Merge pull request #33 from NREL/release/1.2.1

fixes for ngboost imports; bump version to 1.2.1

.github/workflows/test.yaml

@@ -19,7 +19,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11"]
 
     env:
       PYTHON: ${{ matrix.python-version }}
@@ -38,12 +38,17 @@ jobs:
           pip install ".[dev]"
 
       - name: Run mypy
-        run: mypy . 
+        run: mypy .
 
-      - name: Run black
+      - name: Lint with ruff
         run: |
-          black nrel tests --check
+          ruff check
+
+      - name: ruff format check
+        run: |
+          ruff format --check
 
       - name: Python unit tests
         run: |
-          pytest tests/ -v
+          python -m unittest discover tests/
+          

README.md

@@ -1,7 +1,7 @@
 # <img src="docs/images/routeelogo.png" alt="Routee Powertrain" width="100"/>
 
 <div align="left">
-    <img src="https://img.shields.io/badge/python-3.8%20%7C%203.9%20%7C%203.10%20%7C%203.11-blue"/>
+    <img src="https://img.shields.io/badge/python-3.9%20%7C%203.10%20%7C%203.11-blue"/>
   <a href="https://pypi.org/project/nrel.routee.powertrain/">
     <img src="https://img.shields.io/pypi/v/nrel.routee.powertrain" alt="PyPi Latest Release"/>
   </a>

docs/model_training-ngboost.ipynb

@@ -26,17 +26,10 @@
     "import nrel.routee.powertrain as pt\n",
     "\n",
     "from nrel.routee.powertrain.trainers.ngboost_trainer import NGBoostTrainer\n",
-    "from nrel.routee.powertrain.trainers.sklearn_random_forest import SklearnRandomForestTrainer\n",
     "\n",
-    "from nrel.routee.powertrain.estimators.ngboost_estimator import NGBoostEstimator\n",
     "\n",
     "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import time\n",
-    "\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score\n"
+    "\n"
    ]
   },
   {
@@ -53,7 +46,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
     "\n",
     "df = pd.read_csv(\"../tests/routee-powertrain-test-data/sample_train_data.csv\")"
    ]

nrel/routee/powertrain/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.1"

nrel/routee/powertrain/__init__.py

@@ -1,15 +1,28 @@
 import logging
 from pathlib import Path
 
+__all__ = [
+    "DataColumn",
+    "FeatureSet",
+    "Constraints",
+    "TargetSet",
+    "Model",
+    "ModelConfig",
+    "PowertrainType",
+    "list_available_models",
+    "load_model",
+    "load_sample_route",
+    "visualize_features",
+    "contour_plot",
+]
+
 from .core.features import DataColumn, FeatureSet, Constraints, TargetSet
 from .core.model import Model
 from .core.model_config import ModelConfig
 from .core.powertrain_type import PowertrainType
 from .io.load import list_available_models, load_model, load_sample_route
 from .validation.feature_visualization import visualize_features, contour_plot
 
-__version__ = "1.0.0"
-
 log = logging.getLogger()
 log.setLevel(logging.INFO)
 

nrel/routee/powertrain/core/metadata.py

@@ -33,7 +33,11 @@ def to_json(self) -> str:
     @classmethod
     def from_dict(cls, d: dict) -> Metadata:
         v = get_version()
-        if d["routee_version"] != v:
+        major_v = v.split(".")[0]
+
+        incoming_v = d["routee_version"]
+        incoming_major_v = incoming_v.split(".")[0]
+        if incoming_major_v != major_v:
             warnings.warn(
                 "this model was trained using routee-powertrain version "
                 f"{d['routee_version']} but you're using version {v}"

nrel/routee/powertrain/core/model.py

@@ -411,7 +411,7 @@ def __repr__(self) -> str:
             for feature in feature_set.features:
                 summary_lines.append(f"Feature: {feature.name} ({feature.units})")
             summary_lines.append(
-                f"Distance: {config.distance.name} " f"({config.distance.units})"
+                f"Distance: {config.distance.name} ({config.distance.units})"
             )
             for target in config.target.targets:
                 summary_lines.append(f"Target: {target.name} ({target.units})")

nrel/routee/powertrain/core/model_config.py

@@ -95,8 +95,9 @@ def __post_init__(self):
         feature_set_ids = [f.features_id for f in self.feature_sets]
         if len(feature_set_ids) != len(set(feature_set_ids)):
             raise ValueError(
-                "Feature sets must have unique ids. "
-                "Found duplicate ids: {}".format(feature_set_ids)
+                "Feature sets must have unique ids. Found duplicate ids: {}".format(
+                    feature_set_ids
+                )
             )
 
