New package structure

.gitmodules

@@ -1,9 +1,9 @@
 [submodule "pybmix/src/bayesmix"]
-	path = pybmix/core/pybmixcpp/bayesmix
+	path = pybmixlib/bayesmix
 	url = https://github.com/bayesmix-dev/bayesmix.git
 	depth = 1
 	update = merge
 [submodule "lib/pybind11"]
-	path = lib/pybind11
+	path = pybmixlib/pybind11
 	depth = 1
 	url = https://github.com/pybind/pybind11.git

CMakeLists.txt

@@ -1,27 +1,24 @@
 cmake_minimum_required(VERSION 3.13.0)
-project(pybmixcpp)
+project(pybmix)
 
-set (CMAKE_CXX_STANDARD 14)
-set(COMPILE_OPTIONS -D_REENTRANT -fPIC)
-set(CMAKE_BUILD_TYPE Release)
-set(CMAKE_CXX_FLAGS_RELEASE "-O3 -funroll-loops -ftree-vectorize")
-set(CMAKE_FIND_PACKAGE_PREFER_CONFIG TRUE)
+SET(SOURCE_DIR "${CMAKE_CURRENT_LIST_DIR}/pybmixlib/bayesmix")
 
+option(DISABLE_TESTS ON)
+option(DISABLE_BENCHMARKS ON)
+option(DISABLE_DOCS ON)
+option(DISABLE_PLOTS ON)
+option(DISABLE_EXAMPLES ON)
+option(BUILD_RUN OFF)
 
-SET(SOURCE_DIR "${CMAKE_CURRENT_LIST_DIR}/pybmix/core/pybmixcpp")
-add_subdirectory(${SOURCE_DIR}/bayesmix)
+add_subdirectory(${SOURCE_DIR})
 include_directories(${SOURCE_DIR})
 SET_SOURCE_FILES_PROPERTIES(${PROTO_HEADERS} ${PROTO_SOURCES} PROPERTIES GENERATED TRUE)
 
-# Generate python module
-add_subdirectory(lib/pybind11)
-pybind11_add_module(pybmixcpp ${SOURCES}
-    "${SOURCE_DIR}/module.cpp"
-    "${SOURCE_DIR}/algorithm_wrapper.hpp"
-    "${SOURCE_DIR}/algorithm_wrapper.cpp"
-    "${SOURCE_DIR}/serialized_collector.hpp"
-    "${SOURCE_DIR}/serialized_collector.cpp"
-    ${PROTO_HEADERS} ${PROTO_SOURCES})
+message ("*** PROTOC "  protobuf::protoc)
+message ("*** Protobuf_VERSION "  ${Protobuf_VERSION})
+message ("*** Protobuf_PROTOC_LIBRARIES "  ${Protobuf_PROTOC_LIBRARIES})
+
+
 
 # generate Python's proto classes
 set(PY_PROTO_DIR "${CMAKE_CURRENT_LIST_DIR}/pybmix/proto")
@@ -34,22 +31,15 @@ foreach(PROTO_FILE IN LISTS ProtoFiles)
   message(STATUS "GENERATING PYTHON protoc proto(cc): ${PROTO_FILE} --> ${PROTO_PY}")
   add_custom_command(
     OUTPUT ${PROTO_PY}
-    COMMAND protobuf::protoc "--proto_path=${SOURCE_DIR}/bayesmix/src/proto"
+    COMMAND /usr/local/bin/protoc "--proto_path=${SOURCE_DIR}/src/proto"
     ${PROTO_DIRS} "--python_out=${PY_PROTO_DIR}" ${PROTO_FILE}
     DEPENDS ${PROTO_FILE} protobuf::protoc
     COMMENT "Generate Python protocol buffer for ${PROTO_FILE}"
     VERBATIM)
     list(APPEND PROTO_PYS ${PROTO_PY})
 endforeach()
 
-find_package (TBB EXACT PATHS ${TBB_ROOT})
-find_package(OpenMP REQUIRED)
-
-message("INCLUDE_PATHS" ${INCLUDE_PATHS})
-
-target_include_directories(pybmixcpp PUBLIC ${BAYESMIX_INCLUDE_PATHS})
-target_compile_definitions(pybmixcpp PRIVATE VERSION_INFO=${EXAMPLE_VERSION_INFO})
-target_link_libraries(pybmixcpp PUBLIC bayesmixlib ${BAYESMIX_LINK_LIBRARIES})
-target_compile_options(pybmixcpp PUBLIC ${BAYESMIX_COMPILE_OPTIONS})
+SET_SOURCE_FILES_PROPERTIES(${PROTO_PYS} PROPERTIES GENERATED TRUE)
 
