causilo 1.0.0__tar.gz

causilo-1.0.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Nums AI Inc.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

causilo-1.0.0/MANIFEST.in

@@ -0,0 +1,9 @@
+include LICENSE README.md pyproject.toml
+recursive-include src *.py
+recursive-include tests *.py
+recursive-include examples *.py
+prune reports
+prune artifacts
+prune tools
+prune .github
+global-exclude __pycache__ *.py[cod]

causilo-1.0.0/PKG-INFO

@@ -0,0 +1,144 @@
+Metadata-Version: 2.4
+Name: causilo
+Version: 1.0.0
+Summary: Pretrained tabular classification and regression
+Author-email: "Nums AI Inc." <contact@nums.world>
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/nums-ai/causilo
+Project-URL: Issues, https://github.com/nums-ai/causilo/issues
+Project-URL: Models, https://huggingface.co/nums-ai/causilo
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: <3.13,>=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.13
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: scipy
+Requires-Dist: scikit-learn>=1.6
+Requires-Dist: safetensors>=0.8
+Requires-Dist: huggingface-hub>=0.28
+Requires-Dist: psutil
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Requires-Dist: joblib; extra == "dev"
+Dynamic: license-file
+
+# Causilo
+
+Causilo is a pretrained tabular foundation model from Nums AI Inc., supporting classification and regression through a scikit-learn interface.
+
+[Apache-2.0 code](https://github.com/nums-ai/causilo/blob/main/LICENSE) · [Causilo License v1.0 model weights](https://huggingface.co/nums-ai/causilo/blob/main/LICENSE) · [License & contact](#license--contact)
+
+## Installation
+
+Python 3.10–3.12 and PyTorch 2.13+ are required.
+
+```bash
+pip install causilo
+hf auth login
+```
+
+Authenticate with an account that has access to the [model weights](https://huggingface.co/nums-ai/causilo). Package installation does not grant weight access; the first fit downloads and caches the task's checkpoint. `device="auto"` uses CUDA when available, otherwise CPU. Use `CUDA_VISIBLE_DEVICES=0` to select a GPU.
+
+## Quick start
+
+```python
+from causilo import CausiloClassifier, CausiloRegressor
+
+classifier = CausiloClassifier(n_estimators=8, random_state=42)
+classifier.fit(X_train, y_train)
+labels = classifier.predict(X_test)
+probabilities = classifier.predict_proba(X_test)
+
+regressor = CausiloRegressor(n_estimators=8, random_state=42)
+regressor.fit(X_train, y_train)
+predictions = regressor.predict(X_test)
+```
+
+
+Inputs can be NumPy arrays or pandas DataFrames, including categorical features and missing feature values. Use pandas categorical dtype for numeric category codes. NumPy object arrays infer numeric columns; strings and Booleans remain categorical. Prediction reuses the fitted schema, including handling unseen categories.
+
+Classification supports up to 10 classes; regression returns point predictions. Targets must not be missing. See runnable [classification](https://github.com/nums-ai/causilo/blob/main/examples/classification.py) and [regression](https://github.com/nums-ai/causilo/blob/main/examples/regression.py) examples.
+
+## Benchmarks
+
+Official TabArena default-only evaluation: 51 datasets, 51 Lite splits and 816 Full splits, using eight estimators and seed 42. System methods are excluded. Full plots show the top 16 model families by their best Elo, with default, tuned and ensembled variants.
+
+| Suite   | Task           |   Elo position |   Elo ↑ |   Improvability ↓ |
+|:--------|:---------------|---------------:|--------:|------------------:|
+| Lite    | Overall        |              1 |  1817.4 |            0.0596 |
+| Lite    | Classification |              1 |  1780.1 |            0.0747 |
+| Lite    | Regression     |              1 |  2168.2 |            0.0155 |
+| Full    | Overall        |              1 |  1792.9 |            0.0684 |
