### Install Development Dependencies

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

Install all necessary development dependencies, including test, examples, and documentation packages, using the provided make command.

```bash
make install-dev
```

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

### Development Setup and Workflow

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

This snippet outlines the essential steps for setting up a development environment, including cloning the repository, creating a virtual environment, installing dependencies, formatting code, running checks, and testing.

```bash
git clone git@github.com:your-username/auto-sklearn.git
cd auto-sklearn
git checkout -b my_new_branch development

# Initialize autosklearn/automl_common submodule
git submodule update --init --recursive

# Create a virtual environment and activate it so there are no package
# conflicts
python -m venv my-virtual-env
source my-virtual-env/bin/activate

make install-dev
# pip install -e "[test,docs,examples]" # To manually install things

# Edit files...

# Format code
make format

# Check for any issues
make check

# ... fix any issues

# If you changed documentation:
# This will generate all documentation and check links
make doc
make links
make examples  # mainly needed if you modified some examples

# ... fix any issues

# If you edited any code
# Check out pytest --help if you want to only run specific tests
pytest

# ... fix any issues

# If you want to run pre-commit, the formatting checks we run on github
pre-commit install
pre-commit run --all-files

# ... fix any issues

# Check the changed files
git status

# Add the changes
git add {changed files}
git commit -m "Meaningful as you can make it message"

# Push back to your fork
git push --set-upstream origin my_new_branch
```

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

### Generate Example Documentation

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

Process Python files in the 'examples' folder to generate HTML output showcasing code and its results using sphinx-gallery.

```bash
make examples
```

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

### Manually Install Submodules

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

If submodules were not cloned initially or need manual installation, use this command.

```bash
git submodule update --init --recursive
```

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

### Manually Install Editable Package with Extras

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

Install the current package in editable mode with optional dependencies for testing, examples, and documentation. Use quotes if your shell requires it.

```bash
pip install -e .[test,examples,doc]
```

```bash
pip install -e " .[test,examples,doc]"
```

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

### Install build tools and SWIG on Ubuntu

Source: https://github.com/automl/auto-sklearn/blob/development/doc/installation.rst

Install necessary build tools (g++, make) and SWIG on Ubuntu systems to ensure a smooth installation of auto-sklearn and its dependencies.

```bash
sudo apt-get install build-essential swig python3-dev
```

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

### Install auto-sklearn using pip

Source: https://github.com/automl/auto-sklearn/blob/development/doc/installation.rst

Install the auto-sklearn package using pip. This is the standard installation method.

```bash
pip3 install auto-sklearn
```

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

### Install auto-sklearn in editable mode from source

Source: https://github.com/automl/auto-sklearn/blob/development/doc/installation.rst

Install auto-sklearn in editable mode from the cloned source code, including optional dependencies for testing and documentation.

```bash
pip install -e ".[test,doc,examples]"
```

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

### Create Virtual Environment

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

Set up a Python virtual environment to manage project dependencies separately. This example creates an environment named 'my-virtual-env'.

```bash
python -m venv my-virtual-env
source my-virtual-env/bin/activate
```

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

### Install Pre-commit Hook

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

Set up the pre-commit framework to automatically run code checks before each commit. Assumes `make install-dev` has been run.

```bash
pre-commit install
```

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

### Start Jupyter Notebook in Docker

Source: https://github.com/automl/auto-sklearn/blob/development/doc/installation.rst

Run a Docker container to start a Jupyter notebook server, mapping the current directory and exposing port 8888.

```bash
docker run -it -v ${PWD}:/opt/nb -p 8888:8888 mfeurer/auto-sklearn:master /bin/bash -c "mkdir -p /opt/nb && jupyter notebook --notebook-dir=/opt/nb --ip='0.0.0.0' --port=8888 --no-browser --allow-root"
```

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

### Start Interactive Docker Session

Source: https://github.com/automl/auto-sklearn/blob/development/doc/installation.rst

Launch an interactive terminal session within the Auto-Sklearn Docker container.

```bash
docker run -it mfeurer/auto-sklearn:master
```

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

### Install GCC and SWIG with Conda

Source: https://github.com/automl/auto-sklearn/blob/development/doc/installation.rst

Install the Conda-shipped GCC compiler and SWIG on Linux distributions to resolve potential compiler version incompatibilities when using Anaconda.

```bash
conda install gxx_linux-64 gcc_linux-64 swig
```

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

### Initialize AutoSklearnClassifier

Source: https://github.com/automl/auto-sklearn/blob/development/doc/manual.rst

This snippet shows how to initialize an AutoSklearnClassifier. Ensure you have the autosklearn library installed and imported.

```python
import autosklearn.classification
automl = autosklearn.classification.AutoSklearnClassifier()
automl.fit(X_train, y_train)
```

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

### Initialize git submodules after cloning

Source: https://github.com/automl/auto-sklearn/blob/development/doc/installation.rst

