From d34455d09b55f75c15d836a3112ad88463fef552 Mon Sep 17 00:00:00 2001
From: Wei Ji <weiji.leong@vuw.ac.nz>
Date: Wed, 27 May 2020 22:34:40 +1200
Subject: [PATCH] :card_file_box: Chunk ATL11 dataset along cycle_number when
 loading

Reading in all our ATL11 Zarr files in chunks of 6 along "cycle_number". Should be a bit more optimal (fingers crossed) when calculating along the time dimension, compared to having chunks with 2 "cycle_number"s before. Needed for what is coming next - calculating dhdt over Antarctica! But first, we'll need to package up some of the functions properly.
---
 atl11_play.ipynb | 3 +++
 atl11_play.py    | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/atl11_play.ipynb b/atl11_play.ipynb
index 69bef72..3598287 100644
--- a/atl11_play.ipynb
+++ b/atl11_play.ipynb
@@ -123,8 +123,11 @@
    },
    "outputs": [],
    "source": [
+    "# Load dataset from all Zarr stores\n",
+    "# Aligning chunks spatially along cycle_number (i.e. time)\n",
     "ds = xr.open_mfdataset(\n",
     "    paths=stores,\n",
+    "    chunks={\"cycle_number\": 6},\n",
     "    group=\"pt123\",\n",
     "    engine=\"zarr\",\n",
     "    combine=\"nested\",\n",
diff --git a/atl11_play.py b/atl11_play.py
index 8451279..1ca6b76 100644
--- a/atl11_play.py
+++ b/atl11_play.py
@@ -63,8 +63,11 @@
 print(f"{len(stores)} reference ground track Zarr stores")
 
 # %%
+# Load dataset from all Zarr stores
+# Aligning chunks spatially along cycle_number (i.e. time)
 ds = xr.open_mfdataset(
     paths=stores,
+    chunks={"cycle_number": 6},
     group="pt123",
     engine="zarr",
     combine="nested",