### Install Documentation Dependencies

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/CONTRIBUTING.md

Install dependencies required to build the project documentation locally. Recommended to use a separate environment.

```bash
pip install -r docs/requirements.txt
```

--------------------------------

### Install Development Dependencies

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/CONTRIBUTING.md

Install the necessary dependencies for local development, including testing and linting tools.

```bash
pip install -e ".[dev]"
```

--------------------------------

### Running the HiClass Example

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/full_example.md

Execute the saved Python script from your terminal to run the HiClass example.

```bash
python hello_hiclass.py

```

--------------------------------

### Failed HiClass Import

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/verify.md

This example demonstrates the expected output when HiClass is not installed correctly. A ModuleNotFoundError will be raised, indicating an issue with the installation.

```python
Python 3.9.7 (default, Sep 16 2021, 13:09:58)
[GCC 7.5.0] :: Anaconda, Inc. on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import hiclass
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
ModuleNotFoundError: No module named 'hiclass'

```

--------------------------------

### Install Pipenv

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/pipenv.md

Installs the pipenv package using pip.

```bash
pip install pipenv
```

--------------------------------

### Install HiClass using pip

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/install.md

Install the base HiClass package from PyPI. This is the recommended method.

```bash
pip install hiclass
```

--------------------------------

### Install Git Hooks

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/CONTRIBUTING.md

Set up pre-commit hooks to automatically format code and catch potential issues before committing.

```bash
pre-commit install
```

--------------------------------

### Activate Conda Virtual Environment

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/conda.md

Activate the 'hiclass-environment' to start using the isolated Python installation and its packages.

```bash
conda activate hiclass-environment
```

--------------------------------

### Expected Output of HiClass Example

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/full_example.md

The predicted hierarchical labels after running the example script.

```python
[['Animal' 'Reptile' 'Lizard']
 ['Animal' 'Reptile' 'Snake']
 ['Animal' 'Mammal' 'Cow']
 ['Animal' 'Mammal' 'Sheep']]

```

--------------------------------

### Install HiClass with optional packages

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/install.md

Install HiClass along with optional packages, such as 'ray' for parallel processing. Replace '<extra_name>' with the desired extra.

```bash
pip install hiclass"[<extra_name>]"
```

--------------------------------

### Install HiClass using conda

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/install.md

Install HiClass from the conda-forge channel. Use this if you prefer conda for package management.

```bash
conda install -c conda-forge hiclass --yes
```

--------------------------------

### Install Snakemake Environment

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/benchmarks/consumer_complaints/README.md

Clone the HiClass repository and create a Conda environment for Snakemake using the provided YAML file.

```shell
git clone https://github.com/scikit-learn-contrib/hiclass.git
cd hiclass/benchmarks/consumer_complaints
conda env create --name snakemake --file envs/snakemake.yml
```

--------------------------------

### LocalClassifierPerNode Example

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Demonstrates fitting and predicting with the LocalClassifierPerNode. This snippet shows a basic usage scenario with sample data.

```python
>>> from hiclass import LocalClassifierPerNode
>>> y = [['1', '1.1'], ['2', '2.1']]
>>> X = [[1, 2], [3, 4]]
>>> lcpn = LocalClassifierPerNode()
>>> lcpn.fit(X, y)
>>> lcpn.predict(X)
array([['1', '1.1'],
   ['2', '2.1']])
```

--------------------------------

### Activate Pipenv Shell

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/pipenv.md

Starts a new shell session with the Pipenv virtual environment activated.

```bash
pipenv shell
```

--------------------------------

### Full HiClass Example with RandomForest

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/full_example.md

This snippet demonstrates how to train a LocalClassifierPerNode using RandomForestClassifier for hierarchical classification. Save this code as hello_hiclass.py.

```python
"""Contents of hello_hiclass.py"""
from hiclass import LocalClassifierPerNode
from sklearn.ensemble import RandomForestClassifier

# Define data
X_train = [[1], [2], [3], [4]]
X_test = [[4], [3], [2], [1]]
Y_train = [
    ['Animal', 'Mammal', 'Sheep'],
    ['Animal', 'Mammal', 'Cow'],
    ['Animal', 'Reptile', 'Snake'],
    ['Animal', 'Reptile', 'Lizard'],
]

# Use random forest classifiers for every node
rf = RandomForestClassifier()
classifier = LocalClassifierPerNode(local_classifier=rf)

# Train local classifier per node
classifier.fit(X_train, Y_train)

# Predict
predictions = classifier.predict(X_test)
print(predictions)

```

--------------------------------

### Random Forest Hyperparameter Tuning Configuration

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/benchmarks/consumer_complaints/README.md

