stochtree 0.0.1__tar.gz

stochtree-0.0.1/CMakeLists.txt

@@ -0,0 +1,165 @@
+# Build options
+option(USE_DEBUG "Set to ON for Debug mode" OFF)
+option(USE_SANITIZER "Use santizer flags" ON)
+option(BUILD_TEST "Build C++ tests with Google Test" ON)
+option(BUILD_DEBUG_TARGETS "Build Standalone C++ Programs for Debugging" ON)
+option(BUILD_PYTHON "Build Shared Library for Python Package" OFF)
+
+# Require at least C++17
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+
+# Default to CMake 3.16
+cmake_minimum_required(VERSION 3.16)
+
+# Define the project
+project(stochtree LANGUAGES C CXX)
+
+# Sanitizer support
+set(
+  ENABLED_SANITIZERS
+  "address" "undefined"
+  CACHE
+  STRING
+  "Semicolon separated list of sanitizer names, e.g., 'address;leak'. \
+Supported sanitizers are address, leak, undefined and thread."
+)
+if(USE_SANITIZER)
+  include(cmake/Sanitizer.cmake)
+  enable_sanitizers("${ENABLED_SANITIZERS}")
+endif()
+
+# Debug flags
+if(USE_DEBUG)
+    add_definitions(-DDEBUG)
+endif()
+
+if(UNIX OR MINGW OR CYGWIN)
+  set(
+    CMAKE_CXX_FLAGS
+    "${CMAKE_CXX_FLAGS} -pthread -w"
+  )
+  if(USE_DEBUG)
+      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -g -O0")
+  else()
+      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -O3")
+  endif()
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-unknown-pragmas -Wno-unused-private-field")
+endif()
+
+if(MSVC)
+    set(
+      variables
+        CMAKE_C_FLAGS_DEBUG
+        CMAKE_C_FLAGS_MINSIZEREL
+        CMAKE_C_FLAGS_RELEASE
+        CMAKE_C_FLAGS_RELWITHDEBINFO
+        CMAKE_CXX_FLAGS_DEBUG
+        CMAKE_CXX_FLAGS_MINSIZEREL
+        CMAKE_CXX_FLAGS_RELEASE
+        CMAKE_CXX_FLAGS_RELWITHDEBINFO
+    )
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /W4 /MP /utf-8")
+    if(USE_DEBUG)
+        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Od")
+    else()
+        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /O2 /Ob2 /Oi /Ot /Oy")
+    endif()
+else()
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fPIC")
+    if(NOT USE_DEBUG)
+      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -funroll-loops")
+    endif()
+endif()
+
+# Header file directory
+set(StochTree_HEADER_DIR ${PROJECT_SOURCE_DIR}/include)
+
+# boost.math header file directory
+set(BOOSTMATH_HEADER_DIR ${PROJECT_SOURCE_DIR}/deps/boost_math/include)
+
+# Eigen header file directory
+set(EIGEN_HEADER_DIR ${PROJECT_SOURCE_DIR}/deps/eigen)
+
+# fast_double_parser header file directory
+set(FAST_DOUBLE_PARSER_HEADER_DIR ${PROJECT_SOURCE_DIR}/deps/fast_double_parser/include)
+
+# fmt header file directory
+set(FMT_HEADER_DIR ${PROJECT_SOURCE_DIR}/deps/fmt/include)
+
+# Library directory
+set(LIBRARY_OUTPUT_PATH ${PROJECT_SOURCE_DIR}/build)
+
+# Aggregate the source files underpinning the implementation in the C++ library
+file(
+  GLOB 
+  SOURCES 
+  src/container.cpp
+  src/cutpoint_candidates.cpp
+  src/data.cpp
+  src/io.cpp
+  src/json11.cpp
+  src/leaf_model.cpp
+  src/partition_tracker.cpp
+  src/random_effects.cpp
+  src/tree.cpp
+)
+
+# Define the C++ source code as a target
+add_library(stochtree_objs OBJECT ${SOURCES})
+
+# Include the headers in the source library
+target_include_directories(stochtree_objs PRIVATE ${StochTree_HEADER_DIR} ${BOOSTMATH_HEADER_DIR} ${EIGEN_HEADER_DIR} ${FAST_DOUBLE_PARSER_HEADER_DIR} ${FMT_HEADER_DIR})
+
+if(APPLE)
+  set(CMAKE_SHARED_LIBRARY_SUFFIX ".so")
+endif()
+
+# Python shared library
+if (BUILD_PYTHON)
+  # Add pybind11 module
+  add_subdirectory(deps/pybind11)
+  pybind11_add_module(stochtree_cpp src/py_stochtree.cpp)
+
+  # Link to C++ source and headers
+  target_include_directories(stochtree_cpp PRIVATE ${StochTree_HEADER_DIR} ${BOOSTMATH_HEADER_DIR} ${EIGEN_HEADER_DIR} ${FAST_DOUBLE_PARSER_HEADER_DIR} ${FMT_HEADER_DIR})
+  target_link_libraries(stochtree_cpp PRIVATE stochtree_objs)
+
+  # EXAMPLE_VERSION_INFO is defined by setup.py and passed into the C++ code as a
+  # define (VERSION_INFO) here.
+  target_compile_definitions(stochtree_cpp PRIVATE VERSION_INFO=${EXAMPLE_VERSION_INFO})
+endif()
+
+# Build C++ test program
+if(BUILD_TEST)
+  # Download the GoogleTest dependency if necessary
+  include(FetchContent)
+  FetchContent_Declare(
+    googletest
+    GIT_REPOSITORY https://github.com/google/googletest.git
+    GIT_TAG        e2239ee6043f73722e7aa812a459f54a28552929 # release-1.14.0
+  )
+  # For Windows: Prevent overriding the parent project's compiler/linker settings
+  set(gtest_force_shared_crt ON CACHE BOOL "" FORCE)
+  FetchContent_MakeAvailable(googletest)
+
+  # Build test suite
+  enable_testing()
+  include(GoogleTest)
+  file(GLOB CPP_TEST_SOURCES test/cpp/*.cpp)
+  add_executable(teststochtree ${CPP_TEST_SOURCES})
+  set(STOCHTREE_TEST_HEADER_DIR ${PROJECT_SOURCE_DIR}/test/cpp)
+  target_include_directories(teststochtree PRIVATE ${StochTree_HEADER_DIR} ${BOOSTMATH_HEADER_DIR} ${EIGEN_HEADER_DIR} ${STOCHTREE_TEST_HEADER_DIR} ${FAST_DOUBLE_PARSER_HEADER_DIR} ${FMT_HEADER_DIR})
+  target_link_libraries(teststochtree PRIVATE stochtree_objs GTest::gtest_main)
+  gtest_discover_tests(teststochtree)
+endif()
+
+# Standalone C++ Program for Debugging
+if(BUILD_DEBUG_TARGETS)
+  # Build test suite
+  add_executable(debugstochtree debug/api_debug.cpp)
+  set(StochTree_DEBUG_HEADER_DIR ${PROJECT_SOURCE_DIR}/debug)
+  target_include_directories(debugstochtree PRIVATE ${StochTree_HEADER_DIR} ${BOOSTMATH_HEADER_DIR} ${EIGEN_HEADER_DIR} ${StochTree_DEBUG_HEADER_DIR} ${FAST_DOUBLE_PARSER_HEADER_DIR} ${FMT_HEADER_DIR})
+  target_link_libraries(debugstochtree PRIVATE stochtree_objs)
+endif()
+

