add grid set and tests. clean tests and conftest to amtch actual step…

src/floatmatcher/gridset.py

@@ -0,0 +1,50 @@
+# gridset.py: validated wrapper around a normalized grid dataset
+
+from dataclasses import dataclass, field
+import xarray as xr
+import numpy as np 
+
+@dataclass
+class GridSet:
+    """Thin validated wrapper around a normalized grid dataset.
+
+    Wraps a normalized ``xr.Dataset`` (coords ``lat``/``lon``, and ``time`` in
+    the 3D case), validating it at construction and deriving its regime. The
+    dataset is kept intact and accessible as ``grid.dataset``
+    """
+
+    dataset: xr.Dataset
+    # convention the Product promises; None -> skip the check
+    regime: str = field(init=False)     # "2D" or "3D", derived at construction
+
+    def __post_init__(self) -> None:
+
+        if "lon" not in self.dataset.coords or "lat" not in self.dataset.coords:
+            raise ValueError(
+                "The dataset given to GridSet object doesn't have lon or lat "
+                "coordinates"
+            )
+
+        if len(self.dataset.data_vars)<1:
+            raise ValueError("There is no variable in the dataset given to GridSet")
+
+        # test of lat/lon unicity
+        lon = self.dataset["lon"].values
+        lat = self.dataset["lat"].values
+        if len(np.unique(lon)) != len(lon):
+            raise ValueError("grid: duplicated longitudes in array")
+        if len(np.unique(lat)) != len(lat):
+            raise ValueError("grid: duplicated latitudes in array")
+
+        # select regime 3D/2D
+        if "time" in self.dataset.coords : 
+            self.regime = "3D"
+            # test time unicity if 3D regime
+            times = self.dataset["time"].values
+            if len(np.unique(times)) != len(times):
+                raise ValueError("grid: duplicate timestamps (overlapping files?)")
+        else:
+            self.regime = "2D"
+
+
+

tests/conftest.py

@@ -0,0 +1,29 @@
+# tests/conftest.py: fixtures shared across the test suite
+
+
+import numpy as np
+import pytest
+import xarray as xr
+
+from helpers import make_grid, daily_timestamps
+
+
+# ---------- grids ----------
+
+lat = [0.0, 1.0, 2.0]
+lon = [10.0, 20.0, 30.0, 40.0]
+
+
+@pytest.fixture
+def grid_2d_ds():
+    ds = make_grid(lat, lon)
+    ds["v"] = 100.0 * ds["lat"] + ds["lon"]
+    return ds
+
+
+@pytest.fixture
+def grid_3d_ds():
+    ds = make_grid(lat, lon, time=daily_timestamps(2))
+    ds["v"] = (100.0 * ds["lat"] + ds["lon"]
+               + xr.DataArray(np.arange(ds.sizes["time"]), dims="time"))
+    return ds

tests/helpers.py

@@ -1,6 +1,6 @@
 # tests/helpers.py: helpers shared across the test folder
 import numpy as np
-
+import xarray as xr
 
 def set_timestamps(*days):
     """Timestamps for the given 2015-01-xx days."""
@@ -13,3 +13,27 @@ def set_timestamps(*days):
 def daily_timestamps(n):
     """n consecutive daily timestamps starting 2015-01-01."""
     return set_timestamps(*range(1, n + 1))
+
+def make_grid(lat, lon, time=None, variables=("v",)):
+    """Build a GridSet-ready Dataset filled with zeros.
+    """
+    lat = np.asarray(lat, dtype=float)
+    lon = np.asarray(lon, dtype=float)
+    if isinstance(variables, str):
+        variables = (variables,)
+
+    if time is None:
+        dims = ("lat", "lon")
+        coords = {"lat": lat, "lon": lon}
+        shape = (lat.size, lon.size)
+    else:
+        time = np.asarray(time, dtype="datetime64[ns]")
+        dims = ("time", "lat", "lon")
+        coords = {"time": time, "lat": lat, "lon": lon}
+        shape = (time.size, lat.size, lon.size)
+
+    data_vars = {}
+    for name in variables:
+        data_vars[name] = (dims, np.zeros(shape))
+
+    return xr.Dataset(data_vars, coords=coords)

tests/test_gridset.py

@@ -0,0 +1,61 @@
+# tests/test_gridset.py
+import pytest
+
+from floatmatcher.gridset import GridSet
+
+
+# ───────────── regime derivation ─────────────
+
+def test_regime_3d(grid_3d_ds):
+    """A grid with a time coord is 3D."""
+    assert GridSet(grid_3d_ds).regime == "3D"
+
+def test_regime_2d(grid_2d_ds):
+    """A grid without a time coord is 2D."""
+    assert GridSet(grid_2d_ds).regime == "2D"
+
+
+# ───────────── validation ─────────────
+
+def test_dataset_is_kept(grid_3d_ds):
+    """GridSet wraps the dataset without transforming it."""
+    grid = GridSet(grid_3d_ds)
+    assert grid.dataset is grid_3d_ds          # same object, not a copy
+
+def test_missing_lat_3d_raises(grid_3d_ds):
+    """A grid without lat is rejected."""
+    with pytest.raises(ValueError):
+        GridSet(grid_3d_ds.drop_vars("lat"))
+
+def test_missing_lat_2d_raises(grid_2d_ds):
+    """A grid without lat is rejected."""
+    with pytest.raises(ValueError):
+        GridSet(grid_2d_ds.drop_vars("lat"))
+
+def test_no_data_variable_raises(grid_2d_ds):
+    """A grid with coords but no data variable is rejected."""
+    with pytest.raises(ValueError):
+        GridSet(grid_2d_ds.drop_vars("v"))   # removes the only variable
+
+
+
+
+# ───────────── suffled and duplicated coordinates ─────────────
+
+def test_shuffled_lon_is_accepted(grid_3d_ds):
+    """ order does not matter: the KDTree works on a point cloud"""
+    ds = grid_3d_ds.isel(lon=[2, 0, 1])            # [30,10,20] 
+    assert GridSet(ds).regime == "3D"
+
+
+def test_duplicate_lon_raises(grid_3d_ds):
+    """two nodes at the same position would make the nearest lookup ambiguous"""
+    ds = grid_3d_ds.isel(lon=[0, 1, 1])
+    with pytest.raises(ValueError):
+        GridSet(ds)
+
+
+def test_decreasing_time_is_accepted(grid_3d_ds):
+    """ decreasing time is accepted """
+    ds = grid_3d_ds.isel(time=slice(None, None, -1))
+    assert GridSet(ds).regime == "3D"