mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
140 lines
3.4 KiB
Plaintext
140 lines
3.4 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "9b721926",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Open City Data"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "35c00849",
|
|
"metadata": {},
|
|
"source": [
|
|
"[Socrata](https://dev.socrata.com/foundry/data.sfgov.org/vw6y-z8j6) provides an API for city open data. \n",
|
|
"\n",
|
|
"For a dataset such as [SF crime](https://data.sfgov.org/Public-Safety/Police-Department-Incident-Reports-Historical-2003/tmnf-yvry), to to the `API` tab on top right. \n",
|
|
"\n",
|
|
"That provides you with the `dataset identifier`.\n",
|
|
"\n",
|
|
"Use the dataset identifier to grab specific tables for a given city_id (`data.sfgov.org`) - \n",
|
|
"\n",
|
|
"E.g., `vw6y-z8j6` for [SF 311 data](https://dev.socrata.com/foundry/data.sfgov.org/vw6y-z8j6).\n",
|
|
"\n",
|
|
"E.g., `tmnf-yvry` for [SF Police data](https://dev.socrata.com/foundry/data.sfgov.org/tmnf-yvry)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "c93cc247",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"! pip install sodapy"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "b3464a02",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.document_loaders import OpenCityDataLoader"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "478c5255",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"dataset = \"vw6y-z8j6\" # 311 data\n",
|
|
"dataset = \"tmnf-yvry\" # crime data\n",
|
|
"loader = OpenCityDataLoader(city_id=\"data.sfgov.org\", dataset_id=dataset, limit=2000)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "fa914fc1",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"WARNING:root:Requests made without an app_token will be subject to strict throttling limits.\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"docs = loader.load()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "73a6def2",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"{'pdid': '4133422003074',\n",
|
|
" 'incidntnum': '041334220',\n",
|
|
" 'incident_code': '03074',\n",
|
|
" 'category': 'ROBBERY',\n",
|
|
" 'descript': 'ROBBERY, BODILY FORCE',\n",
|
|
" 'dayofweek': 'Monday',\n",
|
|
" 'date': '2004-11-22T00:00:00.000',\n",
|
|
" 'time': '17:50',\n",
|
|
" 'pddistrict': 'INGLESIDE',\n",
|
|
" 'resolution': 'NONE',\n",
|
|
" 'address': 'GENEVA AV / SANTOS ST',\n",
|
|
" 'x': '-122.420084075249',\n",
|
|
" 'y': '37.7083109744362',\n",
|
|
" 'location': {'type': 'Point',\n",
|
|
" 'coordinates': [-122.420084075249, 37.7083109744362]},\n",
|
|
" ':@computed_region_26cr_cadq': '9',\n",
|
|
" ':@computed_region_rxqg_mtj9': '8',\n",
|
|
" ':@computed_region_bh8s_q3mv': '309'}"
|
|
]
|
|
},
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"eval(docs[0].page_content)"
|
|
]
|
|
}
|
|
],
|
|
"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": "3.9.16"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|