Example YAML configuration for tuning Random Forest hyperparameters using Optuna and Hydra. Defines parameter choices for n_estimators and criterion.

```yaml
defaults:
  - _self_
  - optuna

hydra:
  sweeper:
    params:
      n_estimators: choice(100, 200)
      criterion: choice("gini", "entropy", "log_loss")

n_estimators: 1
criterion: 1
```

--------------------------------

### LessInclusivePolicy

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/utilities.md

Implements the less inclusive policy, inheriting from InclusivePolicy. It provides methods to initialize the policy and retrieve positive and negative examples for a given node, with a different definition for negative examples.

```APIDOC
## class BinaryPolicy.LessInclusivePolicy(digraph: DiGraph, X: ndarray, y: ndarray, sample_weight=None)

### Description
Implement the less inclusive policy of the referenced paper.

### Parameters
* **digraph** (*nx.DiGraph*) – DiGraph which is used for inferring nodes relationships.
* **X** (*np.ndarray*) – Features which will be used for fitting a model.
* **y** (*np.ndarray*) – Labels which will be assigned to the different samples. Has to be 2D array.
* **sample_weight** (*array-like* *of* *shape* *(**n_samples* *,* *)* *,* *default=None*) – Array of weights that are assigned to individual samples. If not provided, then each sample is given unit weight.

## Method: __init__

### Description
Initialize a BinaryPolicy with the required data.

### Parameters
* **digraph** (*nx.DiGraph*) – DiGraph which is used for inferring nodes relationships.
* **X** (*np.ndarray*) – Features which will be used for fitting a model.
* **y** (*np.ndarray*) – Labels which will be assigned to the different samples. Has to be 2D array.
* **sample_weight** (*array-like* *of* *shape* *(**n_samples* *,* *)* *,* *default=None*) – Array of weights that are assigned to individual samples. If not provided, then each sample is given unit weight.

## Method: get_binary_examples(node)

### Description
Gather all positive and negative examples for a given node.

### Parameters
**node** – Node for which the positive and negative examples should be searched.

### Returns
* **X** (*np.ndarray*) – The subset with positive and negative features.
* **y** (*np.ndarray*) – The subset with positive and negative labels.

## Method: negative_examples(node)

### Description
Gather all negative examples corresponding to the given node. This includes all examples except the examples for the current node and its children.

### Parameters
**node** – Node for which the negative examples should be searched.

### Returns
**negative_examples** – A mask for which examples are included (True) and which are not.
* **Return type:** np.ndarray

## Method: positive_examples(node)

### Description
Gather all positive examples corresponding to the given node. This includes examples for the given node and its descendants.

### Parameters
**node** – Node for which the positive examples should be searched.

### Returns
**positive_examples** – A mask for which examples are included (True) and which are not.
* **Return type:** np.ndarray
```

--------------------------------

### Successful HiClass Import

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/verify.md

Run this code in a Python interpreter to verify a successful HiClass installation. A successful import indicates the library is ready for use.

```python
Python 3.8.13 (default, Mar 28 2022, 11:38:47)
[GCC 7.5.0] :: Anaconda, Inc. on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import hiclass
>>>

```

--------------------------------

### get_params

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Gets the parameters of the estimator, including those of nested objects.

```APIDOC
## get_params(deep=True)

### Description
Get parameters for this estimator.

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Parameters
* **deep** (*bool*, *default=True*) – If True, will return the parameters for this estimator and contained subobjects that are estimators.

### Returns
**params** – Parameter names mapped to their values.

### Return type
dict
```

--------------------------------

### Train and Predict with LocalClassifierPerNode

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/README.md

This snippet shows how to train a LocalClassifierPerNode using RandomForestClassifier for each node and make predictions. Ensure scikit-learn and hiclass are installed.

```python
from hiclass import LocalClassifierPerNode
from sklearn.ensemble import RandomForestClassifier

# Define data
X_train = [[1], [2], [3], [4]]
X_test = [[4], [3], [2], [1]]
Y_train = [
    ['Animal', 'Mammal', 'Sheep'],
    ['Animal', 'Mammal', 'Cow'],
    ['Animal', 'Reptile', 'Snake'],
    ['Animal', 'Reptile', 'Lizard'],
]

# Use random forest classifiers for every node
rf = RandomForestClassifier()
classifier = LocalClassifierPerNode(local_classifier=rf)

# Train local classifier per node
classifier.fit(X_train, Y_train)

# Predict
predictions = classifier.predict(X_test)
```

