API Documentation

geoutils.LandsatGLAD module

geoutils.LandsatGLAD.main()

The function can be used to download the Landsat Analysis Ready Data (GLAD ARD)

Parameters

  • path_aoi – Path for AOI geojson.

  • out_path – The list of available products.

  • start_month – start month in specific year based on the code e.g. 24-May 2000 > 838 (int)

  • end_month – end month in specific year based on code e.g. 12-Sep 2000 > 844 (int)

  • count_years – how many years would like to download (int)

  • username – username for GDAL account

  • password – password for GDAL account

Returns

The saved images in the disk

geoutils.cube module

class geoutils.cube.cube(rast_list)

Bases: object

generate_cube(start_date: str, freq: str)

Generate a data cube from the list of the xarray.DataArray

Parameters

  • start_date – The first raster acqusition date

  • start_date – Frequency to collect the image

Returns

xarray.DataArray

generate_mosaic()

Generate the mosaic with calculation median over time from the list of the xarray.DataArray

Returns

xarray.DataArray

geoutils.cube.get_imgs(img_list: List[str], chunks: Set[int] = (1000, 1000)) → List[xarray.core.dataarray.DataArray]

Opens the rasters as Dask dataArray

Parameters

  • img_list – The list of the image name/path

  • chunks – The chunk size

Returns

list of the opend images (list)

geoutils.cube.to_tif(file: xarray.core.dataarray.DataArray, path: str, crs: int = 4326, cell_size: Optional[int] = None)

Save the generated cube or mosaic to GeoTIFF format

Parameters

  • file – xarray.DataArray

  • path – The path to save the file

  • crs – The coordinate system to save image

  • cell_size – The cell size for resampling

Returns

The saved GeoTiff file on the disk

geoutils.dataClean module

geoutils.dataClean.remove_whitespace(df: pandas.core.frame.DataFrame, skip_rows: Optional[str] = None)
Parameters

  • df – Datafrrame whcih should be checked for white space

  • skip_rows – list of the columns which should be ignored

Returns

remove the white space from columns if exists

geoutils.dataClean.rename_column_name(df: pandas.core.frame.DataFrame, old_column_list: List[str], new_column_list: List[str])
Parameters

  • df – Datafrmae which want to change the name of the columns

  • old_column_list – List of the old columns’ name

  • new_column_list – List of the new columns’ name

Returns

change the name of the columns in the datafrme

geoutils.dataClean.transla(name_row: List[str], language_1: List[str], language_2: List[str])
Parameters

  • name_row – The name in row

  • language_1 – List of the first language

  • language_2 – List of the second language

Returns

translated name for each row

Usage: gdf[‘type_eng’] = gdf[‘type’].apply(transla,args=(lst_1,lst_2))

geoutils.dataExtraction module

geoutils.dataExtraction.extract_class(image: Union[numpy._typing._array_like._SupportsArray[numpy.dtype[Any]], numpy._typing._nested_sequence._NestedSequence[numpy._typing._array_like._SupportsArray[numpy.dtype[Any]]], bool, int, float, complex, str, bytes, numpy._typing._nested_sequence._NestedSequence[Union[bool, int, float, complex, str, bytes]]], codes: List[int], new_code: int)

This function split different high-level classes based on the sub-classes

Parameters

  • image – The original image to extract the groups

  • codes – The list of the codes which should be extracted

  • new_code – The code which should be determined to the new class

Returns

npt.ArrayLike

geoutils.dataExtraction.extract_geotif_to_point(rast_path: str, date: str, gdf_path: str, resample_size, stats: str = 'mean', mask: bool = False, nodata: int = 0) → geopandas.geodataframe.GeoDataFrame

The function extract the values for each date from GeoTIFF raster image

Parameters

  • rast_path – (file object or pathlib.Path object)

  • date – when the raster collected (Form: dd_mm_yyyy). it is important for time series data

  • gdf_path – (str, file object or pathlib.Path object)

  • resample_size – The buffer around the points. For the the point zero should be used

  • stats – The statistics should be used for aggregation

  • mask – The nodata value would be masked; default:False

  • nodata – value which should be consider as NoData value, default:0

Returns

gpd.GeoDataFrame

geoutils.dataExtraction.extract_netcdf_to_point(ds_path: str, gdf_path: str, resample_size: int, stats: str = 'mean', mask: bool = False, nodata: int = - 9999) → geopandas.geodataframe.GeoDataFrame

The function extract the values for each date from NetCDF. Since the NetCDF files usually are multi-temporal it is decided to use multi process for each bands which can save a lot of time.

