mirror of
https://github.com/jupyter/docker-stacks.git
synced 2025-10-12 04:22:58 +00:00
73 lines
1.5 KiB
Plaintext
73 lines
1.5 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"This is a test for the issue [#1168](https://github.com/jupyter/docker-stacks/issues/1168)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from pyspark.sql import SparkSession\n",
|
|
"from pyspark.sql.functions import pandas_udf\n",
|
|
"\n",
|
|
"# Spark session & context\n",
|
|
"spark = SparkSession.builder.master('local').getOrCreate()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"+---+---+\n",
|
|
"| id|age|\n",
|
|
"+---+---+\n",
|
|
"| 1| 21|\n",
|
|
"+---+---+\n",
|
|
"\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"df = spark.createDataFrame([(1, 21), (2, 30)], (\"id\", \"age\"))\n",
|
|
"def filter_func(iterator):\n",
|
|
" for pdf in iterator:\n",
|
|
" yield pdf[pdf.id == 1]\n",
|
|
"\n",
|
|
"df.mapInPandas(filter_func, df.schema).show()"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3",
|
|
"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": "3.8.6"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 4
|
|
}
|