PyIAML 1.0.0__tar.gz → 1.0.2__tar.gz

{pyiaml-1.0.0 → pyiaml-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyIAML
-Version: 1.0.0
+Version: 1.0.2
 Summary: Integrated AutoML for Medical Labs: explainable pipelines for clinical research
 Author-email: Rudy MERIEUX <rmerieux@chu-reims.fr>, Hugo RUELLET <hruellet@chu-reims.fr>, Robin BOURACHOT <rbourachot@chu-reims.fr>, Youssouf DAHLOUK <ydahlouk@chu-reims.fr>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -718,9 +718,12 @@ preprocessing, model search and evaluation into one workflow for classification,
 regression and survival analysis on tabular data.
 
 Researchers can inspect the steps of a selected pipeline, evaluate its predictions
-and generate explanations to discuss with clinicians and data scientists. Modular
-components let teams adapt the workflow to their study while keeping the methods
-available for review.
+and generate explanations to discuss with clinicians and data scientists.
+IAML includes a broad set of built-in methods. **Go further with customization.**
+Add your team's preprocessing steps, models, metrics, validation splitters
+and search optimizers to adapt the workflow to your research domain.
+These contributions can be shared and reused across studies.
+The [extension guide](https://iias-research.github.io/iaml/adaptability.html) shows how to get started.
 
 ## Clinical research workflow
 
@@ -738,13 +741,13 @@ reporting a study and recording the settings needed to repeat an experiment.
 
 ## Installation
 
-Use Python 3.10 or later and Git. Install IAML from GitHub:
+Use Python 3.10 or later:
 
 ```bash
-python -m pip install "git+https://github.com/IIAS-Research/iaml.git"
+python -m pip install PyIAML
 ```
 
-The distribution is named `PyIAML`; the Python import is `iaml`.
+The distribution is named `PyIAML`. The Python import is `iaml`.
 
 ## How to run
 
@@ -754,45 +757,37 @@ It uses a dataset bundled with scikit-learn, so no dataset download is needed.
 ```python
 from sklearn.datasets import load_breast_cancer
 from sklearn.model_selection import train_test_split
-
 from iaml import IAML
 
-
-def main():
+if __name__ == "__main__":
     X, y = load_breast_cancer(return_X_y=True, as_frame=True)
     X_train, X_test, y_train, y_test = train_test_split(
-        X, y, test_size=0.2, stratify=y, random_state=42
+        X, y, stratify=y, random_state=42
     )
-
-    automl = IAML(max_duration=30, max_workers=1)
-    candidates = automl.fit(X_train, y_train, verbose=0)
-    best_candidate = candidates[0]
-
-    predictions = best_candidate.predict(X_test)
-    scores = best_candidate.evaluate(X_test, y_test)
-    print("Predictions:", predictions[:5])
-    print("Test metrics:", scores)
-
-
-if __name__ == "__main__":
-    main()
+    search = IAML(max_duration=30, max_workers=1)
+    search.fit(X_train, y_train)
+    chosen_model = search.chosen_candidate
+    print(chosen_model.evaluate(X_test, y_test))
 ```
 
-`fit` returns a list of fitted `Candidate` objects ordered by performance.
-Prediction and evaluation are methods of a candidate. Keep the `__main__` guard
-when running scripts because training uses multiprocessing. `max_duration` sets
-the search time budget; initialization and final fitting can take additional time.
+`chosen_model` is the selected model, including its preprocessing.
+`evaluate` scores it on the held-out test set. The dataset labels are `0` for
+malignant and `1` for benign. Keep the `__main__` guard because training uses
+multiprocessing. The example uses one worker and a 30-second search budget.
+Final fitting can take additional time.
 
