Skip to content

Commit 1b9a12b

Browse files
mfisher87mfisher87
committed
Init demo notebook for GJ module
1 parent 9324834 commit 1b9a12b

File tree

1 file changed

+388
-0
lines changed

1 file changed

+388
-0
lines changed

‎modules/06-geojupyter/demo.ipynb‎

Lines changed: 388 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,388 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"id": "ccb0fe8e-6b86-403f-84e0-c910f70bfc23",
6+
"metadata": {},
7+
"source": [
8+
"# JupyterGIS demo"
9+
]
10+
},
11+
{
12+
"cell_type": "markdown",
13+
"id": "6a1dcd59-5bd5-4e1a-93d3-8e0850aacc9e",
14+
"metadata": {},
15+
"source": [
16+
"## Outline\n",
17+
"\n",
18+
"* Aggregate gridded data based on vector regions (e.g. neighborhoods) \n",
19+
" * Not straightforward to do in Python \n",
20+
" * Design:\n",
21+
" * Start in a Notebook, prepared with Maryam’s expertise \n",
22+
" * Loading GeoPandas, tools for Zonal Statistics \n",
23+
" * Programmatically create .jGIS document, add input data sources and output data sources. \n",
24+
" * Demonstrate collaboration of JGIS alongside Notebook. Annotation, ad layer from catalog, etc. \n",
25+
" * Examples: \n",
26+
" * [https://medium.com/data-science/zonal-statistics-algorithm-with-python-in-4-steps-382a3b66648a](https://medium.com/data-science/zonal-statistics-algorithm-with-python-in-4-steps-382a3b66648a) \n",
27+
" * [https://automating-gis-processes.github.io/CSC18/lessons/L6/zonal-statistics.html](https://automating-gis-processes.github.io/CSC18/lessons/L6/zonal-statistics.html) \n",
28+
" * [https://carpentries-incubator.github.io/geospatial-python/10-zonal-statistics.html](https://carpentries-incubator.github.io/geospatial-python/10-zonal-statistics.html) \n",
29+
" * From Carl: [https://espm-288.carlboettiger.info/tutorials/python/spatial-4.html](https://espm-288.carlboettiger.info/tutorials/python/spatial-4.html)"
30+
]
31+
},
32+
{
33+
"cell_type": "markdown",
34+
"id": "0b259e2b-0758-430d-ba4e-d48184395473",
35+
"metadata": {},
36+
"source": [
37+
"## From geopythontutorials.com\n",
38+
"\n",
39+
"https://www.geopythontutorials.com/notebooks/xarray_zonal_stats.html?utm_source=chatgpt.com\n",
40+
"\n",
41+
"New dependencies\n",
42+
"\n",
43+
"* rioxarray\n",
44+
"* geocube\n",
45+
"* xarray-spatial"
46+
]
47+
},
48+
{
49+
"cell_type": "markdown",
50+
"id": "a2a3aa9d-1a0e-4065-b7c3-b99492a81800",
51+
"metadata": {},
52+
"source": [
53+
"### Download the data"
54+
]
55+
},
56+
{
57+
"cell_type": "code",
58+
"execution_count": null,
59+
"id": "6b7b45a4-c41a-4c68-8fa2-d7472898af0a",
60+
"metadata": {},
61+
"outputs": [],
62+
"source": [
63+
"import os\n",
64+
"\n",
65+
"data_folder = \"data\"\n",
66+
"\n",
67+
"def download(url, data_folder):\n",
68+
" filename = os.path.join(data_folder, os.path.basename(url))\n",
69+
" if not os.path.exists(filename):\n",
70+
" from urllib.request import urlretrieve\n",
71+
" local, _ = urlretrieve(url, filename)\n",
72+
" print('Downloaded ' + local)\n",
73+
"\n",
74+
"raster_file = 'chirps-v2.0.2021.tif'\n",
75+
"zones_file = 'cb_2021_us_county_500k.zip'\n",
76+
"\n",
77+
"files = [\n",
78+
" 'https://data.chc.ucsb.edu/products/CHIRPS-2.0/global_annual/tifs/' + raster_file,\n",
79+
" 'https://www2.census.gov/geo/tiger/GENZ2021/shp/' + zones_file,\n",
80+
"]\n",
81+
"\n",
82+
"for file in files:\n",
83+
" download(file, data_folder)"
84+
]
85+
},
86+
{
87+
"cell_type": "markdown",
88+
"id": "742d07d7-e745-4e9f-8c46-2662be64e54f",
89+
"metadata": {},
90+
"source": [
91+
"### Data pre-processing"
92+
]
93+
},
94+
{
95+
"cell_type": "code",
96+
"execution_count": null,
97+
"id": "17aa7d8f-51a5-4022-b784-5c6021053f65",
98+
"metadata": {},
99+
"outputs": [],
100+
"source": [
101+
"import geopandas as gpd\n",
102+
"\n",
103+
