Chore/finalize v1.0.0

.github/workflows/ci.yml

@@ -2,6 +2,7 @@ name: CI
 
 on:
   workflow_dispatch:
+  workflow_call:
   push:
     branches:
       - main
@@ -150,6 +151,38 @@ jobs:
       - name: Run unit tests
         run: poetry run pytest tests/ -v
 
+  min-deps:
+    name: Minimum supported dependencies
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Install Poetry
+        run: pipx install poetry
+
+      - name: Configure Poetry
+        run: poetry config virtualenvs.in-project true
+
+      - name: Install dependencies
+        run: poetry install
+
+      - name: Force the declared minimum runtime dependency versions
+        run: |
+          poetry run pip install \
+            "numpy==1.24.*" \
+            "pandas==2.0.*" \
+            "scipy==1.10.*" \
+            "scikit-learn==1.6.*"
+
+      - name: Run unit tests against the minimum versions
+        run: poetry run pytest tests/ -q
+
   smoke:
     name: Smoke tests (Python 3.12, ubuntu)
     runs-on: ubuntu-latest
@@ -248,6 +281,8 @@ jobs:
             module: sentence_transformers
           - extra: lightgbm
             module: lightgbm
+          - extra: polars
+            module: polars
 
     steps:
       - uses: actions/checkout@v4

.github/workflows/publish-pypi.yml

@@ -15,8 +15,14 @@ permissions:
   id-token: write
 
 jobs:
+  ci:
+    name: Full CI (required before publish)
+    uses: ./.github/workflows/ci.yml
+    secrets: inherit
+
   publish:
     runs-on: ubuntu-latest
+    needs: ci
     environment: pypi-publish
     # The "v*.*.*" trigger also matches RC tags (e.g. v2.0.0rc2), so guard
     # against publishing pre-releases to real PyPI. RC tags are handled by

.github/workflows/publish-testpypi.yml

@@ -16,8 +16,14 @@ permissions:
   id-token: write
 
 jobs:
+  ci:
+    name: Full CI (required before publish)
+    uses: ./.github/workflows/ci.yml
+    secrets: inherit
+
   publish-rc:
     runs-on: ubuntu-latest
+    needs: ci
     environment: testpypi-publish
 
     steps:

README.md

@@ -73,10 +73,10 @@ y = np.random.randn(100)
 # Global strategies: PLE for numerics, integer codes for categoricals
 preprocessor = Preprocessor(numerical_method="ple", categorical_method="int")
 
-X = preprocessor.fit_transform(df, y)   # dict of transformed feature blocks
+X = preprocessor.fit_transform(df, y)   # single stacked array, one row per sample
 
-print({k: v.shape for k, v in X.items()})
-# {'num_age': (100, 7), 'num_income': (100, 7), 'cat_city': (100, 1)}
+print(X.shape)
+# (100, 15)
 ```
 
 > **Note:** PreTab accepts a `pandas.DataFrame` or a `numpy.ndarray` and infers numerical
@@ -185,7 +185,7 @@ pip install "pretab[all]"          # both of the above
 ```bash
 git clone https://github.com/OpenTabular/PreTab
 cd PreTab
-pip install -e ".[dev]"
+poetry install
 ```
 
 ## Usage
@@ -209,8 +209,8 @@ preprocessor = Preprocessor(
     task="regression",
 )
 
-X_dict = preprocessor.fit_transform(df, y)               # {"num_age": ..., "cat_city": ...}
-X_array = preprocessor.transform(df, return_array=True)  # single stacked ndarray
+X_array = preprocessor.fit_transform(df, y)              # single stacked ndarray
+X_dict = preprocessor.transform(df, return_array=False)  # {"num_age": ..., "cat_city": ...}
 
 preprocessor.get_feature_info(verbose=True)              # inspect resolved strategies
 ```
@@ -227,8 +227,10 @@ experience  numerical    imputer -> minmax -> quantile     1      -
 city        categorical  imputer -> onehot -> to_float     4      4
 ```
 
-> **Note:** `transform` returns a dict of feature blocks by default (keys prefixed `num_`
-> and `cat_`), or a single stacked array when you pass `return_array=True`.
+> **Note:** `transform` returns a single stacked array by default, so a `Preprocessor` drops
+> straight into a plain `sklearn.pipeline.Pipeline`. Pass `output_structure="blocks"` (or
+> `return_array=False` for a single call) for the dict-of-feature-blocks form instead (keys
+> prefixed `num_` and `cat_`).
 
 ### Standalone transformers
 

docs/core_concepts/configuration.md

@@ -122,6 +122,7 @@ in depth.
 | `target_aware`, `placement_strategy` | `True`, `"cart"` | [Target awareness](target_awareness.md) |
 | `numerical_imputation`, `categorical_imputation`, `add_missing_indicator` | `"median"`, `"most_frequent"`, `False` | [Missing values](missing_values.md) |
 | `output_format`, `dtype` | `"dense"`, `None` | [Outputs and inspection](outputs_and_inspection.md) |
+| `output_structure` | `"matrix"` | [Outputs and inspection](outputs_and_inspection.md) |
 | `random_state` | `None` | [Reproducibility](reproducibility.md) |
 
 ## Where to go next