Skip to content

Commit d58b0c0

Browse files
tebaditebadi
committed
Add a unit test to cover all the classes at level4
1 parent 9524c6d commit d58b0c0

File tree

1 file changed

+207
-0
lines changed

1 file changed

+207
-0
lines changed

‎tests/test_lc_level34.py‎

Lines changed: 207 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -290,3 +290,210 @@ def normalize_expression(expression):
290290
assert (
291291
normalized_generated == normalized_expected
292292
), f"Expected {expected_expressions}, but got {generated_expressions}"
293+
294+
295+
def test_level4(urban_shape):
296+
297+
level_3_4 = np.array(
298+
[
299+
[
300+
[110, 110, 110, 110, 110, 110],
301+
[110, 110, 110, 110, 110, 110],
302+
[110, 110, 110, 110, 110, 110],
303+
[110, 110, 110, 110, 110, 110],
304+
]
305+
],
306+
dtype="uint8",
307+
)
308+
309+
cultivated = np.array(
310+
[
311+
[
312+
[111, 111, 111, 111, 111, 111],
313+
[111, 111, 111, 111, 111, 111],
314+
[112, 112, 112, 112, 112, 112],
315+
[112, 112, 112, 112, 112, 112],
316+
]
317+
],
318+
dtype="uint8",
319+
)
320+
321+
urban = np.array(
322+
[
323+
[
324+
[255, 255, 255, 255, 255, 255],
325+
[255, 255, 255, 255, 255, 255],
326+
[255, 255, 255, 255, 255, 255],
327+
[255, 255, 255, 255, 255, 255],
328+
]
329+
],
330+
dtype="uint8",
331+
)
332+
333+
woody = np.array(
334+
[
335+
[
336+
[113, 114, 113, 113, 113, 113],
337+
[113, 114, 114, 114, 114, 114],
338+
[113, 114, 113, 113, 113, 113],
339+
[113, 114, 114, 114, 114, 114],
340+
]
341+
],
342+
dtype="uint8",
343+
)
344+
345+
pv_pc_50 = np.array(
346+
[
347+
[
348+
[np.nan, np.nan, 66, 41, 21, 5],
349+
[3, 66, 41, 21, 5, 3],
350+
[np.nan, np.nan, 66, 41, 21, 5],
351+
[3, 66, 41, 21, 5, 3],
352+
]
353+
],
354+
dtype="float32",
355+
)
356+
357+
water_season = np.array(
358+
[
359+
[
360+
[255, 255, 255, 255, 255, 255],
361+
[255, 255, 255, 255, 255, 255],
362+
[255, 255, 255, 255, 255, 255],
363+
[255, 255, 255, 255, 255, 255],
364+
]
365+
],
366+
dtype="uint8",
367+
)
368+
369+
water_frequency = np.array(
370+
[
371+
[
372+
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
373+
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
374+
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
375+
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
376+
]
377+
],
378+
dtype="float32",
379+
)
380+
381+
bs_pc_50 = np.array(
382+
[
383+
[
384+
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
385+
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
386+
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
387+
[np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
388+
]
389+
],
390+
dtype="float32",
391+
)
392+
393+
tuples = [
394+
(np.datetime64("2000-01-01T00"), np.datetime64("2000-01-01")),
395+
]
396+
index = pd.MultiIndex.from_tuples(tuples, names=["time", "solar_day"])
397+
398+
affine = Affine.translation(10, 0) * Affine.scale(
399+
(20 - 10) / level_3_4.shape[2], (5 - 0) / level_3_4.shape[1]
400+
)
401+
geobox = GeoBox(
402+
crs="epsg:3577",
403+
affine=affine,
404+
width=level_3_4.shape[2],
405+
height=level_3_4.shape[1],
406+
)
407+
coords = geobox.xr_coords()
408+
409+
data_vars = {
410+
"level_3_4": xr.DataArray(
411+
da.from_array(level_3_4, chunks=(1, -1, -1)),
412+
dims=("spec", "y", "x"),
413+
attrs={"nodata": 255},
414+
),
415+
"artificial_surface": xr.DataArray(
416+
da.from_array(urban, chunks=(1, -1, -1)),
417+
dims=("spec", "y", "x"),
418+
attrs={"nodata": 255},
419+
),
420+
"cultivated": xr.DataArray(
421+
da.from_array(cultivated, chunks=(1, -1, -1)),
422+
dims=("spec", "y", "x"),
423+
attrs={"nodata": 255},
424+
),
425+
"woody": xr.DataArray(
426+
da.from_array(woody, chunks=(1, -1, -1)),
427+
dims=("spec", "y", "x"),
428+
attrs={"nodata": 255},
429+
),
430+
"pv_pc_50": xr.DataArray(
431+
da.from_array(pv_pc_50, chunks=(1, -1, -1)),
432+
dims=("spec", "y", "x"),
433+
attrs={"nodata": 255},
434+
),
435+
"bs_pc_50": xr.DataArray(
436+
da.from_array(bs_pc_50, chunks=(1, -1, -1)),
437+
dims=("spec", "y", "x"),
438+
attrs={"nodata": 255},
439+
),
440+
"water_frequency": xr.DataArray(
441+
da.from_array(water_frequency, chunks=(1, -1, -1)),
442+
dims=("spec", "y", "x"),
443+
attrs={"nodata": 255},
444+
),
445+
"water_season": xr.DataArray(
446+
da.from_array(water_season, chunks=(1, -1, -1)),
447+
dims=("spec", "y", "x"),
448+
attrs={"nodata": 255},
449+
),
450+
}
451+
452+
xx = xr.Dataset(data_vars=data_vars, coords=coords)
453+
xx = xx.assign_coords(xr.Coordinates.from_pandas_multiindex(index, "spec"))
454+
455+
expected_l4 = np.array(
456+
[
457+
[2, 3, 9, 10, 11, 12],
458+
[13, 14, 15, 16, 17, 18],
459+
[20, 21, 27, 28, 29, 30],
460+
[31, 32, 33, 34, 35, 36],
461+
],
462+
dtype="uint8",
463+
)
464+
465+
expected_l3 = np.array(
466+
[
467+
[111, 111, 111, 111, 111, 111],
468+
[111, 111, 111, 111, 111, 111],
469+
[112, 112, 112, 112, 112, 112],
470+
[112, 112, 112, 112, 112, 112],
471+
],
472+
dtype="uint8",
473+
)
474+
475+
stats_l4 = StatsLccsLevel4(
476+
measurements=["level3", "level4"],
477+
class_def_path="s3://dea-public-data-dev/lccs_validation/c3/data_to_plot/"
478+
"lccs_colour_scheme_golden_dark_au_c3.csv",
479+
class_condition={
480+
"level3": ["level1", "artificial_surface", "cultivated"],
481+
"level4": [
482+
"level1",
483+
"level3",
484+
"woody",
485+
"water_season",
486+
"water_frequency",
487+
"pv_pc_50",
488+
"bs_pc_50",
489+
],
490+
},
491+
data_var_condition={"level1": "level_3_4"},
492+
urban_mask=urban_shape,
493+
filter_expression="mock > 9",
494+
mask_threshold=0.3,
495+
)
496+
ds = stats_l4.reduce(xx)
497+
498+
assert (ds.level3.compute() == expected_l3).all()
499+
assert (ds.level4.compute() == expected_l4).all()

0 commit comments

Comments
 (0)