Remove BoTorch Workaround (old)

.github/workflows/ci.yml

@@ -1,6 +1,6 @@
 # NOTES:
 # - The map syntax used for matrix is flagged red but actually works
-# - This runs everything in Python 3.11, except the fulltest which is also run in 3.8
+# - This runs everything in Python 3.11, except the fulltest which is also run in 3.9
 # - Only coretest and fulltest environments are cached due to space limit
 
 name: Continuous Integration
@@ -114,7 +114,7 @@ jobs:
     needs: [typecheck, audit]
     strategy:
       matrix:
-        py-version: [ {semantic: '3.8', tox: 'py38'} ]
+        py-version: [ {semantic: '3.11', tox: 'py311'} ]
     name: Core Tests ${{ matrix.py-version.semantic }}
     runs-on: ubuntu-latest
     steps:
@@ -136,7 +136,7 @@ jobs:
     needs: [typecheck, audit]
     strategy:
       matrix:
-        py-version: [ {semantic: '3.8', tox: 'py38'}, {semantic: '3.11', tox: 'py311'} ]
+        py-version: [ {semantic: '3.9', tox: 'py39'}, {semantic: '3.11', tox: 'py311'} ]
     name: Full Tests ${{ matrix.py-version.semantic }}
     runs-on: ubuntu-latest
     steps:

.github/workflows/regular.yml

@@ -1,6 +1,6 @@
 # NOTES:
 # - The map syntax used for matrix is flagged red but actually works
-# - This runs everything in Python 3.8, 3.9, 3.10 and 3.11
+# - This runs everything in Python 3.9, 3.10 and 3.11
 # - No environments are cached due to space limit
 
 name: Regular Checks
@@ -40,7 +40,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        py-version: [ {semantic: '3.8', tox: 'py38'}, {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
+        py-version: [ {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
     name: Lint ${{ matrix.py-version.semantic }}
     runs-on: ubuntu-latest
     steps:
@@ -59,7 +59,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        py-version: [ {semantic: '3.8', tox: 'py38'}, {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
+        py-version: [ {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
     name: Type Check ${{ matrix.py-version.semantic }}
     runs-on: ubuntu-latest
     steps:
@@ -78,7 +78,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        py-version: [ {semantic: '3.8', tox: 'py38'}, {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
+        py-version: [ {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
     name: Audit ${{ matrix.py-version.semantic }}
     runs-on: ubuntu-latest
     steps:
@@ -97,7 +97,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        py-version: [ {semantic: '3.8', tox: 'py38'}, {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
+        py-version: [ {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
     name: Core Tests ${{ matrix.py-version.semantic }}
     runs-on: ubuntu-latest
     steps:
@@ -120,7 +120,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        py-version: [ {semantic: '3.8', tox: 'py38'}, {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
+        py-version: [ {semantic: '3.9', tox: 'py39'}, {semantic: '3.10', tox: 'py310'}, {semantic: '3.11', tox: 'py311'} ]
     name: Full Tests ${{ matrix.py-version.semantic }}
     runs-on: ubuntu-latest
     steps:

.gitignore

@@ -21,10 +21,11 @@ build
 
 # Testing
 .tox
-.coverage
-.coverage.*
-.hypothesis/
+.coverage*
+.hypothesis
 .pytest_cache
+.mypy_cache
+.ruff_cache
 htmlcov
 
 # Pictures created by backtesting

CHANGELOG.md

@@ -4,6 +4,14 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+### Changed
+- BoTorch dependency bumped to `>=0.9.3`
+
+### Removed
+- Workaround for BoTorch hybrid recommender data type
+- Support for Python 3.8
+
 ## [0.7.2] - 2024-01-24
 ### Added
 - Target enums 
@@ -46,7 +54,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Specifying target configs without explicit type information is deprecated
 - Specifying parameters/constraints at the top level of a campaign configuration JSON is
   deprecated. Instead, an explicit `searchspace` field must be provided with an optional
-  `constructor` entry.
+  `constructor` entry
 
 ## [0.7.1] - 2023-12-07
 ### Added

baybe/recommenders/bayesian.py

@@ -4,7 +4,6 @@
 from functools import partial
 from typing import Any, Callable, ClassVar, Literal, Optional
 
