### Compare Experiment Setup

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html?q=

Compares the setup configuration between two experiments.

```python
compare_setup_with(experiment_to_compare_with: Experiment) -> dict[str, Table]
```

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

### Install h2osteam library

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/h2oai-cloud/dai-steam.html

Install the required Python package from the provided S3 URL.

```bash
pip install https://enterprise-steam.s3.amazonaws.com/release/1.9.4/python/h2osteam-1.9.4-py2.py3-none-any.whl
```

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

### Get Experiment Summary

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html?q=

Retrieves a brief overview of the experiment setup and results.

```python
summary: str | None
```

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

### Create an experiment

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Example demonstrating how to initialize a client, create datasets, and launch a classification experiment with specific settings.

```python
client = driverlessai.Client(address='http://localhost:12345',
username='py', password='py')
train_dataset = client.datasets.create(
    data="s3://h2o-public-test-data/smalldata/airlines/AirlinesTrain.csv",
    data_source="s3",
    name="Airlines-data",
    description="My airline dataset",
)
test_dataset = client.datasets.create(
    data="s3://h2o-public-test-data/smalldata/airlines/AirlinesTest.csv",
    data_source="s3",
    name="Airlines-data",
    description="My airline dataset",
)
experiment = client.experiments.create(
    dataset=train_dataset,
    target_col=train_dataset.columns[-1],
    test_dataset=test_dataset,
    task='classification',
    scorer='F1',
    accuracy=5,
    time=5,
    interpretability=5,
    name='demo_day_experiment'
)
```

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

### Configure and Use OAuth2TokenProvider

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/token_providers.html

Example of initializing the provider with credentials and passing it to the Driverless AI client.

```python
# Create a token provider with a refresh token from the Driverless AI web UI
token_provider = driverlessai.token_providers.OAuth2TokenProvider(
    refresh_token="eyJhbGciOiJIUzI1N...",
    client_id="python_client",
    token_endpoint_url="https://keycloak-server/auth/realms/driverlessai/protocol/openid-connect/token",
    token_introspection_url="https://keycloak-server/auth/realms/driverlessai/protocol/openid-connect/token/introspect"
)

# Use the token provider to get authorization to connect to the server
client = driverlessai.Client(
    address="https://localhost:12345",
    token_provider=token_provider.ensure_fresh_token
)
```

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

### get

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html?q=

Initializes an Interpretation object by its key.

```APIDOC
## get(key)

### Description
Initializes an Interpretation object but does not request information from the server. This is useful for populating lists without making multiple network calls.

### Parameters
- **key** (str) - Required - Driverless AI server's unique ID for the MLI interpretation.
```

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

### Install H2O Driverless AI

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/getting-started.html

Install the package using pip or conda package managers.

```bash
pip install driverlessai
```

```bash
conda install -c h2oai driverlessai
```

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

### Update Experiment Tags Example

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html?q=

Demonstrates creating a project, linking an experiment, and clearing all existing tags from that experiment.

```python
project = client.projects.create(
    name="test project",
    description="project description",
)
project.link_experiment(experiment)
project.update_experiment_tags(experiment, [])
```

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

### get

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Initializes an Interpretation object by key without requesting information from the server.

```APIDOC
## get(key: str)

### Description
Initializes an Interpretation object but does not request information from the server. This is useful for populating lists without making multiple network calls.

### Parameters
- **key** (str) - Required - Driverless AI server's unique ID for the MLI interpretation.
```

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

### Get Interpretation Settings

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Returns the configuration settings for the interpretation.

```python
settings: dict[str, Any]
```

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

### get

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Returns an Experiment object corresponding to an experiment on the Driverless AI server.

```APIDOC
## get(key)

### Description
Returns an Experiment object corresponding to an experiment on the Driverless AI server. If the experiment only exists on H2O.ai Storage, it will be imported to the server first.

### Parameters
- **key** (str) - Required - Driverless AI server's unique ID for the experiment.
```

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

### create_async(data, data_source='upload', data_source_config=None, force=False, name=None, description=None)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html?q=

Launches the creation of a dataset in the Driverless AI server.

```APIDOC
## create_async(data, data_source='upload', data_source_config=None, force=False, name=None, description=None)

### Description
Launches the creation of a dataset in the Driverless AI server.

### Parameters
- **data** (str | DataFrame) - Required - Path to the data file(s), or path to a directory, or a SQL query, or a pandas Dataframe.
- **data_source** (str) - Optional - Name of the connector to import data from.
- **data_source_config** (dict[str, str]) - Optional - A dictionary of configuration options for advanced connectors.
- **force** (bool) - Optional - Whether to create the dataset even when a dataset already exists with the same name.
- **name** (str) - Optional - Name for the created dataset.
- **description** (str | None) - Optional - Description for the created dataset.

### Returns
- **DatasetJob** - Started the dataset job.
```

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

### Create a New Project

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/projects/create-a-project.html

Create a project with a specified name and description.

```python
project = dai.projects.create(
    name="Example", 
    description="For Driverless AI Python client documenation."
)
```

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

### get_by_name

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Get the experiment specified by the name.

```APIDOC
## get_by_name(name)

### Description
Get the experiment specified by the name.

### Parameters
- **name** (str) - Required - Name of the experiment.

### Returns
- **Experiment | None** - The experiment with the name if exists, otherwise None.
```