--------------------------------

### Define Data for Pipeline Example

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/README.md

Prepare text data and corresponding hierarchical labels for training a scikit-learn pipeline with HiClass. This data is used to demonstrate feature extraction and hierarchical classification.

```python
from hiclass import LocalClassifierPerParentNode
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline

# Define data
X_train = [
    'Struggling to repay loan',
    'Unable to get annual report',
]
X_test = [
    'Unable to get annual report',
    'Struggling to repay loan',
]
Y_train = [
    ['Loan', 'Student loan'],
    ['Credit reporting', 'Reports']
]
```

--------------------------------

### InclusivePolicy

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/utilities.md

Implements the inclusive policy for binary classification. It provides methods to initialize the policy and retrieve positive and negative examples for a given node.

```APIDOC
## class BinaryPolicy.InclusivePolicy(digraph: DiGraph, X: ndarray, y: ndarray, sample_weight=None)

### Description
Implement the inclusive policy of the referenced paper.

### Parameters
* **digraph** (*nx.DiGraph*) – DiGraph which is used for inferring nodes relationships.
* **X** (*np.ndarray*) – Features which will be used for fitting a model.
* **y** (*np.ndarray*) – Labels which will be assigned to the different samples. Has to be 2D array.
* **sample_weight** (*array-like* *of* *shape* *(**n_samples* *,* *)* *,* *default=None*) – Array of weights that are assigned to individual samples. If not provided, then each sample is given unit weight.

## Method: __init__

### Description
Initialize a BinaryPolicy with the required data.

### Parameters
* **digraph** (*nx.DiGraph*) – DiGraph which is used for inferring nodes relationships.
* **X** (*np.ndarray*) – Features which will be used for fitting a model.
* **y** (*np.ndarray*) – Labels which will be assigned to the different samples. Has to be 2D array.
* **sample_weight** (*array-like* *of* *shape* *(**n_samples* *,* *)* *,* *default=None*) – Array of weights that are assigned to individual samples. If not provided, then each sample is given unit weight.

## Method: get_binary_examples(node)

### Description
Gather all positive and negative examples for a given node.

### Parameters
**node** – Node for which the positive and negative examples should be searched.

### Returns
* **X** (*np.ndarray*) – The subset with positive and negative features.
* **y** (*np.ndarray*) – The subset with positive and negative labels.

## Method: negative_examples(node)

### Description
Gather all negative examples corresponding to the given node. This includes all examples, except the examples for the given node, its descendants and successors.

### Parameters
**node** – Node for which the negative examples should be searched.

### Returns
**negative_examples** – A mask for which examples are included (True) and which are not.
* **Return type:** np.ndarray

## Method: positive_examples(node)

### Description
Gather all positive examples corresponding to the given node. This includes examples for the given node and its descendants.

### Parameters
**node** – Node for which the positive examples should be searched.

### Returns
**positive_examples** – A mask for which examples are included (True) and which are not.
* **Return type:** np.ndarray
```

--------------------------------

### get_params(deep=True)

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Gets the parameters of the estimator, with an option to include nested estimators.

```APIDOC
## get_params(deep=True)

### Description
Get parameters for this estimator.

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Parameters
* **deep** (*bool*, *default=True*) – If True, will return the parameters for this estimator and contained subobjects that are estimators.

### Returns
* **params** – Parameter names mapped to their values.

### Return type
dict
```

--------------------------------

### Build Documentation Locally

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/CONTRIBUTING.md

Navigate to the docs directory and build the HTML documentation. This allows for previewing changes.

```bash
cd docs
make html
```

--------------------------------

### Create and Navigate to Environment Directory

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/pipenv.md

Creates a new directory for the virtual environment and changes the current directory to it.

```bash
mkdir hiclass-environment && cd hiclass-environment
```

--------------------------------

### Fit and Predict with LocalClassifierPerLevel

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Demonstrates how to initialize, fit, and predict using the LocalClassifierPerLevel class with sample data.

```python
>>> from hiclass import LocalClassifierPerLevel
>>> y = [['1', '1.1'], ['2', '2.1']]
>>> X = [[1, 2], [3, 4]]
>>> lcpl = LocalClassifierPerLevel()
>>> lcpl.fit(X, y)
>>> lcpl.predict(X)
array([['1', '1.1'],
   ['2', '2.1']])
```

--------------------------------

### Initialize and Use FlatClassifier

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Demonstrates how to initialize a FlatClassifier, fit it with sample data and hierarchical labels, and then predict using the fitted classifier. This snippet shows the basic workflow for using the FlatClassifier.

```python
>>> from hiclass import FlatClassifier
>>> y = [['1', '1.1'], ['2', '2.1']]
>>> X = [[1, 2], [3, 4]]
>>> flat = FlatClassifier()
>>> flat.fit(X, y)
>>> flat.predict(X)
array([['1', '1.1'],
    ['2', '2.1']])
```