-import numpy as np
 import pandas as pd
 from attrs import define, field, validators
 from botorch.acquisition import (
@@ -18,7 +17,6 @@
     qUpperConfidenceBound,
 )
 from botorch.optim import optimize_acqf, optimize_acqf_discrete, optimize_acqf_mixed
-from sklearn.metrics import pairwise_distances_argmin
 
 from baybe.acquisition import PartialAcquisitionFunction, debotorchize
 from baybe.exceptions import NoMCAcquisitionFunctionError
@@ -295,7 +293,6 @@ def _recommend_discrete(
                 on=list(candidates_comp),
             )["index"]
         )
-        assert len(points) == len(idxs)
 
         return idxs
 
@@ -382,7 +379,8 @@ def _recommend_hybrid(
         # format expected by BoTorch
         # TODO: Currently assumes that discrete parameters are first and continuous
         #   second. Once parameter redesign [11611] is completed, we might adjust this.
-        candidates_comp.columns = list(range(len(candidates_comp.columns)))
+        num_comp_columns = len(candidates_comp.columns)
+        candidates_comp.columns = list(range(num_comp_columns))
         fixed_features_list = candidates_comp.to_dict("records")
 
         # Actual call of the BoTorch optimization routine
@@ -397,15 +395,15 @@ def _recommend_hybrid(
                 equality_constraints=[
                     c.to_botorch(
                         searchspace.continuous.parameters,
-                        idx_offset=len(candidates_comp.columns),
+                        idx_offset=num_comp_columns,
                     )
                     for c in searchspace.continuous.constraints_lin_eq
                 ]
                 or None,  # TODO: https://github.com/pytorch/botorch/issues/2042
                 inequality_constraints=[
                     c.to_botorch(
                         searchspace.continuous.parameters,
-                        idx_offset=len(candidates_comp.columns),
+                        idx_offset=num_comp_columns,
                     )
                     for c in searchspace.continuous.constraints_lin_ineq
                 ]
@@ -417,40 +415,28 @@ def _recommend_hybrid(
                 f"acquisition functions."
             ) from ex
 
-        # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
-        # TODO [14819]: The following code is necessary due to floating point
-        #   inaccuracies introduced by BoTorch (potentially due to some float32
-        #   conversion?). The current workaround is the match the recommendations back
-        #   to the closest candidate points.
-
         # Split discrete and continuous parts
-        disc_points = points[:, : len(candidates_comp.columns)]
-        cont_points = points[:, len(candidates_comp.columns) :]
-
-        # Find the closest match with the discrete candidates
-        candidates_comp_np = candidates_comp.to_numpy()
-        disc_points_np = disc_points.numpy()
-        if not disc_points_np.flags["C_CONTIGUOUS"]:
-            disc_points_np = np.ascontiguousarray(disc_points_np)
-        if not candidates_comp_np.flags["C_CONTIGUOUS"]:
-            candidates_comp_np = np.ascontiguousarray(candidates_comp_np)
-        disc_idxs_iloc = pairwise_distances_argmin(
-            disc_points_np, candidates_comp_np, metric="manhattan"
-        )
+        disc_points = points[:, :num_comp_columns]
+        cont_points = points[:, num_comp_columns:]
 
-        # Get the actual search space dataframe indices
-        disc_idxs_loc = candidates_comp.iloc[disc_idxs_iloc].index
+        # Get selected candidate indices
+        idxs = pd.Index(
+            pd.merge(
+                candidates_comp.reset_index(),
+                pd.DataFrame(disc_points, columns=candidates_comp.columns),
+                on=list(candidates_comp),
+            )["index"]
+        )
 
         # Get experimental representation of discrete and continuous parts
-        rec_disc_exp = searchspace.discrete.exp_rep.loc[disc_idxs_loc]
+        rec_disc_exp = searchspace.discrete.exp_rep.loc[idxs]
         rec_cont_exp = pd.DataFrame(
             cont_points, columns=searchspace.continuous.param_names
         )
 
-        # Adjust the index of the continuous part and concatenate both
+        # Adjust the index of the continuous part and create overall recommendations
         rec_cont_exp.index = rec_disc_exp.index
         rec_exp = pd.concat([rec_disc_exp, rec_cont_exp], axis=1)
-        # <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
 
         return rec_exp
 

baybe/recommenders/sampling.py

@@ -46,7 +46,6 @@ def _recommend_hybrid(
             replace=len(disc_candidates) < batch_quantity,
         )
 
-        cont_random.reset_index(drop=True)
         cont_random.index = disc_random.index
         return pd.concat([disc_random, cont_random], axis=1)
 

examples/Serialization/basic_serialization.py

@@ -73,7 +73,7 @@
 # We next serialize the campaign to JSON.
 # This yields a JSON representation in string format.
 # Since it is rather complex, we do not print this string here.
-# Note: Dataframes are encoded via binary parquet and are hence not human-readable.
+# Note: Dataframes are binary-encoded and are hence not human-readable.
 string = campaign.to_json()
 
