Update the band names and fix the nodata in a few LC modules.

odc/stats/plugins/l34_utils/l4_veg_cover.py

@@ -9,10 +9,10 @@ def canopyco_veg_con(xx: xr.Dataset, veg_threshold):
 
     # Mask NODATA
     pv_pc_50 = expr_eval(
-        "where(a!=nodata, a, nodata)",
+        "where(a==a, a, nodata)",
         {"a": xx.pv_pc_50.data},
         name="mark_nodata",
-        dtype="uint8",
+        dtype="float32",
         **{"nodata": NODATA},
     )
 

odc/stats/plugins/l34_utils/lc_level3.py

@@ -14,10 +14,10 @@ def lc_level3(xx: xr.Dataset):
 
     res = expr_eval(
         "where((a!=a)|(a>=nodata), b, a)",
-        {"a": xx.cultivated_class.data, "b": xx.classes_l3_l4.data},
+        {"a": xx.cultivated.data, "b": xx.classes_l3_l4.data},
         name="mask_cultivated",
         dtype="float32",
-        **{"nodata": xx.cultivated_class.attrs.get("nodata")},
+        **{"nodata": xx.cultivated.attrs.get("nodata")},
     )
 
     # Mask urban results with bare sfc (210)

odc/stats/plugins/l34_utils/lc_lifeform.py

@@ -1,14 +1,25 @@
 from odc.stats._algebra import expr_eval
 import xarray as xr
 
+NODATA = 255
+
 
 def lifeform(xx: xr.Dataset):
 
     # 113 ----> 1 woody
     # 114 ----> 2 herbaceous
+
+    lifeform_mask = expr_eval(
+        "where((a!=a)|(a>=nodata), nodata, a)",
+        {"a": xx.woody.data},
+        name="mark_lifeform",
+        dtype="float32",
+        **{"nodata": NODATA},
+    )
+
     lifeform_mask = expr_eval(
         "where(a==113, 1, a)",
-        {"a": xx.woody_cover.data},
+        {"a": lifeform_mask},
         name="mark_lifeform",
         dtype="uint8",
     )

odc/stats/plugins/l34_utils/lc_water_seasonality.py

@@ -12,11 +12,11 @@ def water_seasonality(xx: xr.Dataset, water_seasonality_threshold):
 
     # Apply nodata
     water_frequency = expr_eval(
-        "where((a==watersea_nodata), nodata, a)",
+        "where((a!=a)|(a==watersea_nodata), nodata, a)",
         {"a": xx.water_frequency.data},
         name="mark_water_season",
-        dtype="uint8",
-        **{"watersea_nodata": WATER_FREQ_NODATA, "nodata": NODATA},
+        dtype="float32",
+        **{"nodata": NODATA, "watersea_nodata": WATER_FREQ_NODATA},
     )
 
     water_season_mask = expr_eval(

odc/stats/plugins/lc_level34.py

@@ -94,9 +94,7 @@ def reduce(self, xx: xr.Dataset) -> xr.Dataset:
             xx, self.bare_threshold, veg_cover
         )
 
-        l4 = l4_natural_aquatic.natural_auquatic_veg(
-            l4, lifeform, veg_cover, water_seasonality
-        )
+        l4 = l4_natural_aquatic.natural_auquatic_veg(l4, veg_cover, water_seasonality)
 
         level4 = l4_surface.lc_l4_surface(l4, level3, bare_gradation)
 

odc/stats/plugins/lc_veg_class_a1.py

@@ -149,7 +149,7 @@ def l3_class(self, xx: xr.Dataset):
                         {"a": data, "b": l3_mask},
                         name="intertidal_veg",
                         dtype="uint8",
-                        **{"m": self.output_classes["aquatic_veg"]},
+                        **{"m": self.output_classes["aquatic_veg_herb"]},
                     )
                 elif b == "canopy_cover_class":
                     # aquatic_veg: (mangroves > 0) & (mangroves != nodata)
@@ -161,7 +161,7 @@ def l3_class(self, xx: xr.Dataset):
                         dtype="uint8",
                         **{
                             "nodata": xx[b].attrs["nodata"],
-                            "m": self.output_classes["aquatic_veg"],
+                            "m": self.output_classes["aquatic_veg_wood"],
                         },
                     )
 