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

### Create an Experiment

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/getting-started.html

Preview an experiment configuration using a previously created dataset.

```python
experiment = client.experiments.preview(
    train_dataset=dataset,
    target_column="C5",
    task="classification",
    name="iris-experiment",
)
```

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

### Retrain Experiment

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/experiments/new-model-with-same-parameters.html

Start a new experiment using the parameters of an existing one, with optional overrides for settings like accuracy.

```python
ex.retrain(accuracy=5)
```

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

### Access Documentation and GUI

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/server.html

Retrieve URLs for the server documentation or web interface.

```python
docs(search: str = None) -> Hyperlink
```

```python
# Search the DAI docs for "experiments"
client.server.docs(search="experiments")
```

```python
gui() -> Hyperlink
```

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

### get_previous_predictions

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Get all previous predictions of the current experiment.

```APIDOC
## get_previous_predictions()

### Description
Get all previous predictions of the current experiment. Requires Driverless AI server 1.11.0 or higher.
```

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

### get_linked_projects

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Get all the projects that the current experiment belongs to.

```APIDOC
## get_linked_projects()

### Description
Get all the projects that the current experiment belongs to. Requires Driverless AI server 1.10.5 or higher.
```

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

### create_async(experiment, **config_overrides)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/autodoc.html?q=

Launches the creation of a new AutoDoc asynchronously.

```APIDOC
## create_async(experiment, **config_overrides)

### Description
Launches creation of a new AutoDoc and returns a job object to monitor progress.

### Parameters
- **experiment** (Experiment) - Required - The experiment to generate the document for.
- **config_overrides** (Any) - Optional - Configuration overrides for AutoDoc generation.

### Returns
- **AutoDocJob** - The started AutoDoc job.
```

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

### create_async(data, data_source, data_source_config, force, name, description)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html

Launches the creation of a dataset in the Driverless AI server asynchronously.

```APIDOC
## create_async(data, data_source, data_source_config, force, name, description)

### Description
Launches the creation of a dataset in the Driverless AI server.

### Parameters
- **data** (str | DataFrame) - Required - Path to the data file(s), directory, SQL query, or a pandas Dataframe.
- **data_source** (str) - Optional (default: 'upload') - Name of the connector to import data from.
- **data_source_config** (dict[str, str]) - Optional (default: None) - Configuration options for advanced connectors.
- **force** (bool) - Optional (default: False) - Whether to create the dataset even when a dataset already exists with the same name.
- **name** (str) - Optional (default: None) - Name for the created dataset.
- **description** (str | None) - Optional (default: None) - Description for the created dataset.

### Returns
- **DatasetJob** - The started dataset job.
```

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

### variable_importance(...)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Get variable importance of an iteration in a Table.

```APIDOC
## variable_importance(iteration: int = None, model_index: int = None) -> Table | None

### Description
Get variable importance of an iteration in a Table.

### Parameters
- **iteration** (int) - Optional (default: None) - Zero-based index of the iteration of the experiment.
- **model_index** (int) - Optional (default: None) - The zero-based index of model that was generated in a particular iteration.
```

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

### create_async

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Launches the creation of an experiment in the Driverless AI server and returns an experiment object to track the experiment status.

```APIDOC
## create_async(train_dataset, target_column, task, force=False, name=None, description=None, **kwargs)

### Description
Launches the creation of an experiment in the Driverless AI server and returns an experiment object to track the experiment status.

### Parameters
- **train_dataset** (Dataset) - Required - Dataset object.
- **target_column** (str | None) - Required - The name of column in train_dataset (pass None if task is 'unsupervised').
- **task** (str) - Required - One of 'regression', 'classification', or 'unsupervised'.
- **force** (bool) - Optional - Create a new experiment even if experiment with same name already exists.
- **name** (str) - Optional - The display name for the experiment.
- **description** (str | None) - Optional - Description of the experiment.
```

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

### Get Column Summaries

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/dataset-column-details.html

Generate summaries for all columns in the dataset.

```python
dataset.column_summaries()
```

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

### Import Dataset Using Server-Configured MinIO Credentials

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/create/import-dataset-with-minio-connector.html

Create a dataset from MinIO using credentials already configured on the Driverless AI server.

```python
dataset_from_minio = dai.datasets.create(
    data_source="minio",
    name="train_data",
    data="h2oaidev/cc_train.csv",
    force=True,
)

dataset_from_minio.head()
```

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

### Get Interpretation Experiment

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Retrieves the experiment associated with the interpretation.

```python
experiment: Experiment | None
```

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

### Get Interpretation Dataset

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Retrieves the dataset associated with the interpretation.

```python
dataset: Dataset | None
```

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

### create_async(experiment, **config_overrides)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/autodoc.html

Launches an asynchronous job to create a new AutoDoc.

```APIDOC
## create_async(experiment, **config_overrides)

### Description
Launches creation of a new AutoDoc as an asynchronous job.

### Parameters
- **experiment** (Experiment) - Required - The experiment to generate the document for.
- **config_overrides** (Any) - Optional - Configuration overrides for AutoDoc generation.

### Returns
- **AutoDocJob** - The started AutoDoc job.
```

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

### create(name: str, description: str | None = None, force: bool = False) -> Project

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html?q=

Creates a new project in the Driverless AI server.

```APIDOC
## create(name: str, description: str | None = None, force: bool = False) -> Project

### Description
Creates a project in the Driverless AI server.

### Parameters
- **name** (str) - Required - Display name for project.
- **description** (str | None) - Optional - Description of project.
- **force** (bool) - Optional - Whether to create the project even when a project already exists with the same name.

### Returns
- **Project** - Created project.
```