         # now check all the types

nrel/routee/powertrain/estimators/ngboost_estimator.py

@@ -1,21 +1,19 @@
 from __future__ import annotations
 
-# from abc import ABC, abstractmethod
 from pathlib import Path
-import joblib
 import base64
 import io
 import json
 import pandas as pd
-from ngboost import NGBRegressor
+
+from importlib.util import find_spec
 
 from nrel.routee.powertrain.core.features import DataColumn, FeatureSet, TargetSet
 from nrel.routee.powertrain.core.model_config import PredictMethod
 from nrel.routee.powertrain.estimators.estimator_interface import Estimator
 
 
 class NGBoostEstimator(Estimator):
-
     def __init__(self, ngboost) -> None:
         self.model = ngboost
 
@@ -41,10 +39,23 @@ def to_file(self, filepath: str | Path):
             json.dump(self.to_dict(), f)
 
     @classmethod
-    def from_dict(cls, in_dict: dict) -> "NGBRegressor":
+    def from_dict(cls, in_dict: dict) -> NGBoostEstimator:
         """
         Load an estimator from a bytes object in memory
         """
+        if find_spec("ngboost") is None:
+            raise ImportError(
+                "The NGBoostEstimator estimator requires extra dependencies like joblib and ngboost. "
+                "To install, you can do pip install nrel.routee.powertrain[ngboost]"
+            )
+
+        if find_spec("joblib") is None:
+            raise ImportError(
+                "The NGBoostEstimator estimator requires extra dependencies like joblib and ngboost. "
+                "To install, you can do pip install nrel.routee.powertrain[ngboost]"
+            )
+        else:
+            import joblib
 
         model_base64 = in_dict.get("ngboost_model")
 
@@ -60,6 +71,13 @@ def to_dict(self) -> dict:
         """
         Serialize an estimator to a python dictionary
         """
+        try:
+            import joblib
+        except ImportError:
+            raise ImportError(
+                "The NGBoostEstimator estimator requires extra dependencies like joblib and ngboost. "
+                "To install, you can do pip install nrel.routee.powertrain[ngboost]"
+            )
         byte_stream = io.BytesIO()
         joblib.dump(self.model, byte_stream)
         byte_stream.seek(0)

nrel/routee/powertrain/estimators/sklearn/__init__.py

@@ -1 +1,3 @@
 from .estimator import SKLearnEstimator
+
+__all__ = ["SKLearnEstimator"]

nrel/routee/powertrain/trainers/ngboost_trainer.py

@@ -1,8 +1,7 @@
-from enum import Enum
 import pandas as pd
 
 from ngboost import NGBRegressor
-from ngboost.distns import Exponential, Normal
+from ngboost.distns import Normal
 
 
 from nrel.routee.powertrain.core.model_config import ModelConfig
@@ -21,7 +20,6 @@ def __init__(
         learning_rate: float = 0.01,
         random_state: int = 52,
     ):
-
         self.n_estimators = n_estimators
         self.dist = dist
         self.verbose = verbose

nrel/routee/powertrain/utils/fs.py

@@ -13,7 +13,7 @@ def read(path: Path):
         return fp.read()
 
 
-def get_version(path: Path = root() / "__init__.py"):
+def get_version(path: Path = root() / "__about__.py"):
     with path.open("r") as fp:
         for line in fp.readlines():
             if line.startswith("__version__"):

nrel/routee/powertrain/validation/errors.py

@@ -5,7 +5,6 @@
 
 import numpy as np
 import pandas as pd
-from scipy.stats import norm
 
 from nrel.routee.powertrain.core.features import FeatureSetId
 from nrel.routee.powertrain.core.model_config import ModelConfig
@@ -85,6 +84,13 @@ def calculate_nll(target, target_pred, target_std) -> float:
     """
     Calculate Negative Log-Likelihood (NLL).
     """
+    try:
+        from scipy.stats import norm
+    except ImportError:
+        raise ImportError(
+            "The calculate_nll function requires scipy. "
+            "To install, you can do pip install scipy"
+        )
     nll = -np.mean(norm.logpdf(target, loc=target_pred, scale=target_std))
     return nll
 