-add_custom_target(genterate_protos ALL DEPENDS ${PROTO_PYS})
+add_custom_target(generate_protos ALL DEPENDS ${PROTO_PYS})
+add_custom_target(two_to_three ALL COMMAND ${CMAKE_CURRENT_LIST_DIR}/convert_proto.sh DEPENDS generate_protos)

docs/examples/clustering_univ_data.ipynb

@@ -16,9 +16,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "'NoneType' object has no attribute 'enum_types_by_name'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "Input \u001b[0;32mIn [1]\u001b[0m, in \u001b[0;36m<cell line: 4>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mnumpy\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mnp\u001b[39;00m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mmatplotlib\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpyplot\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mplt\u001b[39;00m\n\u001b[0;32m----> 4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpybmix\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmixing\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m DirichletProcessMixing, StickBreakMixing\n\u001b[1;32m      5\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpybmix\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mhierarchy\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m UnivariateNormal\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpybmix\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmixture_model\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m MixtureModel\n",
+      "File \u001b[0;32m~/dev/tests/pybmix/pybmix/core/mixing.py:8\u001b[0m, in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mjoblib\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m Parallel, delayed\n\u001b[1;32m      6\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mscipy\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mspecial\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m loggamma, gamma\n\u001b[0;32m----> 8\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mpybmix\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mproto\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmixing_id_pb2\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mmixing_id\u001b[39;00m\n\u001b[1;32m      9\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpybmix\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mproto\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdistribution_pb2\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m BetaDistribution, GammaDistribution\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpybmix\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mproto\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmixing_prior_pb2\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m DPPrior, PYPrior, TruncSBPrior\n",
+      "File \u001b[0;32m~/dev/tests/pybmix/pybmix/proto/mixing_id_pb2.py:20\u001b[0m, in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     13\u001b[0m _sym_db \u001b[38;5;241m=\u001b[39m _symbol_database\u001b[38;5;241m.\u001b[39mDefault()\n\u001b[1;32m     18\u001b[0m DESCRIPTOR \u001b[38;5;241m=\u001b[39m _descriptor_pool\u001b[38;5;241m.\u001b[39mDefault()\u001b[38;5;241m.\u001b[39mAddSerializedFile(\u001b[38;5;124mb\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x0f\u001b[39;00m\u001b[38;5;124mmixing_id.proto\u001b[39m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\x08\u001b[39;00m\u001b[38;5;130;01m\\x62\u001b[39;00m\u001b[38;5;130;01m\\x61\u001b[39;00m\u001b[38;5;124myesmix*O\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x08\u001b[39;00m\u001b[38;5;124mMixingId\u001b[39m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x0e\u001b[39;00m\u001b[38;5;124mUNKNOWN_MIXING\u001b[39m\u001b[38;5;130;01m\\x10\u001b[39;00m\u001b[38;5;130;01m\\x00\u001b[39;00m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\x06\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x02\u001b[39;00m\u001b[38;5;130;01m\\x44\u001b[39;00m\u001b[38;5;124mP\u001b[39m\u001b[38;5;130;01m\\x10\u001b[39;00m\u001b[38;5;130;01m\\x01\u001b[39;00m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\x06\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x02\u001b[39;00m\u001b[38;5;124mPY\u001b[39m\u001b[38;5;130;01m\\x10\u001b[39;00m\u001b[38;5;130;01m\\x02\u001b[39;00m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\t\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x05\u001b[39;00m\u001b[38;5;124mLogSB\u001b[39m\u001b[38;5;130;01m\\x10\u001b[39;00m\u001b[38;5;130;01m\\x03\u001b[39;00m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\x0b\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x07\u001b[39;00m\u001b[38;5;124mTruncSB\u001b[39m\u001b[38;5;130;01m\\x10\u001b[39;00m\u001b[38;5;130;01m\\x04\u001b[39;00m\u001b[38;5;130;01m\\x12\u001b[39;00m\u001b[38;5;130;01m\\x07\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\x03\u001b[39;00m\u001b[38;5;124mMFM\u001b[39m\u001b[38;5;130;01m\\x10\u001b[39;00m\u001b[38;5;130;01m\\x05\u001b[39;00m\u001b[38;5;130;01m\\x62\u001b[39;00m\u001b[38;5;130;01m\\x06\u001b[39;00m\u001b[38;5;124mproto3\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m---> 20\u001b[0m _MIXINGID \u001b[38;5;241m=\u001b[39m \u001b[43mDESCRIPTOR\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43menum_types_by_name\u001b[49m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mMixingId\u001b[39m\u001b[38;5;124m'\u001b[39m]\n\u001b[1;32m     21\u001b[0m MixingId \u001b[38;5;241m=\u001b[39m enum_type_wrapper\u001b[38;5;241m.\u001b[39mEnumTypeWrapper(_MIXINGID)\n\u001b[1;32m     22\u001b[0m UNKNOWN_MIXING \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0\u001b[39m\n",
+      "\u001b[0;31mAttributeError\u001b[0m: 'NoneType' object has no attribute 'enum_types_by_name'"
+     ]
+    }
+   ],
    "source": [
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
@@ -215,7 +229,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -229,7 +243,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.0"
+   "version": "3.10.2"
   }
  },
  "nbformat": 4,

