From 536313f935619c7ccf1e8caea036de4ffb56ea20 Mon Sep 17 00:00:00 2001
From: aradhakrishnanGFDL <aparna.radhakrishnan@noaa.gov>
Date: Tue, 30 Jul 2024 21:44:41 -0400
Subject: [PATCH 1/3] builder config temporal subset change

---
 catalogbuilder/intakebuilder/builderconfig.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/catalogbuilder/intakebuilder/builderconfig.py b/catalogbuilder/intakebuilder/builderconfig.py
index 2eb95ef..0ca71ae 100644
--- a/catalogbuilder/intakebuilder/builderconfig.py
+++ b/catalogbuilder/intakebuilder/builderconfig.py
@@ -15,7 +15,7 @@
 headerlist = ["activity_id", "institution_id", "source_id", "experiment_id",
                   "frequency", "realm", "table_id",
                   "member_id", "grid_label", "variable_id",
-                  "temporal_subset", "chunk_freq","grid_label","platform","dimensions","cell_methods","path"]
+                  "time_range", "chunk_freq","grid_label","platform","dimensions","cell_methods","path"]
 
 #what kind of directory structure to expect?
 #For a directory structure like /archive/am5/am5/am5f3b1r0/c96L65_am5f3b1r0_pdclim1850F/gfdl.ncrc5-deploy-prod-openmp/pp
@@ -29,7 +29,7 @@
 
 
 output_path_template = ['NA','NA','source_id','NA','experiment_id','platform','custom_pp','realm','cell_methods','frequency','chunk_freq']
-output_file_template = ['realm','temporal_subset','variable_id']
+output_file_template = ['realm','time_range','variable_id']
 
 #OUTPUT FILE INFO is currently passed as command-line argument.
 #We will revisit adding a csvfile, jsonfile and logfile configuration to the builder configuration file in the future.

From 7c1f0ca85486809b789caaab9402fcf1a8cad402 Mon Sep 17 00:00:00 2001
From: aradhakrishnanGFDL <aparna.radhakrishnan@noaa.gov>
Date: Tue, 6 Aug 2024 13:22:59 -0400
Subject: [PATCH 2/3] quick test script to explore catalog

---
 catalogbuilder/scripts/dmget.py       |  6 ++++++
 catalogbuilder/scripts/getdatasets.py | 28 +++++++++++++++++++++++++++
 2 files changed, 34 insertions(+)
 create mode 100644 catalogbuilder/scripts/dmget.py
 create mode 100644 catalogbuilder/scripts/getdatasets.py

diff --git a/catalogbuilder/scripts/dmget.py b/catalogbuilder/scripts/dmget.py
new file mode 100644
index 0000000..4472d64
--- /dev/null
+++ b/catalogbuilder/scripts/dmget.py
@@ -0,0 +1,6 @@
+import os
+#for simple dmget usage, just use this !dmget {file}
+#use following to wrap the dmget call for each path in the catalog
+def dmgetmagic(x):
+    cmd = 'dmget %s'% str(x) 
+    return os.system(cmd)
diff --git a/catalogbuilder/scripts/getdatasets.py b/catalogbuilder/scripts/getdatasets.py
new file mode 100644
index 0000000..0e6c8d5
--- /dev/null
+++ b/catalogbuilder/scripts/getdatasets.py
@@ -0,0 +1,28 @@
+import intake_esm, intake, dmget
+cat = "/home/a1r/github/noaa-gfdl/catalogs/c96L65_am5f7b10r0_amip30_0806.json"
+col = intake.open_esm_datastore(cat)
+print("Dataframe summary")
+print("---------------------")
+print(col.df)
+#lets search
+freq = "day"
+cfname = "air_temperature"
+esmcat = col.search(frequency = freq, standard_name = cfname)
+print("Search results in:")
+print("---------------------")
+print(esmcat)
+##dmget data
+print("dmgetting")
+print("---------------------")
+dmstatus = esmcat.df["path"].apply(dmget.dmgetmagic)
+print("dgmet status")
+print("---------------------")
+dmstatus = esmcat.df["path"].apply(dmget.dmgetmagic)
+print(dmstatus)
+print("Aggregating and creating a dictionary with dataset names as keys and the values as the xarray dataset object")
+dset_dict = esmcat.to_dataset_dict(cdf_kwargs={'chunks': {'time':5}, 'decode_times': False})
+print("print dataset keys/names")
+print("---------------------")
+for k in dset_dict.keys(): 
+    print(k)
+

From 763f862607cf137f917a82d4050d48dcf82ae204 Mon Sep 17 00:00:00 2001
From: aradhakrishnanGFDL <aparna.radhakrishnan@noaa.gov>
Date: Tue, 6 Aug 2024 13:25:16 -0400
Subject: [PATCH 3/3] add time range to agg temporarily for mdtf

---
 catalogbuilder/cats/gfdl_template.json | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/catalogbuilder/cats/gfdl_template.json b/catalogbuilder/cats/gfdl_template.json
index 09bac46..63a8890 100644
--- a/catalogbuilder/cats/gfdl_template.json
+++ b/catalogbuilder/cats/gfdl_template.json
@@ -111,7 +111,8 @@
       "grid_label", 
       "realm",
       "member_id",
-      "chunk_freq"
+      "chunk_freq",
+      "time_range"
     ],
     "aggregations": [
       {