xarray-regrid/tests/test_reduce.py at f73194700b806099660f75bbd0bc2351bb3f4479 · xarray-contrib/xarray-regrid · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
import numpy as np
import pytest
import xarray as xr
from numpy.testing import assert_array_equal

from xarray_regrid import Grid, create_regridding_dataset

EXP_LABELS = np.array([0, 1, 2, 3])  # labels that are in the dummy data


@pytest.fixture
def dummy_lc_data():
    data = np.array(
        [
            [2, 2, 2, 2, 0, 0, 0, 0, 0, 0, 0],
            [2, 2, 0, 2, 0, 0, 0, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
            [3, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1],
            [3, 3, 3, 3, 0, 0, 0, 0, 1, 1, 1],
            [3, 3, 0, 3, 0, 0, 0, 0, 1, 1, 1],
        ]
    )
    lat_coords = np.linspace(0, 40, num=11)
    lon_coords = np.linspace(0, 40, num=11)

    ds = xr.Dataset(
        data_vars={
            "lc": (["longitude", "latitude"], data),
        },
        coords={
            "longitude": (["longitude"], lon_coords),
            "latitude": (["latitude"], lat_coords),
        },
        attrs={"test": "not empty"},
    )
    ds["longitude"].attrs = {"units": "degrees_east"}
    ds["latitude"].attrs = {"units": "degrees_north"}
    return ds


def make_expected_ds(expected_data) -> xr.Dataset:
    lat_coords = np.linspace(0, 40, num=6)
    lon_coords = np.linspace(0, 40, num=6)

    return xr.Dataset(
        data_vars={
            "lc": (["longitude", "latitude"], expected_data),
        },
        coords={
            "longitude": (["longitude"], lon_coords),
            "latitude": (["latitude"], lat_coords),
        },
    )


@pytest.fixture
def dummy_target_grid():
    new_grid = Grid(
        north=40,
        east=40,
        south=0,
        west=0,
        resolution_lat=8,
        resolution_lon=8,
    )
    return create_regridding_dataset(new_grid)


@pytest.fixture
def oversized_dummy_target_grid():
    new_grid = Grid(
        north=48,
        east=48,
        south=-8,
        west=-8,
        resolution_lat=8,
        resolution_lon=8,
    )
    return create_regridding_dataset(new_grid)


def test_most_common(dummy_lc_data, dummy_target_grid):
    expected_data = np.array(
        [
            [2, 2, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0],
            [0, 0, 0, 0, 0, 0],
            [3, 3, 0, 0, 0, 1],
        ],
        dtype="uint8",
    )
    input_data_int = dummy_lc_data["lc"].astype("uint8")

    regrid_result = input_data_int.regrid.most_common(
        dummy_target_grid,
        values=EXP_LABELS,
    )
    xr.testing.assert_equal(
        regrid_result,
        make_expected_ds(expected_data)["lc"],
    )

    assert regrid_result.dtype == input_data_int.dtype


def test_least_common(dummy_lc_data, dummy_target_grid):
    # Currently just test if the method runs: code is 99% the same as most_common
    dummy_lc_data["lc"].regrid.least_common(
        dummy_target_grid,
        values=EXP_LABELS,
    )


def test_oversized_most_common(dummy_lc_data, oversized_dummy_target_grid):
    expected_data = np.array(
        [
            [np.nan, np.nan, np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
            [np.nan, 2, 2, 0, 0, 0, 0, np.nan],
            [np.nan, 0, 0, 0, 0, 0, 0, np.nan],
            [np.nan, 0, 0, 0, 0, 0, 0, np.nan],
            [np.nan, 0, 0, 0, 0, 0, 0, np.nan],
            [np.nan, 0, 0, 0, 0, 0, 0, np.nan],
            [np.nan, 3, 3, 0, 0, 0, 1, np.nan],
            [np.nan, np.nan, np.nan, np.nan, np.nan, np.nan, np.nan, np.nan],
        ]
    )

    lat_coords = np.linspace(-8, 48, num=8)
    lon_coords = np.linspace(-8, 48, num=8)

    expected = xr.Dataset(
        data_vars={
            "lc": (["longitude", "latitude"], expected_data),
        },
        coords={
            "longitude": (["longitude"], lon_coords),
            "latitude": (["latitude"], lat_coords),
        },
    )
    xr.testing.assert_equal(
        dummy_lc_data["lc"].regrid.most_common(
            oversized_dummy_target_grid,
            values=EXP_LABELS,
        ),
        expected["lc"],
    )


def test_attrs_dataarray(dummy_lc_data, dummy_target_grid):
    dummy_lc_data["lc"].attrs = {"test": "testing"}
    da_regrid = dummy_lc_data["lc"].regrid.most_common(
        dummy_target_grid,
        values=EXP_LABELS,
    )
    assert da_regrid.attrs != {}
    assert da_regrid.attrs == dummy_lc_data["lc"].attrs
    assert da_regrid["longitude"].attrs == dummy_target_grid["longitude"].attrs


