[chore]: Trident directory name change to Fabric

samples/src/main/fabric/NYC-GreenTaxi-Read-Write-Data-To-Kusto.ipynb

@@ -0,0 +1,168 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "cellStatus": "{\"Ramachandran G\":{\"queued_time\":\"2023-03-23T08:37:28.0477136Z\",\"session_start_time\":\"2023-03-23T08:37:28.3245362Z\",\"execution_start_time\":\"2023-03-23T08:37:41.7858145Z\",\"execution_finish_time\":\"2023-03-23T08:38:02.2179974Z\",\"state\":\"finished\",\"livy_statement_state\":\"available\"}}",
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "# Azure storage access info\n",
+    "blob_account_name = \"azureopendatastorage\"\n",
+    "blob_container_name = \"nyctlc\"\n",
+    "blob_relative_path = \"green\"\n",
+    "blob_sas_token = r\"\"\n",
+    "\n",
+    "# Allow SPARK to read from Blob remotely\n",
+    "wasbs_path = 'wasbs://%s@%s.blob.core.windows.net/%s' % (blob_container_name, blob_account_name, blob_relative_path)\n",
+    "spark.conf.set(\n",
+    "  'fs.azure.sas.%s.%s.blob.core.windows.net' % (blob_container_name, blob_account_name),\n",
+    "  blob_sas_token)\n",
+    "print('Remote blob path: ' + wasbs_path)\n",
+    "\n",
+    "# SPARK read parquet, note that it won't load any data yet by now\n",
+    "df = spark.read.parquet(wasbs_path)\n",
+    "# Display top 10 rows\n",
+    "print('Displaying top 10 rows: ')\n",
+    "df.printSchema"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "cellStatus": "{\"Ramachandran G\":{\"queued_time\":\"2023-03-23T08:40:42.2507992Z\",\"session_start_time\":null,\"execution_start_time\":\"2023-03-23T08:40:42.7470834Z\",\"execution_finish_time\":\"2023-03-23T08:40:43.1656264Z\",\"state\":\"finished\",\"livy_statement_state\":\"available\"}}",
+    "jupyter": {
+     "outputs_hidden": false,
+     "source_hidden": false
+    },
+    "nteract": {
+     "transient": {
+      "deleting": false
+     }
+    }
+   },
+   "outputs": [],
+   "source": [
+    "#The target where this data will be written to\n",
+    "kustoUri = \"https://<fabric-kusto>.kusto.data.microsoft.com\"#e.g.\"https://fabrickusto.z0.kusto.data.microsoft.com\"\n",
+    "database=\"Stocks\"\n",
+    "table=\"GreenTaxiData\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "cellStatus": "{\"Ramachandran G\":{\"queued_time\":\"2023-03-23T08:40:46.5885086Z\",\"session_start_time\":null,\"execution_start_time\":\"2023-03-23T08:40:46.965185Z\",\"execution_finish_time\":\"2023-03-23T08:49:19.0524624Z\",\"state\":\"finished\",\"livy_statement_state\":\"available\"}}",
+    "jupyter": {
+     "outputs_hidden": false,
+     "source_hidden": false
+    },
+    "nteract": {
+     "transient": {
+      "deleting": false
+     }
+    }
+   },
+   "outputs": [],
+   "source": [
+    "#This is an example of writing data to Kusto. The source data is read as a blob into a dataframe from Azure Open Data for GreenTaxi / Limousines in NYC.\n",
+    "#The access token is created using the user's credential and will be used to write the data to the Kusto table GreenTaxiData, therefore the user is required \n",
+    "#for 'user' privileges or above on the target database and table 'admin' privileges if the table already exists. If the table does not exist, \n",
+    "#it will be created with the DataFrame schema.\n",
+    "df.write.format(\"com.microsoft.kusto.spark.synapse.datasource\").\\\n",
+    "option(\"kustoCluster\",kustoUri).\\\n",
+    "option(\"kustoDatabase\",database).\\\n",
+    "option(\"kustoTable\", table).\\\n",
+    "option(\"accessToken\", mssparkutils.credentials.getToken('kusto')).\\\n",
+    "option(\"tableCreateOptions\", \"CreateIfNotExist\").mode(\"Append\").save()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "cellStatus": "{\"Ramachandran G\":{\"queued_time\":\"2023-03-23T08:49:29.7202163Z\",\"session_start_time\":null,\"execution_start_time\":\"2023-03-23T08:49:30.1748177Z\",\"execution_finish_time\":\"2023-03-23T08:49:30.6119991Z\",\"state\":\"finished\",\"livy_statement_state\":\"available\"}}",
+    "jupyter": {
+     "outputs_hidden": false,
+     "source_hidden": false
+    },
+    "nteract": {
+     "transient": {
+      "deleting": false
+     }
+    }
+   },
+   "outputs": [],
+   "source": [
+    "#This is an example of Reading data from Kusto. Here the query retrieves the max,min fares and distances that the taxi recorded every month from the years 2014 to 2020\n",
+    "kustoQuery = \"GreenTaxiData |  where puYear between (2014 .. 2020 ) | summarize  MaxDistance=max(tripDistance) , MaxFare = max(fareAmount) ,MinDistance=min(tripDistance) , MinFare = min(fareAmount) by puYear,puMonth | order by puYear,puMonth desc\"\n",
+    "kustoDf  = spark.read\\\n",
+    "            .format(\"com.microsoft.kusto.spark.synapse.datasource\")\\\n",
+    "            .option(\"accessToken\", mssparkutils.credentials.getToken('kusto'))\\\n",
+    "            .option(\"kustoCluster\", kustoUri)\\\n",
+    "            .option(\"kustoDatabase\", database) \\\n",
+    "            .option(\"kustoQuery\", kustoQuery).load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "cellStatus": "{\"Ramachandran G\":{\"queued_time\":\"2023-03-23T08:49:36.5443089Z\",\"session_start_time\":null,\"execution_start_time\":\"2023-03-23T08:49:37.0371176Z\",\"execution_finish_time\":\"2023-03-23T08:49:42.6677216Z\",\"state\":\"finished\",\"livy_statement_state\":\"available\"}}",
+    "jupyter": {
+     "outputs_hidden": false,
+     "source_hidden": false
+    },
+    "nteract": {
+     "transient": {
+      "deleting": false
+     }
+    }
+   },
+   "outputs": [],
+   "source": [
+    "kustoDf.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "description": "",
+  "kernel_info": {
+   "name": "synapse_pyspark"
+  },
+  "kernelspec": {
+   "display_name": "Synapse PySpark",
+   "language": "Python",
+   "name": "synapse_pyspark"
+  },
+  "language_info": {
+   "name": "python"
+  },
+  "notebook_environment": {},
+  "save_output": true,
+  "spark_compute": {
+   "compute_id": "/trident/default",
+   "session_options": {
+    "conf": {
+     "spark.livy.synapse.ipythonInterpreter.enabled": "true"
+    },
+    "enableDebugMode": false,
+    "keepAliveTimeout": 30
+   }
+  },
+  "synapse_widget": {
+   "state": {},
+   "version": "0.1"
+  },
+  "trident": {
+   "lakehouse": {}
+  },
+  "widgets": {}
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}