def process(geom_data, raster_data, process_kwargs):
if process_kwargs.get("empty"):
return {
"features": gpd.GeoDataFrame([]),
"projection": process_kwargs["projection"],
}
elif process_kwargs["mode"] == "extent":
return geom_data
features = geom_data["features"]
if len(features) == 0:
return geom_data
result = features.copy()
# transform the features into the aggregation projection
req_srs = process_kwargs["req_srs"]
agg_srs = process_kwargs["agg_srs"]
agg_geometries = utils.geoseries_transform(features["geometry"],
req_srs, agg_srs)
statistic = process_kwargs["statistic"]
percentile = utils.parse_percentile_statistic(statistic)
if percentile:
statistic = "percentile"
agg_func = partial(AggregateRaster.STATISTICS[statistic]["func"],
qval=percentile)
else:
agg_func = AggregateRaster.STATISTICS[statistic]["func"]
extensive = AggregateRaster.STATISTICS[statistic]["extensive"]
result_column = process_kwargs["result_column"]
# this is only there for the AggregateRasterAboveThreshold
threshold_name = process_kwargs.get("threshold_name")
if threshold_name:
# get the threshold, appending NaN for unlabeled pixels
threshold_values = np.empty((len(features) + 1, ), dtype="f4")
threshold_values[:-1] = features[threshold_name].values
threshold_values[-1] = np.nan
else:
threshold_values = None
# investigate the raster data
if raster_data is None:
values = no_data_value = None
else:
values = raster_data["values"]
no_data_value = raster_data["no_data_value"]
if values is None or np.all(values == no_data_value): # skip the rest
result[result_column] = 0 if extensive else np.nan
return {"features": result, "projection": req_srs}
depth, height, width = values.shape
pixel_size = process_kwargs["pixel_size"]
actual_pixel_size = process_kwargs["actual_pixel_size"]
# process in groups of disjoint subsets of the features
agg = np.full((depth, len(features)), np.nan, dtype="f4")
for select in bucketize(features.bounds.values):
rasterize_result = utils.rasterize_geoseries(
agg_geometries.iloc[select],
process_kwargs["agg_bbox"],
agg_srs,
height,
width,
values=np.asarray(select, dtype=np.int32), # GDAL needs int32
)
labels = rasterize_result["values"][0]
# if there is a threshold, generate a raster with thresholds
if threshold_name:
# mode="clip" ensures that unlabeled cells use the appended NaN
thresholds = np.take(threshold_values, labels, mode="clip")
else:
thresholds = None
for frame_no, frame in enumerate(values):
# limit statistics to active pixels
active = frame != no_data_value
# if there is a threshold, mask the frame
if threshold_name:
valid = ~np.isnan(thresholds) # to suppress warnings
active[~valid] = False # no threshold -> no aggregation
active[valid] &= frame[valid] >= thresholds[valid]
# if there is no single active value: do not aggregate
if not active.any():
continue
# select features that actually have data
# (min, max, median, and percentile cannot handle it otherwise)
active_labels = labels[active]
select_and_active = list(
set(np.unique(active_labels)) & set(select))
if not select_and_active:
continue
agg[frame_no][select_and_active] = agg_func(
1 if statistic == "count" else frame[active],
labels=active_labels,
index=select_and_active,
)
if extensive: # sum and count
agg[~np.isfinite(agg)] = 0
# extensive aggregations have to be scaled
if actual_pixel_size != pixel_size:
agg *= (actual_pixel_size / pixel_size)**2
else:
agg[~np.isfinite(agg)] = np.nan # replaces inf by nan
if depth == 1:
result[result_column] = agg[0]
else:
# store an array in a dataframe cell: set each cell with [np.array]
result[result_column] = [[x] for x in agg.T]
return {"features": result, "projection": req_srs}
def process(geom_data, raster_data, process_kwargs):
if process_kwargs.get("empty"):
return {
"features": gpd.GeoDataFrame([]),
"projection": process_kwargs["projection"],
}
elif process_kwargs["mode"] == "extent":
return geom_data
features = geom_data["features"]
if len(features) == 0:
return geom_data
result = features.copy()
# transform the features into the aggregation projection
req_srs = process_kwargs["req_srs"]
agg_srs = process_kwargs["agg_srs"]
agg_geometries = utils.geoseries_transform(
features["geometry"],
req_srs,
agg_srs,
)
statistic = process_kwargs["statistic"]
percentile = utils.parse_percentile_statistic(statistic)
if percentile:
statistic = "percentile"
agg_func = partial(AggregateRaster.STATISTICS[statistic]["func"],
qval=percentile)
else:
agg_func = AggregateRaster.STATISTICS[statistic]["func"]
extensive = AggregateRaster.STATISTICS[statistic]["extensive"]
result_column = process_kwargs["result_column"]
# this is only there for the AggregateRasterAboveThreshold
threshold_name = process_kwargs.get("threshold_name")
# investigate the raster data
if raster_data is None:
values = no_data_value = None
else:
values = raster_data["values"]
no_data_value = raster_data["no_data_value"]
if values is None or np.all(values == no_data_value): # skip the rest
result[result_column] = 0 if extensive else np.nan
return {"features": result, "projection": req_srs}
depth, height, width = values.shape
pixel_size = process_kwargs["pixel_size"]
actual_pixel_size = process_kwargs["actual_pixel_size"]
# process in groups of disjoint subsets of the features
agg = np.full((depth, len(features)), np.nan, dtype="f4")
for select in bucketize(features.bounds.values):
agg_geometries_bucket = agg_geometries.iloc[select]
index = features.index[select]
rasterize_result = utils.rasterize_geoseries(
agg_geometries_bucket,
process_kwargs["agg_bbox"],
agg_srs,
height,
width,
values=index,
)
labels = rasterize_result["values"][0]
# if there is a threshold, generate a raster with thresholds
if threshold_name:
thresholds = features.loc[labels.ravel(),
threshold_name].values.reshape(
labels.shape)
else:
thresholds = None
for frame_no, frame in enumerate(values):
# limit statistics to active pixels
active = frame != no_data_value
# if there is a threshold, mask the frame
if threshold_name:
valid = ~np.isnan(thresholds) # to suppress warnings
active[~valid] = False # no threshold -> no aggregation
active[valid] &= frame[valid] >= thresholds[valid]
# if there is no single active value: do not aggregate
if not active.any():
continue
with warnings.catch_warnings():
# we may get divide by 0 if any geometry does not contain
# any 'active' values
warnings.simplefilter("ignore")
agg[frame_no][select] = agg_func(
1 if statistic == "count" else frame[active],
labels=labels[active],
index=index,
)
if extensive: # sum and count
agg[~np.isfinite(agg)] = 0
# extensive aggregations have to be scaled
if actual_pixel_size != pixel_size:
agg *= (actual_pixel_size / pixel_size)**2
else:
agg[~np.isfinite(agg)] = np.nan # replaces inf by nan
if depth == 1:
result[result_column] = agg[0]
else:
# store an array in a dataframe cell: set each cell with [np.array]
result[result_column] = [[x] for x in agg.T]
return {"features": result, "projection": req_srs}