cs-ml-tools 2025.12.4__tar.gz

cs_ml_tools-2025.12.4/.github/workflows/docs.yml

@@ -0,0 +1,52 @@
+name: Documentation
+run-name: Build and Deploy Documentation for commit ${{ github.sha }} 
+
+# build the documentation whenever there are new commits on main
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+    # Alternative: only build for tags.
+    # tags:
+    #   - '*'
+
+# security: restrict permissions for CI jobs.
+permissions:
+  contents: read
+
+jobs:
+  # Build the documentation and upload the static HTML files as an artifact.
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      # ADJUST THIS: install all dependencies (including pdoc)
+      - run: pip install -e .
+      - run: pip install pdoc
+      # ADJUST THIS: build your documentation into docs/.
+      # We use a custom build script for pdoc itself, ideally you just run `pdoc -o docs/ ...` here.
+      - run: mkdir docs; pdoc -o docs -d numpy ml_tools
+
+      - uses: actions/upload-pages-artifact@v3
+        with:
+          path: docs/
+
+  # Deploy the artifact to GitHub pages.
+  # This is a separate job so that only actions/deploy-pages has the necessary permissions.
+  deploy:
+    needs: build
+    runs-on: ubuntu-latest
+    permissions:
+      pages: write
+      id-token: write
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - id: deployment
+        uses: actions/deploy-pages@v4

cs_ml_tools-2025.12.4/.github/workflows/publish-PyPI.yml

@@ -0,0 +1,65 @@
+name: Publish to PyPI
+run-name: Publish Python Package to PyPI for release ${{ github.event.release.tag_name }}
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+    inputs:
+      tag_name:
+        description: 'Git tag to checkout and publish'
+        required: false
+        type: string
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+        - name: Checkout code
+          uses: actions/checkout@v4
+          with:
+            ref: ${{ inputs.tag_name || github.ref }}
+
+        - name: Set up Python
+          uses: actions/setup-python@v5
+          with:
+            python-version: "3.x"
+            
+        - name: Install pypa/build
+          run: >-
+            python3 -m
+            pip install
+            build
+            --user
+        - name: Build a binary wheel and a source tarball
+          run: python3 -m build
+        - name: Store the distribution packages
+          uses: actions/upload-artifact@v4
+          with:
+            name: python-package-distributions
+            path: dist/
+  publish-to-pypi:
+    name: Publish to PyPI 
+    needs:
+    - build
+    runs-on: ubuntu-latest
+
+    environment:
+      name: pypi
+      url: https://pypi.org/p/cs-ml-tools
+
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution 📦 to TestPyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        repository-url: https://test.pypi.org/legacy/

cs_ml_tools-2025.12.4/.github/workflows/publish-testPyPI.yml

@@ -0,0 +1,65 @@
+name: Publish to TestPyPI
+run-name: Publish Python Package to TestPyPI for release ${{ github.event.release.tag_name }}
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+    inputs:
+      tag_name:
+        description: 'Git tag to checkout and publish'
+        required: false
+        type: string
+          
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+        - name: Checkout code
+          uses: actions/checkout@v4
+          with:
+            ref: ${{ inputs.tag_name || github.ref }}
+
+        - name: Set up Python
+          uses: actions/setup-python@v5
+          with:
+            python-version: "3.x"
+
+        - name: Install pypa/build
+          run: >-
+            python3 -m
+            pip install
+            build
+            --user
+        - name: Build a binary wheel and a source tarball
+          run: python3 -m build
+        - name: Store the distribution packages
+          uses: actions/upload-artifact@v4
+          with:
+            name: python-package-distributions
+            path: dist/
+  publish-to-testpypi:
+    name: Publish to TestPyPI 
+    needs:
+    - build
+    runs-on: ubuntu-latest
+
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/cs-ml-tools
+
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution 📦 to TestPyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        repository-url: https://test.pypi.org/legacy/

cs_ml_tools-2025.12.4/.gitignore

@@ -0,0 +1,7 @@
+.idea
+
+__pycache__
+
+.DS_Store
+            
+ml_tools.egg-info

cs_ml_tools-2025.12.4/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2020 claudio525
+
+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.