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

### Create a Dataset via JDBC

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html

Demonstrates creating a dataset using a JDBC connection configuration.

```python
dataset = client.datasets.create(
    data="SELECT * FROM creditcard",
    data_source="jdbc",
    data_source_config=dict(
        jdbc_jar="/opt/jdbc-drivers/mysql/mysql-connector-java-8.0.23.jar",
        jdbc_driver="com.mysql.cj.jdbc.Driver",
        jdbc_url="jdbc:mysql://localhost:3306/datasets",
        jdbc_username="root",
        jdbc_password="root"
    ),
    name="creditcard",
    description="Sample creditcard data",
    force=True,
)
```

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

### Get Interpretation Run Duration

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Returns the duration of the interpretation run in seconds.

```python
run_duration: float | None
```

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

### Create a project

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html?q=

Creates a new project in the Driverless AI server. Use the force parameter to overwrite existing projects with the same name.

```python
create(
    name: str, description: str | None = None, force: bool = False
) -> Project
```

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

### get(key)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html

Retrieves a dataset from the Driverless AI server by its unique ID.

```APIDOC
## get(key)

### Description
Retrieves a dataset in the Driverless AI server. If the dataset only exists in H2O Storage then it will be imported into the server first.

### Parameters
- **key** (str) - Required - The unique ID of the dataset.

### Returns
- **Dataset** - The dataset corresponding to the key.
```

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

### create_async(dataset: Dataset) -> VisualizationJob

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/autoviz.html

Launches the creation of a dataset visualization.

```APIDOC
## create_async(dataset: Dataset) -> VisualizationJob

### Description
Launches the creation of a dataset visualization.

### Parameters
- **dataset** (Dataset) - Required - The dataset to be visualized.

### Returns
- **VisualizationJob** - Started visualization job.
```

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

### Get Experiment Tags

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html?q=

Retrieve tags for a specific experiment linked to the project.

```python
get_experiment_tags(experiment: Experiment) -> list[str]
```

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

### Client(address, username=None, password=None, token_provider=None, verify=True, backend_version_override=None, authentication_method=None, auto_fetch_client=None)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/core.html

Initializes a connection to a Driverless AI server. This constructor handles authentication and configuration for the session.

```APIDOC
## Client Constructor

### Description
Connect with a Driverless AI server and interact with it.

### Parameters
- **address** (str) - Required - Full URL to the Driverless AI server to connect with.
- **username** (str | None) - Optional - Username to authenticate with the server.
- **password** (str | None) - Optional - Password to authenticate with the server.
- **token_provider** (Callable[[], str] | None) - Optional - A function that returns a token to authenticate with the server.
- **verify** (bool | str) - Optional - Enable or disable SSL certificate verification or provide a path to a CA bundle.
- **backend_version_override** (str | None) - Optional - Disables server version detection and uses the specified server version.
- **authentication_method** (str | None) - Optional - The authentication method used to connect to the server.
- **auto_fetch_client** (bool | None) - Optional - Allows the client to download the matching h2oai_client wheel from the server.
```

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

### create(data, data_source, data_source_config, force, name, description)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html

Creates a new dataset in the Driverless AI server.

```APIDOC
## create(data, data_source, data_source_config, force, name, description)

### Description
Creates a dataset in the Driverless AI server.

### Parameters
- **data** (str | DataFrame) - Required - Path to the data file(s), directory, SQL query, or a pandas Dataframe.
- **data_source** (str) - Optional (default: 'upload') - Name of the connector to import data from.
- **data_source_config** (dict[str, str]) - Optional (default: None) - Configuration options for advanced connectors.
- **force** (bool) - Optional (default: False) - Whether to create the dataset even when a dataset already exists with the same name.
- **name** (str) - Optional (default: None) - Name for the created dataset.
- **description** (str | None) - Optional (default: None) - Description for the created dataset.

### Returns
- **Dataset** - The created dataset object.
```

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

### get(key: str) -> Project

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html?q=

Retrieves a specific project by its unique ID.

```APIDOC
## get(key: str) -> Project

### Description
Retrieves a project in the Driverless AI server.

### Parameters
- **key** (str) - Required - The unique ID of the project.

### Returns
- **Project** - The project corresponding to the key.
```

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

### Retrieve Diagnostic Scores

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/model-diagnostics.html

Get the performance metrics and scores calculated for a model diagnostic.

```python
model_diagnostic.scores
```

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

### create_async

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Launches the creation of an MLI interpretation in the Driverless AI server asynchronously.

```APIDOC
## create_async(experiment=None, dataset=None, name=None, force=False, validate_settings=True, **kwargs)

### Description
Launches the creation of an MLI interpretation in the Driverless AI server.

### Parameters
- **experiment** (Experiment | None) - Optional - The experiment to interpret.
- **dataset** (Dataset | None) - Optional - The dataset to use for the interpretation.
- **name** (str | None) - Optional - The display name for the interpretation.
- **force** (bool) - Optional - Create the new interpretation even if the interpretation with the same name already exists.
- **validate_settings** (bool) - Optional - Whether to validate settings.

### Example
interpretation = client.mli.create_async(experiment=my_experiment, name="My MLI Interpretation", target_column="target", prediction_column="prediction")
print(f"Interpretation created with key: {interpretation.key}")
```

