mirror of
https://github.com/hwchase17/langchain.git
synced 2026-04-03 10:55:08 +00:00
aff771923a
Use docusaurus versioning with a callout, merged master as well @hwchase17 @baskaryan --------- Signed-off-by: Weichen Xu <weichen.xu@databricks.com> Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com> Co-authored-by: Leonid Ganeline <leo.gan.57@gmail.com> Co-authored-by: Leonid Kuligin <lkuligin@yandex.ru> Co-authored-by: Averi Kitsch <akitsch@google.com> Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Nuno Campos <nuno@langchain.dev> Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com> Co-authored-by: Martín Gotelli Ferenaz <martingotelliferenaz@gmail.com> Co-authored-by: Fayfox <admin@fayfox.com> Co-authored-by: Eugene Yurtsev <eugene@langchain.dev> Co-authored-by: Dawson Bauer <105886620+djbauer2@users.noreply.github.com> Co-authored-by: Ravindu Somawansa <ravindu.somawansa@gmail.com> Co-authored-by: Dhruv Chawla <43818888+Dominastorm@users.noreply.github.com> Co-authored-by: ccurme <chester.curme@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: WeichenXu <weichen.xu@databricks.com> Co-authored-by: Benito Geordie <89472452+benitoThree@users.noreply.github.com> Co-authored-by: kartikTAI <129414343+kartikTAI@users.noreply.github.com> Co-authored-by: Kartik Sarangmath <kartik@thirdai.com> Co-authored-by: Sevin F. Varoglu <sfvaroglu@octoml.ai> Co-authored-by: MacanPN <martin.triska@gmail.com> Co-authored-by: Prashanth Rao <35005448+prrao87@users.noreply.github.com> Co-authored-by: Hyeongchan Kim <kozistr@gmail.com> Co-authored-by: sdan <git@sdan.io> Co-authored-by: Guangdong Liu <liugddx@gmail.com> Co-authored-by: Rahul Triptahi <rahul.psit.ec@gmail.com> Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com> Co-authored-by: pjb157 <84070455+pjb157@users.noreply.github.com> Co-authored-by: Eun Hye Kim <ehkim1440@gmail.com> Co-authored-by: kaijietti <43436010+kaijietti@users.noreply.github.com> Co-authored-by: Pengcheng Liu <pcliu.fd@gmail.com> Co-authored-by: Tomer Cagan <tomer@tomercagan.com> Co-authored-by: Christophe Bornet <cbornet@hotmail.com>
305 lines
11 KiB
Plaintext
305 lines
11 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"attachments": {},
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Xorbits Pandas DataFrame\n",
|
|
"\n",
|
|
"This notebook goes over how to load data from a [xorbits.pandas](https://doc.xorbits.io/en/latest/reference/pandas/frame.html) DataFrame."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"%pip install --upgrade --quiet xorbits"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import xorbits.pandas as pd"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"df = pd.read_csv(\"example_data/mlb_teams_2012.csv\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"application/vnd.jupyter.widget-view+json": {
|
|
"model_id": "b0d1d84e23c04f1296f63b3ea3dd1e5b",
|
|
"version_major": 2,
|
|
"version_minor": 0
|
|
},
|
|
"text/plain": [
|
|
" 0%| | 0.00/100 [00:00<?, ?it/s]"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div>\n",
|
|
"<style scoped>\n",
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
" vertical-align: middle;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe tbody tr th {\n",
|
|
" vertical-align: top;\n",
|
|
" }\n",
|
|
"\n",
|
|
" .dataframe thead th {\n",
|
|
" text-align: right;\n",
|
|
" }\n",
|
|
"</style>\n",
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
" <thead>\n",
|
|
" <tr style=\"text-align: right;\">\n",
|
|
" <th></th>\n",
|
|
" <th>Team</th>\n",
|
|
" <th>\"Payroll (millions)\"</th>\n",
|
|
" <th>\"Wins\"</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>0</th>\n",
|
|
" <td>Nationals</td>\n",
|
|
" <td>81.34</td>\n",
|
|
" <td>98</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>1</th>\n",
|
|
" <td>Reds</td>\n",
|
|
" <td>82.20</td>\n",
|
|
" <td>97</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>2</th>\n",
|
|
" <td>Yankees</td>\n",
