Merge branch 'main' into spacy

Author: isabelizimm

.github/workflows/docs.yml

@@ -76,12 +76,13 @@ jobs:
           ALIAS: ${{ steps.deployment.outputs.env }}
 
       - name: Update Github Deployment
-        uses: bobheadxi/deployments@v0.4.3
-        if: ${{ always() }}
+        uses: bobheadxi/deployments@v1
+        if: always()
         with:
           step: finish
           token: ${{ secrets.GITHUB_TOKEN }}
           status: ${{ job.status }}
+          env: ${{ steps.deployment.outputs.env }}j
           deployment_id: ${{ steps.deployment.outputs.deployment_id }}
           env_url: 'https://${{ steps.deployment.outputs.env }}--relaxed-mooncake-704252.netlify.app'
           logs: 'https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}'

.github/workflows/tests.yml

@@ -32,7 +32,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          python -m pip install -e .[all]
+          python -m pip install -e ".[dev,all_models]"
       - name: Run Tests
         run: |
           pytest -m 'not rsc_test and not docker' --cov --cov-report xml
@@ -109,3 +109,32 @@ jobs:
       - name: Run tests
         run: |
           pytest vetiver/tests/test_sklearn.py
+
+  typecheck:
+    runs-on: ubuntu-latest
+
+    # We want to run on external PRs, but not on our own internal PRs as they'll be run
+    # by the push to the branch.
+    if: github.event_name == 'push' || github.event.pull_request.head.repo.full_name != github.repository
+
+    strategy:
+      matrix:
+        python-version: [3.11]
+
+    steps:
+      - name: Checkout Code
+        uses: actions/checkout@v3
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install Packages
+        shell: bash
+        run: |
+          pip install ".[dev,all_models]"
+
+      - name: Run Tests
+        shell: bash
+        run: make typecheck

Makefile

@@ -91,5 +91,8 @@ dev-stop:
 	docker-compose down
 	rm -f $(RSC_API_KEYS)
 
+typecheck:
+	pyright
+
 $(RSC_API_KEYS): dev-start
 	python script/setup-rsconnect/dump_api_keys.py $@

docs/Makefile

@@ -5,6 +5,6 @@
 # Catch-all target:
 %: Makefile
 	python version_config.py
-	python -m quartodoc build
+	python -m quartodoc build --verbose
 	python -m quartodoc interlinks
 	quarto render

pyproject.toml

@@ -18,3 +18,65 @@ markers = [
 [tool.setuptools_scm]
 fallback_version = "999"
 version_scheme = 'post-release'
+
+########## Tool - Pyright ##########
+[tool.pyright]
+# Paths of directories or files that should be included. If no paths
+# are specified, pyright defaults to the directory that contains the
+# config file. Paths may contain wildcard characters ** (a directory or
+# multiple levels of directories), * (a sequence of zero or more
+# characters), or ? (a single character). If no include paths are
+# specified, the root path for the workspace is assumed.
+include = [
+    "vetiver/"
+   ]
+
+# Paths of directories or files whose diagnostic output (errors and
+# warnings) should be suppressed even if they are an included file or
+# within the transitive closure of an included file. Paths may contain
+# wildcard characters ** (a directory or multiple levels of
+# directories), * (a sequence of zero or more characters), or ? (a
+# single character).
+ignore = [
+    #"vetiver/__init__.py",
+    #"vetiver/attach_pkgs.py",
+    "vetiver/helpers.py",
+    "vetiver/meta.py",
+    "vetiver/mock.py",
+    "vetiver/model_card.py",
+    "vetiver/monitor.py",
+    "vetiver/pin_read_write.py",
+    "vetiver/prototype.py",
+    "vetiver/rsconnect.py",
+    "vetiver/server.py",
+    "vetiver/types.py",
+    "vetiver/utils.py",
+    "vetiver/vetiver_model.py",
+    "vetiver/write_docker.py",
+    "vetiver/write_fastapi.py",
+    "vetiver/handlers/",
+    "vetiver/data/",
+    "vetiver/tests"
+]
+
+# Set of identifiers that should be assumed to contain a constant
+# value wherever used within this program. For example, { "DEBUG": true
+# } indicates that pyright should assume that the identifier DEBUG will
+# always be equal to True. If this identifier is used within a
+# conditional expression (such as if not DEBUG:) pyright will use the
+# indicated value to determine whether the guarded block is reachable
+# or not. Member expressions that reference one of these constants
+# (e.g. my_module.DEBUG) are also supported.
+defineConstant = { DEBUG = true }
+
+# typeCheckingMode = "strict"
+useLibraryCodeForTypes = true
+reportUnnecessaryTypeIgnoreComment = true
+
+# Specifies a list of execution environments (see below). Execution
+# environments are searched from start to finish by comparing the path
+# of a source file with the root path specified in the execution
+# environment.
+executionEnvironments = []
+
+stubPath = ""

