def rct_stats(udf_data: UdfData):
"""Compute univariate statistics for each raster collection tile
Args:
udf_data (UdfData): The UDF data object that contains raster and vector tiles
Returns:
This function will not return anything, the UdfData object "udf_data" must be used to store the resulting
data.
"""
# The dictionary that stores the statistical data
stats = {}
# Iterate over each raster collection tile and compute statistical values
for tile in udf_data.raster_collection_tiles:
# make sure to cast the values to floats, otherwise they are not serializable
stats[tile.id] = dict(sum=float(tile.data.sum()), mean=float(tile.data.mean()),
min=float(tile.data.min()), max=float(tile.data.max()))
# Create the structured data object
sd = StructuredData(description="Statistical data sum, min, max and mean "
"for each raster collection tile as dict",
data=stats,
type="dict")
# Remove all collections and set the StructuredData list
udf_data.del_raster_collection_tiles()
udf_data.del_feature_collection_tiles()
udf_data.set_structured_data_list([sd,])
def fct_sampling(udf_data: UdfData):
"""Sample any number of raster collection tiles with a single feature collection (the first if several are provided)
and store the samples values in the input feature collection. Each time-slice of a raster collection is
stored as a separate column in the feature collection. Hence, the size of the feature collection attributes
is (number_of_raster_tile * number_of_xy_slices) x number_of_features.
The number of columns is equal to (number_of_raster_tile * number_of_xy_slices).
A single feature collection id stored in the input data object that contains the sample attributes and
the original data.
Args:
udf_data (UdfData): The UDF data object that contains raster and vector tiles
Returns:
This function will not return anything, the UdfData object "udf_data" must be used to store the resulting
data.
"""
if not udf_data.feature_collection_tiles:
raise Exception("A single feature collection is required as input")
if len(udf_data.feature_collection_tiles) > 1:
raise Exception("The first feature collection will be used for sampling")
# Get the first feature collection
fct = udf_data.feature_collection_tiles[0]
features = fct.data
# Iterate over each raster tile
for tile in udf_data.raster_collection_tiles:
# Compute the number and names of the attribute columns
num_slices = len(tile.data)
columns = {}
column_names = []
for slice in range(num_slices):
column_name = tile.id + "_%i"%slice
column_names.append(column_name)
columns[column_name] = []
# Sample the raster data with each point
for feature in features.geometry:
# Check if the feature is a point
if feature.type == 'Point':
x = feature.x
y = feature.y
values = tile.sample(top=y, left=x)
# Store the values in column specific arrays
if values:
for column_name, value in zip(column_names, values):
columns[column_name].append(value)
else:
for column_name in column_names:
columns[column_name].append(math.nan)
else:
raise Exception("Only points are allowed for sampling")
# Attach the sampled attribute data to the GeoDataFrame
for column_name in column_names:
features[column_name] = columns[column_name]
# Create the output feature collection
fct = FeatureCollectionTile(id=fct.id + "_sample", data=features,
start_times=fct.start_times, end_times=fct.end_times)
# Insert the new tiles as list of feature collection tiles in the input object. The new tiles will
# replace the original input tiles.
udf_data.set_feature_collection_tiles([fct,])
# Remove the raster collection tiles
udf_data.del_raster_collection_tiles()