From 9a9f72b9c69bc653b5dcfc3622b251c63973dc3c Mon Sep 17 00:00:00 2001
From: Alex Merose <al@merose.com>
Date: Sat, 23 Mar 2024 20:55:21 +0530
Subject: [PATCH] Simplest version of the SST Demo.

---
 demo/sst | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)
 create mode 100644 demo/sst

diff --git a/demo/sst b/demo/sst
new file mode 100644
index 0000000..6e38b6e
--- /dev/null
+++ b/demo/sst
@@ -0,0 +1,41 @@
+#!/usr/bin/env python3
+"""Demo of calculating global average sea surface temperature (SST) with SQL.
+
+Please run the following to access the ERA5 dataset:
+```
+gcloud auth application-default login
+```
+"""
+import xarray as xr
+import xarray_sql as qr
+
+# TODO(alxmrs): Add coiled or dask cluster code. 
+
+era5_ds = xr.open_zarr(
+  'gs://gcp-public-data-arco-era5/ar/'
+  '1959-2022-full_37-1h-0p25deg-chunk-1.zarr-v2',
+  chunks={'time': 240, 'level': 1}
+)
+print('dataset opened.')
+# TODO(alxmrs): Slice to small time range based on script args.
+era5_sst_ds = era5_ds[['sea_surface_temperature']].sel(
+  level=1000,  # surface level only.
+)
+
+# chunk sizes determined from VM memory limit of 16 GB.
+c = qr.Context()
+c.create_table('era5', era5_sst_ds, chunks=dict(time=24))
+
+print('beginning query.')
+df = c.sql("""
+SELECT
+  DATE("time") as date,
+  AVG("sea_surface_temperature") as daily_avg_sst
+FROM 
+  "era5" 
+GROUP BY
+  DATE("time")
+""")
+
+# TODO(alxmrs): time slice should be in file name. 
+df.to_csv('global_avg_sst_*.cvs')
\ No newline at end of file