Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-10-31 15:20:26 +00:00
Code Issues Packages Projects Releases Wiki Activity
d37ce48e60
langchain/docs/extras/integrations/document_loaders/polars_dataframe.ipynb

226 lines
10 KiB
Plaintext
Raw Normal View History

Add to support polars (#9610) ### Description Polars is a DataFrame interface on top of an OLAP Query Engine implemented in Rust. Polars is faster to read than pandas, so I'm looking forward to seeing it added to the document loader. ### Dependencies polars (https://pola-rs.github.io/polars-book/user-guide/) --------- Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-22 14:36:24 +00:00
{
"cells": [
{
"cell_type": "markdown",
"id": "213a38a2",
"metadata": {},
"source": [
"# Polars DataFrame\n",
"\n",
"This notebook goes over how to load data from a [polars](https://pola-rs.github.io/polars-book/user-guide/) DataFrame."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f6a7a9e4-80d6-486a-b2e3-636c568aa97c",
"metadata": {},
"outputs": [],
"source": [
"#!pip install polars"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "79331964",
"metadata": {},
"outputs": [],
"source": [
"import polars as pl"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "e487044c",
"metadata": {},
"outputs": [],
"source": [
"df = pl.read_csv(\"example_data/mlb_teams_2012.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "ac273ca1",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div><style>\n",
".dataframe > thead > tr > th,\n",
".dataframe > tbody > tr > td {\n",
" text-align: right;\n",
"}\n",
"</style>\n",
"<small>shape: (5, 3)</small><table border=\"1\" class=\"dataframe\"><thead><tr><th>Team</th><th> &quot;Payroll (millions)&quot;</th><th> &quot;Wins&quot;</th></tr><tr><td>str</td><td>f64</td><td>i64</td></tr></thead><tbody><tr><td>&quot;Nationals&quot;</td><td>81.34</td><td>98</td></tr><tr><td>&quot;Reds&quot;</td><td>82.2</td><td>97</td></tr><tr><td>&quot;Yankees&quot;</td><td>197.96</td><td>95</td></tr><tr><td>&quot;Giants&quot;</td><td>117.62</td><td>94</td></tr><tr><td>&quot;Braves&quot;</td><td>83.31</td><td>94</td></tr></tbody></table></div>"
],
"text/plain": [
"shape: (5, 3)\n",
"┌───────────┬───────────────────────┬─────────┐\n",
"│ Team ┆ \"Payroll (millions)\" ┆ \"Wins\" │\n",
"│ --- ┆ --- ┆ --- │\n",
"│ str ┆ f64 ┆ i64 │\n",
"╞═══════════╪═══════════════════════╪═════════╡\n",
"│ Nationals ┆ 81.34 ┆ 98 │\n",
"│ Reds ┆ 82.2 ┆ 97 │\n",
"│ Yankees ┆ 197.96 ┆ 95 │\n",
"│ Giants ┆ 117.62 ┆ 94 │\n",
"│ Braves ┆ 83.31 ┆ 94 │\n",
"└───────────┴───────────────────────┴─────────┘"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "66e47a13",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import PolarsDataFrameLoader"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "2334caca",
"metadata": {},
"outputs": [],
"source": [
"loader = PolarsDataFrameLoader(df, page_content_column=\"Team\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "d616c2b0",
"metadata": {},
"outputs": [
{
"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,
"id": "beb55c2f",
"metadata": {},
"outputs": [
{
"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": "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": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue Copy Permalink