 ## Documentation
 
 The [user guides](https://iias-research.github.io/iaml/) cover data preparation, model search, evaluation
 and interpretation:
 
-- [Getting started](https://iias-research.github.io/iaml/quick_start.html): prepare data and run an example.
-- [Usage](https://iias-research.github.io/iaml/usage.html): configure a search and evaluate predictions.
-- [Explainability](https://iias-research.github.io/iaml/explainability.html): interpret model predictions.
-- [Research guide](https://iias-research.github.io/iaml/scientific.html): report methods and record experiment settings.
-- [Component status](https://iias-research.github.io/iaml/component_status.html): find available and experimental components.
+- [Quick Start](https://iias-research.github.io/iaml/quick_start.html): install IAML and run an example.
+- [01 / Build](https://iias-research.github.io/iaml/usage.html): prepare data and configure a search.
+- [02 / Evaluate](https://iias-research.github.io/iaml/evaluation.html): assess predictions on held-out data.
+- [03 / Explain](https://iias-research.github.io/iaml/explainability.html): inspect methods and interpret feature contributions.
+- [Study reporting](https://iias-research.github.io/iaml/scientific.html): save outputs and record experiment settings.
+- [Extending IAML](https://iias-research.github.io/iaml/adaptability.html): add reusable methods for your team's research.
+- [Component availability](https://iias-research.github.io/iaml/component_status.html): explore the main component families and their API documentation.
 
 ## Credits
 

{pyiaml-1.0.0 → pyiaml-1.0.2}/PyIAML.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyIAML
-Version: 1.0.0
+Version: 1.0.2
 Summary: Integrated AutoML for Medical Labs: explainable pipelines for clinical research
 Author-email: Rudy MERIEUX <rmerieux@chu-reims.fr>, Hugo RUELLET <hruellet@chu-reims.fr>, Robin BOURACHOT <rbourachot@chu-reims.fr>, Youssouf DAHLOUK <ydahlouk@chu-reims.fr>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -718,9 +718,12 @@ preprocessing, model search and evaluation into one workflow for classification,
 regression and survival analysis on tabular data.
 
 Researchers can inspect the steps of a selected pipeline, evaluate its predictions
-and generate explanations to discuss with clinicians and data scientists. Modular
-components let teams adapt the workflow to their study while keeping the methods
-available for review.
+and generate explanations to discuss with clinicians and data scientists.
+IAML includes a broad set of built-in methods. **Go further with customization.**
+Add your team's preprocessing steps, models, metrics, validation splitters
+and search optimizers to adapt the workflow to your research domain.
+These contributions can be shared and reused across studies.
+The [extension guide](https://iias-research.github.io/iaml/adaptability.html) shows how to get started.
 
 ## Clinical research workflow
 
@@ -738,13 +741,13 @@ reporting a study and recording the settings needed to repeat an experiment.
 
 ## Installation
 
-Use Python 3.10 or later and Git. Install IAML from GitHub:
+Use Python 3.10 or later:
 
 ```bash
-python -m pip install "git+https://github.com/IIAS-Research/iaml.git"
+python -m pip install PyIAML
 ```
 
-The distribution is named `PyIAML`; the Python import is `iaml`.
+The distribution is named `PyIAML`. The Python import is `iaml`.
 
 ## How to run
 
@@ -754,45 +757,37 @@ It uses a dataset bundled with scikit-learn, so no dataset download is needed.
 ```python
 from sklearn.datasets import load_breast_cancer
 from sklearn.model_selection import train_test_split
-
 from iaml import IAML
 
-
-def main():
+if __name__ == "__main__":
     X, y = load_breast_cancer(return_X_y=True, as_frame=True)
     X_train, X_test, y_train, y_test = train_test_split(
-        X, y, test_size=0.2, stratify=y, random_state=42
+        X, y, stratify=y, random_state=42
     )
-
-    automl = IAML(max_duration=30, max_workers=1)
-    candidates = automl.fit(X_train, y_train, verbose=0)
-    best_candidate = candidates[0]
-
-    predictions = best_candidate.predict(X_test)
-    scores = best_candidate.evaluate(X_test, y_test)
-    print("Predictions:", predictions[:5])
-    print("Test metrics:", scores)
-
-
-if __name__ == "__main__":
-    main()
+    search = IAML(max_duration=30, max_workers=1)
+    search.fit(X_train, y_train)
+    chosen_model = search.chosen_candidate
+    print(chosen_model.evaluate(X_test, y_test))
 ```
 
-`fit` returns a list of fitted `Candidate` objects ordered by performance.
-Prediction and evaluation are methods of a candidate. Keep the `__main__` guard
-when running scripts because training uses multiprocessing. `max_duration` sets
-the search time budget; initialization and final fitting can take additional time.
+`chosen_model` is the selected model, including its preprocessing.
+`evaluate` scores it on the held-out test set. The dataset labels are `0` for
+malignant and `1` for benign. Keep the `__main__` guard because training uses
+multiprocessing. The example uses one worker and a 30-second search budget.
+Final fitting can take additional time.
 