@@ -93,6 +99,13 @@ def calculate_crps(target, target_pred, target_std) -> float:
     """
     Calculate Continuous Ranked Probability Score (CRPS).
     """
+    try:
+        from scipy.stats import norm
+    except ImportError:
+        raise ImportError(
+            "The calculate_nll function requires scipy. "
+            "To install, you can do pip install scipy"
+        )
     # CDF of the predicted distribution
     z = (target - target_pred) / target_std
     crps = target_std * (
@@ -344,6 +357,13 @@ def compute_errors(
                 )
 
             if isinstance(estimator, NGBoostEstimator):
+                try:
+                    from scipy.stats import norm
+                except ImportError:
+                    raise ImportError(
+                        "The errors for the NGBoostEstimator requires other dependnecies like scipy. "
+                        "To install, you can do `pip install nrel.routee.powertrain[ngboost]"
+                    )
                 target_std = np.array(predictions[energy_name + "_std"])
                 alpha = 0.05
                 z = norm.ppf(1 - alpha / 2)  # z-score for 95% confidence

pyproject.toml

@@ -1,10 +1,10 @@
 [build-system]
-requires = ["setuptools>=63.0.0", "wheel"]
-build-backend = "setuptools.build_meta"
+requires = ["hatchling"]
+build-backend = "hatchling.build"
 
 [project]
 name = "nrel.routee.powertrain"
-version = "1.2.0"
+dynamic = ["version"]
 description = "RouteE-Powertrain is a tool for predicting energy usage over a set of road links."
 readme = "README.md"
 authors = [{ name = "National Renewable Energy Laboratory" }]
@@ -18,22 +18,22 @@ classifiers = [
     "Topic :: Scientific/Engineering",
 ]
 dependencies = ["pandas", "numpy", "onnx", "onnxruntime==1.18.1"]
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 
 [project.optional-dependencies]
-scikit = ["scikit-learn", "skl2onnx"]
-ngboost = ["ngboost"]
+scikit = ["scikit-learn==1.2.2", "skl2onnx"]
+ngboost = ["ngboost==0.5.2", "scikit-learn==1.2.2"]
 plot = ["matplotlib"]
 dev = [
     "nrel.routee.powertrain[scikit]",
     "nrel.routee.powertrain[plot]",
     "nrel.routee.powertrain[ngboost]",
     "tqdm",
     "pytest",
-    "black",
     "mypy",
     "maturin",
     "ruff",
+    "hatch",
     "shapely",
     "boxsdk",
     "jupyter-book",
@@ -49,20 +49,70 @@ dev = [
 [project.urls]
 Homepage = "https://github.com/NREL/routee-powertrain"
 
-[tool.setuptools.packages.find]
-where = ["."] # list of folders that contain the packages (["."] by default)
-include = [
-    "nrel*",
-] # package names should match these glob patterns (["*"] by default)
+[tool.hatch.version]
+path = "nrel/routee/powertrain/__about__.py"
 
-[tool.setuptools.package-data]
-"nrel.routee.powertrain" = ["py.typed"]
+[tool.hatch.build.targets.sdist]
+exclude = ["scripts/", "tests/", "docs/"]
 
-[tool.ruff.per-file-ignores]
-"__init__.py" = ["F401"]
+[tool.hatch.build.targets.wheel]
+packages = ["nrel/routee/powertrain"]
 
 [tool.mypy]
 ignore_missing_imports = true
 namespace_packages = true
 explicit_package_bases = true
 exclude = ["docs/", "build/", "dist/"]
+
+[tool.ruff]
+include = ["nrel/**/*.py", "tests/*.py"]
+# Exclude a variety of commonly ignored directories.
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".ipynb_checkpoints",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pyenv",
+    ".pytest_cache",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    ".vscode",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "site-packages",
+    "venv",
+]
+
+# Same as Black.
+line-length = 88
+indent-width = 4
+
+# Assume Python 3.9
+target-version = "py39"
+
+[tool.ruff.lint]
+# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
+# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
+# McCabe complexity (`C901`) by default.
+select = ["E4", "E7", "E9", "F"]
+ignore = []
+
+# Allow fix for all enabled rules (when `--fix`) is provided.
+fixable = ["ALL"]
+unfixable = []
+
+# Allow unused variables when underscore-prefixed.
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"