Updating project-template to recent versions

[Dr4k3z]

When following the instructions on how to define our own estimator within the sklearn framework, I went through this repo.

Although I found it quite useful, I feel like it could be improved and updated, to be in line with most recent scikit-learn versions. I believe the code is compatible with sklearn version 1.4.2. For instance, I noticed the code uses an old API for data validation, like here

project-template/skltemplate/_template.py

Lines 76 to 81 in fc9f82e

	# `_validate_data` is defined in the `BaseEstimator` class.
	# It allows to:
	# - run different checks on the input data;
	# - define some attributes associated to the input data: `n_features_in_` and
	# `feature_names_in_`.
	X, y = self._validate_data(X, y, accept_sparse=True)

According to this, since version 1.6.0 the validate_data api is no longer part of the Base.BaseEstimator class, but rather inside of sklearn.utils.validation module.
In this pr I made this tiny change to the _template.py source code. I've briely run the unit tests and apart from the following error

FAILED tests/test_common.py::test_estimators[TemplateEstimator()-check_estimator_sparse_tag] - AssertionError: Estimator TemplateEstimator didn't fail when fitted on sparse data but should have according to its tag self.input_tags.sparse=False. The t...
FAILED tests/test_common.py::test_estimators[TemplateTransformer()-check_estimator_tags_renamed] - TypeError: Estimator TemplateTransformer has defined either `_more_tags` or `_get_tags`, but not `__sklearn_tags__`. If you're customizing tags, and need t...
FAILED tests/test_common.py::test_estimators[TemplateTransformer()-check_estimator_sparse_tag] - AssertionError: Estimator TemplateTransformer didn't fail when fitted on sparse data but should have according to its tag self.input_tags.sparse=False. The...
FAILED tests/test_common.py::test_estimators[TemplateTransformer()-check_transformers_unfitted] - AssertionError: The unfitted transformer TemplateTransformer does not raise an error when transform is called. Perhaps use check_is_fitted in transform.

all other 150 test cases seem to run smoothly.