Skip to content

zonal stats: speed up dask case #572

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Nov 16, 2021
Merged

zonal stats: speed up dask case #572

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2c6d6ea
safely removed nodata_zones arg
thuydotm Oct 27, 2021
b2d1081
dask zonal stats
thuydotm Nov 10, 2021
46b6505
dask case: support zone_ids
thuydotm Nov 10, 2021
8039d63
refactor
thuydotm Nov 15, 2021
5cd5fe4
update docs
thuydotm Nov 15, 2021
632c54a
clean code
thuydotm Nov 16, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 30 additions & 17 deletions xrspatial/tests/test_zonal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,18 +56,14 @@ def check_results(df_np, df_da, expected_results_dict):
df_np[col], expected_results_dict[col], equal_nan=True
).all()

# dask case
assert isinstance(df_da, dd.DataFrame)
df_da = df_da.compute()
assert isinstance(df_da, pd.DataFrame)

# numpy results equal dask results
# zone column
assert (df_np['zone'] == df_da['zone']).all()
if df_da is not None:
# dask case
assert isinstance(df_da, dd.DataFrame)
df_da = df_da.compute()
assert isinstance(df_da, pd.DataFrame)

assert (df_np.columns == df_da.columns).all()
for col in df_np.columns[1:]:
assert np.isclose(df_np[col], df_da[col], equal_nan=True).all()
# numpy results equal dask results, ignoring their indexes
assert np.array_equal(df_np.values, df_da.values, equal_nan=True)


def test_stats():
Expand All @@ -93,7 +89,27 @@ def test_stats():
df_da = stats(zones=zones_da, values=values_da)
check_results(df_np, df_da, default_stats_results)

# ---- custom stats ----
# expected results
stats_results_zone_0_3 = {
'zone': [0, 3],
'mean': [0, 2.4],
'max': [0, 3],
'min': [0, 0],
'sum': [0, 12],
'std': [0, 1.2],
'var': [0, 1.44],
'count': [5, 5]
}

# numpy case
df_np_zone_0_3 = stats(zones=zones_np, values=values_np, zone_ids=[0, 3])

# dask case
df_da_zone_0_3 = stats(zones=zones_da, values=values_da, zone_ids=[0, 3])

check_results(df_np_zone_0_3, df_da_zone_0_3, stats_results_zone_0_3)

# ---- custom stats (NumPy only) ----
# expected results
custom_stats_results = {
'zone': [1, 2],
Expand All @@ -115,13 +131,10 @@ def _range(values):
# numpy case
df_np = stats(
zones=zones_np, values=values_np, stats_funcs=custom_stats,
zone_ids=[1, 2], nodata_zones=0, nodata_values=0
zone_ids=[1, 2], nodata_values=0
)
# dask case
df_da = stats(
zones=zones_da, values=values_da, stats_funcs=custom_stats,
zone_ids=[1, 2], nodata_zones=0, nodata_values=0
)
df_da = None
check_results(df_np, df_da, custom_stats_results)


Expand Down
Loading