--------------------------------

### Initialize and Use LocalClassifierPerParentNode

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Demonstrates how to initialize, fit, and predict using the LocalClassifierPerParentNode. This is useful for basic hierarchical classification tasks.

```python
>>> from hiclass import LocalClassifierPerParentNode
>>> y = [['1', '1.1'], ['2', '2.1']]
>>> X = [[1, 2], [3, 4]]
>>> lcppn = LocalClassifierPerParentNode()
>>> lcppn.fit(X, y)
>>> lcppn.predict(X)
array([['1', '1.1'],
   ['2', '2.1']])
```

--------------------------------

### FlatClassifier.__init__()

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/index.md

Initializes a FlatClassifier instance. This is the constructor for the FlatClassifier class, setting up the initial state of the classifier.

```APIDOC
## FlatClassifier.__init__()

### Description
Initializes a FlatClassifier instance.

### Method
__init__

### Parameters
(No parameters explicitly documented in the source for __init__)
```

--------------------------------

### BinaryPolicy.SiblingsPolicy

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/utilities.md

Implements the siblings policy for binary classification. It is used to infer node relationships and retrieve positive and negative examples for a given node.

```APIDOC
## class BinaryPolicy.SiblingsPolicy

### Description
Implements the siblings policy of the referenced paper.

### Parameters
* **digraph** (*nx.DiGraph*) – DiGraph which is used for inferring nodes relationships.
* **X** (*np.ndarray*) – Features which will be used for fitting a model.
* **y** (*np.ndarray*) – Labels which will be assigned to the different samples. Has to be 2D array.
* **sample_weight** (*array-like* *of* *shape* *(**n_samples* *,* *)* *,* *default=None*) – Array of weights that are assigned to individual samples. If not provided, then each sample is given unit weight.

## method get_binary_examples(node)

### Description
Gather all positive and negative examples for a given node.

### Parameters
* **node** – Node for which the positive and negative examples should be searched.

### Returns
* **X** (*np.ndarray*) – The subset with positive and negative features.
* **y** (*np.ndarray*) – The subset with positive and negative labels.

## method negative_examples(node)

### Description
Gather all negative examples corresponding to the given node. This includes all examples for nodes that have the same ancestors as the given node, as well as their descendants.

### Parameters
* **node** – Node for which the negative examples should be searched.

### Returns
* **negative_examples** (*np.ndarray*) – A mask for which examples are included (True) and which are not.

## method positive_examples(node)

### Description
Gather all positive examples corresponding to the given node. This includes examples for the given node and its descendants.

### Parameters
* **node** – Node for which the positive examples should be searched.

### Returns
* **positive_examples** (*np.ndarray*) – A mask for which examples are included (True) and which are not.
```

--------------------------------

### Instantiate LocalClassifierPerLevel

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/local_classifier.md

Create a LocalClassifierPerLevel model using a RandomForestClassifier for each level in the hierarchy.

```python
rf = RandomForestClassifier()
classifier = LocalClassifierPerLevel(local_classifier=rf)
```

--------------------------------

### LessExclusivePolicy

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/utilities.md

Implements the less exclusive policy, a variation of the binary policy. It allows for gathering positive and negative examples with specific criteria for exclusion.

```APIDOC
## class BinaryPolicy.LessExclusivePolicy

### Description
Implement the less exclusive policy of the referenced paper.

### Parameters
* **digraph** (*nx.DiGraph*) – DiGraph which is used for inferring nodes relationships.
* **X** (*np.ndarray*) – Features which will be used for fitting a model.
* **y** (*np.ndarray*) – Labels which will be assigned to the different samples. Has to be 2D array.
* **sample_weight** (*array-like* *of* *shape* *(**n_samples* *,* *)* *,* *default=None*) – Array of weights that are assigned to individual samples. If not provided, then each sample is given unit weight.

## get_binary_examples(node)

### Description
Gather all positive and negative examples for a given node.

### Parameters
* **node** – Node for which the positive and negative examples should be searched.

### Returns
* **X** (*np.ndarray*) – The subset with positive and negative features.
* **y** (*np.ndarray*) – The subset with positive and negative labels.

## negative_examples(node)

### Description
Gather all negative examples corresponding to the given node. This includes all examples except the examples for the current node and its children.

### Parameters
* **node** – Node for which the negative examples should be searched.

### Returns
**negative_examples** (*np.ndarray*) – A mask for which examples are included (True) and which are not.

## positive_examples(node)

### Description
Gather all positive examples corresponding to the given node. This only includes examples for the given node.

### Parameters
* **node** – Node for which the positive examples should be searched.

### Returns
**positive_examples** (*np.ndarray*) – A mask for which examples are included (True) and which are not.
```