 ## Documentation
 
 The [user guides](https://iias-research.github.io/iaml/) cover data preparation, model search, evaluation
 and interpretation:
 
-- [Getting started](https://iias-research.github.io/iaml/quick_start.html): prepare data and run an example.
-- [Usage](https://iias-research.github.io/iaml/usage.html): configure a search and evaluate predictions.
-- [Explainability](https://iias-research.github.io/iaml/explainability.html): interpret model predictions.
-- [Research guide](https://iias-research.github.io/iaml/scientific.html): report methods and record experiment settings.
-- [Component status](https://iias-research.github.io/iaml/component_status.html): find available and experimental components.
+- [Quick Start](https://iias-research.github.io/iaml/quick_start.html): install IAML and run an example.
+- [01 / Build](https://iias-research.github.io/iaml/usage.html): prepare data and configure a search.
+- [02 / Evaluate](https://iias-research.github.io/iaml/evaluation.html): assess predictions on held-out data.
+- [03 / Explain](https://iias-research.github.io/iaml/explainability.html): inspect methods and interpret feature contributions.
+- [Study reporting](https://iias-research.github.io/iaml/scientific.html): save outputs and record experiment settings.
+- [Extending IAML](https://iias-research.github.io/iaml/adaptability.html): add reusable methods for your team's research.
+- [Component availability](https://iias-research.github.io/iaml/component_status.html): explore the main component families and their API documentation.
 
 ## Credits
 

{pyiaml-1.0.0 → pyiaml-1.0.2}/README.md

@@ -6,9 +6,12 @@ preprocessing, model search and evaluation into one workflow for classification,
 regression and survival analysis on tabular data.
 
 Researchers can inspect the steps of a selected pipeline, evaluate its predictions
-and generate explanations to discuss with clinicians and data scientists. Modular
-components let teams adapt the workflow to their study while keeping the methods
-available for review.
+and generate explanations to discuss with clinicians and data scientists.
+IAML includes a broad set of built-in methods. **Go further with customization.**
+Add your team's preprocessing steps, models, metrics, validation splitters
+and search optimizers to adapt the workflow to your research domain.
+These contributions can be shared and reused across studies.
+The [extension guide](https://iias-research.github.io/iaml/adaptability.html) shows how to get started.
 
 ## Clinical research workflow
 
@@ -26,13 +29,13 @@ reporting a study and recording the settings needed to repeat an experiment.
 
 ## Installation
 
-Use Python 3.10 or later and Git. Install IAML from GitHub:
+Use Python 3.10 or later:
 
 ```bash
-python -m pip install "git+https://github.com/IIAS-Research/iaml.git"
+python -m pip install PyIAML
 ```
 
-The distribution is named `PyIAML`; the Python import is `iaml`.
+The distribution is named `PyIAML`. The Python import is `iaml`.
 
 ## How to run
 
@@ -42,45 +45,37 @@ It uses a dataset bundled with scikit-learn, so no dataset download is needed.
 ```python
 from sklearn.datasets import load_breast_cancer
 from sklearn.model_selection import train_test_split
-
 from iaml import IAML
 
-
-def main():
+if __name__ == "__main__":
     X, y = load_breast_cancer(return_X_y=True, as_frame=True)
     X_train, X_test, y_train, y_test = train_test_split(
-        X, y, test_size=0.2, stratify=y, random_state=42
+        X, y, stratify=y, random_state=42
     )
-
-    automl = IAML(max_duration=30, max_workers=1)
-    candidates = automl.fit(X_train, y_train, verbose=0)
-    best_candidate = candidates[0]
-
-    predictions = best_candidate.predict(X_test)
-    scores = best_candidate.evaluate(X_test, y_test)
-    print("Predictions:", predictions[:5])
-    print("Test metrics:", scores)
-
-
-if __name__ == "__main__":
-    main()
+    search = IAML(max_duration=30, max_workers=1)
+    search.fit(X_train, y_train)
+    chosen_model = search.chosen_candidate
+    print(chosen_model.evaluate(X_test, y_test))
 ```
 
-`fit` returns a list of fitted `Candidate` objects ordered by performance.
-Prediction and evaluation are methods of a candidate. Keep the `__main__` guard
-when running scripts because training uses multiprocessing. `max_duration` sets
-the search time budget; initialization and final fitting can take additional time.
+`chosen_model` is the selected model, including its preprocessing.
+`evaluate` scores it on the held-out test set. The dataset labels are `0` for
+malignant and `1` for benign. Keep the `__main__` guard because training uses
+multiprocessing. The example uses one worker and a 30-second search budget.
+Final fitting can take additional time.
 
