likelihood 2.1.3__tar.gz → 2.2.0rc1__tar.gz

likelihood-2.2.0rc1/Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "rust_py_integration"
+version = "0.1.0"
+edition = "2021"
+
+[lib]
+name = "rust_py_integration"
+crate-type = ["cdylib"]
+
+[dependencies]
+pyo3 = { version = "0.21", features = ["extension-module"] }

likelihood-2.2.0rc1/MANIFEST.in

@@ -0,0 +1,2 @@
+include Cargo.toml
+recursive-include src *.rs

{likelihood-2.1.3 → likelihood-2.2.0rc1}/PKG-INFO

@@ -1,12 +1,11 @@
 Metadata-Version: 2.4
 Name: likelihood
-Version: 2.1.3
+Version: 2.2.0rc1
 Summary: A package that performs the maximum likelihood algorithm.
-Home-page: https://github.com/jzsmoreno/likelihood/
-Author: J. A. Moreno-Guerra
-Author-email: jzs.gm27@gmail.com
-Maintainer: Jafet Castañeda
-Maintainer-email: jafetcc17@gmail.com
+Author-email: "J. A. Moreno-Guerra" <jzs.gm27@gmail.com>
+Maintainer-email: Jafet Castañeda <jafetcc17@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/jzsmoreno/likelihood/
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
@@ -37,19 +36,7 @@ Requires-Dist: tensorflow>=2.15.0; extra == "full"
 Requires-Dist: keras-tuner; extra == "full"
 Requires-Dist: scikit-learn; extra == "full"
 Requires-Dist: torch; extra == "full"
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
 Dynamic: license-file
-Dynamic: maintainer
-Dynamic: maintainer-email
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 ![likelihood](https://raw.githubusercontent.com/jzsmoreno/likelihood/main/likelihood.png)
 

likelihood-2.2.0rc1/likelihood/VERSION

@@ -0,0 +1 @@
+2.2.0rc1

{likelihood-2.1.3 → likelihood-2.2.0rc1}/likelihood/graph/_nn.py

@@ -4,9 +4,8 @@ import os
 os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
 logging.getLogger("tensorflow").setLevel(logging.ERROR)
 
-import warnings
 from multiprocessing import Pool, cpu_count
-from typing import Any, List, Tuple
+from typing import List, Tuple
 
 import numpy as np
 import pandas as pd
@@ -18,143 +17,7 @@ tf.get_logger().setLevel("ERROR")
 
