{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "5c27dfd1-4fe0-4a97-92e6-ddf78889aa93",
   "metadata": {
    "nteract": {
     "transient": {
      "deleting": false
     }
    }
   },
   "source": [
    "### Install the latest .whl package\n",
    "\n",
    "Check [here](https://pypi.org/project/semantic-link-labs/) to see the latest version."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d5cae9db-cef9-48a8-a351-9c5fcc99645c",
   "metadata": {
    "jupyter": {
     "outputs_hidden": true,
     "source_hidden": false
    },
    "nteract": {
     "transient": {
      "deleting": false
     }
    }
   },
   "outputs": [],
   "source": [
    "%pip install semantic-link-labs"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b195eae8",
   "metadata": {},
   "source": [
    "### Import the library"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1344e286",
   "metadata": {},
   "outputs": [],
   "source": [
    "import sempy_labs as labs\n",
    "table_name = 'MyTable' # Enter the name of the delta table\n",
    "lakehouse = 'MyLakehouse' # Enter the name or ID of the lakehouse in which the delta table resides\n",
    "workspace = 'MyWorkspace' # Enter the name or ID of the workspace in which the lakehouse resides"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "baa24264",
   "metadata": {},
   "source": [
    "### Run Delta Analyzer for a given table in the lakehouse attached to your notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0a1903c0",
   "metadata": {},
   "outputs": [],
   "source": [
    "x = labs.delta_analyzer(\n",
    "    table_name=table_name,\n",
    "    lakehouse=lakehouse,\n",
    "    workspace=workspace\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "285986d1",
   "metadata": {},
   "outputs": [],
   "source": [
    "for name, df in x.items():\n",
    "    print(name)\n",
    "    display(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e1d118dd",
   "metadata": {},
   "source": [
    "### Get actual (not approximate) distinct counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d1ecf538",
   "metadata": {},
   "outputs": [],
   "source": [
    "x = labs.delta_analyzer(\n",
    "    table_name=table_name,\n",
    "    approx_distinct_count=False,\n",
    "    lakehouse=lakehouse,\n",
    "    workspace=workspace\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "60aa6592",
   "metadata": {},
   "source": [
    "### Export the results of Delta Analyzer to a set of delta tables in your lakehouse\n",
    "The export always appends results to the delta tables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1d4235ff",
   "metadata": {},
   "outputs": [],
   "source": [
    "x = labs.delta_analyzer(\n",
    "    table_name=table_name,\n",
    "    lakehouse=lakehouse,\n",
    "    workspace=workspace,\n",
    "    export=True\n",
    "    )"
   ]
  }
 ],
 "metadata": {
  "kernel_info": {
   "name": "synapse_pyspark"
  },
  "kernelspec": {
   "display_name": "Synapse PySpark",
   "language": "Python",
   "name": "synapse_pyspark"
  },
  "language_info": {
   "name": "python"
  },
  "microsoft": {
   "language": "python"
  },
  "nteract": {
   "version": "nteract-front-end@1.0.0"
  },
  "spark_compute": {
   "compute_id": "/trident/default"
  },
  "synapse_widget": {
   "state": {},
   "version": "0.1"
  },
  "widgets": {}
 },
 "nbformat": 4,
 "nbformat_minor": 5
}