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

### Get Experiment Size

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html?q=

Retrieves the total size of experiment files in bytes on the server.

```python
size: int
```

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

### Initialize Driverless AI Client

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/create/import-dataset-with-databricks-connector.html

Connect to the Driverless AI server using credentials.

```python
import driverlessai

dai = driverlessai.Client(address='http://localhost:12345', username="py", password="py")
```

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

### create_async(recipe: str, username: str | None = None, password: str | None = None) -> RecipeJob

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/recipes.html?q=

Launches the creation of a custom recipe in the Driverless AI server asynchronously.

```APIDOC
## create_async(recipe: str, username: str | None = None, password: str | None = None) -> RecipeJob

### Description
Launches the creation of a custom recipe in the Driverless AI server.

### Parameters
- **recipe** (str) - Required - The path or URL to the recipe.
- **username** (str | None) - Optional - Username to use when connecting to BitBucket.
- **password** (str | None) - Optional - Password to use when connecting to BitBucket.

### Returns
- **RecipeJob** - The custom recipe job.

### Example
```python
recipe_job = client.recipes.create_async(
    recipe="https://github.com/h2oai/driverlessai-recipes/blob/master/scorers/regression/explained_variance.py"
)
```
```

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

### Interpretation.gui

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Gets the full URL for the interpretation's page in the Driverless AI server.

```APIDOC
## gui() -> Hyperlink

### Description
Gets the full URL for the interpretation's page in the Driverless AI server.
```

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

### Initialize Driverless AI client

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/h2oai-cloud/dai-steam.html?q=

Create a client instance to interact with Driverless AI services managed by Steam.

```python
# Get steam driverlessai client
dai_steam_client = h2osteam.clients.DriverlessClient()
```

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

### Get Interpretation Creation Timestamp

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Returns the POSIX timestamp indicating when the interpretation was created.

```python
creation_timestamp: float
```

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

### get(key: str) -> ModelDiagnostic

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/model_diagnostics.html

Retrieves a specific model diagnostic by its unique key.

```APIDOC
## get(key: str) -> ModelDiagnostic

### Description
Retrieves a model diagnostic in the Driverless AI server.

### Parameters
- **key** (str) - Required - The unique ID of the model diagnostic.

### Returns
- **ModelDiagnostic** - The model diagnostic corresponding to the key.
```

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

### get(key: str) -> Visualization

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/autoviz.html

Retrieves a dataset visualization in the Driverless AI server.

```APIDOC
## get(key: str) -> Visualization

### Description
Retrieves a dataset visualization in the Driverless AI server.

### Parameters
- **key** (str) - Required - The unique ID of the visualization.

### Returns
- **Visualization** - The visualization corresponding to the key.
```

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

### Create a dataset visualization asynchronously

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/autoviz.html

Launches the creation of a dataset visualization and returns a job object.

```python
create_async(dataset: Dataset) -> VisualizationJob
```

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

### Import Dataset via Configuration Dictionary

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/create/import-dataset-with-delta-table-connector.html

Create a dataset by providing the table path through the data_source_config argument.

```python
dataset_from_delta_table = dai.datasets.create(
    data="SELECT * FROM airlines_train",
    data_source="delta_table",
    data_source_config=dict(
        table_path="abfss://<container-name>@<storage-account-name>.dfs.core.windows.net/path/to/airlines_train/",  
    ),
    name="From Delta Table user defined config",
    force=True
)

dataset_from_delta_table.head()
```

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

### Get Confusion Matrix

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html?q=

Retrieves the confusion matrix as a 2D list, optionally specifying a threshold.

```python
confusion_matrix(threshold: float = None) -> list[list[Any]] | None

```

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

### Create a Dataset

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/getting-started.html

Import a dataset into the client from a specified data source.

```python
dataset = client.datasets.create(
    data="s3://h2o-public-test-data/smalldata/iris/iris.csv", 
    data_source="s3", 
    name="iris.csv",
)
```

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

### Get Interpretation Status

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Returns the current status of the interpretation job, with optional verbosity levels.

```python
status(verbose: int = 0) -> str
```

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

### Get Project GUI URL

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html

Retrieve the URL for the project details page in the web interface.

```python
gui() -> Hyperlink

```

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

### Import Dataset Using Server Credentials

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/create/import-dataset-with-s3-connector.html

Create a dataset from an S3 path using the credentials already configured on the Driverless AI server.

```python
dataset_from_s3 = dai.datasets.create(
    data_source="s3",
    name="credit-cards-no-creds",
    data="s3://h2o-datasets/dai/CreditCard_Cat-train.csv",
    force=True,
)

dataset_from_s3.head()
```

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

### Create an asynchronous experiment

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Launches an experiment on the server and returns an object to track its status. Expert settings can be passed as keyword arguments.

```python
client = driverlessai.Client(address='http://localhost:12345',
username='py', password='py')
train_dataset = client.datasets.create(
    data="s3://h2o-public-test-data/smalldata/airlines/AirlinesTrain.csv",
    data_source="s3",
    name="Airlines-data",
    description="My airline dataset",
)
test_dataset = client.datasets.create(
    data="s3://h2o-public-test-data/smalldata/airlines/AirlinesTest.csv",
    data_source="s3",
    name="Airlines-data",
    description="My airline dataset",
)
experiment = client.experiments.create_async(
    dataset=train_dataset,
    target_col=train_dataset.columns[-1],
    test_dataset=test_dataset,
    task='classification',
    scorer='F1',
    accuracy=5,
    time=5,
    interpretability=5,
    name='demo_day_experiment'
)
```

