mapreader.spot_text.runner_base

Classes

`DetRunner`
`DetRecRunner`

Module Contents

class mapreader.spot_text.runner_base.DetRunner

check_georeferencing()

run_all(return_dataframe=False, min_ioa=0.7)

Run the model on all images in the patch dataframe.

Parameters:

return_dataframe (bool, optional) – Whether to return the predictions as a pandas DataFrame, by default False
min_ioa (float, optional) – The minimum intersection over area to consider two polygons the same, by default 0.7

Returns:

A dictionary of predictions for each patch image or a DataFrame if return_dataframe is True.

Return type:

dict or pd.DataFrame or gpd.GeoDataFrame

run_on_images(img_paths, return_dataframe=False, min_ioa=0.7)

Run the model on a list of images.

Parameters:

img_paths (str, pathlib.Path or list) – A list of image paths to run the model on.
return_dataframe (bool, optional) – Whether to return the predictions as a pandas DataFrame, by default False
min_ioa (float, optional) – The minimum intersection over area to consider two polygons the same, by default 0.7

Returns:

A dictionary of predictions for each image or a DataFrame if return_dataframe is True.

Return type:

dict or pd.DataFrame

run_on_image(img_path, return_outputs=False, return_dataframe=False, min_ioa=0.7)

Run the model on a single image.

Parameters:

img_path (str or pathlib.Path) – The path to the image to run the model on.
return_outputs (bool, optional) – Whether to return the outputs direct from the model, by default False
return_dataframe (bool, optional) – Whether to return the predictions as a pandas DataFrame, by default False
min_ioa (float, optional) – The minimum intersection over area to consider two polygons the same, by default 0.7

Returns:

The predictions for the image or the outputs from the model if return_outputs is True.

Return type:

dict or pd.DataFrame

convert_to_parent_pixel_bounds(return_dataframe=False, deduplicate=False, min_ioa=0.7)

Convert the patch predictions to parent predictions by converting pixel bounds.

Parameters:

return_dataframe (bool, optional) – Whether to return the predictions as a pandas DataFrame, by default False
deduplicate (bool, optional) – Whether to deduplicate the parent predictions, by default False. Depending on size of parent images, this can be slow.
min_ioa (float, optional) – The minimum intersection over area to consider two polygons the same, by default 0.7 This is only used if deduplicate is True.

Returns:

A dictionary of predictions for each parent image or a DataFrame if return_dataframe is True.

Return type:

dict or pd.DataFrame

convert_to_coords(return_dataframe=False)

Convert the parent predictions to georeferenced predictions by converting pixel bounds to coordinates.

Parameters:: return_dataframe (bool, optional) – Whether to return the predictions as a geopandas GeoDataFrame, by default False
Returns:: A dictionary of predictions for each parent image or a DataFrame if return_dataframe is True.
Return type:: dict or gpd.GeoDataFrame

save_to_geojson(path_save, centroid=False)

Save the georeferenced predictions to a GeoJSON file.

Parameters:

path_save (str | pathlib.Path, optional) – Path to save the GeoJSON file
centroid (bool, optional) – Whether to convert the polygons to centroids, by default False. NOTE: The original polygon will still be saved as a separate column

Return type:

None

to_geojson(path_save, centroid=False)

Save the georeferenced predictions to a GeoJSON file.

Parameters:

path_save (str | pathlib.Path, optional) – Path to save the GeoJSON file
centroid (bool, optional) – Whether to convert the polygons to centroids, by default False. NOTE: The original polygon will still be saved as a separate column

Return type:

None

to_csv(path_save, centroid=False)

Saves the patch, parent and georeferenced predictions to CSV files.

Parameters:

path_save (str | pathlib.Path) – The path to save the CSV files. Files will be saved as patch_predictions.csv, parent_predictions.csv and geo_predictions.csv.
centroid (bool, optional) – Whether to convert polygons to centroids, by default False. NOTE: The original polygon will still be saved as a separate column.

Return type:

None

Note

Use the save_to_geojson method to save georeferenced predictions to a GeoJSON file.

show_predictions(image_id, figsize=(10, 10), border_color='r', text_color='b')

Show the predictions on an image.

Parameters:

image_id (str) – The image ID to show the predictions on.
figsize (tuple | None, optional) – The size of the figure, by default (10, 10)
border_color (str | None, optional) – The color of the border of the polygons, by default “r”
text_color (str | None, optional) – The color of the text, by default “b”

Raises:

ValueError – If the image ID is not found in the patch or parent predictions.

Return type:

None

explore_predictions(parent_id, xyz_url=None, style_kwargs=None)

Parameters:

parent_id (str)
xyz_url (str | None)
style_kwargs (dict | None)

load_geo_predictions(load_path)

Load georeferenced text predictions from a GeoJSON file.

Parameters:: load_path (str | pathlib.Path) – The path to the GeoJSON file.
Raises:: ValueError – If the path does not point to a GeoJSON file.

Note

This will overwrite any existing predictions!

load_patch_predictions(patch_preds)

Parameters:: patch_preds (str | pathlib.Path | pandas.DataFrame)
Return type:: None

class mapreader.spot_text.runner_base.DetRecRunner

Bases: DetRunner

search_predictions(search_text, ignore_case=True, return_dataframe=False)

Search the predictions for specific text. Accepts regex.

Parameters:

search_text (str) – The text to search for. Can be a regex pattern.
ignore_case (bool, optional) – Whether to ignore case when searching, by default True.
return_dataframe (bool, optional) – Whether to return the results as a pandas DataFrame, by default False.

Returns:

A dictionary containing the search results or a DataFrame if return_dataframe is True.

Return type:

dict | pd.DataFrame

Raises:

ValueError – If no parent predictions are found.

show_search_results(parent_id, figsize=(10, 10), border_color='r', text_color='b')

Show the search results on an image.

Parameters:

parent_id (str) – The image ID to show the predictions on (must be parent level).
figsize (tuple | None, optional) – The size of the figure, by default (10, 10)
border_color (str | None, optional) – The color of the border of the polygons, by default “r”
text_color (str | None, optional) – The color of the text, by default “b”.

Raises:

ValueError – If the image ID is not found in the patch or parent predictions.

Return type:

None

explore_search_results(parent_id, xyz_url=None, style_kwargs=None)

Parameters:

parent_id (str)
xyz_url (str | None)
style_kwargs (dict | None)

save_search_results_to_geojson(path_save, centroid=False)

Convert the search results to georeferenced search results and save them to a GeoJSON file.

Parameters:

path_save (str | pathlib.Path) – The path to save the GeoJSON file.
centroid (bool, optional) – Whether to save the centroid of the polygons as the geometry column, by default False. Note: The original polygon will stil be saved as a separate column.

Raises:

ValueError – If no search results are found.

Return type:

None

search_results_to_geojson(path_save, centroid=False)

Convert the search results to georeferenced search results and save them to a GeoJSON file.

Parameters:

path_save (str | pathlib.Path) – The path to save the GeoJSON file.
centroid (bool, optional) – Whether to save the centroid of the polygons as the geometry column, by default False. Note: The original polygon will stil be saved as a separate column.

Raises:

ValueError – If no search results are found.

Return type:

None