pre-proccess
Browse files- preprocess.ipynb +154 -0
preprocess.ipynb
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 4,
|
6 |
+
"id": "f7e6298c-d886-432a-a1b7-c3fee914c24f",
|
7 |
+
"metadata": {},
|
8 |
+
"outputs": [],
|
9 |
+
"source": [
|
10 |
+
"# boilerplate setup\n",
|
11 |
+
"import leafmap.maplibregl as leafmap\n",
|
12 |
+
"import ibis\n",
|
13 |
+
"from ibis import _\n",
|
14 |
+
"\n",
|
15 |
+
"conn = ibis.duckdb.connect(\"tmp\")\n",
|
16 |
+
"ca_parquet = \"https://data.source.coop/cboettig/ca30x30/ca_areas.parquet\"\n",
|
17 |
+
"# or use local copy:\n",
|
18 |
+
"ca_parquet = \"/home/rstudio/source.coop/cboettig/ca30x30/ca_areas.parquet\"\n"
|
19 |
+
]
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"cell_type": "code",
|
23 |
+
"execution_count": 5,
|
24 |
+
"id": "a0cb34b1-8d70-49bf-80c6-244ecc8ddf84",
|
25 |
+
"metadata": {},
|
26 |
+
"outputs": [],
|
27 |
+
"source": [
|
28 |
+
"buffer = -0.00003 \n",
|
29 |
+
"\n",
|
30 |
+
"tbl = (\n",
|
31 |
+
" conn.read_parquet(\"https://data.source.coop/cboettig/ca30x30/ca_areas.parquet\")\n",
|
32 |
+
" .cast({\"SHAPE\": \"geometry\"})\n",
|
33 |
+
" .rename(geom = \"SHAPE\")\n",
|
34 |
+
" # .filter(_.UNIT_NAME == \"Angeles National Forest\")\n",
|
35 |
+
" .filter(_.reGAP < 3) \n",
|
36 |
+
")\n",
|
37 |
+
"tbl_2023 = tbl.filter(_.Release_Year == 2023).mutate(geom=_.geom.buffer(buffer))\n",
|
38 |
+
"tbl_2024 = tbl.filter(_.Release_Year == 2024)\n",
|
39 |
+
"intersects = tbl_2024.anti_join(tbl_2023, _.geom.intersects(tbl_2023.geom))\n",
|
40 |
+
"\n",
|
41 |
+
"new2024 = intersects.select(\"OBJECTID\").mutate(established = 2024)"
|
42 |
+
]
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"cell_type": "code",
|
46 |
+
"execution_count": 7,
|
47 |
+
"id": "275c171a-f82f-4ee8-991c-1e34eb83a33d",
|
48 |
+
"metadata": {},
|
49 |
+
"outputs": [
|
50 |
+
{
|
51 |
+
"data": {
|
52 |
+
"application/vnd.jupyter.widget-view+json": {
|
53 |
+
"model_id": "998c2484ba604297ad438ed5c17dc59d",
|
54 |
+
"version_major": 2,
|
55 |
+
"version_minor": 0
|
56 |
+
},
|
57 |
+
"text/plain": [
|
58 |
+
"FloatProgress(value=0.0, layout=Layout(width='auto'), style=ProgressStyle(bar_color='black'))"
|
59 |
+
]
|
60 |
+
},
|
61 |
+
"metadata": {},
|
62 |
+
"output_type": "display_data"
|
63 |
+
}
|
64 |
+
],
|
65 |
+
"source": [
|
66 |
+
"ca = (conn\n",
|
67 |
+
" .read_parquet(ca_parquet)\n",
|
68 |
+
" .cast({\"SHAPE\": \"geometry\"})\n",
|
69 |
+
" .mutate(area = _.SHAPE.area())\n",
|
70 |
+
" .filter(_.Release_Year == 2024)\n",
|
71 |
+
" .filter(_.reGAP < 3)\n",
|
72 |
+
" .left_join(new2024, \"OBJECTID\")\n",
|
73 |
+
" .mutate(established=_.established.fill_null(2023))\n",
|
74 |
+
" .mutate(geom = _.SHAPE.convert(\"epsg:3310\",\"epsg:4326\"))\n",