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

### Get Runtime Experiment Insights

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/admin.html?q=

Retrieves system insights for experiments currently running on the server.

```python
get_runtime_experiment_insights(
    user: str = None, start_index: int = 0, count: int = 100
) -> list[RuntimeTaskInsights]
```

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

### ExplainerFrames download method

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Download explainer frames from the Driverless AI server.

```python
download(
    frame_name: str | list[str] = None,
    dst_dir: str = ".",
    file_system: AbstractFileSystem | None = None,
    overwrite: bool = False,
    timeout: float = 30,
) -> dict[str, str]

```

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

### Get DAI Feature Importance Explanation Plot

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Retrieves the original or transformed feature importance plot.

```python
get_plot() -> dict[str, Any]
```

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

### explainer.with_settings()

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/mli/run-specific-explainer.html?q=

Configures settings for a specific explainer.

```APIDOC
## explainer.with_settings(validate_value=True, **kwargs)

### Description
Updates the settings for an explainer. Settings are reset to defaults every time this method is called.

### Parameters
- **validate_value** (bool) - Optional - Enable value validation. Default is True.
- **kwargs** (dict) - Optional - Key-value pairs of settings to update (e.g., sample_size, fast_approx_contribs).
```

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

### View Explainer Settings Documentation

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/mli/run-specific-explainer.html?q=

Access the docstring for the with_settings method to understand how to modify explainer configurations.

```python
orig_shap.with_settings?
```

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

### Get NLP Tokenizer Explanation Plot

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Retrieves a local explanation plot for a specific row number.

```python
get_plot(*, row_number: int | None = None) -> dict[str, Any]
```

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

### Get DatasetJob status

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html

Retrieve a string representation of the current job status with optional verbosity levels.

```python
status(verbose: int = 0) -> str

```

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

### client.server.docs

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/server.html

Returns the full URL to the Driverless AI documentation, with an optional search query.

```APIDOC
## client.server.docs(search: str = None)

### Description
Returns the full URL to the Driverless AI documentation. If a search query is provided, the URL will point to the search results page.

### Parameters
- **search** (str) - Optional - A query to search in docs.

### Response
- **Hyperlink** - The URL to the documentation.
```

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

### Get the AutoViz GUI URL

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/autoviz.html

Returns the full URL to the AutoViz interface in the Driverless AI server.

```python
gui() -> Hyperlink
```

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

### Get Interpretation Explainers

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Returns the list of explainers used in the interpretation. Requires Driverless AI 1.10.5 or higher.

```python
explainers: ExplainerList
```

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

### summarize_async()

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html

Launches the summarization of the dataset using a GPT configured in the Driverless AI server.

```APIDOC
## summarize_async()

### Description
Launches the summarization of the dataset using a GPT configured in the Driverless AI server. Requires Driverless AI server 1.10.6 or higher.

### Returns
- **DatasetSummarizeJob** - Started summarization job.
```

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

### gui

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/deployments.html

Returns the full URL to the Deployments page in the Driverless AI server.

```APIDOC
## gui

### Description
Returns the full URL to the Deployments page in the Driverless AI server.

### Returns
- **Hyperlink** - The full URL to the Deployments page.
```

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

### Filter Explainer Recipes

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/recipes.html?q=

Examples of filtering explainer recipes by their specific properties such as model type or custom status.

```python
# Get all binomial explainer recipes.
binomial_explainers = [
    r for r in client.recipes.explainers.list() if r.for_binomial
]

# Get all multiclass explainer recipes.
multiclass_explainers = [
    r for r in client.recipes.explainers.list() if r.for_multiclass
]

# Get all regression explainer recipes.
regression_explainers = [
    r for r in client.recipes.explainers.list() if r.for_regression
]

# Get all IID explainer recipes.
iid_explainers = [
    r for r in client.recipes.explainers.list() if r.for_iid
]

# Get all time series explainer recipes.
time_series_explainers = [
    r for r in client.recipes.explainers.list() if r.for_timeseries
]

# Get all custom explainer recipes.
custom_explainers = [
    r for r in client.recipes.explainers.list() if r.is_custom
]
```

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

### create(data, data_source='upload', data_source_config=None, force=False, name=None, description=None)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html?q=

Creates a dataset in the Driverless AI server.

```APIDOC
## create(data, data_source='upload', data_source_config=None, force=False, name=None, description=None)

### Description
Creates a dataset in the Driverless AI server.

### Parameters
- **data** (str | DataFrame) - Required - Path to the data file(s), or path to a directory, or a SQL query, or a pandas Dataframe.
- **data_source** (str) - Optional - Name of the connector to import data from.
- **data_source_config** (dict[str, str]) - Optional - A dictionary of configuration options for advanced connectors.
- **force** (bool) - Optional - Whether to create the dataset even when a dataset already exists with the same name.
- **name** (str) - Optional - Name for the created dataset.
- **description** (str | None) - Optional - Description for the created dataset.

### Returns
- **Dataset** - Created dataset.
```