Parameters

  • rast_path – (str, file object or pathlib.Path object)

  • gdf_path – (str, file object or pathlib.Path object)

  • resample_size – The buffer around the points. For the the point zero should be used

  • stats – The statistics should be used for aggregation

  • mask – The nodata value would be masked; default:False

  • nodata – value which should be consider as NoData value, default:0

Returns

gpd.GeoDataFrame

geoutils.grid module

geoutils.grid.generate_BID(gdf: geopandas.geodataframe.GeoDataFrame, coords: Optional[str] = None, cell: Optional[int] = None, x: Optional[float] = None, y: Optional[float] = None, circularity: bool = False)

The function generate ID for each cells in the grid

Parameters
Returns

The unique ID for each cell in the grid

class geoutils.grid.grid(xmin: float, xmax: float, ymin: float, ymax: float, cell_size: float, crs: int = 4326)

Bases: object

cells_within_polygon(gdf: geopandas.geodataframe.GeoDataFrame) → geopandas.geodataframe.GeoDataFrame

Generate cells inside the polygons

Returns

The geo-dataframe of cells inside the polygons

generate_grid() → geopandas.geodataframe.GeoDataFrame

The function generate the Grid based on the bbox received from user

Returns

-> gpd.GeoDataFrame

generate_point(center: bool = True) → geopandas.geodataframe.GeoDataFrame

The function generate the points based on the bbox received from user

Parameters

center – whether to generate point for center of the grid or not

Returns

gpd.GeoDataFrame

geoutils.image module

geoutils.image.exract_boundry(original_img: str, source_img: str, out_path: str, crs: str)

The function allign the original image with source image

Parameters

  • original_img – The image should be mapped to the source image

  • source_image – The image which should not be changed

  • out_path – Output path to save the image

  • crs – the output image projection

Returns

The saved image in the disk

geoutils.image.mosaic_from_tiles(in_put_path: str, out_put_path: str, dtype: str = 'float32', nodata: int = - 9999, mask: Optional[int] = None, format: str = 'GeoTiff')

The function generate a mosaic from the tiles. All the tiles should be in the same projection

Parameters

  • in_put_path – The path to tiles

  • out_put_path – Output path to save the generated mosaic

  • dtype – data type

  • nodata – NAN value which should be assigned

  • format – Image format can be GeoTIFF or NetCDF

Returns

The saved image in the disk

geoutils.modisAPI module

geoutils.modisAPI.main()

Download MODIS and VIIRS Land Product Subsets RESTful Web Service

Parameters

  • satellite – The list of available products.

  • product – Available band names for a product.

  • band – Name of data layer.

  • startDate – Name of data layer. (YYYY-MM-DD’)

  • endDate – Name of data layer. (YYYY-MM-DD’)

  • path_aoi – Path for AOI geojson.

  • crs_aoi – CRS for AOI geojson. Default: 4326

  • ouput_crs – CRS for output. Default: 4326

  • ouput_cellsize – out put image cellsize. Default: 250

  • number_chunks – There is a limit of a maximum ten modis dates per reques. Default: 10

Returns

The saved images in the disk

geoutils.utils module

geoutils.utils.chunk(l: int, n: int)
geoutils.utils.convert_to_NetCDF(subsets, coords, ouput_crs, ouput_cellsize)
geoutils.utils.extract_point(b, rc)

Extract the value for the points

geoutils.utils.extract_point_buffer(b, rc, s)

Extract the value based on the surrounded buffer

geoutils.utils.extract_point_buffer_mask(b, rc, s, nd)

Extract the value based on the surrounded buffer and mask the nodata value in calculation

geoutils.utils.geometry_from_geojson(filepath: str)
geoutils.utils.getSubsetURL(url: str, prod: str, lat: float, lon: float, band: int, sd: str, ed: str, ab: float, lr: float)
geoutils.utils.list_files(dirpath: str, endswith: Optional[str] = None)
geoutils.utils.list_files_with_absolute_paths(dirpath: str, endswith: Optional[str] = None)