bring in eddy flux stacking code

pyproject.toml

@@ -8,7 +8,8 @@ version = "1.1.1"
 authors = [
     {name="Claire Lunch", email="clunch@battelleecology.org"},
     {name="Bridget Hass", email="bhass@battelleecology.org"},
-    {name="Zachary Nickerson", email="nickerson@battelleecology.org"}
+    {name="Zachary Nickerson", email="nickerson@battelleecology.org"},
+    {name="Michelle Sunderman", email="sunderman@battelleecology.org"}
 ]
 description="A package for accessing and wrangling data generated and published by the National Ecological Observatory Network."
 readme = "README.md"
@@ -20,7 +21,8 @@ dependencies = [
     "pyarrow",
     "pyproj",
     "requests",
-    "tqdm"
+    "tqdm",
+    "h5py"
 ]
 
 [project.license]

requirements.txt

@@ -5,4 +5,5 @@ pyarrow>=16.0.0
 pyproj>=3.6.1
 requests>=2.31.0
 tqdm>=4.66.2
-google_crc32c>=1.7.0
+h5py>=3.14.0
+google_crc32c>=1.7.0

src/neonutilities/__init__.py

@@ -12,4 +12,5 @@
     stack_by_table,
     load_by_product,
     dataset_query,
-)
+)
+from .stack_eddy import stack_eddy

src/neonutilities/get_issue_log.py

@@ -65,6 +65,10 @@ def get_change_log_df(dpid, token=None):
         return None
     all_product_info = pd.json_normalize(req.json()["data"])
     change_log_df = pd.DataFrame(all_product_info["changeLogs"][0])
+    if not change_log_df.empty:
+        change_log_df = change_log_df.astype({'id': 'int32', 'parentIssueID': 'str', 'issueDate': 'str',
+                                              'resolvedDate': 'str', 'dateRangeStart': 'str', 'dateRangeEnd': 'str',
+                                              'locationAffected': 'str', 'issue': 'str', 'resolution': 'str'})
 
     return change_log_df
 
@@ -108,13 +112,14 @@ def get_eddy_issue_log(dpid, token=None):
 
     eddy_issue_log_list = []
 
-    for dpid in bundle_dps:
-        change_log_df = get_change_log_df(dpid, token=token)
+    for dp in bundle_dps:
+        change_log_df = get_change_log_df(dp, token=token)
         if change_log_df is not None and not change_log_df.empty:
-            change_log_df["dpid"] = dpid
+            change_log_df.insert(loc=0, column="dpid", value=dp)
             eddy_issue_log_list.append(change_log_df)
 
     eddy_issue_log_df = pd.concat(eddy_issue_log_list, ignore_index=True)
+    eddy_issue_log_df = eddy_issue_log_df.drop_duplicates()
 
     return eddy_issue_log_df