Spatial Coordinates Transformer

The SCoordTransformer class takes input data containing a geometry column with geometries and produces a NumPy array containing the centroids of the geometries, which represent the x and y coordinates.

This transformer can be used to pass location information directly to a model.

The main methods of the class are described in the following table.

Method	Description
`fit`	Not yet implemented as it does not perform any calculations with the training data.
`transform`	Returns the XY coordinates of the geometries. In case of non-point spatial objects (such as lines and polygons), it returns the centroids of the geometries.
`fit_transform`	Calls the `fit` and `transform` methods sequentially with the training data.

See the SCoordTransformer class in Python API Reference for Oracle Spatial AI for more information.

The following example uses the block_groups SpatialDataFrame and the SCoordTransformer class to obtain the centroid’s coordinates from a SpatialDataFrame. The geometries are specified in the geometry column.

from oraclesai.preprocessing import SCoordTransformer 
 
# Define the variables of the training data
X = block_groups[["MEDIAN_INCOME", "MEAN_AGE", "HOUSE_VALUE", "geometry"]] 
 
# Use a referenced coordinate system
X = X.to_crs("epsg:3857") 
 
# Print the given data
print(f">> Original data:\n {X['geometry'].head(5)}")
 
# Transform the data with the SCoordTransformer
coordinates = SCoordTransformer().fit_transform(X) 
 
# Print the transformed data
print(f"\n>> Transformed data:\n {coordinates[:5, :]}")

The resulting output consists of the centroids of the geometries.

>> Original data:
                                             geometry
0  POLYGON ((-13175658.713 4010761.859, -13174935...
1  POLYGON ((-13175749.772 4004714.769, -13174771...
2  POLYGON ((-13179169.173 4002635.119, -13178970...
3  POLYGON ((-13177695.971 4003360.046, -13177503...
4  POLYGON ((-13177368.803 4002939.500, -13176993...

>> Transformed data:
 [[-13174765.1034151    4010231.26409032]
 [-13175173.61624862   4003637.47437617]
 [-13178654.77968995   4002868.5566815 ]
 [-13176298.82436636   4002826.86495246]
 [-13176753.58959072   4002684.55714192]]