Merge pull request #94 from voto-ocean-knowledge/callum-patch-0

add simple glider data example

docs/source/examples/QartodTestExample_Glider.ipynb

@@ -0,0 +1,218 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "\n",
+    "Import ioos qc libraries, as well as erddapy for data fetching and Bokeh for plotting"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import ioos_qc\n",
+    "from ioos_qc.config import Config\n",
+    "from ioos_qc.qartod import aggregate\n",
+    "from ioos_qc.streams import XarrayStream\n",
+    "from ioos_qc.results import collect_results, CollectedResult\n",
+    "import xarray as xr\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import pooch\n",
+    "from bokeh.plotting import output_notebook\n",
+    "\n",
+    "output_notebook()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load the dataset\n",
+    "\n",
+    "Here we use a glider mission from the Baltic as a test dataset.\n",
+    "\n",
+    "https://observations.voiceoftheocean.org/SEA067/M37"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "url = f\"https://github.com/ioos/ioos_qc/releases/download\"\n",
+    "version = \"2.1.0\"\n",
+    "fname = \"nrt_SEA067_M37.nc\"\n",
+    "\n",
+    "download = pooch.retrieve(\n",
+    "    url=f\"{url}/{version}/{fname}\",\n",
+    "    known_hash=\"sha256:06e8a79cc17a2d55bb32dbfdc85f9922c1a1cc14726df004ae971125f91b27ac\",\n",
+    ")\n",
+    "ds = xr.open_dataset(download)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Generate test configs \n",
+    "Make dictionaries of test configurations for salinity. To generate salinity flags, we test against salinity, conductivity and temperature"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "config = {\n",
+    "    \"temperature\": {\n",
+    "        \"qartod\": {\n",
+    "            \"gross_range_test\": {\"suspect_span\": [0, 30], \"fail_span\": [-2.5, 40]},\n",
+    "            \"spike_test\": {\"suspect_threshold\": 2.0, \"fail_threshold\": 6.0}\n",
+    "        }\n",
+    "    },\n",
+    "    \"conductivity\": {\n",
+    "        \"qartod\": {\n",
+    "            \"gross_range_test\": {\"suspect_span\": [6, 42], \"fail_span\": [3, 45]}\n",
+    "        }\n",
+    "    },\n",
+    "    \"salinity\": {\n",
+    "        \"qartod\": {\n",
+    "            \"gross_range_test\": {\"suspect_span\": [5, 38], \"fail_span\": [2, 41]},\n",
+    "            \"spike_test\": {\"suspect_threshold\": 0.3, \"fail_threshold\": 0.9},\n",
+    "            \"location_test\": {\"bbox\": [10, 50, 25, 60]},\n",
+    "        }\n",
+    "    }\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Run the QC\n",
+    "Create the config stream and run it on the salinity data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "c = Config(config)\n",
+    "qc = XarrayStream(ds, lon=\"longitude\", lat=\"latitude\")\n",
+    "runner = list(qc.run(c))\n",
+    "results = collect_results(runner, how='list')\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Aggregate results\n",
+    "\n",
+    "This makes the plotting a bit simpler, as we roll up the flags into one array"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agg = CollectedResult(\n",
+    "    stream_id='',\n",
+    "    package='qartod',\n",
+    "    test='qc_rollup',\n",
+    "    function=aggregate,\n",
+    "    results=aggregate(results),\n",
+    "    tinp=qc.time(),\n",
+    "    data=ds\n",
+    ")\n",
+    "flag_vals = agg.results"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Plot results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "time = ds.time\n",
+    "meaning = np.empty(len(time), dtype=object)\n",
+    "meaning[:] = \"UNKNOWN\"\n",
+    "meaning[flag_vals == 1] = \"GOOD\"\n",
+    "meaning[flag_vals == 9] = \"MISSING\"\n",
+    "meaning[flag_vals == 3] = \"SUSPECT\"\n",
+    "meaning[flag_vals == 4] = \"FAIL\"\n",
+    "df = pd.DataFrame({\"time\": time, \"salinity\": ds[\"salinity\"], \"flag\": flag_vals, \"depth\": ds.depth, \"quality control\": meaning})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from bokeh.plotting import figure, show\n",
+    "from bokeh.sampledata.penguins import data\n",
+    "from bokeh.transform import factor_cmap, factor_mark\n",
+    "\n",
+    "flag_vals = [\"GOOD\",\"UNKNOWN\",\"MISSING\",\"SUSPECT\",\"FAIL\"]\n",
+    "markers = ['hex', 'circle_x', 'circle', 'triangle', 'square']\n",
+    "\n",
+    "p = figure(title = \"Salinity flags\", background_fill_color=\"#fafafa\", x_axis_type='datetime')\n",
+    "p.yaxis.axis_label = 'salinity (PSU)'\n",
+    "\n",
+    "p.scatter(\"time\", \"salinity\", source=df,\n",
+    "          legend_group=\"quality control\", fill_alpha=0.4, size=12,\n",
+    "          marker=factor_mark('quality control', markers, flag_vals),\n",
+    "          color=factor_cmap('quality control', 'Category10_5', flag_vals))\n",
+    "\n",
+    "p.legend.location = \"top_left\"\n",
+    "p.legend.title = \"IOOS flags\"\n",
+    "\n",
+    "show(p)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  },
+  "nbsphinx": {
+   "orphan": true
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}