dmx-learn 1.0.0__tar.gz

dmx_learn-1.0.0/LICENSE

@@ -0,0 +1,27 @@
+Copyright (c) 2025, Adam Walder
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

dmx_learn-1.0.0/MANIFEST.in

@@ -0,0 +1,10 @@
+# Include package data inside your dmx package (if you have any)
+recursive-include src/dmx *.py *.txt *.md
+
+# Exclude everything else
+exclude README.md
+exclude LICENSE
+exclude requirements.txt
+prune docs
+prune examples
+prune tests

dmx_learn-1.0.0/PKG-INFO

@@ -0,0 +1,81 @@
+Metadata-Version: 2.4
+Name: dmx-learn
+Version: 1.0.0
+Summary: A package for estimating heterogeneous probability density functions.
+Author: Adam Walder
+License: BSD
+Keywords: machine learning,density estimation,statistics,heterogeneous data
+Classifier: Programming Language :: Python
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: mpmath
+Requires-Dist: numba
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: pyspark
+Requires-Dist: scipy
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Provides-Extra: optional
+Requires-Dist: mpi4py; extra == "optional"
+Requires-Dist: umap-learn; extra == "optional"
+Dynamic: license-file
+
+dmx-learn - (Distributed Mixture Learning) A package for distributed heterogeneous density estimation. With only a few lines of code you can specify and fit complex models on variable-length heterogenous data.
+
+--------------------------------------------------------------------------------
+
+## 📚 Documentation
+View the full documentation on **Read the Docs**:
+
+👉 [https://dmx-learn.readthedocs.io/en/latest/](https://dmx-learn.readthedocs.io/en/latest/)
+
+## Installation
+
+User installation with pip
+```
+> pip install --user /path/to/package
+```
+
+
+## Building with mpi4py and umap-learn
+
+```
+> cd /path/to/package
+> pip install --user .[optional]
+```
+
+## Stats Examples
+Examples using `stats` distributions that run locally are located in ./dmx/examples/
+
+```
+> export PYHONPATH=$PYTHONPATH:/path./to/dmx-learn
+> PYTHONPATH=/path/to/package/ python ./dmx/examples/stats_examples/mixture_example.py
+```
+
+## Running with Spark
+Examples that run with Apache Spark are located in./dmx/examples_spark/
+
+First build a wheel
+```
+> cd /path/to/dmx-learn
+> pip install setuptools wheel
+> python setup.py bdist_wheel
+```
+
+Run the example with below
+```
+> /path/to/spark/bin/spark-submit --master local[*] --py-files /path/to/package/dist/dmx-learn-0.1.8.4-py3-none-any.whl ./dmx/examples_spark/mixture_example.py
+```
+
+## Running with MPI4PY
+Examples that run with mpi4py are located in ./dmx/mpi4py/examples/
+
+Below will run the example ./dmx/mpi4py/examples/estimation_example.py with 4 cores.
+```
+> export PYHONPATH=$PYTHONPATH:/path./to/dmx-learn
+> mpiexec -n 4 python /path/to/package/dmx/mpi4py/examples/estimation_example.py
+```

dmx_learn-1.0.0/README.md

@@ -0,0 +1,55 @@
+dmx-learn - (Distributed Mixture Learning) A package for distributed heterogeneous density estimation. With only a few lines of code you can specify and fit complex models on variable-length heterogenous data.
+
+--------------------------------------------------------------------------------
+
+## 📚 Documentation
+View the full documentation on **Read the Docs**:
+
+👉 [https://dmx-learn.readthedocs.io/en/latest/](https://dmx-learn.readthedocs.io/en/latest/)
+
+## Installation
+
+User installation with pip
+```
+> pip install --user /path/to/package
+```
+
+
+## Building with mpi4py and umap-learn
+
+```
+> cd /path/to/package
+> pip install --user .[optional]
+```
+
+## Stats Examples
+Examples using `stats` distributions that run locally are located in ./dmx/examples/
+
+```
+> export PYHONPATH=$PYTHONPATH:/path./to/dmx-learn
+> PYTHONPATH=/path/to/package/ python ./dmx/examples/stats_examples/mixture_example.py
+```
+
+## Running with Spark
+Examples that run with Apache Spark are located in./dmx/examples_spark/
+
+First build a wheel
+```
+> cd /path/to/dmx-learn
+> pip install setuptools wheel
+> python setup.py bdist_wheel
+```
+
+Run the example with below
+```
+> /path/to/spark/bin/spark-submit --master local[*] --py-files /path/to/package/dist/dmx-learn-0.1.8.4-py3-none-any.whl ./dmx/examples_spark/mixture_example.py
+```
+
+## Running with MPI4PY
+Examples that run with mpi4py are located in ./dmx/mpi4py/examples/
+
+Below will run the example ./dmx/mpi4py/examples/estimation_example.py with 4 cores.
+```
+> export PYHONPATH=$PYTHONPATH:/path./to/dmx-learn
+> mpiexec -n 4 python /path/to/package/dmx/mpi4py/examples/estimation_example.py
+```