stochtree-0.0.1/LICENSE

@@ -0,0 +1,2 @@
+YEAR: 2024
+COPYRIGHT HOLDER: stochtree authors

stochtree-0.0.1/LICENSE.md

@@ -0,0 +1,21 @@
+# MIT License
+
+Copyright (c) 2024 stochtree authors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

stochtree-0.0.1/MANIFEST.in

@@ -0,0 +1,69 @@
+# Include cmake build instructions
+include CMakeLists.txt
+
+# Vendor package header files
+recursive-include include *.h
+recursive-include include *.hpp
+
+# Vendor package source files (excluding R-specific)
+recursive-include src *.cpp
+recursive-include src *.h
+exclude src/R_data.cpp src/R_random_effects.cpp
+
+# Remove the CRAN extensionless LICENSE file
+exclude LICENSE
+
+# Remove egg info
+prune stochtree.egg-info
+
+# Vendor pybind11 dependencies in PyPI source distribution
+recursive-include deps/pybind11/include/pybind11 *.h
+recursive-include deps/pybind11/tools *
+include deps/pybind11/CMakeLists.txt
+include deps/pybind11/pyproject.toml
+include deps/pybind11/setup.cfg
+include deps/pybind11/setup.py
+
+# Vendor fmt header files in PyPI source distribution
+recursive-include deps/fmt/include/fmt *.h
+
+# Vendor fast_double_parser header file in PyPI source distribution
+include deps/fast_double_parser/include/fast_double_parser.h
+
+# Vendor Eigen header files in PyPI source distribution
+include deps/eigen/Eigen/Cholesky
+include deps/eigen/Eigen/Core
+include deps/eigen/Eigen/Dense
+include deps/eigen/Eigen/Eigenvalues
+include deps/eigen/Eigen/Geometry
+include deps/eigen/Eigen/Householder
+include deps/eigen/Eigen/IterativeLinearSolvers
+include deps/eigen/Eigen/Jacobi
+include deps/eigen/Eigen/LU
+include deps/eigen/Eigen/OrderingMethods
+include deps/eigen/Eigen/QR
+include deps/eigen/Eigen/SVD
+include deps/eigen/Eigen/Sparse
+include deps/eigen/Eigen/SparseCholesky
+include deps/eigen/Eigen/SparseCore
+include deps/eigen/Eigen/SparseQR
+include deps/eigen/Eigen/misc
+include deps/eigen/Eigen/plugins
+recursive-include deps/eigen/Eigen/src/Cholesky *.h
+recursive-include deps/eigen/Eigen/src/Core *.h
+recursive-include deps/eigen/Eigen/src/Dense *.h
+recursive-include deps/eigen/Eigen/src/Eigenvalues *.h
+recursive-include deps/eigen/Eigen/src/Geometry *.h
+recursive-include deps/eigen/Eigen/src/Householder *.h
+recursive-include deps/eigen/Eigen/src/IterativeLinearSolvers *.h
+recursive-include deps/eigen/Eigen/src/Jacobi *.h
+recursive-include deps/eigen/Eigen/src/LU *.h
+recursive-include deps/eigen/Eigen/src/OrderingMethods *.h
+recursive-include deps/eigen/Eigen/src/QR *.h
+recursive-include deps/eigen/Eigen/src/SVD *.h
+recursive-include deps/eigen/Eigen/src/Sparse *.h
+recursive-include deps/eigen/Eigen/src/SparseCholesky *.h
+recursive-include deps/eigen/Eigen/src/SparseCore *.h
+recursive-include deps/eigen/Eigen/src/SparseQR *.h
+recursive-include deps/eigen/Eigen/src/misc *.h
+recursive-include deps/eigen/Eigen/src/plugins *.h

stochtree-0.0.1/PKG-INFO

@@ -0,0 +1,27 @@
+Metadata-Version: 2.1
+Name: stochtree
+Version: 0.0.1
+Summary: Stochastic Tree Ensembles for Machine Learning and Causal Inference
+Home-page: https://github.com/StochasticTree/stochtree
+Author: Drew Herren
+Author-email: drewherrenopensource@gmail.com
+License: MIT
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.8
+License-File: LICENSE
+License-File: LICENSE.md
+Provides-Extra: test
+Requires-Dist: pytest>=6.0; extra == "test"
+
+Stochastic Tree Ensembles for Machine Learning and Causal Inference