+| Full    | Classification |              1 |  1771.8 |            0.0875 |
+| Full    | Regression     |              1 |  2032.6 |            0.0125 |
+
+![Overall performance](https://raw.githubusercontent.com/nums-ai/causilo/main/docs/benchmarks/overall.png)
+
+*Overall — TabArena Full, classification and regression combined.*
+
+<details>
+<summary>Classification and regression</summary>
+
+![Classification performance](https://raw.githubusercontent.com/nums-ai/causilo/main/docs/benchmarks/classification.png)
+
+*Classification — TabArena Full, classification datasets only.*
+
+![Regression performance](https://raw.githubusercontent.com/nums-ai/causilo/main/docs/benchmarks/regression.png)
+
+*Regression — TabArena Full, regression datasets only.*
+
+</details>
+
+Local H100 80 GB comparison, one GPU and eight physical CPU cores per job:
+
+| Model    |   Fit (s/1k) |   Predict (s/1k) |   CPU (GiB) |   GPU (GiB) |
+|:---------|-------------:|-----------------:|------------:|------------:|
+| **Causilo** | **2.504** | **0.251** | **1.94** | 8.15 |
+| TabICLv2 | 3.449 | 0.303 | 2 | 8.37 |
+| TabPFN-3 | 4.18 | 0.686 | 2.87 | **0.88** |
+
+Times are median seconds per 1,000 rows; memory is mean peak usage during fit only. [Protocol, task-level resources and complete leaderboards](https://github.com/nums-ai/causilo/blob/main/docs/benchmarks/README.md).
+
+## Options
+
+| Parameter | Default | Behavior |
+| --- | --- | --- |
+| `n_estimators` | `8` | Number of ensemble members to evaluate |
+| `random_state` | `42` | Nonnegative integer seed for feature and class permutations |
+| `device` | `"auto"` | One available CUDA device, otherwise CPU; explicit `"cpu"` or `"cuda:0"` is supported |
+| `use_kv_cache` | `False` | Prepare and retain attention keys and values during fit |
+| `retain_preprocessing` | `True` | Retain transformed training tables for later prediction |
+
+
+Refit after changing options. Seeds must be nonnegative integers; the same inputs and seed reproduce the fitted permutations without changing global RNG state. Bitwise floating-point determinism is not forced.
+
+Preprocessing and execution policies are fixed. Ensembles cycle through none, rank2gaussian, robust and power normalization. CUDA uses FP16 mixed precision, with regression column stages and both output heads in FP32; CPU uses FP32. Regression target scaling and output restoration use float64.
+
+## Repeated prediction
+
+Set `use_kv_cache=True` to move reusable context computation into fit, trading additional device memory for repeated prediction speed. With `retain_preprocessing=False`, fitted transforms are retained but transformed training tables are recomputed. Refitting replaces the context; a failed fit leaves the estimator unfitted. See [cached prediction](https://github.com/nums-ai/causilo/blob/main/examples/cached_prediction.py).
+
+## Fitted-state storage
+
+```python
+import joblib
+
+joblib.dump(classifier, "classifier.joblib")
+restored = joblib.load("classifier.joblib")
+```
+
+
+Saved state includes fitted preprocessing and optional K/V caches, but excludes pretrained weights. Restoration loads the pinned checkpoint and reuses saved caches. It requires matching Causilo and dependency versions, including Python major/minor. Automatic device selection runs again; an unavailable explicit device fails. See [save/restore](https://github.com/nums-ai/causilo/blob/main/examples/save_restore.py).
+
+## License & contact
+
+Code is licensed under [Apache-2.0](https://github.com/nums-ai/causilo/blob/main/LICENSE); model weights are separately licensed under [Causilo License v1.0](https://huggingface.co/nums-ai/causilo/blob/main/LICENSE). Non-commercial research and free research redistribution are permitted under its conditions. Commercial or production use, and hosted/API/SaaS services whether paid or free, require separate licenses. Contact contact@nums.world.