dmx_learn-1.0.0/pyproject.toml

@@ -0,0 +1,53 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "dmx-learn"
+version = "1.0.0"
+description = "A package for estimating heterogeneous probability density functions."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "BSD" }
+authors = [
+  { name="Adam Walder" }
+]
+
+classifiers = [
+  "Programming Language :: Python",
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: Developers",
+]
+
+keywords = [
+  "machine learning",
+  "density estimation",
+  "statistics",
+  "heterogeneous data"
+]
+
+dependencies = [
+  "mpmath",
+  "numba",
+  "numpy",
+  "pandas",
+  "pyspark",
+  "scipy"
+]
+
+[project.optional-dependencies]
+test = [
+  "pytest"
+]
+optional = [
+  "mpi4py",
+  "umap-learn"
+]
+
+[tool.setuptools]
+zip-safe = false
+include-package-data = true
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["dmx"]

dmx_learn-1.0.0/setup.cfg

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

dmx_learn-1.0.0/src/dmx/__init__.py

@@ -0,0 +1,3 @@
+__all__ = ['stats', 'utils','src']
+
+

dmx_learn-1.0.0/src/dmx/arithmetic.py

@@ -0,0 +1,28 @@
+"""
+This module defines mathematical constants and imports commonly used functions from NumPy.
+
+The constants and functions provided here can be used for various mathematical operations
+such as logarithms, exponentiation, and calculations involving pi, square roots, or infinity.
+
+"""
+
+from numpy import (
+    log,  # Natural logarithm
+    exp,  # Exponential function
+    pi,   # Mathematical constant π
+    sqrt, # Square root function
+    abs,  # Absolute value function
+    dot,  # Dot product of two arrays
+    isnan, # Check for NaN values
+    isinf  # Check for infinite values
+)
+
+# Constants
+maxint = 2**31 - 1  # Maximum value for a signed 32-bit integer
+maxrandint = 2**31 - 1  # Maximum random integer value for signed 32-bit range
+one = 1.0  # Floating-point representation of 1
+zero = 0.0  # Floating-point representation of 0
+two = 2.0  # Floating-point representation of 2
+half = 0.5  # Floating-point representation of 0.5
+inf = float('inf')  # Floating-point representation of infinity
+eps = 1.0e-8  # Small value for numerical precision

dmx_learn-1.0.0/src/dmx/bexamples/dpm_auto_example1.py

@@ -0,0 +1,19 @@
+"""Fitting a DPM with an automatic estimator determined from the data."""
+from dmx.utils.automatic import get_dpm_mixture, get_estimator
+from dmx.bstats import *
+import numpy as np
+
+
+if __name__ == '__main__':
+
+    d1 = DiagonalGaussianDistribution([-1, -1, -1], [5, 5, 5])
+    d2 = DiagonalGaussianDistribution([0, 0, 0], [0.1, 0.1, 0.1])
+    d3 = DiagonalGaussianDistribution([2, 2, 2], [1, 1, 1])
+    d4 = DiagonalGaussianDistribution([4, 4, 4], [1, 1, 1])
+    dist1 = MixtureDistribution([d1, d2, d3, d4], [0.3, 0.3, 0.2, 0.2])
+
+    data = dist1.sampler(seed=1).sample(1000)
+    est = get_estimator(data, use_bstats=True)
+    model = get_dpm_mixture(data, rng=np.random.RandomState(1))
+
+    print(str(model))

dmx_learn-1.0.0/src/dmx/bexamples/dpm_auto_example2.py

@@ -0,0 +1,39 @@
+"""Fitting a DPM with an automatic estimator determined from the data."""
+from dmx.utils.automatic import get_dpm_mixture, get_estimator
+from dmx.bstats import *
+import numpy as np
+
+
+if __name__ == '__main__':
+
+    rng = np.random.RandomState(2)
+    m = 10
+    n = 7
+    cc = 2.0
+    ss = 1.5
+    components = []
+    w = np.zeros(m)
+    pvec = np.ones(m) * 0.5
+    for i in range(m):
+        len_dist = IntegerCategoricalDistribution([0.2, 0.3, 0.3, 0.2], min_index=3)
+        dist1 = GaussianDistribution((i + 1) * ss, 1)
+        dist2 = IntegerCategoricalDistribution((np.eye(m)[i, :] + cc) / (m * cc + 1))
+        dist3 = CategoricalDistribution({str(j): ((1.0 + cc) if i == j else cc) / (m * cc + 1) for j in range(m)})
+        dist4 = OptionalDistribution(PoissonDistribution((i + 1) * ss), p=0.1)
+        dist = SequenceDistribution(CompositeDistribution((dist1, dist2, dist3, dist4)), len_dist)
+        components.append(dist)
+        w[i] = np.prod(1 - pvec[:i]) * pvec[i]
+
+    w[n:] = 1.0e-16
+    w /= w.sum()
+
+    dist = MixtureDistribution(components, w)
+    data = dist.sampler(seed=1).sample(300)
+
+    est = get_estimator(data, use_bstats=True)
+    model = get_dpm_mixture(data, rng=np.random.RandomState(1))
+
+    print(str(model))
+    print(model.num_components)
+    for u in model.components:
+        print(str(u))