Update and initialize git submodules if the initial clone did not include them recursively. This is necessary for source installations.

```bash
git clone git@github.com:automl/auto-sklearn.git
cd auto-sklearn
git submodule update --init --recursive
```

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

### Configure Vanilla Auto-Sklearn Classifier

Source: https://github.com/automl/auto-sklearn/blob/development/doc/faq.rst

Use this configuration to obtain the vanilla auto-sklearn setup. Set `ensemble_class` to `autosklearn.ensembles.SingleBest` and `initial_configurations_via_metalearning` to 0. This ensures the best model is chosen based on the validation set and SMAC is used for hyperparameter configuration.

```python
import autosklearn.classification
import autosklearn.ensembles
automl = autosklearn.classification.AutoSklearnClassifier(
    ensemble_class=autosklearn.ensembles.SingleBest,
    initial_configurations_via_metalearning=0
)
```

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

### Create Working Directory

Source: https://github.com/automl/auto-sklearn/blob/development/scripts/readme.md

Sets up a directory to store metadata and output. Ensure the directory path is correctly specified.

```bash
working_directory=~/auto-sklearn-metadata/001
mkdir -p $working_directory
```

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

### Install auto-sklearn with Conda

Source: https://github.com/automl/auto-sklearn/blob/development/doc/installation.rst

Install auto-sklearn using Conda after enabling the conda-forge channel. Ensure your conda version is at least 4.9.

```bash
conda install auto-sklearn
```

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

### View Generated Documentation

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

Open the generated HTML documentation in a web browser. Ensure documentation is built before attempting to view.

```bash
# Firefox
firefox ./doc/build/html/index.html
```

```bash
# Using your default browser
xdg-open ./doc/build/html/index.html
```

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

### Generate Documentation with Sphinx

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

Build the project's HTML documentation using Sphinx. Ensure all documentation is up-to-date and correctly formatted.

```bash
make doc
```

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

### Check Documentation Links

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

Verify that all links within the generated documentation are valid and point to correct destinations.

```bash
make links
```

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

### Add conda-forge channel

Source: https://github.com/automl/auto-sklearn/blob/development/doc/installation.rst

Configure Conda to use the conda-forge channel, which is necessary for installing auto-sklearn via Anaconda.

```bash
conda config --add channels conda-forge
```

```bash
conda config --set channel_priority strict
```

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

### Create ASlib Files

Source: https://github.com/automl/auto-sklearn/blob/development/scripts/readme.md

Generates ASlib (Algorithm Selection Library) files, which are used for algorithm selection tasks.

```bash
python3 04_create_aslib_files.py --working-directory $working_directory --task-type $task_type
```

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

### Create and Checkout New Branch

Source: https://github.com/automl/auto-sklearn/blob/development/CONTRIBUTING.md

Navigate into the cloned repository and create a new branch based on the 'development' branch for your changes.

```bash
cd auto-sklearn
git checkout -b my_new_branch development
```

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

### Create Commands File

Source: https://github.com/automl/auto-sklearn/blob/development/scripts/2015_nips_paper/Readme.md

Generates the commands.txt file needed to run the experiment. Modify the script to change runtime or tasks.

```bash
cd setup
bash create_commands.sh
```

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

### AutoSklearn Classifier with Dataset Loading and Evaluation

Source: https://github.com/automl/auto-sklearn/blob/development/doc/index.rst

This example demonstrates a more complete usage of AutoSklearnClassifier, including loading a dataset, splitting it into training and testing sets, fitting the classifier, making predictions, and evaluating accuracy. It is intended to run for approximately one hour and achieve an accuracy above 0.98.

```python
import autosklearn.classification
import sklearn.model_selection
import sklearn.datasets
import sklearn.metrics

if __name__ == "__main__":
    X, y = sklearn.datasets.load_digits(return_X_y=True)
    X_train, X_test, y_train, y_test = \
        sklearn.model_selection.train_test_split(X, y, random_state=1)
    automl = autosklearn.classification.AutoSklearnClassifier()
    automl.fit(X_train, y_train)
    y_hat = automl.predict(X_test)
    print("Accuracy score", sklearn.metrics.accuracy_score(y_test, y_hat))
```

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

### Configure Vanilla Auto-Sklearn

Source: https://github.com/automl/auto-sklearn/blob/development/doc/manual.rst

Set these parameters to replicate the 'vanilla auto-sklearn' configuration as described in the 'Efficient and Robust Automated Machine Learning' paper. This configuration uses an ensemble size of 1, disables meta-learning for initial configurations, and disallows string features.

```python
import autosklearn.classification
automl = autosklearn.classification.AutoSklearnClassifier(
    ensemble_size=1,
    initial_configurations_via_metalearning=0,
    allow_string_features=False,
)
```

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

### Execute Experiment Commands

Source: https://github.com/automl/auto-sklearn/blob/development/scripts/2015_nips_paper/Readme.md

Runs the commands listed in commands.txt for model fitting and trajectory creation. Commands can be run in parallel.

```bash
cd run
bash run_commands.sh
```