 from likelihood.tools import LoRALayer
 
-
-def compare_similarity_np(arr1: np.ndarray, arr2: np.ndarray, threshold: float = 0.05) -> int:
-    """Vectorized similarity comparison between two numeric/categorical arrays."""
-    arr1 = np.asarray(arr1)
-    arr2 = np.asarray(arr2)
-
-    is_numeric = np.vectorize(
-        lambda a, b: isinstance(a, (int, float)) and isinstance(b, (int, float))
-    )(arr1, arr2)
-
-    similarity = np.zeros_like(arr1, dtype=bool)
-
-    if np.any(is_numeric):
-        a_num = arr1[is_numeric].astype(float)
-        b_num = arr2[is_numeric].astype(float)
-
-        both_zero = (a_num == 0) & (b_num == 0)
-        nonzero = ~both_zero & (a_num != 0) & (b_num != 0)
-        ratio = np.zeros_like(a_num)
-        ratio[nonzero] = np.maximum(a_num[nonzero], b_num[nonzero]) / np.minimum(
-            a_num[nonzero], b_num[nonzero]
-        )
-        numeric_similar = both_zero | ((1 - threshold <= ratio) & (ratio <= 1 + threshold))
-
-        similarity[is_numeric] = numeric_similar
-
-    similarity[~is_numeric] = arr1[~is_numeric] == arr2[~is_numeric]
-
-    return np.count_nonzero(similarity)
-
-
-def compare_pair(pair, data, similarity, threshold):
-    i, j = pair
-    sim = compare_similarity_np(data[i], data[j], threshold=threshold)
-    return (i, j, 1 if sim >= similarity else 0)
-
-
-def cal_adjacency_matrix(
-    df: pd.DataFrame, exclude_subset: List[str] = [], sparse: bool = True, **kwargs
-) -> Tuple[dict, np.ndarray]:
-    """
-    Calculates the adjacency matrix for a given DataFrame using parallel processing.
-
-    Parameters
-    ----------
-    df : `pd.DataFrame`
-        The input DataFrame containing the features.
-    exclude_subset : `List[str]`, `optional`
-        A list of features to exclude from the calculation of the adjacency matrix.
-    sparse : `bool`, `optional`
-        Whether to return a sparse matrix or a dense matrix.
-    **kwargs : `dict`
-        Additional keyword arguments to pass to the `compare_similarity` function.
-
-    Returns
-    -------
-    adj_dict : `dict`
-        A dictionary containing the features.
-    adjacency_matrix : `np.ndarray`
-        The adjacency matrix.
-
-    Keyword Arguments
-    -----------------
-    similarity: `int`
-        The minimum number of features that must be the same in both arrays to be considered similar.
-    threshold : `float`
-        The threshold value used in the `compare_similarity` function. Default is 0.0
-    """
-    if len(exclude_subset) > 0:
-        columns = [col for col in df.columns if col not in exclude_subset]
-        df_ = df[columns].copy()
-    else:
-        df_ = df.copy()
-
-    assert len(df_) > 0
-
-    similarity = kwargs.get("similarity", len(df_.columns) - 1)
-    threshold = kwargs.get("threshold", 0.05)
-    assert similarity <= df_.shape[1]
-
-    data = df_.to_numpy()
-    n = len(data)
-
-    adj_dict = {i: data[i].tolist() for i in range(n)}
-
-    def pair_generator():
-        for i in range(n):
-            for j in range(i, n):
-                yield (i, j)
-
-    with Pool(cpu_count()) as pool:
-        results = pool.starmap(
-            compare_pair, ((pair, data, similarity, threshold) for pair in pair_generator())
-        )
-
-    adjacency_matrix = np.zeros((n, n), dtype=np.uint8)
-    for i, j, val in results:
-        if val:
-            adjacency_matrix[i, j] = 1
-            adjacency_matrix[j, i] = 1
-
-    if sparse:
-        num_nodes = adjacency_matrix.shape[0]
-
-        indices = np.argwhere(adjacency_matrix != 0.0)
-        indices = tf.constant(indices, dtype=tf.int64)
-        values = tf.constant(adjacency_matrix[indices[:, 0], indices[:, 1]], dtype=tf.float32)
-        adjacency_matrix = tf.sparse.SparseTensor(
-            indices=indices, values=values, dense_shape=(num_nodes, num_nodes)
-        )
-
-    return adj_dict, adjacency_matrix
-
-
-class Data:
-    def __init__(
-        self,
-        df: pd.DataFrame,
-        target: str | None = None,
-        exclude_subset: List[str] = [],
-        **kwargs,
-    ):
-        sparse = kwargs.get("sparse", True)
-        threshold = kwargs.get("threshold", 0.05)
-        _, adjacency = cal_adjacency_matrix(
-            df, exclude_subset=exclude_subset, sparse=sparse, threshold=threshold
-        )
-        if target is not None:
-            X = df.drop(columns=[target] + exclude_subset)
-        else:
-            X = df.drop(columns=exclude_subset)
-        self.columns = X.columns
-        X = X.to_numpy()
-        self.x = np.asarray(X).astype(np.float32)
-        self.adjacency = adjacency
-        if target is not None:
-            self.y = np.asarray(df[target].values).astype(np.int32)
+from .nn import Data, cal_adjacency_matrix, compare_pair, compare_similarity_np
 
 
 @tf.keras.utils.register_keras_serializable(package="Custom", name="VanillaGNNLayer")

{likelihood-2.1.3 → likelihood-2.2.0rc1}/likelihood/graph/nn.py

@@ -15,6 +15,7 @@ from sklearn.metrics import f1_score
 
 tf.get_logger().setLevel("ERROR")
 
+from likelihood import rust_py_integration
 from likelihood.tools import LoRALayer
 
 

{likelihood-2.1.3 → likelihood-2.2.0rc1}/likelihood.egg-info/PKG-INFO

@@ -1,12 +1,11 @@
 Metadata-Version: 2.4
 Name: likelihood
-Version: 2.1.3
+Version: 2.2.0rc1
 Summary: A package that performs the maximum likelihood algorithm.
-Home-page: https://github.com/jzsmoreno/likelihood/
-Author: J. A. Moreno-Guerra
-Author-email: jzs.gm27@gmail.com
-Maintainer: Jafet Castañeda
-Maintainer-email: jafetcc17@gmail.com
+Author-email: "J. A. Moreno-Guerra" <jzs.gm27@gmail.com>
+Maintainer-email: Jafet Castañeda <jafetcc17@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/jzsmoreno/likelihood/
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
@@ -37,19 +36,7 @@ Requires-Dist: tensorflow>=2.15.0; extra == "full"
 Requires-Dist: keras-tuner; extra == "full"
 Requires-Dist: scikit-learn; extra == "full"
 Requires-Dist: torch; extra == "full"
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
 Dynamic: license-file
-Dynamic: maintainer
-Dynamic: maintainer-email
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 ![likelihood](https://raw.githubusercontent.com/jzsmoreno/likelihood/main/likelihood.png)
 