pybmix/core/mixture_model.py

@@ -6,7 +6,7 @@
 from pybmix.core.hierarchy import BaseHierarchy
 from pybmix.core.chain import MCMCchain
 from pybmix.proto.algorithm_state_pb2 import AlgorithmState
-from pybmix.core.pybmixcpp import AlgorithmWrapper, ostream_redirect
+from pybmixlib import AlgorithmWrapper, ostream_redirect
 
 MARGINAL_ALGORITHMS = ["Neal2", "Neal3", "Neal8"] 
 CONDITIONAL_ALGORITHMS = ["BlockedGibbs"]

pybmix/estimators/cluster_estimator.py

@@ -1,7 +1,7 @@
 import numpy as np
 
 from pybmix.core.mixture_model import MixtureModel
-from pybmix.core.pybmixcpp import _minbinder_cluster_estimate, ostream_redirect
+from pybmixlib import _minbinder_cluster_estimate, ostream_redirect
 
 class ClusterEstimator(object):
     """

pybmix/core/pybmixcpp/algorithm_wrapper.hpp → pybmixlib/algorithm_wrapper.hpp

@@ -1,6 +1,7 @@
 #ifndef PYBMIX_ALGORITHM_WRAPPER_
 #define PYBMIX_ALGORITHM_WRAPPER_
 
+#include <stan/math/rev.hpp>
 #include <pybind11/eigen.h>
 #include <pybind11/pybind11.h>
 #include <pybind11/stl.h>

pybmix/core/pybmixcpp/example.cpp → pybmixlib/example.cpp

@@ -1,8 +1,10 @@
-#include <pybind11/eigen.h>
+#include <stan/math/rev.hpp>
+
+// #include <pybind11/eigen.h>
 #include <pybind11/pybind11.h>
 #include <pybind11/stl.h>
 
-#include <Eigen/Dense>
+// #include <Eigen/Dense>
 
 #include "algorithm_wrapper.hpp"
 #include "bayesmix/src/utils/distributions.hpp"

pybmix/core/pybmixcpp/module.cpp → pybmixlib/module.cpp

@@ -1,4 +1,4 @@
-#include <pybind11/eigen.h>
+// #include <pybind11/eigen.h>
 #include <pybind11/iostream.h>
 #include <pybind11/pybind11.h>
 #include <pybind11/stl.h>
@@ -9,7 +9,7 @@
 
 namespace py = pybind11;
 
-PYBIND11_MODULE(pybmixcpp, m) {
+PYBIND11_MODULE(pybmixlib, m) {
   py::add_ostream_redirect(m, "ostream_redirect");
   add_algorithm_wrapper(m);
   add_serialized_collector(m);

