Merge pull request #14 from AutoResearch/ci/update-pre-commit-hooks-a…

…nd-add-workflow

ci: update pre-commit hooks and add workflow

.github/workflows/test-pre-commit-hooks.yml

@@ -0,0 +1,25 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Test pre-commit-hooks
+
+on:
+  pull_request:
+  merge_group:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.8'
+        cache: 'pip'
+    - run: pip install pre-commit
+    - uses: actions/cache@v3
+      with:
+        path: ~/.cache/pre-commit
+        key: pre-commit-3|${{ env.pythonLocation }}|${{ runner.os }}|${{ hashFiles('.pre-commit-config.yaml') }}
+    - run: pre-commit run --all-files --show-diff-on-failure --color=always

.pre-commit-config.yaml

@@ -1,28 +1,37 @@
 repos:
   - repo: https://github.com/ambv/black
-    rev: 22.12.0
+    rev: 23.7.0
     hooks:
       - id: black
   - repo: https://github.com/pycqa/isort
     rev: 5.12.0
     hooks:
       - id: isort
         args:
-        - "--profile=black"
         - "--filter-files"
         - "--project=autora"
   - repo: https://github.com/pycqa/flake8
-    rev: 6.0.0
+    rev: 6.1.0
     hooks:
       - id: flake8
         args:
         - "--max-line-length=100"
         - "--extend-ignore=E203"
+        - "--per-file-ignores=__init__.py:F401"
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: "v0.991"
+    rev: "v1.5.1"
     hooks:
       - id: mypy
-        additional_dependencies: [types-requests]
+        additional_dependencies: [types-requests,types-tqdm,autora-core,scipy,pytest]
         language_version: python3.8
+        args:
+          - "--namespace-packages"
+          - "--explicit-package-bases"
+  - repo: https://github.com/srstevenson/nb-clean
+    rev: 2.4.0
+    hooks:
+      - id: nb-clean
+        args:
+          - --preserve-cell-outputs
 default_language_version:
   python: python3

docs/Basic Usage.ipynb

@@ -3,19 +3,15 @@
   {
    "attachments": {},
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "source": [
     "# Basic Usage"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# Uncomment the following line when running on Google Colab\n",
@@ -24,20 +20,16 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "source": [
     "Let's generate a simple data set with two features $x_1, x_2 \\in [0, 1]$ and a target $y$. We will use the following generative model:\n",
     "$y = 2 x_1 - e^{(5 x_2)}$"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": null,
+   "metadata": {},
    "outputs": [],
    "source": [
     "import numpy as np\n",
@@ -51,19 +43,15 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "source": [
     "Now let us define the search space, that is, the space of operations to consider when searching over the space of computation graphs."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": null,
+   "metadata": {},
    "outputs": [],
    "source": [
     "primitives = [\n",
@@ -79,9 +67,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "source": [
     "## Set Up The DARTS Regressor\n",
     "\n",
@@ -101,10 +87,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": null,
+   "metadata": {},
    "outputs": [],
    "source": [
     "from autora.theorist.darts import DARTSRegressor\n",
@@ -123,19 +107,15 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "source": [
     "Now we have everything to run differentiable architecture search and visualize the model resulting from the highest architecture weights. Note that the current model corresponds to the model with the highest architecture weights."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": null,
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -216,7 +196,7 @@
        "<graphviz.graphs.Digraph at 0x288b726d0>"
       ]
      },
-     "execution_count": 4,
+     "execution_count": null,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -228,19 +208,15 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "source": [
     "We can refine the fit by running the `fit` method again, after changing the parameters. This allows us to keep the same architecture but refit the parameters in the final sampled model, for example:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": null,
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -321,7 +297,7 @@
        "<graphviz.graphs.Digraph at 0x174355df0>"
       ]
      },
-     "execution_count": 5,
+     "execution_count": null,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -337,19 +313,15 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "source": [
     "We can also change how the model is sampled from the architecture weight distribution:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": null,
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -430,7 +402,7 @@
        "<graphviz.graphs.Digraph at 0x1746b7dc0>"
       ]
      },
-     "execution_count": 6,
+     "execution_count": null,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -447,19 +419,15 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "source": [
     "To recover the initial model, we need to return the sampling strategy to the default `\"max\"`:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "collapsed": false
-   },
+   "execution_count": null,
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -540,7 +508,7 @@
        "<graphviz.graphs.Digraph at 0x119bba670>"
       ]
      },
-     "execution_count": 7,
+     "execution_count": null,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -557,9 +525,7 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false
-   },
+   "metadata": {},
    "source": [
     "As long as the architecture has not been refitted in the meantime, the architecture should be identical to the initial result, as the `sampling_strategy=\"max\"` is deterministic. The coefficients of the architecture functions may, however, be different, as they have different starting values compared to when they were initially set.\n"
    ]
@@ -580,8 +546,7 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython2"
   }
  },
  "nbformat": 4,

pyproject.toml

@@ -25,6 +25,16 @@ dev = [
     "autora-synthetic"
 ]
 
+[tool.isort]
+profile = "black"
+
+[tool.mypy]
+mypy_path="./src"
+
+[[tool.mypy.overrides]]
+module = ["matplotlib.*", "autora.*", "sklearn.*", "torch.*", "graphviz.*", "mkdocs_gen_files.*", "pandas.*", "numpy.*","scipy.*"]
+ignore_missing_imports=true
+
 [project.urls]
 homepage = "http://www.empiricalresearch.ai"
 repository = "https://github.com/AutoResearch/autora-theorist-darts"

src/autora/theorist/darts/__init__.py

@@ -1,3 +1,3 @@
 from .model_search import DARTSType
 from .operations import PRIMITIVES
-from .regressor import DARTSRegressor, DARTSExecutionMonitor
+from .regressor import DARTSExecutionMonitor, DARTSRegressor

src/autora/theorist/darts/model_search.py

@@ -505,6 +505,7 @@ def genotype(self, sample: bool = False) -> Genotype:
         Returns:
             genotype: genotype describing the current (sampled) architecture
         """
+
         # this function uses the architecture weights to retrieve the
         # operations with the highest weights
         def _parse(weights):
@@ -613,9 +614,7 @@ def count_parameters(self, print_parameters: bool = False) -> Tuple[int, int, li
 
             tmp_param_list = list()
             if isiterable(op._ops[maxIdx[0].item(0)]):  # Zero is not iterable
-
                 for subop in op._ops[maxIdx[0].item(0)]:
-
                     for parameter in subop.parameters():
                         tmp_param_list.append(parameter.data.numpy().squeeze())
                         if parameter.requires_grad is True:

src/autora/theorist/darts/operations.py

@@ -88,15 +88,13 @@ def get_operation_label(
         else:
             classifier_str = input_var + " .* ("
         for param_idx, param in enumerate(params):
-
             if param_idx > 0:
                 if output_format == "latex":
                     classifier_str += " + \\left("
                 else:
                     classifier_str += " .+ ("
 
             if isiterable(param.tolist()):
-
                 param_formatted = list()
                 for value in param.tolist():
                     param_formatted.append(format_string.format(value))
@@ -541,7 +539,6 @@ def forward(self, x: torch.Tensor) -> torch.Tensor:
 
 
 def operation_factory(name):
-
     if name == "none":
         return Zero(1)
     elif name == "add":