--------------------------------

### Activate Virtual Environment (Unix-like)

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/venv.md

Activates the previously created Python virtual environment. This command is for Unix-like systems (Linux, macOS). After activation, your shell prompt will change to indicate the active environment.

```bash
source env/hiclass-environment/bin/activate
```

--------------------------------

### ExclusivePolicy

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/utilities.md

Implements the exclusive policy for binary classification. It provides methods to initialize the policy and gather positive and negative examples for a given node.

```APIDOC
## class BinaryPolicy.ExclusivePolicy

### Description
Implements the exclusive policy of the referenced paper.

### Parameters
* **digraph** (*nx.DiGraph*) – DiGraph which is used for inferring nodes relationships.
* **X** (*np.ndarray*) – Features which will be used for fitting a model.
* **y** (*np.ndarray*) – Labels which will be assigned to the different samples. Has to be 2D array.
* **sample_weight** (*array-like* *of* *shape* *(**n_samples* *,* *)* *,* *default=None*) – Array of weights that are assigned to individual samples. If not provided, then each sample is given unit weight.

## get_binary_examples(node)

### Description
Gather all positive and negative examples for a given node.

### Parameters
* **node** – Node for which the positive and negative examples should be searched.

### Returns
* **X** (*np.ndarray*) – The subset with positive and negative features.
* **y** (*np.ndarray*) – The subset with positive and negative labels.

## negative_examples(node)

### Description
Gather all negative examples corresponding to the given node. This includes all examples except the positive ones.

### Parameters
* **node** – Node for which the negative examples should be searched.

### Returns
**negative_examples** (*np.ndarray*) – A mask for which examples are included (True) and which are not.

## positive_examples(node)

### Description
Gather all positive examples corresponding to the given node. This only includes examples for the given node.

### Parameters
* **node** – Node for which the positive examples should be searched.

### Returns
**positive_examples** (*np.ndarray*) – A mask for which examples are included (True) and which are not.
```

--------------------------------

### Instantiate LocalClassifierPerNode

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/local_classifier.md

Create a LocalClassifierPerNode model using a RandomForestClassifier for each node, excluding the root.

```python
rf = RandomForestClassifier()
classifier = LocalClassifierPerNode(local_classifier=rf)
```

--------------------------------

### BinaryPolicy.ExclusiveSiblingsPolicy

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/utilities.md

Implements the exclusive siblings policy for binary classification. It is used to infer node relationships and retrieve positive and negative examples for a given node.

```APIDOC
## class BinaryPolicy.ExclusiveSiblingsPolicy

### Description
Implement the exclusive siblings policy of the referenced paper.

### Parameters
* **digraph** (*nx.DiGraph*) – DiGraph which is used for inferring nodes relationships.
* **X** (*np.ndarray*) – Features which will be used for fitting a model.
* **y** (*np.ndarray*) – Labels which will be assigned to the different samples. Has to be 2D array.
* **sample_weight** (*array-like* *of* *shape* *(**n_samples* *,* *)* *,* *default=None*) – Array of weights that are assigned to individual samples. If not provided, then each sample is given unit weight.

## method get_binary_examples(node)

### Description
Gather all positive and negative examples for a given node.

### Parameters
* **node** – Node for which the positive and negative examples should be searched.

### Returns
* **X** (*np.ndarray*) – The subset with positive and negative features.
* **y** (*np.ndarray*) – The subset with positive and negative labels.

## method negative_examples(node)

### Description
Gather all negative examples corresponding to the given node. This includes examples for all nodes that have the same parent as the given node.

### Parameters
* **node** – Node for which the negative examples should be searched.

### Returns
* **negative_examples** (*np.ndarray*) – A mask for which examples are included (True) and which are not.

## method positive_examples(node)

### Description
Gather all positive examples corresponding to the given node. This only includes examples for the given node.

### Parameters
* **node** – Node for which the positive examples should be searched.

### Returns
* **positive_examples** (*np.ndarray*) – A mask for which examples are included (True) and which are not.
```