stochtree-0.0.1/README.md

@@ -0,0 +1,175 @@
+# StochasticTree
+
+[![C++ Tests](https://github.com/StochasticTree/stochtree/actions/workflows/cpp-test.yml/badge.svg)](https://github.com/StochasticTree/stochtree/actions/workflows/cpp-test.yml)
+[![Python Tests](https://github.com/StochasticTree/stochtree/actions/workflows/python-test.yml/badge.svg)](https://github.com/StochasticTree/stochtree/actions/workflows/python-test.yml)
+[![R Tests](https://github.com/StochasticTree/stochtree/actions/workflows/r-test.yml/badge.svg)](https://github.com/StochasticTree/stochtree/actions/workflows/r-test.yml)
+
+Software for building stochastic tree ensembles (i.e. BART, XBART) for supervised learning and causal inference.
+
+# Getting Started
+
+`StochasticTree` is composed of a C++ "core" and R / Python interfaces to that core. 
+Details on installation and use are available below:
+
+* [Python](#python-package)
+* [R](#r-package)
+* [C++ core](#c-core)
+
+# Python Package
+
+The python package is not yet on PyPI but can be installed from source using pip's [git interface](https://pip.pypa.io/en/stable/topics/vcs-support/). 
+To proceed, you will need a working version of [git](https://git-scm.com) and python 3.8 or greater (available from several sources, one of the most 
+straightforward being the [anaconda](https://docs.conda.io/projects/conda/en/stable/user-guide/install/index.html) suite).
+
+## Quick start
+
+Without worrying about virtual environments (detailed further below), `stochtree` can be installed from the command line
+
+```
+pip install numpy scipy pytest pandas scikit-learn pybind11
+pip install git+https://github.com/StochasticTree/stochtree.git
+```
+
+## Virtual environment installation
+
+Often, users prefer to manage different projects (with different package / python version requirements) in virtual environments. 
+
+### Conda
+
+Conda provides a straightforward experience in managing python dependencies, avoiding version conflicts / ABI issues / etc.
+
+To build stochtree using a `conda` based workflow, first create and activate a conda environment with the requisite dependencies
+
+```{bash}
+conda create -n stochtree-dev -c conda-forge python=3.10 numpy scipy pytest pandas pybind11 scikit-learn matplotlib seaborn
+conda activate stochtree-dev
+```
+
+Then install the package from github via pip
+
+```{bash}
+pip install git+https://github.com/StochasticTree/stochtree.git
+```
+
+(*Note*: if you'd also like to run `stochtree`'s notebook examples, you will also need jupyterlab, seaborn, and matplotlib)
+
+```{bash}
+conda install matplotlib seaborn
+pip install jupyterlab
+```
+
+With these dependencies installed, you can [clone the repo](###cloning-the-repository) and run the `demo/` examples.
+
+### Venv
+
+You could also use venv for environment management. First, navigate to the folder in which you usually store virtual environments 
+(i.e. `cd /path/to/envs`) and create and activate a virtual environment:
+
+```{bash}
+python -m venv venv
+source venv/bin/activate
+```
+
+Install all of the package (and demo notebook) dependencies
+
+```{bash}
+pip install numpy scipy pytest pandas scikit-learn pybind11
+```
+
+Then install stochtree via
+
+```{bash}
+pip install git+https://github.com/StochasticTree/stochtree.git
+```
+
+As above, if you'd like to run the notebook examples in the `demo/` subfolder, you will also need jupyterlab, seaborn, and matplotlib and you will have to [clone the repo](###cloning-the-repository)
+
+```{bash}
+pip install matplotlib seaborn jupyterlab
+```
+
+# R Package
+
+The package can be installed in R via
+
+```
+remotes::install_github("StochasticTree/stochtree", ref="r-dev")
+```
+
+# C++ Core
+
+While the C++ core links to both R and Python for a performant, high-level interface, 