|
75 |
+
" .rename(name = \"UNIT_NAME\", access_type = \"ACCESS_TYP\", manager = \"MNG_AGNCY\",\n",
|
76 |
+
" manager_type = \"MNG_AG_LEV\", id = \"OBJECTID\", type = \"TYPE\")\n",
|
77 |
+
" .select(_.established, _.reGAP, _.name, _.access_type, _.manager, _.manager_type,\n",
|
78 |
+
" _.Easement, _.Acres, _.id, _.type, _.geom)\n",
|
79 |
+
" )\n",
|
80 |
+
"ca.to_parquet(\"ca2024.parquet\")"
|
81 |
+
]
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"cell_type": "markdown",
|
85 |
+
"id": "ebbb2650-4442-4e54-8467-5e681d6fab9e",
|
86 |
+
"metadata": {},
|
87 |
+
"source": [
|
88 |
+
"Using difference (overlap) instead:"
|
89 |
+
]
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"cell_type": "code",
|
93 |
+
"execution_count": null,
|
94 |
+
"id": "6f3df8c1-a603-4dd5-be84-8deaae928d0a",
|
95 |
+
"metadata": {},
|
96 |
+
"outputs": [],
|
97 |
+
"source": [
|
98 |
+
"# compute some summary tables:\n",
|
99 |
+
"\n",
|
100 |
+
"(ca\n",
|
101 |
+
" .filter(_.established == 2024)\n",
|
102 |
+
" .filter(_.manager_type == manager_type)\n",
|
103 |
+
" .group_by(_.manager, _.manager_type)\n",
|
104 |
+
" .agg(area = _.Acres.sum())\n",
|
105 |
+
" .order_by(_.area.desc())\n",
|
106 |
+
" .execute()\n",
|
107 |
+
")"
|
108 |
+
]
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"cell_type": "code",
|
112 |
+
"execution_count": null,
|
113 |
+
"id": "c62854f6-1456-4207-8c69-53af17970102",
|
114 |
+
"metadata": {},
|
115 |
+
"outputs": [],
|
116 |
+
"source": [
|
117 |
+
"gdf = ca.filter(_.manager == \"United States National Park Service\", _.established== 2024).execute()\n",
|
118 |
+
"established = {'property': 'established',\n",
|
119 |
+
" 'type': 'categorical',\n",
|
120 |
+
" 'stops': [\n",
|
121 |
+
" [2023, \"#26542C80\"], \n",
|
122 |
+
" [2024, \"#F3AB3D80\"]]\n",
|
123 |
+
" }\n",
|
124 |
+
"paint = {\"fill-color\": established}\n",
|
125 |
+
"\n",
|
126 |
+
"m = leafmap.Map(style=\"positron\")\n",
|
127 |
+
"m.add_gdf(gdf,layer_type=\"fill\", name = \"CA 30x30\", paint = paint)\n",
|
128 |
+
"m.add_layer_control()\n",
|
129 |
+
"m"
|
130 |
+
]
|
131 |
+
}
|
132 |
+
],
|
133 |
+
"metadata": {
|
134 |
+
"kernelspec": {
|
135 |
+
"display_name": "Python 3 (ipykernel)",
|
136 |
+
"language": "python",
|
137 |
+
"name": "python3"
|
138 |
+
},
|
139 |
+
"language_info": {
|
140 |
+
"codemirror_mode": {
|
141 |
+
"name": "ipython",
|
142 |
+
"version": 3
|
143 |
+
},
|
144 |
+
"file_extension": ".py",
|
145 |
+
"mimetype": "text/x-python",
|
146 |
+
"name": "python",
|
147 |
+
"nbconvert_exporter": "python",
|
148 |
+
"pygments_lexer": "ipython3",
|
149 |
+
"version": "3.11.10"
|
150 |
+
}
|
151 |
+
},
|
152 |
+
"nbformat": 4,
|
153 |
+
"nbformat_minor": 5
|
154 |
+
}
|