--------------------------------

### set_fit_request(sample_weight: bool | None | str = '$UNCHANGED$')

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Configures metadata routing for the `fit` method, specifying whether `sample_weight` metadata should be requested.

```APIDOC
## set_fit_request(sample_weight: bool | None | str = '$UNCHANGED$')

### Description
Configure whether metadata should be requested to be passed to the `fit` method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with `enable_metadata_routing=True` (see `sklearn.set_config()`).
Please check the User Guide on how the routing
mechanism works.

The options for each parameter are:

- `True`: metadata is requested, and passed to `fit` if provided. The request is ignored if metadata is not provided.
- `False`: metadata is not requested and the meta-estimator will not pass it to `fit`.
- `None`: metadata is not requested, and the meta-estimator will raise an error if the user provides it.
- `str`: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (`sklearn.utils.metadata_routing.UNCHANGED`) retains the existing request. This allows you to change the request for some parameters and not others.

#### Versionadded
Added in version 1.3.

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Parameters
* **sample_weight** (*str*, *True*, *False*, or *None*, *default=sklearn.utils.metadata_routing.UNCHANGED*) – Metadata routing for `sample_weight` parameter in `fit`.

### Returns
* **self** – The updated object.

### Return type
object
```

--------------------------------

### Running HiClass Pipeline Locally with Snakemake

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/benchmarks/consumer_complaints/README.md

Command to activate the conda environment and run the Snakemake pipeline locally. Includes flags for continued execution, printing commands, reasoning, conda usage, and core count.

```shell
conda activate snakemake
snakemake --keep-going --printshellcmds --reason --use-conda --cores 48
```

--------------------------------

### Create Python Virtual Environment (Unix-like)

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/venv.md

Creates a new Python virtual environment named 'hiclass-environment' inside an 'env' subdirectory using the `venv` module. This command is for Unix-like systems (Linux, macOS).

```bash
python -m venv env/hiclass-environment
```

--------------------------------

### Instantiate LocalClassifierPerParentNode

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/local_classifier.md

Create a LocalClassifierPerParentNode model using a RandomForestClassifier for each parent node.

```python
rf = RandomForestClassifier()
classifier = LocalClassifierPerParentNode(local_classifier=rf)
```

--------------------------------

### Run Local Tests

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/CONTRIBUTING.md

Execute the test suite locally with coverage reporting. Ensures code quality and adherence to standards.

```bash
pytest -v --cov=hiclass --cov-fail-under=90 --cov-report html
```

--------------------------------

### Create Python Virtual Environment (Windows)

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/venv.md

Creates a new Python virtual environment named 'hiclass-environment' inside an 'env' subdirectory using the `venv` module. This command is for Windows systems.

```bash
python -m venv env\hiclass-environment
```

--------------------------------

### Activate Virtual Environment (Windows)

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/venv.md

Activates the previously created Python virtual environment. This command is for Windows systems. After activation, your shell prompt will change to indicate the active environment.

```bash
.\env\hiclass-environment\Scripts\activate
```

--------------------------------

### Import LocalClassifierPerNode

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/local_classifier.md

Import the LocalClassifierPerNode class and RandomForestClassifier for use in local hierarchical classification.

```python
from hiclass import LocalClassifierPerNode
from sklearn.ensemble import RandomForestClassifier
```

--------------------------------

### Import LocalClassifierPerLevel

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/local_classifier.md

Import the LocalClassifierPerLevel class and RandomForestClassifier for use in local hierarchical classification.

```python
from hiclass import LocalClassifierPerLevel
from sklearn.ensemble import RandomForestClassifier
```

--------------------------------

### Local Classifier Per Node with Isotonic Calibration

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/algorithms/calibration.md

Demonstrates training and calibrating a LocalClassifierPerNode using RandomForestClassifier with isotonic regression and multiply probability aggregation. Requires scikit-learn and hiclass.

```python
from sklearn.ensemble import RandomForestClassifier

from hiclass import LocalClassifierPerNode

# Define data
X_train = [[1], [2], [3], [4]]
X_test = [[4], [3], [2], [1]]
X_cal = [[5], [6], [7], [8]]
Y_train = [
    ["Animal", "Mammal", "Sheep"],
    ["Animal", "Mammal", "Cow"],
    ["Animal", "Reptile", "Snake"],
    ["Animal", "Reptile", "Lizard"],
]

Y_cal = [
    ["Animal", "Mammal", "Cow"],
    ["Animal", "Mammal", "Sheep"],
    ["Animal", "Reptile", "Lizard"],
    ["Animal", "Reptile", "Snake"],
]

# Use random forest classifiers for every node
rf = RandomForestClassifier()

# Use local classifier per node with isotonic regression as calibration method
classifier = LocalClassifierPerNode(
    local_classifier=rf, calibration_method="isotonic", probability_combiner="multiply"
)

# Train local classifier per node
classifier.fit(X_train, Y_train)

# Calibrate local classifier per node
classifier.calibrate(X_cal, Y_cal)

# Predict probabilities
probabilities = classifier.predict_proba(X_test)

# Print probabilities and labels for the last level
print(classifier.classes_[2])
print(probabilities)
```