causilo-1.0.0/README.md

@@ -0,0 +1,111 @@
+# Causilo
+
+Causilo is a pretrained tabular foundation model from Nums AI Inc., supporting classification and regression through a scikit-learn interface.
+
+[Apache-2.0 code](https://github.com/nums-ai/causilo/blob/main/LICENSE) · [Causilo License v1.0 model weights](https://huggingface.co/nums-ai/causilo/blob/main/LICENSE) · [License & contact](#license--contact)
+
+## Installation
+
+Python 3.10–3.12 and PyTorch 2.13+ are required.
+
+```bash
+pip install causilo
+hf auth login
+```
+
+Authenticate with an account that has access to the [model weights](https://huggingface.co/nums-ai/causilo). Package installation does not grant weight access; the first fit downloads and caches the task's checkpoint. `device="auto"` uses CUDA when available, otherwise CPU. Use `CUDA_VISIBLE_DEVICES=0` to select a GPU.
+
+## Quick start
+
+```python
+from causilo import CausiloClassifier, CausiloRegressor
+
+classifier = CausiloClassifier(n_estimators=8, random_state=42)
+classifier.fit(X_train, y_train)
+labels = classifier.predict(X_test)
+probabilities = classifier.predict_proba(X_test)
+
+regressor = CausiloRegressor(n_estimators=8, random_state=42)
+regressor.fit(X_train, y_train)
+predictions = regressor.predict(X_test)
+```
+
+
+Inputs can be NumPy arrays or pandas DataFrames, including categorical features and missing feature values. Use pandas categorical dtype for numeric category codes. NumPy object arrays infer numeric columns; strings and Booleans remain categorical. Prediction reuses the fitted schema, including handling unseen categories.
+
+Classification supports up to 10 classes; regression returns point predictions. Targets must not be missing. See runnable [classification](https://github.com/nums-ai/causilo/blob/main/examples/classification.py) and [regression](https://github.com/nums-ai/causilo/blob/main/examples/regression.py) examples.
+
+## Benchmarks
+
+Official TabArena default-only evaluation: 51 datasets, 51 Lite splits and 816 Full splits, using eight estimators and seed 42. System methods are excluded. Full plots show the top 16 model families by their best Elo, with default, tuned and ensembled variants.
+
+| Suite   | Task           |   Elo position |   Elo ↑ |   Improvability ↓ |
+|:--------|:---------------|---------------:|--------:|------------------:|
+| Lite    | Overall        |              1 |  1817.4 |            0.0596 |
+| Lite    | Classification |              1 |  1780.1 |            0.0747 |
+| Lite    | Regression     |              1 |  2168.2 |            0.0155 |
+| Full    | Overall        |              1 |  1792.9 |            0.0684 |
+| Full    | Classification |              1 |  1771.8 |            0.0875 |
+| Full    | Regression     |              1 |  2032.6 |            0.0125 |
+
+![Overall performance](https://raw.githubusercontent.com/nums-ai/causilo/main/docs/benchmarks/overall.png)
+
+*Overall — TabArena Full, classification and regression combined.*
+
+<details>
+<summary>Classification and regression</summary>
+
+![Classification performance](https://raw.githubusercontent.com/nums-ai/causilo/main/docs/benchmarks/classification.png)
+
+*Classification — TabArena Full, classification datasets only.*
+
+![Regression performance](https://raw.githubusercontent.com/nums-ai/causilo/main/docs/benchmarks/regression.png)
+
+*Regression — TabArena Full, regression datasets only.*
+
+</details>
+
+Local H100 80 GB comparison, one GPU and eight physical CPU cores per job:
+
+| Model    |   Fit (s/1k) |   Predict (s/1k) |   CPU (GiB) |   GPU (GiB) |
+|:---------|-------------:|-----------------:|------------:|------------:|
+| **Causilo** | **2.504** | **0.251** | **1.94** | 8.15 |
+| TabICLv2 | 3.449 | 0.303 | 2 | 8.37 |
+| TabPFN-3 | 4.18 | 0.686 | 2.87 | **0.88** |
+
+Times are median seconds per 1,000 rows; memory is mean peak usage during fit only. [Protocol, task-level resources and complete leaderboards](https://github.com/nums-ai/causilo/blob/main/docs/benchmarks/README.md).
+
+## Options
+
+| Parameter | Default | Behavior |
+| --- | --- | --- |
+| `n_estimators` | `8` | Number of ensemble members to evaluate |
+| `random_state` | `42` | Nonnegative integer seed for feature and class permutations |
+| `device` | `"auto"` | One available CUDA device, otherwise CPU; explicit `"cpu"` or `"cuda:0"` is supported |
+| `use_kv_cache` | `False` | Prepare and retain attention keys and values during fit |
+| `retain_preprocessing` | `True` | Retain transformed training tables for later prediction |
+
+
+Refit after changing options. Seeds must be nonnegative integers; the same inputs and seed reproduce the fitted permutations without changing global RNG state. Bitwise floating-point determinism is not forced.
+
+Preprocessing and execution policies are fixed. Ensembles cycle through none, rank2gaussian, robust and power normalization. CUDA uses FP16 mixed precision, with regression column stages and both output heads in FP32; CPU uses FP32. Regression target scaling and output restoration use float64.
+
+## Repeated prediction
+
+Set `use_kv_cache=True` to move reusable context computation into fit, trading additional device memory for repeated prediction speed. With `retain_preprocessing=False`, fitted transforms are retained but transformed training tables are recomputed. Refitting replaces the context; a failed fit leaves the estimator unfitted. See [cached prediction](https://github.com/nums-ai/causilo/blob/main/examples/cached_prediction.py).
+
+## Fitted-state storage
+
+```python
+import joblib
+
+joblib.dump(classifier, "classifier.joblib")
+restored = joblib.load("classifier.joblib")
+```
+
+
+Saved state includes fitted preprocessing and optional K/V caches, but excludes pretrained weights. Restoration loads the pinned checkpoint and reuses saved caches. It requires matching Causilo and dependency versions, including Python major/minor. Automatic device selection runs again; an unavailable explicit device fails. See [save/restore](https://github.com/nums-ai/causilo/blob/main/examples/save_restore.py).
+
+## License & contact
+
+Code is licensed under [Apache-2.0](https://github.com/nums-ai/causilo/blob/main/LICENSE); model weights are separately licensed under [Causilo License v1.0](https://huggingface.co/nums-ai/causilo/blob/main/LICENSE). Non-commercial research and free research redistribution are permitted under its conditions. Commercial or production use, and hosted/API/SaaS services whether paid or free, require separate licenses. Contact contact@nums.world.

