github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-10-31 16:08:59 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
1d68470bac47aa19d7fecca7d4bcfe54c793fbf3
langchain/docs/extras/integrations/document_loaders/pandas_dataframe.ipynb
Bagatur c8c8635dc9 mv module integrations docs (#8101)
2023-07-23 23:23:16 -07:00

270 lines
11 KiB
Plaintext
Raw Blame History

{
"cells": [
{
"cell_type": "markdown",
"id": "213a38a2",
"metadata": {},
"source": [
"# Pandas DataFrame\n",
"\n",
"This notebook goes over how to load data from a [pandas](https://pandas.pydata.org/pandas-docs/stable/user_guide/index.html) DataFrame."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f6a7a9e4-80d6-486a-b2e3-636c568aa97c",
"metadata": {},
"outputs": [],
"source": [
"#!pip install pandas"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "79331964",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "e487044c",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"example_data/mlb_teams_2012.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "ac273ca1",
"metadata": {},
"outputs": [
{
"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": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "66e47a13",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import DataFrameLoader"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "2334caca",
"metadata": {},
"outputs": [],
"source": [
"loader = DataFrameLoader(df, page_content_column=\"Team\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"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": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"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": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue View Git Blame Copy Permalink