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

### create(train_dataset, target_column, task, force=False, name=None, description=None, **kwargs)

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Creates a new experiment in the Driverless AI server. Users can specify the training dataset, target column, task type, and various expert settings via keyword arguments.

```APIDOC
## create(train_dataset, target_column, task, force=False, name=None, description=None, **kwargs)

### Description
Creates an experiment in the Driverless AI server.

### Parameters
- **train_dataset** (Dataset) - Required - Dataset object.
- **target_column** (str | None) - Required - Name of the column in train_dataset (pass None if task is 'unsupervised').
- **task** (str) - Required - One of 'regression', 'classification', or 'unsupervised'.
- **force** (bool) - Optional - Create a new experiment even if experiment with same name already exists. Default: False.
- **name** (str) - Optional - Display the name of experiment.
- **description** (str) - Optional - Description of the experiment. (only available from Driverless AI version 2.0 onwards)
- **kwargs** (Any) - Optional - Additional expert settings such as accuracy, time, interpretability, scorer, models, transformers, validation_dataset, test_dataset, weight_column, fold_column, time_column, time_groups_columns, unavailable_at_prediction_time_columns, drop_columns, enable_gpus, reproducible, time_period_in_seconds, num_prediction_periods, num_gap_periods, or config_overrides.

### Returns
- **Experiment** - The created experiment object.
```

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

### List and Download Server Logs

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/admin-api-methods.html

Lists available server logs and provides an option to download them. Requires Driverless AI 1.10.5 or later.

```python
# List server logs (Driverless AI 1.10.5+)
logs = client.admin.list_server_logs()
print("Num logs:", len(logs))
if logs:
    log = logs[0]
    print("Path :", log.file_path)
    print("Size (bytes) :", log.size)
    print("Created :", log.created)
    print("Last modified :", log.last_modified)
    # Download the log file to the current directory
    # downloaded_path = log.download(dst_dir=".")
    # print("Downloaded to:", downloaded_path)
```

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

### Convert Explainer Data to pandas DataFrame

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/mli/access-explainer-data.html?q=

Converts explainer data to a pandas DataFrame. Requires the pandas library to be installed.

```python
orig_shapley_data.data_as_pandas()
```

```python
pdp_data.data_as_pandas()
```

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

### List projects

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html?q=

Retrieves a sequence of projects from the server, with optional pagination using start_index and count.

```python
list(start_index: int = 0, count: int = None) -> Sequence[Project]
```

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

### Get Interpretation Parameter Summary

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Retrieves a summary table of the interpretation parameters. Requires Driverless AI 1.10.5 or higher.

```python
parameter_summary() -> Table
```

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

### Get Explanation Plots Mapping

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Returns a mapping of explanation plots for the interpretation. Requires Driverless AI 1.10.5 or higher.

```python
explanation_plots: Mapping[int | str, list[ExplanationPlot]]
```

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

### list()

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/recipes.html?q=

Retrieves a sequence of all available explainer recipes from the Driverless AI server.

```APIDOC
## list()

### Description
Retrieves all explainer recipes available in the Driverless AI server.

### Signature
`list() -> Sequence[ExplainerRecipe]`

### Example
```python
# Get all binomial explainer recipes.
binomial_explainers = [
    r for r in client.recipes.explainers.list() if r.for_binomial
]

# Get all multiclass explainer recipes.
multiclass_explainers = [
    r for r in client.recipes.explainers.list() if r.for_multiclass
]

# Get all regression explainer recipes.
regression_explainers = [
    r for r in client.recipes.explainers.list() if r.for_regression
]

# Get all IID explainer recipes.
iid_explainers = [
    r for r in client.recipes.explainers.list() if r.for_iid
]

# Get all time series explainer recipes.
time_series_explainers = [
    r for r in client.recipes.explainers.list() if r.for_timeseries
]

# Get all custom explainer recipes.
custom_explainers = [
    r for r in client.recipes.explainers.list() if r.is_custom
]
```
```

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

### client.server.gui

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/server.html

Returns the full URL to the Driverless AI server web UI.

```APIDOC
## client.server.gui()

### Description
Returns the full URL to the Driverless AI server web UI.

### Response
- **Hyperlink** - URL to the web UI.
```

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

### Run Batch TTA Forecast by Interval

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html

Executes a TTA forecast by sliding the forecast start forward by a defined runtime_interval.

```python
pred = experiment.predict_batch_tta(
    dataset=ds,
    run_mode="by_interval",
    runtime_interval=1,
    prediction_periods=4,
    aggregation_mode="median",
)
df = pred.to_pandas()
```

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

### Run Experiment Preview with Custom Transformers

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/experiments/use-a-custom-transformer.html?q=

Configure an experiment preview using a specific dataset and a list of custom transformers.

```python
ds = dai.datasets.list()[0]
dai.experiments.preview(
    train_dataset=ds, 
    target_column=ds.columns[-1], 
    task='classification', 
    transformers=custom_transformers
)
```

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

### Get runtime insights for experiments

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/admin-api-methods.html

Retrieves system resource usage metrics for currently running experiments on Driverless AI 2.0+.

```python
# System insights for running experiments (Driverless AI 2.0+)
insights = client.admin.get_runtime_experiment_insights()
print("Num running experiments:", len(insights))
if insights:
    ri = insights[0]
    print("Entity ID :", ri.entity_id)
    print("Username :", ri.username)
    print("CPU usage :", ri.cpu_usage)
    print("Memory usage (bytes) :", ri.memory_usage)
    print("GPU usage :", ri.gpu_usage)
    print("Disk usage (bytes) :", ri.disk_usage)
    print("Creation timestamp :", ri.creation_timestamp)
    print("Worker info :", ri.worker_info)

# From an ExperimentProxy (only if running)
# if experiments and experiments[0].is_running():
#     ri2 = experiments[0].runtime_insights
#     print("Experiment runtime CPU usage :", ri2.cpu_usage)
```