 ## Documentation
 
 The [user guides](https://iias-research.github.io/iaml/) cover data preparation, model search, evaluation
 and interpretation:
 
-- [Getting started](https://iias-research.github.io/iaml/quick_start.html): prepare data and run an example.
-- [Usage](https://iias-research.github.io/iaml/usage.html): configure a search and evaluate predictions.
-- [Explainability](https://iias-research.github.io/iaml/explainability.html): interpret model predictions.
-- [Research guide](https://iias-research.github.io/iaml/scientific.html): report methods and record experiment settings.
-- [Component status](https://iias-research.github.io/iaml/component_status.html): find available and experimental components.
+- [Quick Start](https://iias-research.github.io/iaml/quick_start.html): install IAML and run an example.
+- [01 / Build](https://iias-research.github.io/iaml/usage.html): prepare data and configure a search.
+- [02 / Evaluate](https://iias-research.github.io/iaml/evaluation.html): assess predictions on held-out data.
+- [03 / Explain](https://iias-research.github.io/iaml/explainability.html): inspect methods and interpret feature contributions.
+- [Study reporting](https://iias-research.github.io/iaml/scientific.html): save outputs and record experiment settings.
+- [Extending IAML](https://iias-research.github.io/iaml/adaptability.html): add reusable methods for your team's research.
+- [Component availability](https://iias-research.github.io/iaml/component_status.html): explore the main component families and their API documentation.
 
 ## Credits
 

{pyiaml-1.0.0 → pyiaml-1.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PyIAML"
-version = "1.0.0"
+version = "1.0.2"
 authors = [
     { name="Rudy MERIEUX", email="rmerieux@chu-reims.fr" },
     { name="Hugo RUELLET", email="hruellet@chu-reims.fr" },
@@ -65,7 +65,7 @@ dev-dependencies = [
     "ipywidgets>=8.1.5",
     "pre-commit>=3.8.0",
     "sphinx-autoapi>=3.3.3",
-    "sphinx-rtd-theme>=3.0.2",
+    "furo>=2025.12.19",
 ]
 
 [tool.uv.dependency-groups]

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/actionables/cleaning/act_encode_target_column.py

@@ -2,7 +2,7 @@
 
 This prototype transforms y rather than X, recomputes the mapping on each call,
 and cannot reverse predictions. It is incompatible with the pipeline transformer
-contract and must remain outside automatic cleaning. See docs/component_status.rst.
+contract and must remain outside automatic cleaning.
 """
 
 import textwrap

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/actionables/cleaning/act_mice.py

@@ -35,7 +35,7 @@ class ActMICEForestImputer(Actionable):
     """[STEP] Impute missing values with MICE (miceforest/LightGBM).
 
     Copies and serialized steps retain fitted state without rebuilding models.
-    Accessing ``kernel`` or transforming data restores a private kernel; refitting
+    Accessing ``kernel`` or transforming data restores a private kernel. Refitting
     replaces that state directly.
     """
 

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/actionables/features_precleaning/act_drop_bad_quality_rows.py

@@ -1,7 +1,7 @@
 """Experimental row filter, available only through an explicit module import.
 
 Its missingness threshold, minimum sample policy and alignment of resampled data
-need integration tests before automatic use. See docs/component_status.rst.
+need integration tests before automatic use.
 """
 from typing import Any
 import textwrap

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/actionables/features_preprocessing/act_cyclical_date_encoding.py

@@ -2,7 +2,6 @@
 
 Date conversion and cleaning precede automatic feature preprocessing, so this
 component needs an explicit position while datetime columns are still available.
-See docs/component_status.rst.
 """
 import textwrap
 import numpy as np

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/actionables/features_preprocessing/act_polynomial_features.py

@@ -1,7 +1,7 @@
 """Experimental polynomial expansion, available only through an explicit import.
 
