chore: bump dependencies

environment.yml

@@ -2,37 +2,47 @@ name: spras
 channels:
   - conda-forge
 dependencies:
-  - adjusttext=0.7.3.1
-  - bioconda::snakemake-minimal=8.17.0
-  - docker-py=5.0
-  - matplotlib=3.6
-  - networkx=2.8
-  - pandas=1.5
-  - numpy=1.26.4
-  - pre-commit=2.20 # Only required for development
-  - go=1.24 # Only required for development
-  - pytest=8.0 # Only required for development
-  - python=3.11
-  - pip=22.1
-  - requests=2.28
-  - scikit-learn=1.2
-  - seaborn=0.12
-  - spython=0.2
-  # for dsub
-  - python-dateutil<=2.9.0
-  - pytz<=2024.1
-  - pyyaml<=6.0.1
-  - tenacity<=8.2.3
-  - tabulate<=0.9.0
+  - adjusttext=1.3.0
+  - bioconda::snakemake-minimal=9.6.2
+  # Conda refers to pypi/docker as docker-py.
+  - docker-py=7.1.0
+  - matplotlib=3.10.3
+  - networkx=3.5
+  - pandas=2.3.0
+  - numpy=2.3.1
+  - requests=2.32.4
+  - scikit-learn=1.7.0
+  - seaborn=0.13.2
+  - spython=0.3.14
+
   # Only required for GraphSpace
-  - commonmark=0.9
-  - docutils=0.19
-  - jinja2=3.1
-  - mock=4.0
-  - recommonmark=0.7
-  - sphinx=6.0
+  - commonmark=0.9.1
+  - docutils=0.20.1
+  - jinja2=3.1.6
+  - mock=5.2.0
+  - recommonmark=0.7.1
+  - sphinx=7.4.7
   - sphinx-rtd-theme=2.0.0
+  # graphspace_python is under pip
+
+  # conda-specific for dsub
+  - python-dateutil=2.9.0
+  - pytz=2025.2
+  - pyyaml=6.0.2
+  - tenacity=9.1.2
+  - tabulate=0.9.0
+
+  # toolchain deps
+  - pip=22.1
+  # This should be the same as requires-python minus the >=.
+  - python=3.11
+
+  # development dependencies
+  - pre-commit=4.2.0
+  - pytest=8.4.1
+  # development dependencies - conda-specific
+  - go=1.24
+
   - pip:
       - graphspace_python==1.3.1
       - dsub==0.4.13
-

pyproject.toml

@@ -19,34 +19,35 @@ classifiers = [
 requires-python = ">=3.11"
 dependencies = [
     "adjusttext==0.7.3",
-    # A bug was introduced in older versions of snakemake that prevent it from running. Update to fix
-    "snakemake==8.17.0",
-    "docker==5.0.3", # Switched from docker-py to docker because docker-py is not maintained in pypi. This appears to have no effect
-    "matplotlib==3.6",
-    "networkx==2.8",
-    "pandas==1.5",
-    "numpy==1.26.4",
-    "pip==22.1",
-    "requests==2.28",
-    "scikit-learn==1.2",
-    "seaborn==0.12",
-    "spython==0.2",
+    "snakemake==9.6.2",
+    "docker==7.1.0",
+    "matplotlib==3.10.3",
+    "networkx==3.5",
+    "pandas==2.3.0",
+    "numpy==2.3.1",
+    "requests==2.32.4",
+    "scikit-learn==1.7.0",
+    "seaborn==0.13.2",
+    "spython==0.3.14",
     # Only required for GraphSpace
     "commonmark==0.9",
-    "docutils==0.19",
-    "jinja2==3.1",
-    "mock==4.0",
-    "recommonmark==0.7",
-    "sphinx==6.0",
-    "graphspace_python==1.3.1",
+    "docutils==0.20.1",
+    "jinja2==3.1.6",
+    "mock==5.2.0",
+    "recommonmark==0.7.1",
+    "sphinx==7.4.7",
     "sphinx-rtd-theme==2.0.0",
+    "graphspace_python==1.3.1",
+
+    # toolchain deps
+    "pip==22.1",
 ]
 