--------------------------------

### Train and Predict with Pipeline

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/README.md

Execute the training and prediction steps using the previously defined scikit-learn pipeline. This demonstrates the end-to-end workflow for hierarchical multi-label classification with feature extraction.

```python
# Train local classifier per parent node
pipeline.fit(X_train, Y_train)

# Predict
predictions = pipeline.predict(X_test)
```

--------------------------------

### Import LocalClassifierPerParentNode

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/local_classifier.md

Import the LocalClassifierPerParentNode class and RandomForestClassifier for use in local hierarchical classification.

```python
from hiclass import LocalClassifierPerParentNode
from sklearn.ensemble import RandomForestClassifier
```

--------------------------------

### Create Conda Virtual Environment

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/get_started/conda.md

Use this command to create a new isolated Python 3.8 environment named 'hiclass-environment'. The '--yes' flag automatically confirms prompts.

```bash
conda create --name hiclass-environment python=3.8 --yes
```

--------------------------------

### Calculate F1 Score with Different Averaging Methods

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/utilities.md

Demonstrates how to compute the F1 score using 'micro' and 'macro' averaging. Ensure y_true and y_pred are properly formatted hierarchical labels.

```python
>>> import numpy as np
>>> from hiclass.metrics import f1
>>> y_true = [[0, 1, 2], [3, 4, 5]]
>>> y_pred = [[0, 1, 2], [6, 7, 8]]
>>> f1(y_true, y_pred, average='micro')
0.5
>>> f1(y_true, y_pred, average='macro')
0.5
```

--------------------------------

### fit(X, y, sample_weight=None)

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Fits a local classifier per node using the provided training data and optional sample weights.

```APIDOC
## fit(X, y, sample_weight=None)

### Description
Fit a local classifier per node.

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Parameters
* **X** (*{array-like*, *sparse matrix}* *of* *shape* *(**n_samples*, *n_features*) – The training input samples. Internally, its dtype will be converted to `dtype=np.float32`. If a sparse matrix is provided, it will be converted into a sparse `csr_matrix`.
* **y** (*array-like* *of* *shape* *(**n_samples*, *n_levels*) – The target values, i.e., hierarchical class labels for classification.
* **sample_weight** (*array-like* *of* *shape* *(**n_samples*,)* *,* *default=None*) – Array of weights that are assigned to individual samples. If not provided, then each sample is given unit weight.

### Returns
* **self** – Fitted estimator.

### Return type
object
```

--------------------------------

### Snakemake Cluster Job Submission with Slurm

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/benchmarks/consumer_complaints/README.md

This command submits a Snakemake pipeline to a Slurm cluster. It configures both the `srun` command for Snakemake execution and the parameters for individual jobs submitted to Slurm.

```shell
srun \
--account <name> \
--mem=<memory-snakemake>G \
--cpus-per-task=<cpus> \
--time=<days>-<hours>:<minutes>:<seconds> \
--partition <partition> \
snakemake \
--keep-going \
--printshellcmds \
--reason \
--use-conda \
--cores <cores> \
--resources mem_gb=<total-memory-for-all-jobs> \
--restart-times <restart> \
--jobs <jobs> \
--cluster \
"sbatch \
--account <account> \
--partition <partition> \
--mem=<memory-per-job>G \
--cpus-per-task=<cpus-per-job> \
--time=<days>-<hours>:<minutes>:<seconds>"
```

--------------------------------

### Handle Zero Division in F1 Score Calculation

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/utilities.md

Shows how to manage cases where the F1 score is ill-defined due to zero division. The `zero_division` parameter can be set to 0.0, 1.0, or np.nan to control the output.

```python
>>> # zero division
>>> y_true = [[0, 1], [2, 3]]
>>> y_pred = [[4, 5], [6, 7]]
>>> f1(y_true, y_pred)
F-score is ill-defined and being set to 0.0. Use `zero_division` parameter to control this behavior.
0.0
>>> f1(y_true, y_pred, zero_division=1.0)
1.0
>>> f1(y_true, y_pred, zero_division=np.nan)
nan
```