+the C++ code can be compiled and unit-tested and compiled into a standalone 
+[debug program](https://github.com/StochasticTree/stochtree/tree/main/debug).
+
+## Compilation
+
+### Cloning the Repository
+
+To clone the repository, you must have git installed, which you can do following [these instructions](https://learn.microsoft.com/en-us/devops/develop/git/install-and-set-up-git). 
+
+Once git is available at the command line, navigate to the folder that will store this project (in bash / zsh, this is done by running `cd` followed by the path to the directory). 
+Then, clone the `stochtree` repo as a subfolder by running
+```{bash}
+git clone --recursive https://github.com/StochasticTree/stochtree.git
+```
+
+*NOTE*: this project incorporates several dependencies as [git submodules](https://git-scm.com/book/en/v2/Git-Tools-Submodules), 
+which is why the `--recursive` flag is necessary (some systems may perform a recursive clone without this flag, but 
+`--recursive` ensures this behavior on all platforms). If you have already cloned the repo without the `--recursive` flag, 
+you can retrieve the submodules recursively by running `git submodule update --init --recursive` in the main repo directory.
+
+
+### CMake Build
+
+The C++ project can be built independently from the R / Python packages using `cmake`. 
+See [here](https://cmake.org/install/) for details on installing cmake (alternatively, 
+on MacOS, `cmake` can be installed using [homebrew](https://formulae.brew.sh/formula/cmake)).
+Once `cmake` is installed, you can build the CLI by navigating to the main 
+project directory at your command line (i.e. `cd /path/to/stochtree`) and 
+running the following code 
+
+```{bash}
+rm -rf build
+mkdir build
+cmake -S . -B build
+cmake --build build
+```
+
+The CMake build has two primary targets, which are detailed below
+
+#### Debug Program
+
+`debug/api_debug.cpp` defines a standalone target that can be straightforwardly run with a debugger (i.e. `lldb`, `gdb`) 
+while making non-trivial changes to the C++ code.
+This debugging program is compiled as part of the CMake build if the `BUILD_DEBUG_TARGETS` option in `CMakeLists.txt` is set to `ON`.
+
+Once the program has been built, it can be run from the command line via `./build/debugstochtree` or attached to a debugger 
+via `lldb ./build/debugstochtree` (clang) or `gdb ./build/debugstochtree` (gcc).
+
+#### Unit Tests
+
+We test `stochtree` using the [GoogleTest](https://google.github.io/googletest/) framework.
+Unit tests are compiled into a single target as part of the CMake build if the `BUILD_TEST` option is set to `ON` 
+and the test suite can be run after compilation via `./build/teststochtree`
+
+## Xcode
+
+While using `gdb` or `lldb` on `debugstochtree` at the command line is very helpful, users may prefer debugging in a full-fledged IDE like xcode. This project's C++ core can be converted to an xcode project from `CMakeLists.txt`, but first you must turn off sanitizers (xcode seems to have its own way of setting this at build time for different configurations, and having injected 
+`-fsanitize=address` statically into compiler arguments will cause xcode errors). To do this, modify the `USE_SANITIZER` line in `CMakeLists.txt`:
+
+```
+option(USE_SANITIZER "Use santizer flags" OFF)
+```
+
+To generate an XCode project based on the build targets and specifications defined in a `CMakeLists.txt`, navigate to the main project folder (i.e. `cd /path/to/project`) and run the following commands:
+
+```{bash}
+rm -rf xcode/
+mkdir xcode
+cd xcode
+cmake -G Xcode .. -DCMAKE_C_COMPILER=cc -DCMAKE_CXX_COMPILER=c++
+cd ..
+```
+
+Now, if you navigate to the xcode subfolder (in Finder), you should be able to click on a `.xcodeproj` file and the project will open in XCode.