cs_ml_tools-2025.12.4/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.4
+Name: cs-ml-tools
+Version: 2025.12.4
+Summary: A collection of tools for machine learning
+Author: Claudio Schill
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: streamlit
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: tslearn
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: pyyaml
+Requires-Dist: torch
+Requires-Dist: statsmodels
+Dynamic: license-file
+
+[Documentation](https://claudio525.github.io/ml_tools/ml_tools.html)

cs_ml_tools-2025.12.4/README.md

@@ -0,0 +1 @@
+[Documentation](https://claudio525.github.io/ml_tools/ml_tools.html)

cs_ml_tools-2025.12.4/cs_ml_tools.egg-info/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.4
+Name: cs-ml-tools
+Version: 2025.12.4
+Summary: A collection of tools for machine learning
+Author: Claudio Schill
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: streamlit
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: tslearn
+Requires-Dist: matplotlib
+Requires-Dist: seaborn
+Requires-Dist: pyyaml
+Requires-Dist: torch
+Requires-Dist: statsmodels
+Dynamic: license-file
+
+[Documentation](https://claudio525.github.io/ml_tools/ml_tools.html)

cs_ml_tools-2025.12.4/cs_ml_tools.egg-info/SOURCES.txt

@@ -0,0 +1,27 @@
+.gitignore
+LICENSE
+README.md
+pyproject.toml
+requirements.txt
+.github/workflows/docs.yml
+.github/workflows/publish-PyPI.yml
+.github/workflows/publish-testPyPI.yml
+cs_ml_tools.egg-info/PKG-INFO
+cs_ml_tools.egg-info/SOURCES.txt
+cs_ml_tools.egg-info/dependency_links.txt
+cs_ml_tools.egg-info/requires.txt
+cs_ml_tools.egg-info/top_level.txt
+ml_tools/__init__.py
+ml_tools/array_utils.py
+ml_tools/distance_calculation.py
+ml_tools/dl_model_arch_utils.py
+ml_tools/plotting.py
+ml_tools/utils.py
+ml_tools/quarto/__init__.py
+ml_tools/quarto/utils.py
+ml_tools/scripts/nb_utils.py
+ml_tools/streamlit/__init__.py
+ml_tools/streamlit/utils.py
+ml_tools/torch/TabularDataLoader.py
+ml_tools/torch/__init__.py
+ml_tools/torch/utils.py

cs_ml_tools-2025.12.4/cs_ml_tools.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

cs_ml_tools-2025.12.4/cs_ml_tools.egg-info/requires.txt

@@ -0,0 +1,9 @@
+streamlit
+numpy
+pandas
+tslearn
+matplotlib
+seaborn
+pyyaml
+torch
+statsmodels

cs_ml_tools-2025.12.4/cs_ml_tools.egg-info/top_level.txt

@@ -0,0 +1 @@
+ml_tools

cs_ml_tools-2025.12.4/ml_tools/__init__.py

@@ -0,0 +1,39 @@
+r"""
+Library for machine learning tools.
+
+Modules:
+    - utils: General utility functions.
+    - array_utils: Utility functions for arrays.
+    - plotting: Plotting functions.
+    - distance_calculation: Functions for calculating distances.
+    - streamlit: Functions for working with streamlit.
+    - dl_model_arch_utils: Functions for working with deep learning model architectures.
+    - torch: Functions for working with PyTorch.
+"""
+
+from . import utils
+from . import array_utils
+from . import plotting
+from . import distance_calculation
+from . import dl_model_arch_utils
+from . import streamlit
+from . import quarto
+
+
+optional_imports = []
+try:
+    from . import torch
+    optional_imports.append("torch")
+except ImportError:
+    pass
+
+
+__all__ = [
+    "utils",
+    "array_utils",
+    "plotting",
+    "distance_calculation",
+    "streamlit",
+    "dl_model_arch_utils",
+    "quarto",
+] + optional_imports