pybmixlib/setup.py

@@ -0,0 +1,140 @@
+import os
+import re
+import subprocess
+import sys
+
+from setuptools import Extension, setup
+from setuptools.command.build_ext import build_ext
+
+# Convert distutils Windows platform specifiers to CMake -A arguments
+PLAT_TO_CMAKE = {
+    "win32": "Win32",
+    "win-amd64": "x64",
+    "win-arm32": "ARM",
+    "win-arm64": "ARM64",
+}
+
+
+# A CMakeExtension needs a sourcedir instead of a file list.
+# The name must be the _single_ output extension from the CMake build.
+# If you need multiple extensions, see scikit-build.
+class CMakeExtension(Extension):
+    def __init__(self, name, sourcedir=""):
+        Extension.__init__(self, name, sources=[])
+        self.sourcedir = os.path.abspath(sourcedir)
+
+
+class CMakeBuild(build_ext):
+    def build_extension(self, ext):
+        extdir = os.path.abspath(os.path.dirname(self.get_ext_fullpath(ext.name)))
+
+        # required for auto-detection & inclusion of auxiliary "native" libs
+        if not extdir.endswith(os.path.sep):
+            extdir += os.path.sep
+
+        debug = int(os.environ.get("DEBUG", 0)) if self.debug is None else self.debug
+        cfg = "Debug" if debug else "Release"
+
+        # CMake lets you override the generator - we need to check this.
+        # Can be set with Conda-Build, for example.
+        cmake_generator = os.environ.get("CMAKE_GENERATOR", "")
+
+        # Set Python_EXECUTABLE instead if you use PYBIND11_FINDPYTHON
+        # EXAMPLE_VERSION_INFO shows you how to pass a value into the C++ code
+        # from Python.
+        cmake_args = [
+            f"-DDISABLE_BENCHMARKS=TRUE",
+            f"-DDISABLE_PLOTS=TRUE",
+            f"-DDISABLE_EXAMPLES=TRUE",
+            f"-DDISABLE_DOCS=TRUE",
+            f"-DDISABLE_TESTS=TRUE",
+            f"-DFORCE_PROTO_BUILD=TRUE",
+            f"-DCMAKE_LIBRARY_OUTPUT_DIRECTORY={extdir}",
+            f"-DPYTHON_EXECUTABLE={sys.executable}",
+            f"-DCMAKE_BUILD_TYPE={cfg}",  # not used on MSVC, but no harm
+        ]
+        build_args = []
+        # Adding CMake arguments set as environment variable
+        # (needed e.g. to build for ARM OSx on conda-forge)
+        if "CMAKE_ARGS" in os.environ:
+            cmake_args += [item for item in os.environ["CMAKE_ARGS"].split(" ") if item]
+
+        # In this example, we pass in the version to C++. You might not need to.
+        cmake_args += [f"-DEXAMPLE_VERSION_INFO={self.distribution.get_version()}"]
+
+        if self.compiler.compiler_type != "msvc":
+            # Using Ninja-build since it a) is available as a wheel and b)
+            # multithreads automatically. MSVC would require all variables be
+            # exported for Ninja to pick it up, which is a little tricky to do.
+            # Users can override the generator with CMAKE_GENERATOR in CMake
+            # 3.15+.
+            if not cmake_generator or cmake_generator == "Ninja":
+                try:
+                    import ninja  # noqa: F401
+
+                    ninja_executable_path = os.path.join(ninja.BIN_DIR, "ninja")
+                    cmake_args += [
+                        "-GNinja",
+                        f"-DCMAKE_MAKE_PROGRAM:FILEPATH={ninja_executable_path}",
+                    ]
+                except ImportError:
+                    pass
+
+        else:
+
+            # Single config generators are handled "normally"
+            single_config = any(x in cmake_generator for x in {"NMake", "Ninja"})
+
+            # CMake allows an arch-in-generator style for backward compatibility
+            contains_arch = any(x in cmake_generator for x in {"ARM", "Win64"})
+
+            # Specify the arch if using MSVC generator, but only if it doesn't
+            # contain a backward-compatibility arch spec already in the
+            # generator name.
+            if not single_config and not contains_arch:
+                cmake_args += ["-A", PLAT_TO_CMAKE[self.plat_name]]
+
+            # Multi-config generators have a different way to specify configs
+            if not single_config:
+                cmake_args += [
+                    f"-DCMAKE_LIBRARY_OUTPUT_DIRECTORY_{cfg.upper()}={extdir}"
+                ]
+                build_args += ["--config", cfg]
+
+        if sys.platform.startswith("darwin"):
+            # Cross-compile support for macOS - respect ARCHFLAGS if set
+            archs = re.findall(r"-arch (\S+)", os.environ.get("ARCHFLAGS", ""))
+            if archs:
+                cmake_args += ["-DCMAKE_OSX_ARCHITECTURES={}".format(";".join(archs))]
+
+        # Set CMAKE_BUILD_PARALLEL_LEVEL to control the parallel build level
+        # across all generators.
+        if "CMAKE_BUILD_PARALLEL_LEVEL" not in os.environ:
+            # self.parallel is a Python 3 only way to set parallel jobs by hand
+            # using -j in the build_ext call, not supported by pip or PyPA-build.
+            if hasattr(self, "parallel") and self.parallel:
+                # CMake 3.12+ only.
+                build_args += [f"-j{self.parallel}"]
+
+        build_temp = os.path.join(self.build_temp, ext.name)
+        if not os.path.exists(build_temp):
+            os.makedirs(build_temp)
+
+        subprocess.check_call(["cmake", ext.sourcedir] + cmake_args, cwd=build_temp)
+        subprocess.check_call(["cmake", "--build", "."] + build_args, cwd=build_temp)
+
+
+if __name__ == "__main__":
+
+    setup(
+        name="pybmixlib",
+        version="0.0.1",
+        author="Mario Beraha",
+        author_email="[email protected]",
+        description="Python Bayesian Mixtures",
+        long_description="",
+        ext_modules=[CMakeExtension("pybmixlib")],
+        cmdclass={"build_ext": CMakeBuild},
+        zip_safe=False,
+        python_requires=">=3.6",
+    )