@pytest.mark.xfail  # most common currently does not work for datasets
def test_attrs_dataset(dummy_lc_data, dummy_target_grid):
    ds_regrid = dummy_lc_data.regrid.most_common(
        dummy_target_grid,
        values=EXP_LABELS,
    )
    assert ds_regrid.attrs != {}
    assert ds_regrid.attrs == dummy_lc_data.attrs
    assert ds_regrid["longitude"].attrs == dummy_target_grid["longitude"].attrs


@pytest.mark.parametrize("dataarray", [True])  # most common does not work for datasets
def test_coord_order_original(dummy_lc_data, dummy_target_grid, dataarray):
    input_data = dummy_lc_data["lc"] if dataarray else dummy_lc_data
    ds_regrid = input_data.regrid.most_common(
        dummy_target_grid,
        values=EXP_LABELS,
    )
    assert_array_equal(ds_regrid["latitude"], dummy_target_grid["latitude"])
    assert_array_equal(ds_regrid["longitude"], dummy_target_grid["longitude"])


@pytest.mark.parametrize("coord", ["latitude", "longitude"])
@pytest.mark.parametrize("dataarray", [True])  # most common does not work for datasets
def test_coord_order_reversed(dummy_lc_data, dummy_target_grid, coord, dataarray):
    input_data = dummy_lc_data["lc"] if dataarray else dummy_lc_data
    dummy_target_grid[coord] = list(reversed(dummy_target_grid[coord]))
    ds_regrid = input_data.regrid.most_common(
        dummy_target_grid,
        values=EXP_LABELS,
    )
    assert_array_equal(ds_regrid["latitude"], dummy_target_grid["latitude"])
    assert_array_equal(ds_regrid["longitude"], dummy_target_grid["longitude"])


def test_min(dummy_lc_data, dummy_target_grid):
    expected_data = np.array(
        [
            [2.0, 2.0, 0.0, 0.0, 0.0, 0.0],
            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
            [3.0, 0.0, 0.0, 0.0, 0.0, 1.0],
        ]
    )

    xr.testing.assert_equal(
        dummy_lc_data["lc"].astype(float).regrid.stat(dummy_target_grid, "min"),
        make_expected_ds(expected_data)["lc"],
    )


def test_var(dummy_lc_data, dummy_target_grid):
    expected_data = np.array(
        [
            [0.0, 0.0, 1.0, 0.0, 0.0, 0.0],
            [1.0, 0.75, 0.75, 0.0, 0.0, 0.0],
            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
            [2.25, 0.0, 0.0, 0.0, 0.0, 0.25],
            [0.0, 1.6875, 2.25, 0.0, 0.25, 0.0],
        ]
    )

    xr.testing.assert_equal(
        dummy_lc_data["lc"].astype(float).regrid.stat(dummy_target_grid, "var"),
        make_expected_ds(expected_data)["lc"],
    )


def test_unsorted_coords(dummy_lc_data, dummy_target_grid):
    """Should pass if the input data has coords that are not ordered."""
    expected_data = np.array(
        [
            [0.0, 0.0, 1.0, 0.0, 0.0, 0.0],
            [1.0, 0.75, 0.75, 0.0, 0.0, 0.0],
            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
            [0.0, 0.0, 0.0, 0.0, 0.0, 0.0],
            [2.25, 0.0, 0.0, 0.0, 0.0, 0.25],
            [0.0, 1.6875, 2.25, 0.0, 0.25, 0.0],
        ]
    )
    lc_data = dummy_lc_data.copy()

    lc_data["scramble_order"] = lc_data["latitude"] * 0 + np.array(
        [1, 3, 7, 0, 2, 8, 9, -1, 5, 11, 12]
    )
    lc_data = lc_data.sortby("scramble_order")

    xr.testing.assert_equal(
        lc_data["lc"].astype(float).regrid.stat(dummy_target_grid, "var"),
        make_expected_ds(expected_data)["lc"],
    )