Small pipeline fixes (#72)

* Remove default for subset

This is easy to forget and then run with subset without the intention to actually subset

* Improve file name

Closes #69

- Zero padding for counter
- v before version number
- Underscores instead of hyphon separators
- Drop hyphons from date stamp

* Bump version to 02

* Make mgrs sample file external

Closes #71

* Add date to raster metadata

Closes #70

* Improve print statement

scripts/datacube.py

@@ -399,6 +399,12 @@ def convert_attrs_and_coords_objects_to_str(data):
 
 
 @click.command()
+@click.option(
+    "--sample",
+    required=False,
+    default="https://clay-mgrs-samples.s3.amazonaws.com/mgrs_sample.fgb",
+    help="Location of MGRS tile sample",
+)
 @click.option(
     "--index",
     required=False,
@@ -414,13 +420,13 @@ def convert_attrs_and_coords_objects_to_str(data):
 @click.option(
     "--subset",
     required=False,
-    default="1000,1000,2000,2000",
+    default=None,
     help="For debugging, subset x and y to this pixel window.",
 )
-def main(index, subset, bucket):
-    print("Starting algorithm", index)
+def main(sample, index, subset, bucket):
+    print("Starting algorithm for MGRS tile with index", index)
     index = int(index)
-    tiles = gpd.read_file("mgrs_sample.gpkg")
+    tiles = gpd.read_file(sample)
     tile = tiles.iloc[index]
     start_year = 2017
     end_year = 2023

scripts/tile.py

@@ -21,7 +21,7 @@
 PIXELS_PER_TILE = TILE_SIZE * TILE_SIZE
 BAD_PIXEL_MAX_PERCENTAGE = 0.3
 SCL_FILTER = [0, 1, 3, 8, 9, 10]
-VERSION = "01"
+VERSION = "02"
 
 
 def filter_clouds_nodata(tile):
@@ -99,11 +99,18 @@ def tiler(stack, date, mgrs, bucket):
                 ] * (len(tile.band) - 3)
 
                 # Write tile to tempdir
-                name = f"{dir}/claytile-{mgrs}-{date}-{VERSION}-{counter}.tif"
+                name = "{dir}/claytile_{mgrs}_{date}_v{version}_{counter}.tif".format(
+                    dir=dir,
+                    mgrs=mgrs,
+                    date=date.replace("-", ""),
+                    version=VERSION,
+                    counter=str(counter).zfill(4),
+                )
                 tile.rio.to_raster(name, compress="deflate")
 
                 with rasterio.open(name, "r+") as rst:
                     rst.colorinterp = color
+                    rst.update_tags(date=date)
 
         print(f"Syncing {dir} with s3://{bucket}/{VERSION}/{mgrs}/{date}")
         subprocess.run(