tests/test_landcover_plugin_a1.py

@@ -128,7 +128,8 @@ def dataset():
 def test_l3_classes(dataset):
     stats_l3 = StatsVegClassL1(
         output_classes={
-            "aquatic_veg": 124,
+            "aquatic_veg_wood": 124,
+            "aquatic_veg_herb": 125,
             "terrestrial_veg": 110,
             "water": 221,
             "intertidal": 223,
@@ -141,7 +142,7 @@ def test_l3_classes(dataset):
     expected_res = np.array(
         [
             [
-                [223, 221, 210, 124],
+                [223, 221, 210, 125],
                 [223, 223, 223, 210],
                 [223, 221, 223, 223],
                 [221, 223, 223, 223],
@@ -157,7 +158,8 @@ def test_l3_classes(dataset):
 def test_l4_water_seasonality(dataset):
     stats_l3 = StatsVegClassL1(
         output_classes={
-            "aquatic_veg": 124,
+            "aquatic_veg_wood": 124,
+            "aquatic_veg_herb": 125,
             "terrestrial_veg": 110,
             "water": 221,
             "intertidal": 223,
@@ -203,7 +205,8 @@ def test_l4_water_seasonality(dataset):
 def test_reduce(dataset):
     stats_l3 = StatsVegClassL1(
         output_classes={
-            "aquatic_veg": 124,
+            "aquatic_veg_wood": 124,
+            "aquatic_veg_herb": 125,
             "terrestrial_veg": 110,
             "water": 221,
             "intertidal": 223,

tests/test_lc_l34.py

@@ -116,12 +116,12 @@ def image_groups():
             dims=("spec", "y", "x"),
             attrs={"nodata": 255},
         ),
-        "cultivated_class": xr.DataArray(
+        "cultivated": xr.DataArray(
             da.from_array(cultivated, chunks=(1, -1, -1)),
             dims=("spec", "y", "x"),
             attrs={"nodata": 255},
         ),
-        "woody_cover": xr.DataArray(
+        "woody": xr.DataArray(
             da.from_array(woody, chunks=(1, -1, -1)),
             dims=("spec", "y", "x"),
             attrs={"nodata": 255},

tests/test_lc_l4_ctv.py

@@ -37,12 +37,12 @@ def image_groups(l34, urban, cultivated, woody, pv_pc_50):
             dims=("spec", "y", "x"),
             attrs={"nodata": 255},
         ),
-        "cultivated_class": xr.DataArray(
+        "cultivated": xr.DataArray(
             da.from_array(cultivated, chunks=(1, -1, -1)),
             dims=("spec", "y", "x"),
             attrs={"nodata": 255},
         ),
-        "woody_cover": xr.DataArray(
+        "woody": xr.DataArray(
             da.from_array(woody, chunks=(1, -1, -1)),
             dims=("spec", "y", "x"),
             attrs={"nodata": 255},
@@ -300,6 +300,7 @@ def test_ctv_classes_woody_herbaceous():
     l4_ctv = l4_cultivated.lc_l4_cultivated(
         xx.classes_l3_l4, level3, lifeform, veg_cover
     )
+
     assert (l4_ctv.compute() == expected_cultivated_classes).all()
 
 

tests/test_lc_l4_natural_surface.py

@@ -46,12 +46,12 @@ def image_groups(l34, urban, woody, bs_pc_50, pv_pc_50, cultivated, water_freque
             dims=("spec", "y", "x"),
             attrs={"nodata": 255},
         ),
-        "cultivated_class": xr.DataArray(
+        "cultivated": xr.DataArray(
             da.from_array(cultivated, chunks=(1, -1, -1)),
             dims=("spec", "y", "x"),
             attrs={"nodata": 255},
         ),
-        "woody_cover": xr.DataArray(
+        "woody": xr.DataArray(
             da.from_array(woody, chunks=(1, -1, -1)),
             dims=("spec", "y", "x"),
             attrs={"nodata": 255},
@@ -188,7 +188,7 @@ def test_ns():
         xx, stats_l4.water_seasonality_threshold
     )
     l4_ctv_ntv_nav = l4_natural_aquatic.natural_auquatic_veg(
-        l4_ctv_ntv, lifeform, veg_cover, water_seasonality
+        l4_ctv_ntv, veg_cover, water_seasonality
     )
 
     # Bare gradation