stochtree-0.0.1/deps/eigen/Eigen/Cholesky

@@ -0,0 +1,45 @@
+// This file is part of Eigen, a lightweight C++ template library
+// for linear algebra.
+//
+// This Source Code Form is subject to the terms of the Mozilla
+// Public License v. 2.0. If a copy of the MPL was not distributed
+// with this file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+#ifndef EIGEN_CHOLESKY_MODULE_H
+#define EIGEN_CHOLESKY_MODULE_H
+
+#include "Core"
+#include "Jacobi"
+
+#include "src/Core/util/DisableStupidWarnings.h"
+
+/** \defgroup Cholesky_Module Cholesky module
+  *
+  *
+  *
+  * This module provides two variants of the Cholesky decomposition for selfadjoint (hermitian) matrices.
+  * Those decompositions are also accessible via the following methods:
+  *  - MatrixBase::llt()
+  *  - MatrixBase::ldlt()
+  *  - SelfAdjointView::llt()
+  *  - SelfAdjointView::ldlt()
+  *
+  * \code
+  * #include <Eigen/Cholesky>
+  * \endcode
+  */
+
+#include "src/Cholesky/LLT.h"
+#include "src/Cholesky/LDLT.h"
+#ifdef EIGEN_USE_LAPACKE
+#ifdef EIGEN_USE_MKL
+#include "mkl_lapacke.h"
+#else
+#include "src/misc/lapacke.h"
+#endif
+#include "src/Cholesky/LLT_LAPACKE.h"
+#endif
+
+#include "src/Core/util/ReenableStupidWarnings.h"
+
+#endif // EIGEN_CHOLESKY_MODULE_H