gridfm-graphkit 0.0.2__tar.gz → 0.0.3__tar.gz

{gridfm_graphkit-0.0.2 → gridfm_graphkit-0.0.3}/PKG-INFO

@@ -1,15 +1,17 @@
 Metadata-Version: 2.4
 Name: gridfm-graphkit
-Version: 0.0.2
+Version: 0.0.3
 Summary: Grid Foundation Model
 Author-email: Matteo Mazzonelli <matteo.mazzonelli1@ibm.com>, Alban Puech <apuech@seas.harvard.edu>, Tamara Govindasamy <tamara.govindasamy@ibm.com>, Mangaliso Mngomezulu <mngomezulum@ibm.com>, Etienne Vos <etienne.vos@ibm.com>, Celia Cintas <celia.cintas@ibm.com>, Jonas Weiss <jwe@zurich.ibm.com>
 Maintainer-email: Matteo Mazzonelli <matteo.mazzonelli1@ibm.com>
 License-Expression: Apache-2.0
 Keywords: electric power grid,foundational model,graph neural networks
 Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: >=3.12.10
+Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: mlflow>=3.1.0

{gridfm_graphkit-0.0.2 → gridfm_graphkit-0.0.3}/gridfm_graphkit.egg-info/PKG-INFO

@@ -1,15 +1,17 @@
 Metadata-Version: 2.4
 Name: gridfm-graphkit
-Version: 0.0.2
+Version: 0.0.3
 Summary: Grid Foundation Model
 Author-email: Matteo Mazzonelli <matteo.mazzonelli1@ibm.com>, Alban Puech <apuech@seas.harvard.edu>, Tamara Govindasamy <tamara.govindasamy@ibm.com>, Mangaliso Mngomezulu <mngomezulum@ibm.com>, Etienne Vos <etienne.vos@ibm.com>, Celia Cintas <celia.cintas@ibm.com>, Jonas Weiss <jwe@zurich.ibm.com>
 Maintainer-email: Matteo Mazzonelli <matteo.mazzonelli1@ibm.com>
 License-Expression: Apache-2.0
 Keywords: electric power grid,foundational model,graph neural networks
 Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Requires-Python: >=3.12.10
+Requires-Python: <3.13,>=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: mlflow>=3.1.0

{gridfm_graphkit-0.0.2 → gridfm_graphkit-0.0.3}/gridfm_graphkit.egg-info/SOURCES.txt

@@ -30,5 +30,6 @@ gridfm_graphkit/training/trainer.py
 gridfm_graphkit/utils/__init__.py
 gridfm_graphkit/utils/loss.py
 gridfm_graphkit/utils/visualization.py
+tests/test_model_outputs.py
 tests/test_training.py
 tests/test_yaml_configs.py

{gridfm_graphkit-0.0.2 → gridfm_graphkit-0.0.3}/pyproject.toml

@@ -9,10 +9,10 @@ namespaces = false
 [project]
 name = "gridfm-graphkit"
 description = "Grid Foundation Model"
-version = "0.0.2"
+version = "0.0.3"
 readme = "README.md"
 license = "Apache-2.0"
-requires-python = ">=3.12.10"
+requires-python = ">=3.10,<3.13"
 
 authors = [
   {name = "Matteo Mazzonelli", email = "matteo.mazzonelli1@ibm.com"},
@@ -32,6 +32,8 @@ keywords = ["electric power grid", "foundational model", "graph neural networks"
 
 classifiers = [
   "Development Status :: 2 - Pre-Alpha",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Topic :: Scientific/Engineering :: Artificial Intelligence"
 ]

gridfm_graphkit-0.0.3/tests/test_model_outputs.py

@@ -0,0 +1,55 @@
+import torch
+import numpy as np
+import pytest
+
+# Device setup
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Input shape config
+num_nodes = 1
+x_dim = 9
+pe_dim = 20
+edge_attr_dim = 2
+
+# List of models and reference files to check
+models_to_test = [
+    (
+        "v0_1_2",
+        "examples/models/GridFM_v0_1_2.pth",
+        "tests/data/reference_output_v0_1_2.npy",
+    ),
+    (
+        "v0_2_3",
+        "examples/models/GridFM_v0_2_3.pth",
+        "tests/data/reference_output_v0_2_3.npy",
+    ),
+]
+
+
+@pytest.mark.parametrize("version, model_path, ref_output_path", models_to_test)
+def test_model_matches_reference(version, model_path, ref_output_path):
+    torch.manual_seed(0)
+
+    # Prepare zero input
+    x = torch.zeros((num_nodes, x_dim), device=device)
+    pe = torch.zeros((num_nodes, pe_dim), device=device)
+    edge_index = torch.tensor([[0], [0]], device=device)
+    edge_attr = torch.zeros((1, edge_attr_dim), device=device)
+    batch = torch.zeros(num_nodes, dtype=torch.long, device=device)
+
+    # Load model
+    model = torch.load(model_path, weights_only=False, map_location=device).to(device)
+    model.eval()
+
+    # Get current output
+    with torch.no_grad():
+        output = model(x, pe, edge_index, edge_attr, batch).cpu().numpy()
+
+    # Load saved reference
+    reference = np.load(ref_output_path)
+
+    # Exact match assertion
+    assert np.allclose(output, reference, rtol=1e-5, atol=1e-6), (
+        f"Model output for {version} does not match reference within tolerance.\n"
+        f"Max absolute difference: {np.max(np.abs(output - reference))}"
+    )