{likelihood-2.1.3 → likelihood-2.2.0rc1}/likelihood.egg-info/SOURCES.txt

@@ -1,12 +1,18 @@
+Cargo.toml
 LICENSE
+MANIFEST.in
 README.md
+pyproject.toml
+requirements.txt
 setup.py
+likelihood/VERSION
 likelihood/__init__.py
 likelihood/main.py
 likelihood/pipes.py
 likelihood.egg-info/PKG-INFO
 likelihood.egg-info/SOURCES.txt
 likelihood.egg-info/dependency_links.txt
+likelihood.egg-info/not-zip-safe
 likelihood.egg-info/requires.txt
 likelihood.egg-info/top_level.txt
 likelihood/graph/__init__.py
@@ -34,4 +40,5 @@ likelihood/tools/impute.py
 likelihood/tools/models_tools.py
 likelihood/tools/numeric_tools.py
 likelihood/tools/reports.py
-likelihood/tools/tools.py
+likelihood/tools/tools.py
+src/lib.rs

likelihood-2.2.0rc1/likelihood.egg-info/not-zip-safe

@@ -0,0 +1 @@
+

likelihood-2.2.0rc1/likelihood.egg-info/top_level.txt

@@ -0,0 +1,5 @@
+dist
+docs
+examples
+likelihood
+src

likelihood-2.2.0rc1/pyproject.toml

@@ -0,0 +1,46 @@
+[build-system]
+requires = [
+  "setuptools>=61",
+  "wheel",
+  "setuptools-rust>=1.8",
+]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "likelihood"
+authors = [
+  { name = "J. A. Moreno-Guerra", email = "jzs.gm27@gmail.com" }
+]
+maintainers = [
+  { name = "Jafet Castañeda", email = "jafetcc17@gmail.com" }
+]
+description = "A package that performs the maximum likelihood algorithm."
+readme = { file = "README.md", content-type = "text/markdown" }
+requires-python = ">=3.10"
+license = { text = "MIT" }
+urls = { Homepage = "https://github.com/jzsmoreno/likelihood/" }
+
+dynamic = ["version", "dependencies"]
+
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "License :: OSI Approved :: MIT License",
+  "Operating System :: OS Independent",
+]
+
+[project.optional-dependencies]
+full = [
+  "networkx",
+  "pyvis",
+  "tensorflow>=2.15.0",
+  "keras-tuner",
+  "scikit-learn",
+  "torch",
+]
+
+[tool.setuptools]
+packages = { find = {} }
+
+[tool.setuptools.dynamic]
+version = { file = ["likelihood/VERSION"] }
+dependencies = { file = ["requirements.txt"] }

likelihood-2.2.0rc1/requirements.txt

@@ -0,0 +1,17 @@
+black[jupyter]>=24.3.0
+mypy-extensions>=1.0.0
+types-openpyxl>=3.1.0.15
+pydocstyle>=6.3.0
+flake8>=6.0.0
+isort>=5.12.0
+mypy>=1.4.1
+numpy<3.0.0,>=1.26.4
+pydot==2.0.0
+matplotlib
+packaging
+graphviz
+seaborn
+pyyaml
+pandas 
+corner
+tqdm

likelihood-2.2.0rc1/setup.py

@@ -0,0 +1,14 @@
+from setuptools import find_packages, setup
+from setuptools_rust import Binding, RustExtension
+
+setup(
+    packages=find_packages(),
+    rust_extensions=[
+        RustExtension(
+            "likelihood.rust_py_integration",
+            path="Cargo.toml",
+            binding=Binding.PyO3,
+        )
+    ],
+    zip_safe=False,
+)

likelihood-2.2.0rc1/src/lib.rs

@@ -0,0 +1,12 @@
+use pyo3::prelude::*;
+
+#[pyfunction]
+fn print_hello() {
+    println!("Hello from Rust integration!");
+}
+
+#[pymodule]
+fn rust_py_integration(_py: Python, m: &PyModule) -> PyResult<()> {
+    m.add_function(wrap_pyfunction!(print_hello, m)?)?;
+    Ok(())
+}

likelihood-2.1.3/likelihood.egg-info/top_level.txt

@@ -1 +0,0 @@
-likelihood

likelihood-2.1.3/setup.py

@@ -1,42 +0,0 @@
-from pathlib import Path
-
-import setuptools
-
-# Parse the requirements.txt file
-with open("requirements.txt", "r") as f:
-    install_requires = f.read().splitlines()
-
-with open("README.md", "r") as fh:
-    long_description = fh.read()
-
-about = {}
-ROOT_DIR = Path(__file__).resolve().parent
-PACKAGE_DIR = ROOT_DIR / "likelihood"
-with open(PACKAGE_DIR / "VERSION") as f:
-    _version = f.read().strip()
-    about["__version__"] = _version
-
-setuptools.setup(
-    name="likelihood",
-    version=about["__version__"],
-    author="J. A. Moreno-Guerra",
-    author_email="jzs.gm27@gmail.com",
-    maintainer="Jafet Castañeda",
-    maintainer_email="jafetcc17@gmail.com",
-    description="A package that performs the maximum likelihood algorithm.",
-    py_modules=["likelihood"],
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    url="https://github.com/jzsmoreno/likelihood/",
-    packages=setuptools.find_packages(),
-    install_requires=install_requires,
-    extras_require={
-        "full": ["networkx", "pyvis", "tensorflow>=2.15.0", "keras-tuner", "scikit-learn", "torch"],
-    },
-    classifiers=[
-        "Programming Language :: Python :: 3",
-        "License :: OSI Approved :: MIT License",
-        "Operating System :: OS Independent",
-    ],
-    python_requires=">=3.10",
-)