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

### Create Custom Recipe

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/recipes.html?q=

Synchronously create a custom recipe from a path or URL.

```python
create(recipe: str, username: str = None, password: str = None) -> Recipe
```

```python
recipe = client.recipes.create(
    recipe="https://github.com/h2oai/driverlessai-recipes/blob/master/scorers/regression/explained_variance.py"
)
```

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

### Get Dataset Tags

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html?q=

Retrieve tags for a specific dataset linked to the project. Requires Driverless AI server 1.11.0 or higher.

```python
get_dataset_tags(dataset: Dataset) -> list[str]
```

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

### Import h2osteam library

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/h2oai-cloud/dai-steam.html?q=

Initial import required to access Steam client functionality.

```python
import h2osteam
```

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

### Get Shapley Summary Explanation Plot

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Retrieves a Shapley summary plot, optionally filtered by class name or specific page number.

```python
get_plot(*, class_name: str | None = None, page_num: int = 1) -> dict[str, Any]
```

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

### create(recipe: str, username: str = None, password: str = None) -> Recipe

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/recipes.html?q=

Creates a custom recipe in the Driverless AI server.

```APIDOC
## create(recipe: str, username: str = None, password: str = None) -> Recipe

### Description
Creates a custom recipe in the Driverless AI server.

### Parameters
- **recipe** (str) - Required - The path or URL to the recipe.
- **username** (str) - Optional - Username to use when connecting to BitBucket.
- **password** (str) - Optional - Password to use when connecting to BitBucket.

### Returns
- **Recipe** - Created custom recipe.

### Example
```python
recipe = client.recipes.create(
    recipe="https://github.com/h2oai/driverlessai-recipes/blob/master/scorers/regression/explained_variance.py"
)
```
```

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

### gui()

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html

Returns the full URL to the dataset details page in the Driverless AI server.

```APIDOC
## gui()

### Description
Returns the full URL to the dataset details page in the Driverless AI server.

### Returns
- **Hyperlink** - URL to the dataset details page.
```

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

### Get Global Feature Importance Explanation Plot

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Retrieves a global explanation plot, optionally filtered by class name for multinomial classification.

```python
get_plot(*, class_name: str | None = None) -> dict[str, Any]
```

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

### Preview Experiment Settings

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/experiments/search-expert-settings.html

Use this method to preview experiment configurations including training datasets, target columns, and task types.

```python
dai.experiments.preview( train_dataset=ds, target_column='airline_sentiment', task='classification', **settings )
```

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

### Get Decision Tree Explanation Plot

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Retrieves an explanation plot for a Decision Tree model, optionally filtered by row number or class name.

```python
get_plot(
    *, row_number: int | None = None, class_name: str | None = None
) -> dict[str, Any]
```

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

### Get Random Forest PDP Plot

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Retrieves a partial dependence plot for a Random Forest model, optionally filtered by row number or feature name.

```python
get_plot(
    *, row_number: int | None = None, feature_name: str | None = None
) -> dict[str, Any]
```

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

### retrain_async(...) -> Experiment

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/experiments.html?q=

Launch creation of a new experiment asynchronously.

```APIDOC
## retrain_async(use_smart_checkpoint: bool = False, final_pipeline_only: bool = False, final_models_only: bool = False, **kwargs: Any) -> Experiment

### Description
Launch creation of a new experiment using the same datasets and settings. Through kwargs it's possible to pass new datasets or overwrite settings.

### Parameters
- **use_smart_checkpoint** (bool) - Optional (default: False) - Start the experiment from the last smart checkpoint.
- **final_pipeline_only** (bool) - Optional (default: False) - Trains the final pipeline using smart checkpoint if available, otherwise uses default hyperparameters.
- **final_models_only** (bool) - Optional (default: False) - Trains the final pipeline models (but not transformers) using smart checkpoint if available, otherwise uses default hyperparameters and transformers.
- **kwargs** (Any) - Optional - Datasets and experiment settings as defined in experiments.create().
```

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

### Set Logical Data Types for Dataset Columns

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/datasets.html

Defines the logical data types for columns to guide transformer selection. Use None to unset existing types.

```python
# Import the prostate dataset.
dataset = client.datasets.create(
    data="s3://h2o-public-test-data/smalldata/prostate/prostate.csv",
    data_source="s3",
)

# Set the logical types
dataset.set_logical_types(
    {"ID": "id", "AGE": ["categorical", "numerical"], "RACE": None}
)
```

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

### gui

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/mli.html

Prints the full URL for the user's MLI page in the Driverless AI server.

```APIDOC
## gui()

### Description
Prints the full URL for the user's MLI page in the Driverless AI server.
```

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

### gui() -> Hyperlink

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html?q=

Returns the URL to the Projects page in the Driverless AI server.

```APIDOC
## gui() -> Hyperlink

### Description
Returns the full URL to the Projects page in the Driverless AI server.

### Returns
- **Hyperlink** - The full URL to the Projects page.
```

