🐛 fix the andro datasets (#489)

* fix url

* put back decode_times default value to True

* update docstring

* Enhance andro tests

* format

* bump version

---------

Co-authored-by: Kevin Santana <[email protected]>

clouddrift/adapters/andro.py

@@ -29,9 +29,9 @@
 from clouddrift.adapters.utils import download_with_progress
 
 # order of the URLs is important
-ANDRO_URL = "https://www.seanoe.org/data/00360/47077/data/91950.dat"
+ANDRO_URL = "https://www.seanoe.org/data/00360/47077/data/109566.dat"
 ANDRO_TMP_PATH = os.path.join(tempfile.gettempdir(), "clouddrift", "andro")
-ANDRO_VERSION = "2022-03-04"
+ANDRO_VERSION = "2024-03-25"
 
 
 def to_xarray(tmp_path: str | None = None):
@@ -325,7 +325,7 @@ def to_xarray(tmp_path: str | None = None):
 
     # global attributes
     attrs = {
-        "title": "ANDRO: An Argo-based deep displacement dataset",
+        "title": "ANDRO: An Argo-based deep displacement dataset (Quality controlled data)",
         "history": f"Dataset updated on {ANDRO_VERSION}",
         "date_created": datetime.now().isoformat(),
         "publisher_name": "SEANOE (SEA scieNtific Open data Edition)",

clouddrift/datasets.py

@@ -549,7 +549,7 @@ def yomaha(decode_times: bool = True) -> xr.Dataset:
     return _dataset_filecache("yomaha.nc", decode_times, adapters.yomaha.to_xarray)
 
 
-def andro(decode_times: bool = False) -> xr.Dataset:
+def andro(decode_times: bool = True) -> xr.Dataset:
     """Returns the ANDRO as a ragged array Xarray dataset.
 
     The function will first look for the ragged-array dataset on the local
@@ -573,36 +573,36 @@ def andro(decode_times: bool = False) -> xr.Dataset:
     >>> from clouddrift.datasets import andro
     >>> ds = andro()
     >>> ds
-    <xarray.Dataset>
-    Dimensions:     (obs: 1360753, traj: 9996)
+    <xarray.Dataset> Size: 110MB
+    Dimensions:     (obs: 510630, traj: 3344)
     Coordinates:
-        time_d      (obs) datetime64[ns] ...
-        time_s      (obs) datetime64[ns] ...
-        time_lp     (obs) datetime64[ns] ...
-        time_lc     (obs) datetime64[ns] ...
-        id          (traj) int64 ...
+        time_d      (obs) datetime64[ns] 4MB ...
+        time_s      (obs) datetime64[ns] 4MB ...
+        time_lp     (obs) datetime64[ns] 4MB ...
+        time_lc     (obs) datetime64[ns] 4MB ...
+        id          (traj) float32 13kB ...
     Dimensions without coordinates: obs, traj
     Data variables: (12/33)
-        lon_d       (obs) float64 ...
-        lat_d       (obs) float64 ...
-        pres_d      (obs) float32 ...
-        temp_d      (obs) float32 ...
-        sal_d       (obs) float32 ...
-        ve_d        (obs) float32 ...
+        lon_d       (obs) float64 4MB ...
+        lat_d       (obs) float64 4MB ...
+        pres_d      (obs) float32 2MB ...
+        temp_d      (obs) float32 2MB ...
+        sal_d       (obs) float32 2MB ...
+        ve_d        (obs) float32 2MB ...
         ...          ...
-        lon_lc      (obs) float64 ...
-        lat_lc      (obs) float64 ...
-        surf_fix    (obs) int64 ...
-        cycle       (obs) int64 ...
-        profile_id  (obs) float32 ...
-        rowsize     (traj) int64 ...
+        lon_lc      (obs) float64 4MB ...
+        lat_lc      (obs) float64 4MB ...
+        surf_fix    (obs) float32 2MB ...
+        cycle       (obs) float32 2MB ...
+        profile_id  (obs) float32 2MB ...
+        rowsize     (traj) int64 27kB ...
     Attributes:
-        title:           ANDRO: An Argo-based deep displacement dataset
-        history:         2022-03-04
-        date_created:    2023-12-08T00:52:00.937120
+        title:           ANDRO: An Argo-based deep displacement dataset (Quality ...
+        history:         Dataset updated on 2024-03-25
+        date_created:    2024-07-02T12:11:50.643492
         publisher_name:  SEANOE (SEA scieNtific Open data Edition)
         publisher_url:   https://www.seanoe.org/data/00360/47077/
-        license:         freely available
+        license:         Creative Commons Attribution 4.0 International License (...
 
     Reference
     ---------

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "clouddrift"
-version = "0.38.1"
+version = "0.39.0"
 
 authors = [
   { name="Shane Elipot", email="[email protected]" },

tests/datasets_tests.py

@@ -49,7 +49,16 @@ def test_subsurface_floats_opens(self):
 
     def test_andro_opens(self):
         with datasets.andro() as ds:
-            self.assertTrue(ds)
+            self.assertTrue(ds is not None)
+            self.assertTrue(len(ds.variables) > 0)
+            self.assertTrue(len(ds["lon_d"]) > 0)
+
+            self.assertTrue(
+                len(ds.lat_d[np.logical_or(ds.lat_d > 90, ds.lat_d < -90)]) == 0
+            )
+            self.assertTrue(
+                len(ds.lat_d[np.logical_or(ds.lon_d > 180, ds.lon_d < -180)]) == 0
+            )
 
     def test_yomaha_opens(self):
         with datasets.yomaha() as ds: