60 lines
1.4 KiB
Plaintext
60 lines
1.4 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"source": ["# Databricks Notebook"],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": ["%python\n", "def transform_data(df):\n", " return df.dropna()\n"],
|
|
"metadata": {},
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": ["%sql\n", "SELECT * FROM catalog.schema.raw_data\n", "JOIN catalog.schema.lookup ON raw_data.id = lookup.id\n"],
|
|
"metadata": {},
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": ["%r\n", "clean_data <- function(x) {\n", " na.omit(x)\n", "}\n"],
|
|
"metadata": {},
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": ["%scala\n", "val x = 1\n"],
|
|
"metadata": {},
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": ["%md\n", "## Results section\n"],
|
|
"metadata": {},
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": ["def process_results(data):\n", " result = transform_data(data)\n", " return result\n"],
|
|
"metadata": {},
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"source": ["%sql\n", "CREATE TABLE catalog.schema.output AS SELECT * FROM catalog.schema.raw_data\n"],
|
|
"metadata": {},
|
|
"outputs": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"language": "python",
|
|
"display_name": "Python 3"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|