|
|
" <td>197.96</td>\n",
|
|
" <td>95</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>3</th>\n",
|
|
" <td>Giants</td>\n",
|
|
" <td>117.62</td>\n",
|
|
" <td>94</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>4</th>\n",
|
|
" <td>Braves</td>\n",
|
|
" <td>83.31</td>\n",
|
|
" <td>94</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" Team \"Payroll (millions)\" \"Wins\"\n",
|
|
"0 Nationals 81.34 98\n",
|
|
"1 Reds 82.20 97\n",
|
|
"2 Yankees 197.96 95\n",
|
|
"3 Giants 117.62 94\n",
|
|
"4 Braves 83.31 94"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"df.head()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain_community.document_loaders import XorbitsLoader"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"loader = XorbitsLoader(df, page_content_column=\"Team\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"application/vnd.jupyter.widget-view+json": {
|
|
"model_id": "c8c8b67f1aae4a3c9de7734bb6cf738e",
|
|
"version_major": 2,
|
|
"version_minor": 0
|
|
},
|
|
"text/plain": [
|
|
" 0%| | 0.00/100 [00:00<?, ?it/s]"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[Document(page_content='Nationals', metadata={' \"Payroll (millions)\"': 81.34, ' \"Wins\"': 98}),\n",
|
|
" Document(page_content='Reds', metadata={' \"Payroll (millions)\"': 82.2, ' \"Wins\"': 97}),\n",
|
|
" Document(page_content='Yankees', metadata={' \"Payroll (millions)\"': 197.96, ' \"Wins\"': 95}),\n",
|
|
" Document(page_content='Giants', metadata={' \"Payroll (millions)\"': 117.62, ' \"Wins\"': 94}),\n",
|
|
" Document(page_content='Braves', metadata={' \"Payroll (millions)\"': 83.31, ' \"Wins\"': 94}),\n",
|
|
" Document(page_content='Athletics', metadata={' \"Payroll (millions)\"': 55.37, ' \"Wins\"': 94}),\n",
|
|
" Document(page_content='Rangers', metadata={' \"Payroll (millions)\"': 120.51, ' \"Wins\"': 93}),\n",
|
|
" Document(page_content='Orioles', metadata={' \"Payroll (millions)\"': 81.43, ' \"Wins\"': 93}),\n",
|
|
" Document(page_content='Rays', metadata={' \"Payroll (millions)\"': 64.17, ' \"Wins\"': 90}),\n",
|
|
" Document(page_content='Angels', metadata={' \"Payroll (millions)\"': 154.49, ' \"Wins\"': 89}),\n",
|
|
" Document(page_content='Tigers', metadata={' \"Payroll (millions)\"': 132.3, ' \"Wins\"': 88}),\n",
|
|
" Document(page_content='Cardinals', metadata={' \"Payroll (millions)\"': 110.3, ' \"Wins\"': 88}),\n",
|
|
" Document(page_content='Dodgers', metadata={' \"Payroll (millions)\"': 95.14, ' \"Wins\"': 86}),\n",
|
|
" Document(page_content='White Sox', metadata={' \"Payroll (millions)\"': 96.92, ' \"Wins\"': 85}),\n",
|
|
" Document(page_content='Brewers', metadata={' \"Payroll (millions)\"': 97.65, ' \"Wins\"': 83}),\n",
|
|
" Document(page_content='Phillies', metadata={' \"Payroll (millions)\"': 174.54, ' \"Wins\"': 81}),\n",
|
|
" Document(page_content='Diamondbacks', metadata={' \"Payroll (millions)\"': 74.28, ' \"Wins\"': 81}),\n",
|
|
" Document(page_content='Pirates', metadata={' \"Payroll (millions)\"': 63.43, ' \"Wins\"': 79}),\n",
|
|
" Document(page_content='Padres', metadata={' \"Payroll (millions)\"': 55.24, ' \"Wins\"': 76}),\n",
|
|
" Document(page_content='Mariners', metadata={' \"Payroll (millions)\"': 81.97, ' \"Wins\"': 75}),\n",
|
|
" Document(page_content='Mets', metadata={' \"Payroll (millions)\"': 93.35, ' \"Wins\"': 74}),\n",
|
|
" Document(page_content='Blue Jays', metadata={' \"Payroll (millions)\"': 75.48, ' \"Wins\"': 73}),\n",
|
|
" Document(page_content='Royals', metadata={' \"Payroll (millions)\"': 60.91, ' \"Wins\"': 72}),\n",
|
|
" Document(page_content='Marlins', metadata={' \"Payroll (millions)\"': 118.07, ' \"Wins\"': 69}),\n",
|
|
" Document(page_content='Red Sox', metadata={' \"Payroll (millions)\"': 173.18, ' \"Wins\"': 69}),\n",
|
|
" Document(page_content='Indians', metadata={' \"Payroll (millions)\"': 78.43, ' \"Wins\"': 68}),\n",
|
|
" Document(page_content='Twins', metadata={' \"Payroll (millions)\"': 94.08, ' \"Wins\"': 66}),\n",
