Pkg depedecies bug fix on docs build

[ramosv]

The following issue was presented on the docs build
* ModuleNotFoundError: No module named 'statsmodels'
I mocked package. We will see if it works after merging

[Copilot]

Pull Request Overview

This PR addresses a missing statsmodels dependency in the documentation build by mocking and adding it, bumps the package version to 1.0.7, and refactors import error handling and dataset loading logic.

• Bump version to 1.0.7 across setup, init, README, and changelog
• Add statsmodels to install_requires and Sphinx config/mock imports
• Update preprocess_clinical return logic and comment out legacy dataset splitting
• Introduce ImportError with instructions for missing PyTorch/PyG modules

Reviewed Changes

Copilot reviewed 22 out of 22 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
setup.cfg	Version bump to 1.0.7 and add statsmodels
docs/source/conf.py	Update Sphinx styles, execution settings, and mock statsmodels
docs/source/_autosummary/...preprocess.rst	Remove multipletests from autosummary
bioneuralnet/utils/preprocess.py	Change concat to include df_ignore and modify return
bioneuralnet/network_embedding/gnn_models.py	Wrap PyTorch imports in try/except and reformat init signatures
bioneuralnet/network_embedding/gnn_embedding.py	Reorder imports, wrap imports in try/except
bioneuralnet/downstream_task/subject_representation.py	Add error handling for missing torch and unused tempfile import
bioneuralnet/downstream_task/dpmon.py	Add error handling for missing torch-geometric
bioneuralnet/datasets/dataset_loader.py	Comment out legacy CSV part-loading logic
bioneuralnet/init.py	Version bump to 1.0.7
README.md	Update welcome header to 1.0.7
CHANGELOG.md	Update changelog header to 1.0.7 and fix version range

Comments suppressed due to low confidence (3)

docs/source/_autosummary/bioneuralnet.utils.preprocess.rst:12

• The multipletests function was removed from the autosummary, which will omit it from generated docs. If this deletion was unintentional, please re-add it or adjust the RST accordingly.

-      multipletests

CHANGELOG.md:72

• Typo in 'realease'; it should be spelled 'release'.

- **New realease**: A new release will include documentation for the other updates. (1.1.0)

bioneuralnet/utils/preprocess.py:96

• Previously df_ignore columns were preserved in the final output but are now dropped. Confirm if df_ignore should be included in the return or removed from the concatenation step.

    return df_features[selected_columns]

[abdelhafizm]

lgtm