setup.cfg

@@ -41,6 +41,10 @@ install_requires =
 [options.extras_require]
 all =
     vetiver[dev]
+    vetiver[all_models]
+    vetiver[docs]
+
+all_models =
     vetiver[torch]
     vetiver[statsmodels]
     vetiver[xgboost]
@@ -50,18 +54,23 @@ dev =
     pytest
     pytest-cov
     pytest-snapshot
+    vetiver[typecheck]
 
 docs =
     quartodoc
 
-torch =
-    torch
-
 statsmodels =
     statsmodels
 
+torch =
+    torch
+
 xgboost =
     xgboost
 
 spacy =
     spacy
+
+typecheck =
+    pyright
+    pandas-stubs

vetiver/__init__.py

@@ -7,7 +7,7 @@
 from .server import VetiverAPI, vetiver_endpoint, predict  # noqa
 from .mock import get_mock_data, get_mock_model  # noqa
 from .pin_read_write import vetiver_pin_write  # noqa
-from .attach_pkgs import load_pkgs  # noqa
+from .attach_pkgs import load_pkgs, get_board_pkgs  # noqa
 from .meta import VetiverMeta  # noqa
 from .write_docker import write_docker, prepare_docker  # noqa
 from .write_fastapi import write_app, vetiver_write_app  # noqa

vetiver/attach_pkgs.py

@@ -1,31 +1,41 @@
+from __future__ import annotations
+import typing
+
 import tempfile
 import os
+import warnings
 from .vetiver_model import VetiverModel
 from .meta import VetiverMeta
 
+if typing.TYPE_CHECKING:
+    from typing import Optional
+    from pathlib import Path
+
 
-def load_pkgs(model: VetiverModel = None, packages: list = None, path=""):
+def load_pkgs(
+    model: VetiverModel, packages: Optional[list] = None, path: str | Path = ""
+):
     """Load packages necessary for predictions
 
-    Args
-    ----
-        model: VetiverModel
-            VetiverModel to extract packages from
-        packages: list
-            List of extra packages to include
-        path: str
-            Where to save output file
+    Parameters
+    ----------
+    model: VetiverModel
+        VetiverModel to extract packages from
+    packages: list
+        List of extra packages to include
+    path: str
+        Where to save output file
     """
 
     required_pkgs = ["vetiver"]
     if packages:
-        required_pkgs = list(set(required_pkgs + packages))
+        required_pkgs += packages
 
     if isinstance(model.metadata, dict):
         model.metadata = VetiverMeta.from_dict(model.metadata)
 
     if model.metadata.required_pkgs:
-        required_pkgs = list(set(required_pkgs + model.metadata.required_pkgs))
+        required_pkgs += model.metadata.required_pkgs
 
     tmp = tempfile.NamedTemporaryFile(suffix=".in", delete=False)
     tmp.close()
@@ -36,3 +46,37 @@ def load_pkgs(model: VetiverModel = None, packages: list = None, path=""):
 
     os.system(f"pip-compile {tmp.name} --output-file={path}requirements.txt")
     os.remove(tmp.name)
+
+
+def get_board_pkgs(board) -> list[str]:
+    """
+    Extract packages required for pin board authorization
+
+    Parameters
+    ----------
+    board:
+        A pin board, created by `pins.board_folder()` or another `board_` function.
+
+    Returns
+    --------
+    list[str]
+    """
+    prot = board.fs.protocol
+
+    if prot == "rsc":
+        return ["rsconnect-python"]
+    elif prot == "file":
+        return []
+    elif prot == ["s3", "s3a"]:
+        return ["s3fs"]
+    elif prot == "abfs":
+        return ["adlfs"]
+    elif prot == ("gcs", "gs"):
+        return ["gcsfs"]
+    else:
+        warnings.warn(
+            f"required packages unknown for board protocol: {prot}, "
+            "add to model's metadata to export",
+            UserWarning,
+        )
+        return []

vetiver/pin_read_write.py

@@ -43,7 +43,10 @@ def vetiver_pin_write(board, model: VetiverModel, versioned: bool = True):
     >>> vetiver.vetiver_pin_write(model_board, v)
     """
     if not board.allow_pickle_read:
-        raise NotImplementedError  # must be pickle-able
+        raise ValueError(
+            "board does not allow pickled models. Set "
+            "allow_pickle_read to True on board creation."
+        )
 
     inform(
         _log,

vetiver/tests/test_pin_write.py

@@ -16,7 +16,7 @@ def test_board_pin_write_error():
         model=model, prototype_data=X_df, model_name="model", versioned=None
     )
     board = pins.board_temp()
-    with pytest.raises(NotImplementedError):
+    with pytest.raises(ValueError):
         vetiver_pin_write(board=board, model=v)