cs_ml_tools-2025.12.4/ml_tools/array_utils.py

@@ -0,0 +1,237 @@
+from typing import Sequence
+
+import numpy as np
+import pandas as pd
+
+
+def find_nearest(array: np.ndarray[float], value: float) -> int:
+    """
+    Returns the index of the entry that is
+    closest to the specified value.
+
+    This assumes that the array is sorted!
+
+    Parameters
+    ----------
+    array: array of floats
+        The array to search
+    value: float
+        The value to search for
+
+    Returns
+    -------
+    ix: int
+        The index of the nearest value
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> arr = np.array([1.0, 2.5, 3.8, 4.2, 5.9, 7.1])
+    >>> find_nearest(arr, 3.9)
+    2
+    >>> find_nearest(arr, 5.0)
+    3
+    >>> find_nearest(arr, 7.1)
+    5
+    """
+    ix = (np.abs(array - value)).argmin()
+    return ix
+
+
+def find_nearest_larger(array: np.ndarray[float], value: float) -> int:
+    """
+    Returns the index of the entry that is
+    closest to the specified value. If no exact match
+    is found the nearest larger value is returned.
+
+    This assumes that the array is sorted!
+
+    Parameters
+    ----------
+    array: array of floats
+        The array to search
+    value: float
+        The value to search for
+
+    Returns
+    -------
+    ix: int
+        The index of the nearest (larger) value
+
+    Raises
+    ------
+    ValueError
+        If the value is larger than the largest value in the array
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> arr = np.array([1.0, 2.5, 3.8, 4.2, 5.9, 7.1])
+    >>> find_nearest_larger(arr, 4.0)
+    3
+    >>> find_nearest_larger(arr, 5.0)
+    4
+    >>> find_nearest_larger(arr, 7.1)
+    5
+    """
+    ix = find_nearest(array, value)
+
+    if array[ix] == value or array[ix] > value:
+        return ix
+    else:
+        if ix == array.size - 1:
+            raise ValueError("Value is larger than the largest value in the array")
+        return ix + 1
+
+
+def find_nearest_smaller(array: np.ndarray[float], value: float) -> int:
+    """
+    Returns the index of the entry that is
+    closest to the specified value. If no exact match
+    is found the nearest larger value is returned.
+
+    This assumes that the array is sorted!
+
+    Parameters
+    ----------
+    array: array of floats
+        The array to search
+    value: float
+        The value to search for
+
+    Returns
+    -------
+    ix: int
+        The index of the nearest (smaller) value
+
+    Raises
+    ------
+    ValueError
+        If the value is smaller than the smallest value in the array
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> arr = np.array([1.0, 2.5, 3.8, 4.2, 5.9, 7.1])
+    >>> find_nearest_smaller(arr, 4.0)
+    2
+    >>> find_nearest_smaller(arr, 5.0)
+    3
+    >>> find_nearest_smaller(arr, 1.0)
+    0
+    """
+    ix = find_nearest(array, value)
+
+    if array[ix] == value or array[ix] < value:
+        return ix
+    else:
+        if ix == 0:
+            raise ValueError("Value is smaller than the smallest value in the array")
+        return ix - 1
+    
+def find_nearest_smaller_vec(array: np.ndarray[float], values: np.ndarray[float]) -> np.ndarray[int]:
+    """
+    Returns the indices of the entries that are
+    closest to the specified values. If no exact match
+    is found the nearest smaller value is returned.
+
+    This assumes that the array is sorted!
+
+    Parameters
+    ----------
+    array: array of floats
+        The array to search
+    values: array of floats
+        The values to search for
+
+    Returns
+    -------
+    ix: np.ndarray[int]
+        The indices of the nearest (smaller) values
+
+    Raises
+    ------
+    ValueError
+        If any value is smaller than the smallest value in the array
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> arr = np.array([1.0, 2.5, 3.8, 4.2, 5.9, 7.1])
+    >>> values = np.array([4.0, 5.0, 1.0])
+    >>> find_nearest_smaller_vec(arr, values)
+    array([2, 3, 0])
+    """
+    if len(array.shape) != 1:
+        raise ValueError("Input array must be 1D")
+    if len(values.shape) != 1:
+        raise ValueError("Input values must be 1D")
+    
+    tmp = np.tile((np.arange(array.size)), (values.shape[0], 1))
+    return np.argmax(np.where(array <= values[:, None], tmp, -1), axis=1)
+
+
+def pandas_isin(array_1: np.ndarray, array_2: np.ndarray) -> np.ndarray:
+    """
+    This is the same as a np.isin,
+    however it is significantly faster for large arrays
+
+    Parameters
+    ----------
+    array_1: array of any type
+    array_2: array of any type
+
+    Returns
+    -------
+    np.ndarray
+        The boolean array
+
+    References
+    ----------
+    [1] Stackoverflow: https://stackoverflow.com/questions/15939748/check-if-each-element-in-a-numpy-array-is-in-another-array
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> arr = np.array([1, 2, 3, 4, 5])
+    >>> arr2 = np.array([1, 3, 5])
+    >>> pandas_isin(arr, arr2)
+    array([ True, False,  True, False,  True])
+    """
+    return pd.Index(pd.unique(array_2)).get_indexer(array_1) >= 0
+
+
+def numpy_str_join(sep: str, *arrays: str | Sequence[str]) -> np.ndarray[str]:
+    """
+    Joins multiple string arrays together using the specified separator.
+    Also support joining of string values, or a combination of both.
+
+    Parameters
+    ----------
+    sep: str
+        The separator to use
+    arrays: string value or string arrays
+        The arrays (or string values) to join together
+
+    Returns
+    -------
+    np.ndarray
+        The joined string array
+
+    Examples
+    --------
+    Example 1: Joining two arrays
+    >>> numpy_str_join("_", ["a", "b"], ["c", "d"])
+    array(['a_c', 'b_d'], dtype='<U3')
+
+    Example 2: Combination of string value and arrays
+    >>> arr1 = np.array(["a", "b"])
+    >>> numpy_str_join("_", arr1, "c", ["d", "e"])
+    array(['a_c_d', 'b_c_e'], dtype='<U5')
+    """
+    result = arrays[0]
+    for cur_array in arrays[1:]:
+        result = np.char.add(result, sep)
+        result = np.char.add(result, cur_array)
+
+    return result