 

pyproject.toml

@@ -6,14 +6,13 @@ authors = [
 ]
 readme = "README.md"
 license = { text = "Apache-2.0" }
-requires-python =">=3.8,<3.12"
+requires-python =">=3.9,<3.12"
 classifiers = [
     "Development Status :: 4 - Beta",
     "Intended Audience :: Developers",
     "License :: OSI Approved :: Apache Software License",
     "Programming Language :: Python",
     "Programming Language :: Python :: 3 :: Only",
-    "Programming Language :: Python :: 3.8",
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
@@ -30,20 +29,20 @@ keywords = [
 dynamic = ['version']
 dependencies = [
     "attrs>=22.2.0",
-    "botorch>=0.8.1",
+    "botorch>=0.9.3",
     "cattrs>=23.2.0",
     "exceptiongroup",
     "funcy>=1.17",
     "gpytorch>=1.9.1",
     "ngboost>=0.3.12",
     "numpy>=1.24.1",
-    "pandas[parquet]>=1.4.2",
+    "pandas>=1.4.2",
     "protobuf<=3.20.3",
     "scikit-learn>=1.1.1",
     "scikit-learn-extra>=0.3.0",
     "scipy>=1.10.1",
     "setuptools-scm>=7.1.0",
-    "torch>=1.11.0",
+    "torch>=1.13.1",
     "baybe[telemetry]",
 ]
 

tests/README.md

@@ -42,7 +42,6 @@ pytest --cov=baybe
 
 This will produce something like this:
 ```
----------- coverage: platform darwin, python 3.8.6-final-0 -----------
 Name                                 Stmts   Miss  Cover
 --------------------------------------------------------
 baybe/acquisition.py                    58      0   100%
@@ -59,8 +58,8 @@ possibility to test different python variants as well.
 
 ### Environments
 In `tox.ini`, we have configured several environments for running different actions 
-(`fulltest`, `coretest`, `lint`, `audit`) against different versions of python (e.g. `py38`, `py39`, .
-..). 
+(`fulltest`, `coretest`, `lint`, `audit`) against different versions of python
+(e.g. `py310`, `py311`, ...). 
 You can specify both in `tox` to call a certain combination. 
 
 For instance 
@@ -85,13 +84,13 @@ tox -l
 ### Shortcuts
 In case you want to run several combinations, you can specify them like
 ```bash
-tox -e audit-py38,audit-py311
+tox -e audit-py310,audit-py311
 ```
 
 If you omit the python version from the environment, `tox` will use the version 
 from the command-executing environment:
 ```bash
-tox -e coretest  # runs like '-e coretest-py38' if called from a python 3.8 environment
+tox -e coretest  # runs like '-e coretest-py310' if called from a python 3.10 environment
 ```
 
 If you simply want to run all combinations, you can use

tox.ini

@@ -1,25 +1,25 @@
 [tox]
 min_version = 4.9
-env_list = {fulltest,coretest,lint,mypy,audit}-py{38,39,310,311}
+env_list = {fulltest,coretest,lint,mypy,audit}-py{39,310,311}
 isolated_build = True
 
-[testenv:fulltest,fulltest-py{38,39,310,311}]
+[testenv:fulltest,fulltest-py{39,310,311}]
 description = Run PyTest with all extra functionality
 extras = test,chem,examples,simulation,onnx
 passenv = CI
 commands =
     python --version
     pytest -p no:warnings --cov=baybe --durations=5 {posargs}
 
-[testenv:coretest,coretest-py{38,39,310,311}]
+[testenv:coretest,coretest-py{39,310,311}]
 description = Run PyTest with core functionality
 extras = test,examples
 passenv = CI
 commands =
     python --version
     pytest -p no:warnings --cov=baybe --durations=5 {posargs}
 
-[testenv:lint,lint-py{38,39,310,311}]
+[testenv:lint,lint-py{39,310,311}]
 description = Run linters and format checkers
 extras = lint,examples
 skip_install = True
@@ -28,7 +28,7 @@ commands =
     python --version
     pre-commit run --all-files {posargs:--show-diff-on-failure}
 
-[testenv:mypy,mypy-py{38,39,310,311}]
+[testenv:mypy,mypy-py{39,310,311}]
 description = Run mypy
 extras = mypy
 setenv =
@@ -37,7 +37,7 @@ commands =
     python --version
     mypy
 
-[testenv:audit,audit-py{38,39,310,311}]
+[testenv:audit,audit-py{39,310,311}]
 description = Run pip-audit
 extras = dev # audit entire environment
 setenv =
@@ -47,7 +47,7 @@ commands =
     python --version
     pip-audit {env:EXCLUDES:}
 
-[testenv:docs,docs-py{38,39,310,311}]
+[testenv:docs,docs-py{39,310,311}]
 description = Build documentation
 extras = docs
 passenv = BAYBE_DOCS_LINKCHECK_IGNORE