|
|
" Document(page_content='Rockies', metadata={' \"Payroll (millions)\"': 78.06, ' \"Wins\"': 64}),\n",
|
|
" Document(page_content='Cubs', metadata={' \"Payroll (millions)\"': 88.19, ' \"Wins\"': 61}),\n",
|
|
" Document(page_content='Astros', metadata={' \"Payroll (millions)\"': 60.65, ' \"Wins\"': 55})]"
|
|
]
|
|
},
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"loader.load()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"application/vnd.jupyter.widget-view+json": {
|
|
"model_id": "fc85c9f59b3644689d05853159fbd358",
|
|
"version_major": 2,
|
|
"version_minor": 0
|
|
},
|
|
"text/plain": [
|
|
" 0%| | 0.00/100 [00:00<?, ?it/s]"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"page_content='Nationals' metadata={' \"Payroll (millions)\"': 81.34, ' \"Wins\"': 98}\n",
|
|
"page_content='Reds' metadata={' \"Payroll (millions)\"': 82.2, ' \"Wins\"': 97}\n",
|
|
"page_content='Yankees' metadata={' \"Payroll (millions)\"': 197.96, ' \"Wins\"': 95}\n",
|
|
"page_content='Giants' metadata={' \"Payroll (millions)\"': 117.62, ' \"Wins\"': 94}\n",
|
|
"page_content='Braves' metadata={' \"Payroll (millions)\"': 83.31, ' \"Wins\"': 94}\n",
|
|
"page_content='Athletics' metadata={' \"Payroll (millions)\"': 55.37, ' \"Wins\"': 94}\n",
|
|
"page_content='Rangers' metadata={' \"Payroll (millions)\"': 120.51, ' \"Wins\"': 93}\n",
|
|
"page_content='Orioles' metadata={' \"Payroll (millions)\"': 81.43, ' \"Wins\"': 93}\n",
|
|
"page_content='Rays' metadata={' \"Payroll (millions)\"': 64.17, ' \"Wins\"': 90}\n",
|
|
"page_content='Angels' metadata={' \"Payroll (millions)\"': 154.49, ' \"Wins\"': 89}\n",
|
|
"page_content='Tigers' metadata={' \"Payroll (millions)\"': 132.3, ' \"Wins\"': 88}\n",
|
|
"page_content='Cardinals' metadata={' \"Payroll (millions)\"': 110.3, ' \"Wins\"': 88}\n",
|
|
"page_content='Dodgers' metadata={' \"Payroll (millions)\"': 95.14, ' \"Wins\"': 86}\n",
|
|
"page_content='White Sox' metadata={' \"Payroll (millions)\"': 96.92, ' \"Wins\"': 85}\n",
|
|
"page_content='Brewers' metadata={' \"Payroll (millions)\"': 97.65, ' \"Wins\"': 83}\n",
|
|
"page_content='Phillies' metadata={' \"Payroll (millions)\"': 174.54, ' \"Wins\"': 81}\n",
|
|
"page_content='Diamondbacks' metadata={' \"Payroll (millions)\"': 74.28, ' \"Wins\"': 81}\n",
|
|
"page_content='Pirates' metadata={' \"Payroll (millions)\"': 63.43, ' \"Wins\"': 79}\n",
|
|
"page_content='Padres' metadata={' \"Payroll (millions)\"': 55.24, ' \"Wins\"': 76}\n",
|
|
"page_content='Mariners' metadata={' \"Payroll (millions)\"': 81.97, ' \"Wins\"': 75}\n",
|
|
"page_content='Mets' metadata={' \"Payroll (millions)\"': 93.35, ' \"Wins\"': 74}\n",
|
|
"page_content='Blue Jays' metadata={' \"Payroll (millions)\"': 75.48, ' \"Wins\"': 73}\n",
|
|
"page_content='Royals' metadata={' \"Payroll (millions)\"': 60.91, ' \"Wins\"': 72}\n",
|
|
"page_content='Marlins' metadata={' \"Payroll (millions)\"': 118.07, ' \"Wins\"': 69}\n",
|
|
"page_content='Red Sox' metadata={' \"Payroll (millions)\"': 173.18, ' \"Wins\"': 69}\n",
|
|
"page_content='Indians' metadata={' \"Payroll (millions)\"': 78.43, ' \"Wins\"': 68}\n",
|
|
"page_content='Twins' metadata={' \"Payroll (millions)\"': 94.08, ' \"Wins\"': 66}\n",
|
|
"page_content='Rockies' metadata={' \"Payroll (millions)\"': 78.06, ' \"Wins\"': 64}\n",
|
|
"page_content='Cubs' metadata={' \"Payroll (millions)\"': 88.19, ' \"Wins\"': 61}\n",
|
|
"page_content='Astros' metadata={' \"Payroll (millions)\"': 60.65, ' \"Wins\"': 55}\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Use lazy load for larger table, which won't read the full table into memory\n",
|
|
"for i in loader.lazy_load():\n",
|
|
" print(i)"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "base",
|
|
"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": "3.9.13"
|
|
},
|
|
"orig_nbformat": 4
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|