datasets module

Module for accessing the Earth Engine Data Catalog with dot notation.

get_community_data_list()

Gets the list community datasets from https://github.com/samapriya/awesome-gee-community-datasets/blob/master/community_datasets.json

Returns:

Name	Type	Description
list	list	The list of Earth Engine asset IDs.

Source code in geemap/datasets.py

def get_community_data_list() -> list:
    """Gets the list community datasets
        from https://github.com/samapriya/awesome-gee-community-datasets/blob/master/community_datasets.json

    Returns:
        list: The list of Earth Engine asset IDs.
    """
    collections = search_ee_data(".*", regex=True, source="community")
    return [collection.get("id", None) for collection in collections]

get_data_csv()

Gets the file path to the CSV file containing the information about the Earth Engine Data Catalog.

Returns:

Name	Type	Description
str	str	File path to the CSV file.

Source code in geemap/datasets.py

def get_data_csv() -> str:
    """Gets the file path to the CSV file containing the information about the Earth Engine Data Catalog.

    Returns:
        str: File path to the CSV file.
    """
    pkg_dir = str(importlib.resources.files("geemap").joinpath("geemap.py").parent)
    template_dir = os.path.join(pkg_dir, "data/template")
    data_csv = os.path.join(template_dir, "ee_data_catalog.csv")
    return data_csv

get_data_dict()

Gets the Earth Engine Data Catalog as a nested dictionary.

Returns:

Name	Type	Description
dict	dict	The nested dictionary containing the information about the Earth Engine Data Catalog.

Source code in geemap/datasets.py

def get_data_dict() -> dict:
    """Gets the Earth Engine Data Catalog as a nested dictionary.

    Returns:
        dict: The nested dictionary containing the information about the Earth Engine Data Catalog.
    """
    data_dict = {}
    datasets = get_data_list()

    for dataset in datasets:
        tree_dict = {}
        items = dataset.split("/")
        for index, key in enumerate(reversed(items)):
            if index == 0:
                tree_dict = {key: dataset}
            else:
                tree_dict = {key: tree_dict}

        data_dict = merge_dict(data_dict, tree_dict)
        data_dict[dataset.replace("/", "_")] = dataset

    return data_dict

get_data_list()

Gets a list of Earth Engine datasets.

Returns:

Name	Type	Description
list	list	The list of dataset ids.

Source code in geemap/datasets.py

def get_data_list() -> list:
    """Gets a list of Earth Engine datasets.

    Returns:
        list: The list of dataset ids.
    """

    datasets = get_ee_stac_list()
    extra_datasets = get_geemap_data_list()
    community_datasets = get_community_data_list()

    return datasets + extra_datasets + community_datasets

get_ee_stac_list()

Gets the STAC list of the Earth Engine Data Catalog.

Raises:

Type	Description
Exception	If the JSON file fails to download.

Returns:

Name	Type	Description
list	list	The list of Earth Engine asset IDs.

Source code in geemap/datasets.py

def get_ee_stac_list() -> list:
    """Gets the STAC list of the Earth Engine Data Catalog.

    Raises:
        Exception: If the JSON file fails to download.

    Returns:
        list: The list of Earth Engine asset IDs.
    """
    try:
        stac_url = "https://raw.githubusercontent.com/samapriya/Earth-Engine-Datasets-List/master/gee_catalog.json"

        datasets = []
        with urllib.request.urlopen(stac_url) as url:
            data = json.loads(url.read().decode())
            datasets = [item["id"] for item in data]

        return datasets

    except Exception as e:
        raise Exception(e)

get_geemap_data_list()

Gets the list of the public datasets from GEE users.

Returns:

Name	Type	Description
list	list	The list of public datasets from GEE users.

Source code in geemap/datasets.py

def get_geemap_data_list() -> list:
    """Gets the list of the public datasets from GEE users.

    Returns:
        list: The list of public datasets from GEE users.
    """
    extra_ids = [
        "countries",
        "us_states",
        "us_cities",
        "chn_admin_line",
        "chn_admin_level0",
        "chn_admin_level1",
        "chn_admin_level2",
    ]

    extra_datasets = [f"users/giswqs/public/{uid}" for uid in extra_ids]
    return extra_datasets

get_metadata(asset_id, source='ee')

Gets metadata about an Earth Engine asset.

Parameters:

Name	Type	Description	Default
asset_id	str	The Earth Engine asset id.	required
source	str	'ee', 'community' or 'all'.	'ee'

Raises:

Type	Description
Exception	If search fails.

Source code in geemap/datasets.py

def get_metadata(asset_id: str, source: str = "ee") -> dict:
    """Gets metadata about an Earth Engine asset.

    Args:
        asset_id (str): The Earth Engine asset id.
        source (str): 'ee', 'community' or 'all'.

    Raises:
        Exception: If search fails.
    """
    try:
        ee_assets = search_ee_data(asset_id, source=source)
        html = ee_data_html(ee_assets[0])
        html_widget = widgets.HTML()
        html_widget.value = html
        display(html_widget)

    except Exception as e:
        raise Exception(e)

merge_dict(dict1, dict2)

Merges two nested dictionaries.

Parameters:

Name	Type	Description	Default
dict1	dict	The first dictionary to merge.	required
dict2	dict	The second dictionary to merge.	required

Returns:

Name	Type	Description
dict	dict	The merged dictionary.

Source code in geemap/datasets.py

def merge_dict(dict1: dict, dict2: dict) -> dict:
    """Merges two nested dictionaries.

    Args:
        dict1 (dict): The first dictionary to merge.
        dict2 (dict): The second dictionary to merge.

    Returns:
        dict: The merged dictionary.
    """
    return {**dict1, **dict2}

update_data_list(out_dir='.')

Updates the Earth Engine Data Catalog dataset list.

Parameters:

Name	Type	Description	Default
out_dir	str	The output directory to save the GitHub repository. Defaults to ".".	'.'

Raises:

Type	Description
Exception	If the CSV file fails to save.

Source code in geemap/datasets.py

def update_data_list(out_dir=".") -> None:
    """Updates the Earth Engine Data Catalog dataset list.

    Args:
        out_dir (str, optional): The output directory to save the GitHub repository. Defaults to ".".

    Raises:
        Exception: If the CSV file fails to save.
    """
    try:
        url = (
            "https://github.com/samapriya/Earth-Engine-Datasets-List/archive/master.zip"
        )
        filename = "Earth-Engine-Datasets-List-master.zip"
        dir_name = filename.replace(".zip", "")

        out_dir = os.path.abspath(out_dir)
        if not os.path.exists(out_dir):
            os.makedirs(out_dir)

        download_from_url(
            url, out_file_name=filename, out_dir=out_dir, unzip=True, verbose=False
        )

        work_dir = os.path.join(out_dir, dir_name)
        in_csv = list(Path(work_dir).rglob("*.csv"))[0]

        out_csv = get_data_csv()

        shutil.copyfile(in_csv, out_csv)
        os.remove(os.path.join(out_dir, filename))
        shutil.rmtree(os.path.join(out_dir, dir_name))

    except Exception as e:
        raise Exception(e)