives(es):
     if es.dataframe_type == Library.SPARK:
@@ -549,7 +549,8 @@ def test_warns_with_unused_groupby_primitives(pd_es):
     assert record[0].message.args[0] == warning_text
 
     # Should not raise a warning
-    with pytest.warns(None) as record:
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
         dfs(
             entityset=pd_es,
             target_dataframe_name="customers",
@@ -558,8 +559,6 @@ def test_warns_with_unused_groupby_primitives(pd_es):
             features_only=True,
         )
 
-    assert not record
-
 
 def test_warns_with_unused_custom_primitives(pd_es):
     class AboveTen(TransformPrimitive):
@@ -589,7 +588,8 @@ class AboveTen(TransformPrimitive):
     assert record[0].message.args[0] == warning_text
 
     # Should not raise a warning
-    with pytest.warns(None) as record:
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
         dfs(
             entityset=pd_es,
             target_dataframe_name="customers",
@@ -625,7 +625,8 @@ class MaxAboveTen(AggregationPrimitive):
     assert record[0].message.args[0] == warning_text
 
     # Should not raise a warning
-    with pytest.warns(None) as record:
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
         dfs(
             entityset=pd_es,
             target_dataframe_name="sessions",

pyproject.toml

@@ -65,8 +65,8 @@ test = [
     "pytest-timeout >= 2.1.0"
 ]
 dask = [
-    "dask[dataframe] >= 2023.2.0",
-    "distributed >= 2023.2.0",
+    "dask[dataframe] >= 2023.2.0, <2024.3.0",
+    "distributed >= 2023.2.0, <2024.3.0",
     "woodwork[dask] >= 0.28.0",
 ]
 spark = [