"zones_file_path = os.path.join(data_folder, zones_file)\n",
104+
"\n",
105+
"zones_df = gpd.read_file(zones_file_path)\n",
106+
"# TODO: Louisiana instead?\n",
107+
"california_df = zones_df[zones_df['STATE_NAME'] == 'California'].copy()\n",
108+
"california_df.iloc[:5, :5]"
109+
]
110+
},
111+
{
112+
"cell_type": "code",
113+
"execution_count": null,
114+
"id": "68ead58b-fd90-4a30-8cc3-f94b362f09f0",
115+
"metadata": {},
116+
"outputs": [],
117+
"source": [
118+
"california_df['GEOID'] = california_df.GEOID.astype(int)"
119+
]
120+
},
121+
{
122+
"cell_type": "code",
123+
"execution_count": null,
124+
"id": "da98d0a2-b1cc-4a6b-8754-2df48918c3b9",
125+
"metadata": {},
126+
"outputs": [],
127+
"source": [
128+
"import rioxarray as rxr\n",
129+
"\n",
130+
"raster_filepath = os.path.join(data_folder, raster_file)\n",
131+
"raster = rxr.open_rasterio(raster_filepath, mask_and_scale=True)\n",
132+
"clipped = raster.rio.clip(california_df.geometry)\n",
133+
"clipped"
134+
]
135+
},
136+
{
137+
"cell_type": "code",
138+
"execution_count": null,
139+
"id": "e2f81cff-8836-43c1-9477-4950b771bc79",
140+
"metadata": {},
141+
"outputs": [],
142+
"source": [
143+
"precipitation = clipped.sel(band=1)\n",
144+
"precipitation"
145+
]
146+
},
147+
{
148+
"cell_type": "code",
149+
"execution_count": null,
150+
"id": "0b1f55b7-081b-43ec-9bbb-55295a1cb42a",
151+
"metadata": {},
152+
"outputs": [],
153+
"source": [
154+
"from geocube.api.core import make_geocube\n",
155+
"\n",
156+
"california_raster = make_geocube(\n",
157+
" vector_data=california_df,\n",
158+
" measurements=['GEOID'],\n",
159+
" like=precipitation,\n",
160+
")\n",
161+
"california_raster"
162+
]
163+
},
164+
{
165+
"cell_type": "code",
166+
"execution_count": null,
167+
"id": "216b6a74-b543-4896-8348-f84b80babecb",
168+
"metadata": {},
169+
"outputs": [],
170+
"source": [
171+
"from xrspatial import zonal_stats\n",
172+
"\n",
173+
"stats_df = zonal_stats(zones=california_raster.GEOID, values=precipitation)\n",
174+
"stats_df.iloc[:5]"
175+
]
176+
},
177+
{
178+
"cell_type": "code",
179+
"execution_count": null,
180+
"id": "ae05145f-b31c-4d10-8c3e-852c722fa0ec",
181+
"metadata": {},
182+
"outputs": [],
183+
"source": [
184+
"stats_df['GEOID'] = stats_df['zone'].astype(int)"
185+
]
186+
},
187+
{
188+
"cell_type": "code",
189+
"execution_count": null,
190+
"id": "aa371396-e42b-4c18-a07f-7d2eb8cb0ad6",
191+
"metadata": {},
192+
"outputs": [],
193+
"source": [
194+
"joined = california_df.merge(stats_df[['GEOID', 'mean']], on='GEOID')\n",
195+
"joined.iloc[:5, -5:]"
196+
]
197+
},
198+
{
199+
"cell_type": "code",
200+
"execution_count": null,
201+
"id": "e306fe32-9197-455a-aedb-0d3b24fb215d",
202+
"metadata": {},
203+
"outputs": [],
204+
"source": [
205+
"import matplotlib.pyplot as plt\n",
206+
"\n",
207+
"fig, ax = plt.subplots(1, 1)\n",
208+
"fig.set_size_inches(10,10)\n",
209+
"\n",
210+
"legend_kwds={\n",
211+
" 'orientation': 'horizontal', # Make the legend horizontal\n",
212+
" 'shrink': 0.5, # Reduce the size of the legend bar by 50%\n",
213+
" 'pad': 0.05, # Add some padding around the legend\n",
214+
" 'label': 'Precipitation (mm)', # Set the legend label (optional)\n",
215+
" }\n",
216+
"joined.plot(ax=ax, column='mean', cmap='Blues',\n",
217+
" legend=True, legend_kwds=legend_kwds)\n",
218+
"ax.set_axis_off()\n",
219+
"ax.set_title('Total Precipitation 2021 for California Counties')\n",
220+
"plt.show()"
221+
]
222+
},
223+
{
224+
"cell_type": "code",
225+
"execution_count": null,
226+
"id": "0b1d1499-fb42-437e-a979-88ddb74f4822",
227+
"metadata": {},
228+
"outputs": [],
229+
"source": [
230+
"joined.explore()"
231+
]
232+
},
233+
{
234+
"cell_type": "markdown",
235+
"id": "8d63cc59-78cd-4639-9c96-f6ac3e0dd208",
236+
"metadata": {
237+