cs_ml_tools-2025.12.4/ml_tools/distance_calculation.py

@@ -0,0 +1,51 @@
+from typing import Dict
+
+import numpy as np
+import pandas as pd
+
+
+def compute_dtw_dist_matrix(
+    series_df: pd.DataFrame, dtw_params: Dict = None
+) -> pd.DataFrame:
+    """
+    Computes the DTW distance matrix for the given values
+
+    Parameters
+    ----------
+    series_df: array of floats
+        The dataframe of series
+        for which to compute
+        the distance matrix
+
+        Expected shape: [N, K] where
+        N = Number of series
+        K = Number of steps
+    dtw_params: Dictionary
+        Parameters that are passed on to
+        tslearn.metrics.dtw
+
+    Returns
+    -------
+    pd.DataFrame:
+        Distance matrix
+        Shape: [N, N]
+    """
+    from tslearn import metrics
+
+    dtw_params = dict() if dtw_params is None else dtw_params
+
+    N = series_df.shape[0]
+    dist_matrix = np.full((N, N), fill_value=np.nan)
+    for i in range(N):
+        for k in range(i, N):
+            dist_matrix[k, i] = dist_matrix[i, k] = metrics.dtw(
+                series_df.iloc[i], series_df.iloc[k], **dtw_params
+            )
+
+    # Sanity checks
+    assert np.allclose(dist_matrix, dist_matrix.T)
+    assert np.all(~np.isnan(dist_matrix))
+
+    return pd.DataFrame(
+        data=dist_matrix, index=series_df.index, columns=series_df.index
+    )