This package is meant to help you run models on Ellipsis Drive content. It should be used in combination with the ellipsis package.
Install
pip install ellipsisAI
Example
import ellipsisAI as ai
import ellipsis as el
pathId = '170aadad-8eaa-4509-9c0e-c1536d58a1fe'
timestampId = "633b4b9f-d939-4c4a-8d90-0e9fceb64b83"
targetPathId = "066458f4-f018-4f49-a1f0-dedfa71b3368"
tempFolder = 'YOUR_PATH'
#login to get a authentication token
token = el.account.logIn('YOUR_USERNAME','YOUR_PASSWORD')
#retrieve the zoom and bounds of the capture you wish to classify
classificationZoom = ai.getReccomendedClassificationZoom(pathId = pathId, timestampId = timestampId, token = token)
bounds = el.path.raster.timestamp.getBounds(pathId, timestampId, token)
#we create a dummy model. We use the identity function mapping an image to itself. We use the getTleData function to retirve the image for the given input tile ofthe model.
def model(tile):
result = ai.getTileData(pathId = pathId, timestampId = timestampId, tile = tile, token = token)
if result['status'] == 204:
output = np.zeros((1,256,256))
else:
r = result['result']
output = r[0:1,:,:] * 2
return(output)
#apply the model on the given bounds on the given zoomlevel
ai.applyModel(model, bounds, targetPathId, classificationZoom, token, tempFolder)
Functions
applyModel
applyModel(model, bounds, targetPathId, classificationZoom, token, modelNoDataValue = -1, targetFromDate = None, targetToDate = None)
This function applies the given model on all tiles of zoomlevel classificationZoom withing the specified bounds. The results will be written in a new capture of the specified target block.
| Name | Description |
|---|---|
| model | A function mapping given bounds to a 3D numpy array. |
| bounds | A shapely polygon or multipolygon indicating the region you wish to classify |
| targetPathId | The id of the path to write the result to |
| classificationZoom | The zoomlevel of the tiles you wish to use for the model input as integer. |
| token | Your token |
| tempFolder | A path where temporary files can be written |
| modelNoDataValue | Which number of the model output to interpret as transparent |
| targetDate | Dictionary with keys from and to, both must be of type datetime. Defaults to current date |
getTiles
getTiles(bounds, classificationZoom)
This function covers a given bounds with tiles of the given zoomlevel. You can use the result to get tile arguments for the getTileData function
| Name | Description |
|---|---|
| bounds | A shapely polygon or multipolygon |
| classificationZoom | The zoomlevel of the tiles to cover with as int |
getTileData
getTileData(pathId, timestampId, tile, token = None )
This function retrieves raster data for a certain tile.
| Name | Description |
|---|---|
| PathId | Id of the layer to retrieve the raster for |
| timestampId | Id of the timestamp to retrieve the raster for |
| tile | A dictionary with tileX, tileY and zoom as integers |
| token | Your token (optional) |
getReccomendedClassificationZoom
getReccomendedClassificationZoom(pathId, timestampId, token = None)
This function retrieves raster data for a certain tile.
| Name | Description |
|---|---|
| PathId | Id of the layer to retrieve the raster for |
| timestampId | Id of the timestamp to retrieve the raster for |
| token | Your token (optional) |
Metadata
Release files for ellipsisAI 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ellipsisAI-0.1.3.tar.gz | 6.6 kB | Without provenance | Details for ellipsisAI-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ellipsisAI-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for ellipsisAI-0.1.3-py3-none-any.whl |
Total release size: 13.4 kB
Release files / ellipsisAI-0.1.3.tar.gz
| Download URL | ellipsisAI-0.1.3.tar.gz |
|---|---|
| Size | 6.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
aa5a780d32b48b82d26127e40774e30d7656aa5cf7fa69ba20f191d6a0128de7
|
|
BLAKE2b-256 checksum How to use checksums |
a1c7a10f0d826af3c288fee662bf69bfe132867dc4a7b7a5a6ed248c26609507
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.8.0 colorama/0.4.4 importlib-metadata/6.8.0 keyring/23.5.0 pkginfo/1.8.2 readme-renderer/34.0 requests-toolbelt/0.9.1 requests/2.31.0 rfc3986/1.5.0 tqdm/4.57.0 urllib3/1.26.5 CPython/3.10.12
|
Release files / ellipsisAI-0.1.3-py3-none-any.whl
| Download URL | ellipsisAI-0.1.3-py3-none-any.whl |
|---|---|
| Size | 6.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d5027ee2dc0b093c3999e4f81ec565cf19b10d8e2e1397391864f264f550c873
|
|
BLAKE2b-256 checksum How to use checksums |
11bc4843b3d3c4b65edd6274bfe63cc5d0c7b60fe2ce0f23970144bc8b47dc61
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.8.0 colorama/0.4.4 importlib-metadata/6.8.0 keyring/23.5.0 pkginfo/1.8.2 readme-renderer/34.0 requests-toolbelt/0.9.1 requests/2.31.0 rfc3986/1.5.0 tqdm/4.57.0 urllib3/1.26.5 CPython/3.10.12
|
Security for ellipsisAI 0.1.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.