causilo-1.0.0/examples/cached_prediction.py

@@ -0,0 +1,10 @@
+"""Reuse fitted attention context for successive prediction calls."""
+
+from sklearn.datasets import load_iris
+
+from causilo import CausiloClassifier
+
+X, y = load_iris(return_X_y=True, as_frame=True)
+model = CausiloClassifier(use_kv_cache=True).fit(X.iloc[::2], y.iloc[::2])
+for start in (1, 11, 21):
+    print(model.predict_proba(X.iloc[start:start + 5]))

causilo-1.0.0/examples/classification.py

@@ -0,0 +1,12 @@
+"""Fit a classifier and inspect class probabilities."""
+
+from sklearn.datasets import load_iris
+from sklearn.model_selection import train_test_split
+
+from causilo import CausiloClassifier
+
+X, y = load_iris(return_X_y=True, as_frame=True)
+X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0, stratify=y)
+model = CausiloClassifier().fit(X_train, y_train)
+print("Accuracy:", model.score(X_test, y_test))
+print("Probabilities:", model.predict_proba(X_test.iloc[:3]))

causilo-1.0.0/examples/regression.py

@@ -0,0 +1,12 @@
+"""Fit a regressor and inspect point predictions."""
+
+from sklearn.datasets import load_diabetes
+from sklearn.model_selection import train_test_split
+
+from causilo import CausiloRegressor
+
+X, y = load_diabetes(return_X_y=True, as_frame=True)
+X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
+model = CausiloRegressor().fit(X_train, y_train)
+print("R-squared:", model.score(X_test, y_test))
+print("Predictions:", model.predict(X_test.iloc[:3]))

causilo-1.0.0/examples/save_restore.py

@@ -0,0 +1,21 @@
+"""Save fitted context and restore it without another fit."""
+
+from pathlib import Path
+from tempfile import TemporaryDirectory
+
+import joblib
+import numpy as np
+from sklearn.datasets import load_diabetes
+
+from causilo import CausiloRegressor
+
+X, y = load_diabetes(return_X_y=True, as_frame=True)
+model = CausiloRegressor(use_kv_cache=True).fit(X.iloc[:100], y.iloc[:100])
+query = X.iloc[100:105]
+expected = model.predict(query)
+with TemporaryDirectory() as folder:
+    path = Path(folder) / "fitted.joblib"
+    joblib.dump(model, path)
+    restored = joblib.load(path)
+    np.testing.assert_array_equal(restored.predict(query), expected)
+    print(restored.predict(query))