 [project.optional-dependencies]
 dev = [
    # Only required for development
-    "pre-commit==2.20",
-    "pytest==8.0",
+    "pre-commit==4.2.0",
+    "pytest==8.4.1",
 ]
 
 [project.urls]

spras/analysis/ml.py

@@ -303,7 +303,7 @@ def hac_horizontal(dataframe: pd.DataFrame, output_png: str, output_file: str, l
 
     # plotting figure
     plt.figure(figsize=(10, 7))
-    model = AgglomerativeClustering(linkage=linkage, affinity=metric,distance_threshold=0.5, n_clusters=None)
+    model = AgglomerativeClustering(linkage=linkage, metric=metric,distance_threshold=0.5, n_clusters=None)
     model = model.fit(df)
     plt.figure(figsize=(10, 7))
     plt.title("Hierarchical Agglomerative Clustering Dendrogram")

test/ml/expected/expected-pca-coordinates-2.tsv

@@ -0,0 +1,4 @@
+algorithm	PC1	PC2
+test-data-s1	-2.006650210482033	-0.9865875190637743
+test-data-s2	-1.5276508866841987	1.0799457247533237
+test-data-s3	3.534301097166232	-0.0933582056895495

test/ml/expected/expected-pca-coordinates.tsv

@@ -1,4 +1,4 @@
 algorithm	PC1	PC2
-test-data-s1	-2.006650210482033	-0.9865875190637743
-test-data-s2	-1.5276508866841987	1.0799457247533237
-test-data-s3	3.534301097166232	-0.0933582056895495
+test-data-s1	2.006650210482033	-0.9865875190637743
+test-data-s2	1.5276508866841987	1.0799457247533237
+test-data-s3	-3.534301097166232	-0.0933582056895495

test/ml/test_ml.py

@@ -82,8 +82,12 @@ def test_pca(self):
 
     def test_pca_robustness(self):
         dataframe = ml.summarize_networks([INPUT_DIR + 'test-data-s1/s1.txt', INPUT_DIR + 'test-data-s2/s2.txt', INPUT_DIR + 'test-data-s3/s3.txt'])
+        # PCA signage now depends on the input data: we need two differently signed PCA coordinate files.
+        # See https://scikit-learn.org/stable/whats_new/v1.5.html#changed-models for more info.
         expected = pd.read_table(EXPECT_DIR + 'expected-pca-coordinates.tsv')
+        expected_other = pd.read_table(EXPECT_DIR + 'expected-pca-coordinates-2.tsv')
         expected = expected.round(5)
+        expected_other = expected_other.round(5)
         for _ in range(5):
             dataframe_shuffled = dataframe.sample(frac=1, axis=1)  # permute the columns
             ml.pca(dataframe_shuffled, OUT_DIR + 'pca-shuffled-columns.png', OUT_DIR + 'pca-shuffled-columns-variance.txt',
@@ -92,7 +96,7 @@ def test_pca_robustness(self):
             coord = coord.round(5)  # round values to 5 digits to account for numeric differences across machines
             coord.sort_values(by='algorithm', ignore_index=True, inplace=True)
 
-            assert coord.equals(expected)
+            assert coord.equals(expected) or coord.equals(expected_other)
 
         for _ in range(5):
             dataframe_shuffled = dataframe.sample(frac=1, axis=0)  # permute the rows
@@ -102,7 +106,7 @@ def test_pca_robustness(self):
             coord = coord.round(5)  # round values to 5 digits to account for numeric differences across machines
             coord.sort_values(by='algorithm', ignore_index=True, inplace=True)
 
-            assert coord.equals(expected)
+            assert coord.equals(expected) or coord.equals(expected_other)
 
     def test_hac_horizontal(self):
         dataframe = ml.summarize_networks([INPUT_DIR + 'test-data-s1/s1.txt', INPUT_DIR + 'test-data-s2/s2.txt', INPUT_DIR + 'test-data-s3/s3.txt'])