 Unbounded output dimensionality can exhaust memory during automatic exploration.
-Kept outside the default preprocessing stage; see docs/component_status.rst.
+Kept outside the default preprocessing stage.
 """
 import textwrap
 import pandas as pd

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/actionables/predictors/survival/act_aalen_additive_model.py

@@ -2,7 +2,7 @@
 
 Requires the optional, undeclared lifelines dependency. Parameter forwarding and
 the time-by-sample hazard output do not implement IAML's predictor contract yet.
-Excluded from automatic model selection; see docs/component_status.rst.
+Excluded from automatic model selection.
 """
 import textwrap
 from typing import Any

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/cache_keys.py

@@ -32,7 +32,7 @@ def hash_dataset(
 
     Targets are positional, as in Dataset, so their pandas index is not used.
     Serialization preserves their shape and dtype, including structured survival
-    targets. This only serializes local inputs; no pickle is loaded here.
+    targets. This only serializes local inputs. No pickle is loaded here.
     """
     payload = (
         "iaml-dataset-v2",

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/iaml.py

@@ -61,7 +61,7 @@ class IAML:  # pylint: disable=too-many-instance-attributes
     :param int, optional max_workers: Maximum parallel workers. Default to cpu count.
     :param int, optional max_stage_duration: Maximum duration of a stage. Default to None.
     :param callable, optional splitter: Split function to use. Default to kfold_splitter.
-    :param int, optional max_duration: Search time budget; -1 means no global limit.
+    :param int, optional max_duration: Search time budget. -1 means no global limit.
     :param int | str, optional time_before_sample_use: Time before we use sampled data. 
         Default to None.
     :param bool, optional preprocessor: Use preprocessor. Default to False.
@@ -73,7 +73,7 @@ class IAML:  # pylint: disable=too-many-instance-attributes
     :param bool, optional keep_training_history: If True, store detailed CV audit records for
         every evaluated pipeline. Default to False.
     :param bool, optional refit_on_sample: Reuse the initial train_on_n_samples sample for
-        final fitting. If False, refit on all input rows. Default to True; has no effect
+        final fitting. If False, refit on all input rows. Defaults to True. Has no effect
         without a positive train_on_n_samples limit.
     :param initial_preprocessor: Optional clonable sklearn transformer. It must return
         a numeric DataFrame with unchanged rows and index. Every generated pipeline,

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/metrics/cumulative_dynamic_auc.py

@@ -2,7 +2,7 @@
 
 The current implementation passes survival probabilities where risk scores are
 required, and its time grid and aggregation need validation. Importing this module
-must not activate the metric in AutoML. See docs/component_status.rst.
+must not activate the metric in AutoML.
 """
 from typing import Any
 import textwrap

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/sklearn_preprocessor.py

@@ -20,7 +20,7 @@ class SklearnPreprocessor(Step):
     on each supplied Dataset.X, without target values or patient-group columns.
     ``transformer_`` is the fitted clone, retained for prediction/provenance and
     serialization. The template and its hyperparameters participate in cache
-    keys; the learned vocabulary does not alter the pipeline configuration.
+    keys. The learned vocabulary does not alter the pipeline configuration.
 
     A DataFrame output is required so column names and row alignment remain
     explicit. This step is deliberately not registered under a search tag: it

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/step.py

@@ -237,7 +237,7 @@ class Step: # pylint: disable=too-many-public-methods, too-many-instance-attribu
 
         :param bool default: Default behavior when trying to passthrough configurations from
             one step which have no "passthrough" key. When "passthrough" is undefined and "default" 
-            is set to False, the configuration will not be returned; otherwise, the default value 
+            is set to False, the configuration will not be returned. Otherwise, the default value
             for that configuration will be returned.
         :return: A dictionary view of the configuration with parameters' names and values.
         """

{pyiaml-1.0.0 → pyiaml-1.0.2}/src/iaml/timed_pool_executor.py

@@ -437,7 +437,7 @@ class TimedPoolExecutor:  # pylint: disable=too-many-instance-attributes
         """Wait until all the task are finished or timeout is reach
         If timeout is reach -> Remaining tasks will be kill without sending results
 
-        :param float timeout: Maximum seconds to wait; None waits without a timeout.
+        :param float timeout: Maximum seconds to wait. None waits without a timeout.
         :param bool, optional reset: Reset the instance after join(). Defaults to True.
 
         :return: All finished task results