causilo-1.0.0/pyproject.toml

@@ -0,0 +1,48 @@
+[build-system]
+requires = ["setuptools>=77", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "causilo"
+version = "1.0.0"
+description = "Pretrained tabular classification and regression"
+readme = "README.md"
+requires-python = ">=3.10,<3.13"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{name = "Nums AI Inc.", email = "contact@nums.world"}]
+dependencies = [
+    "torch>=2.13", "numpy", "pandas", "scipy", "scikit-learn>=1.6",
+    "safetensors>=0.8", "huggingface-hub>=0.28", "psutil",
+]
+classifiers = [
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Operating System :: POSIX :: Linux",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+
+[project.urls]
+Repository = "https://github.com/nums-ai/causilo"
+Issues = "https://github.com/nums-ai/causilo/issues"
+Models = "https://huggingface.co/nums-ai/causilo"
+
+[project.optional-dependencies]
+dev = ["pytest>=8", "ruff", "build", "twine", "joblib"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+addopts = "-m 'not pretrained'"
+markers = ["pretrained: requires access to official model weights"]
+
+[tool.ruff]
+line-length = 110
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E4", "E7", "E9", "F", "I"]

causilo-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

causilo-1.0.0/src/causilo/__init__.py

@@ -0,0 +1,7 @@
+"""Tabular prediction with fixed pretrained context models."""
+
+__version__ = "1.0.0"
+
+from .estimators import CausiloClassifier, CausiloRegressor
+
+__all__ = ["CausiloClassifier", "CausiloRegressor"]

causilo-1.0.0/src/causilo/checkpoints.py

@@ -0,0 +1,54 @@
+"""Load pinned safetensors weights and verify their task/configuration pairing."""
+
+import hashlib
+import json
+from pathlib import Path
+
+import torch
+from huggingface_hub import snapshot_download
+from safetensors import safe_open
+
+from .model import Model, ModelConfig
+
+REPOSITORY = "nums-ai/causilo"
+RELEASE_COMMIT = "94f2bd91db0737d4da59f347910662905ecb5a09"
+
+
+def load_checkpoint(directory: Path) -> Model:
+    """Validate the format and config hash, then materialize an evaluation model."""
+    encoded = (directory / "config.json").read_bytes()
+    record = json.loads(encoded)
+    expected = {"architecture": "causilo-v1.0", "format_version": 1, "config_version": 1}
+    if any(record.get(key) != value for key, value in expected.items()):
+        raise ValueError("Unsupported model configuration")
+    config = ModelConfig(**record["model"])
+    with safe_open(directory / "model.safetensors", framework="pt") as artifact:
+        metadata = artifact.metadata()
+        required = {
+            "architecture": "causilo-v1.0",
+            "format_version": "1",
+            "task": config.task,
+            "config_sha256": hashlib.sha256(encoded).hexdigest(),
+        }
+        if metadata != required:
+            raise ValueError("Weights do not match their task and configuration")
+        tensors = {key: artifact.get_tensor(key) for key in artifact.keys()}
+    # Construct shapes without allocating a second full copy of the weights.
+    with torch.device("meta"):
+        model = Model(config)
+    model.load_state_dict(tensors, strict=True, assign=True)
+    return model.eval()
+
+
+def load_pretrained_model(task: str) -> Model:
+    """Fetch the task's files at the pinned revision, reusing the Hub cache when available."""
+    folder = "classifier" if task == "classification" else "regressor"
+    root = snapshot_download(
+        REPOSITORY,
+        revision=RELEASE_COMMIT,
+        allow_patterns=[f"{folder}/config.json", f"{folder}/model.safetensors"],
+    )
+    model = load_checkpoint(Path(root) / folder)
+    if model.config.task != task:
+        raise ValueError("The official checkpoint has the wrong prediction task")
+    return model

causilo-1.0.0/src/causilo/data/__init__.py

@@ -0,0 +1 @@
+"""Fitted tabular representations and deterministic ensemble views."""