"jp-MarkdownHeadingCollapsed": true
238+
},
239+
"source": [
240+
"## From Carl's class"
241+
]
242+
},
243+
{
244+
"cell_type": "markdown",
245+
"id": "64b27ffc-7f33-4374-b0a8-160bd3c50567",
246+
"metadata": {},
247+
"source": [
248+
"New dependencies (don't add to environment, this is just for accessing data):\n",
249+
"\n",
250+
"* ibis-duckdb\n",
251+
"* odc\n",
252+
"\n",
253+
"New dependencies (add to environment):\n",
254+
"\n",
255+
"* exactextract"
256+
]
257+
},
258+
{
259+
"cell_type": "markdown",
260+
"id": "936e26c2-05ca-48b4-990d-7097b51e93ac",
261+
"metadata": {},
262+
"source": [
263+
"### Setting up raster data (NDVI)\n",
264+
"\n",
265+
"https://espm-288.carlboettiger.info/tutorials/python/spatial-3.html"
266+
]
267+
},
268+
{
269+
"cell_type": "code",
270+
"execution_count": null,
271+
"id": "21dc77b3-a2dc-4356-86ff-6a9d617231d2",
272+
"metadata": {
273+
"jupyter": {
274+
"source_hidden": true
275+
}
276+
},
277+
"outputs": [],
278+
"source": [
279+
"!export CURL_CA_BUNDLE=/etc/ssl/certs/ca-certificates.crt"
280+
]
281+
},
282+
{
283+
"cell_type": "code",
284+
"execution_count": null,
285+
"id": "edf53f2b-657d-4683-9518-8257a93e5a21",
286+
"metadata": {
287+
"jupyter": {
288+
"source_hidden": true
289+
}
290+
},
291+
"outputs": [],
292+
"source": [
293+
"import ibis\n",
294+
"from ibis import _\n",
295+
"\n",
296+
"con = ibis.duckdb.connect(extensions=[\"spatial\"])\n",
297+
"# TODO: Why doesn't this work?\n",
298+
"# \"does not exist in the file system, and is not recognized as a supported dataset name\"\n",
299+
"#redlines = (\n",
300+
"# con\n",
301+
"# .read_geo(\"/vsicurl/https://dsl.richmond.edu/panorama/redlining/static/mappinginequality.gpkg\")\n",
302+
"# .filter(_.city == \"New Haven\", _.residential)\n",
303+
"#)\n",
304+
"redlines = (\n",
305+
" con\n",
306+
" .read_geo(\"./mappinginequality.gpkg\")\n",
307+
" .filter(_.city == \"New Haven\", _.residential)\n",
308+
")\n",
309+
"city = redlines.execute()\n",
310+
"box = city.total_bounds\n",
311+
"box"
312+
]
313+
},
314+
{
315+
"cell_type": "code",
316+
"execution_count": null,
317+
"id": "61363fcb-e942-489e-a631-9cfb5db72800",
318+
"metadata": {
319+
"jupyter": {
320+
"source_hidden": true
321+
}
322+
},
323+
"outputs": [],
324+
"source": [
325+
"from pystac_client import Client\n",
326+
"\n",
327+
"items = (\n",
328+
" Client.\n",
329+
" open(\"https://earth-search.aws.element84.com/v1\").\n",
330+
" search(\n",
331+
" collections = ['sentinel-2-l2a'],\n",
332+
" bbox = box,\n",
333+
" datetime = \"2024-06-01/2024-09-01\",\n",
334+
" query={\"eo:cloud_cover\": {\"lt\": 20}}).\n",
335+
" item_collection()\n",
336+
")\n",
337+
"items"
338+
]
339+
},
340+
{
341+
"cell_type": "code",
342+
"execution_count": null,
343+
"id": "814ce3ab-c48b-4ee5-b7b1-2572ee6fb305",
344+
"metadata": {
345+
"jupyter": {
346+
"source_hidden": true
347+
}
348+
},
349+
"outputs": [],
350+
"source": [
351+
"import odc.stac"
352+
]
353+
},
354+
{
355+
"cell_type": "code",
356+
"execution_count": null,
357+
"id": "50adaad1-493a-47e2-843c-fa596000dfac",
358+
"metadata": {},
359+
"outputs": [],
360+
"source": [
361+
"### Zonal statistics\n",
362+
"\n",
363+
"https://espm-288.carlboettiger.info/tutorials/python/spatial-4.html"
364+
]
365+
}
366+
],
367+
"metadata": {
368+
"kernelspec": {
369+
"display_name": "Python 3 (ipykernel)",
370+
"language": "python",
371+
"name": "python3"
372+
},
373+
"language_info": {
374+
"codemirror_mode": {
375+
"name": "ipython",
376+
"version": 3
377+
},
378+
"file_extension": ".py",
379+
"mimetype": "text/x-python",
380+
"name": "python",
381+
"nbconvert_exporter": "python",
382+
"pygments_lexer": "ipython3",
383+
"version": "3.13.0"
384+
}
385+
},
386+
"nbformat": 4,
387+
"nbformat_minor": 5
388+
}

0 commit comments

Comments
 (0)