langchain/docs/modules/indexes/document_loaders/examples/pyspark_dataframe.ipynb

98 lines
1.8 KiB
Plaintext
Raw Normal View History

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# PySpack DataFrame Loader\n",
"\n",
"This shows how to load data from a PySpark DataFrame"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#!pip install pyspark"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from pyspark.sql import SparkSession"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"spark = SparkSession.builder.getOrCreate()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = spark.read.csv('example_data/mlb_teams_2012.csv', header=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import PySparkDataFrameLoader"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"loader = PySparkDataFrameLoader(spark, df, page_content_column=\"Team\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"loader.load()"
]
}
],
"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": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}