--------------------------------

### FlatClassifier

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Initializes a FlatClassifier. This classifier flattens the hierarchy internally and uses a provided scikit-learn estimator for classification.

```APIDOC
## class FlatClassifier.FlatClassifier(local_classifier: BaseEstimator = LogisticRegression())

### Description
A flat classifier utility that accepts as input a hierarchy and flattens it internally.

### Parameters
#### `__init__` Parameters
- **local_classifier** (BaseEstimator, default=LogisticRegression) - The scikit-learn model used for the flat classification. Needs to have fit, predict and clone methods.
```

--------------------------------

### FlatClassifier.fit()

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/index.md

Fits the FlatClassifier model to the training data. This method trains the classifier using the provided input features and target labels.

```APIDOC
## FlatClassifier.fit()

### Description
Fits the FlatClassifier model to the training data.

### Method
fit

### Parameters
(No parameters explicitly documented in the source for fit)
```

--------------------------------

### set_fit_request

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Configures metadata routing for the `fit` method.

```APIDOC
## set_fit_request(, sample_weight: bool | None | str = '$UNCHANGED$') -> [LocalClassifierPerParentNode](#LocalClassifierPerParentNode.LocalClassifierPerParentNode)

### Description
Configure whether metadata should be requested to be passed to the `fit` method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with `enable_metadata_routing=True` (see `sklearn.set_config()`).
Please check the User Guide on how the routing
mechanism works.

The options for each parameter are:

- `True`: metadata is requested, and passed to `fit` if provided. The request is ignored if metadata is not provided.
- `False`: metadata is not requested and the meta-estimator will not pass it to `fit`.
- `None`: metadata is not requested, and the meta-estimator will raise an error if the user provides it.
- `str`: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (`sklearn.utils.metadata_routing.UNCHANGED`) retains the existing request. This allows you to change the request for some parameters and not others.

#### Versionadded
Added in version 1.3.

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Parameters
* **sample_weight** (*str*, *True*, *False*, or *None*, *default=sklearn.utils.metadata_routing.UNCHANGED*) – Metadata routing for `sample_weight` parameter in `fit`.

### Returns
**self** – The updated object.

### Return type
object
```

--------------------------------

### set_params

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Sets the parameters of the estimator.

```APIDOC
## set_params(**params)

### Description
Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as `Pipeline`). The latter have parameters of the form `<component>__<parameter>` so that it’s possible to update each component of a nested object.

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Parameters
* **
**params** (*dict*) – Estimator parameters.

### Returns
**self** – Estimator instance.

### Return type
estimator instance
```

--------------------------------

### get_params

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Retrieves the parameters of the estimator, optionally including parameters of contained sub-estimators. This is useful for inspecting the configuration of the classifier.

```APIDOC
## get_params(deep=True)

### Description
Get parameters for this estimator.

### Method
GET (implied)

### Parameters
#### Query Parameters
- **deep** (bool) - Optional - If True, will return the parameters for this estimator and contained subobjects that are estimators.

### Returns
- **params** (dict) - Parameter names mapped to their values.

### Return type
dict
```

--------------------------------

### calibrate

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Fits a local calibrator per node using the provided data.

```APIDOC
## calibrate(X, y)

### Description
Fit a local calibrator per node.

### Parameters
* **X** (array-like or sparse matrix of shape (n_samples, n_features)) – The calibration input samples.
* **y** (array-like of shape (n_samples, n_levels)) – The target values, i.e., hierarchical class labels for classification.

### Returns
self – Calibrated estimator.

### Return type
object
```

--------------------------------

### Build Scikit-learn Pipeline with HiClass

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/README.md

Construct a scikit-learn pipeline that includes text vectorization and a HiClass LocalClassifierPerParentNode. This pipeline is designed to handle sparse matrices efficiently.

```python
# Use logistic regression classifiers for every parent node
lr = LogisticRegression()
pipeline = Pipeline([
    ('count', CountVectorizer()),
    ('tfidf', TfidfTransformer()),
    ('lcppn', LocalClassifierPerParentNode(local_classifier=lr)),
])
```

--------------------------------

### set_params

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Sets the parameters of this estimator. This method works on simple estimators as well as on nested objects.

```APIDOC
## set_params(**params)

### Description
Set the parameters of this estimator.

### Parameters
* **
**params** (dict) – Estimator parameters.

### Returns
self – Estimator instance.

### Return type
estimator instance
```

--------------------------------

### get_metadata_routing()

Source: https://github.com/scikit-learn-contrib/hiclass/blob/main/docs/source/api/classifiers.md

Retrieves the metadata routing configuration for the estimator.

```APIDOC
## get_metadata_routing()

### Description
Get metadata routing of this object.

Please check User Guide on how the routing
mechanism works.

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Returns
* **routing** – A `MetadataRequest` encapsulating routing information.

### Return type
MetadataRequest
```