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

### Import Dataset Using Custom AWS Credentials

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/create/import-dataset-with-s3-connector.html

Override server-side credentials by providing specific AWS access keys via the data_source_config argument. This feature is supported starting from DAI 1.10.4.

```python
dataset_from_custom_s3 = dai.datasets.create(
    data_source="s3",
    name="credit-cards-custom-creds",
    data="s3://h2o-datasets/dai/CreditCard_Cat-train.csv",
    force=True,
    data_source_config={
        "aws_access_key_id": "your AWS access key id",
        "aws_secret_access_key": "your AWS secret access key"
    }
)
dataset_from_custom_s3.head()
```

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

### ExplainerFrames.download

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/mli/access-explainer-data.html

Downloads the explainer frames directly.

```APIDOC
## Method: download()

### Description
Downloads the frames associated with the explainer directly.
```

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

### Import Dataset Using User-Specific MinIO Credentials

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/create/import-dataset-with-minio-connector.html

Override server-configured credentials by providing specific access keys during dataset creation. This requires Driverless AI 1.10.4 or later.

```python
dataset_from_custom_minio = dai.datasets.create(
    data_source="minio",
    name="train_data",
    data="h2oaidev/cc_train.csv",
    force=True,
    data_source_config={
        "minio_access_key_id": 'Your Minio access key ID',
        "minio_secret_access_key": 'Your Minio secret access key',
    }
)
dataset_from_custom_minio.head()
```

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

### Initialize Driverless AI Client

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/server.html

Connect to a Driverless AI server instance using credentials and access server metadata.

```python
client = driverlessai.Client(
    address="http://localhost:12345",
    username="py",
    password="py",
)

client.server.address
client.server.username
client.server.version
```

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

### Upload Custom Explainer Recipe

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/mli/use-a-custom-explainer.html

Upload a recipe from a remote URL or a local file path.

```python
dai.recipes.create("https://github.com/h2oai/driverlessai-recipes/raw/master/explainers/explainers/ale_explainer.py")
```

```python
dai.recipes.create("ale_explainer.py")
```

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

### Create Dataset with Predefined Snowflake Configuration

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/create/import-dataset-with-snowflake-connector.html

Import data using a configuration already set up on the Driverless AI server, requiring only warehouse, database, and schema parameters.

```python
dataset_from_sf = dai.datasets.create(
    data_source="snow",
    name="credit-cards",
    data="SELECT ID, BILL_AMT1, BILL_AMT2, BILL_AMT3, BILL_AMT4, BILL_AMT5 FROM CREDIT_CARD",
    data_source_config=dict(
        snowflake_warehouse="DEMO_WH",
        snowflake_database="CREDIT_CARD",
        snowflake_schema="PUBLIC",
    ),
    force=True,
)

dataset_from_sf.head()
```

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

### Displaying Explainer Settings

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/recipes.html?q=

Retrieve and display the current settings of an explainer recipe.

```python
show_settings(show_dai_name: bool = False) -> Table
```

```python
settings = explainer_recipe.show_settings()
print(settings)
```

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

### Create Dataset from Databricks

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/create/import-dataset-with-databricks-connector.html

Import data by providing a SQL query and the required Databricks configuration parameters.

```python
dataset = dai.datasets.create(
    data='SELECT * FROM my_catalog.my_schema.my_table',
    data_source='databricks',
    data_source_config=dict(
        databricks_warehouse_id='/sql/1.0/warehouses/your_warehouse_id',
        databricks_workspace_instance_name='your_workspace.azuredatabricks.net',
        databricks_personal_access_token='<your-databricks-pat>',
    ),
    name='my-databricks-dataset',
    force=True,
)

dataset.head()
```

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

### Import Folder as Dataset

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/datasets/create/import-folder-as-dataset.html

Creates a dataset from a folder path. If the path ends with a forward slash, the system attempts to upload all files within the folder.

```python
dataset_from_s3 = dai.datasets.create(
    data_source="s3",
    name="dataset_from_s3",
    data="s3://h2o-public-test-data/h2o-autodoc-data/credit-card/",
    force=True,
)

dataset_from_s3.head()
```

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

### Create a Classification Experiment

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/mli/run-interpretation.ipynb

Launch a binomial classification experiment and wait for completion.

```python
ex = dai.experiments.create(train_dataset=ds,
                            target_column='default payment next month', 
                            task='classification',  
                            accuracy=1,
                            time=1,
                            interpretability=1,
                            name='creditcard-mli-interpretation')
```

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

### list(start_index: int = 0, count: int = None) -> Sequence[Project]

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/api/projects.html?q=

Retrieves a list of projects from the server.

```APIDOC
## list(start_index: int = 0, count: int = None) -> Sequence[Project]

### Description
Retrieves projects in the Driverless AI server.

### Parameters
- **start_index** (int) - Optional - The index of the first project to retrieve.
- **count** (int) - Optional - The maximum number of projects to retrieve. If None, retrieves all available projects.

### Returns
- **Sequence[Project]** - Projects.
```

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

### Import Vega

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/model-diagnostics.html

Import the Vega library to render the metric plots.

```python
from vega import Vega
```

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

### List Projects

Source: https://docs.h2o.ai/driverless-ai/pyclient/docs/html/examples/projects/create-a-project.html

Retrieve a list of all projects currently available on the server.

```python
dai.projects.list()
```