moved

Author: brown9804

Workloads-Specific/RealTimeIntelligence/FabricActivatorRulePipeline/GeneratesRandomData.ipynb

@@ -0,0 +1,107 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8d820f25-3c2e-45b3-8a08-af78f0d45e1d",
+   "metadata": {
+    "microsoft": {
+     "language": "python",
+     "language_group": "synapse_pyspark"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Generates Dummy json file in Files/\n",
+    "\n",
+    "# Import necessary libraries\n",
+    "from pyspark.sql import SparkSession\n",
+    "from pyspark.sql.types import *\n",
+    "import random\n",
+    "from datetime import datetime, timedelta\n",
+    "\n",
+    "# Initialize Spark session (if not already initialized)\n",
+    "spark = SparkSession.builder.appName(\"GenerateRandomData\").getOrCreate()\n",
+    "\n",
+    "# Function to generate random data\n",
+    "def generate_random_data(num_entries):\n",
+    "    data = []\n",
+    "    for i in range(1, num_entries + 1):\n",
+    "        name = f\"User{i}\"\n",
+    "        entry = {\n",
+    "            \"id\": i,\n",
+    "            \"name\": name,\n",
+    "            \"age\": random.randint(18, 65),\n",
+    "            \"email\": f\"{name.lower()}@example.com\",\n",
+    "            \"created_at\": (datetime.now() - timedelta(days=random.randint(0, 365))).strftime(\"%Y-%m-%d %H:%M:%S\")\n",
+    "        }\n",
+    "        data.append(entry)\n",
+    "    return data\n",
+    "\n",
+    "# Generate 10 random entries\n",
+    "random_data = generate_random_data(10)\n",
+    "\n",
+    "# Define schema for the DataFrame\n",
+    "schema = StructType([\n",
+    "    StructField(\"id\", IntegerType(), True),\n",
+    "    StructField(\"name\", StringType(), True),\n",
+    "    StructField(\"age\", IntegerType(), True),\n",
+    "    StructField(\"email\", StringType(), True),\n",
+    "    StructField(\"created_at\", StringType(), True)\n",
+    "])\n",
+    "\n",
+    "# Create a DataFrame from the random data\n",
+    "df_random_data = spark.createDataFrame(random_data, schema=schema)\n",
+    "\n",
+    "# Write the DataFrame to the Lakehouse in the specified path\n",
+    "output_path = \"abfss://{WORKSPACE-NAME}@onelake.dfs.fabric.microsoft.com/raw_Bronze.Lakehouse/Files/random_data\" # Replace {WORKSPACE-NAME}\n",
+    "df_random_data.write.format(\"delta\").mode(\"overwrite\").save(output_path)\n",
+    "\n",
+    "print(f\"Random data has been saved to the Lakehouse at '{output_path}'.\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "application/vnd.jupyter.widget-state+json": {
+   "version": "1.0"
+  },
+  "dependencies": {},
+  "kernel_info": {
+   "name": "synapse_pyspark"
+  },
+  "kernelspec": {
+   "display_name": "Synapse PySpark",
+   "language": "Python",
+   "name": "synapse_pyspark"
+  },
+  "language_info": {
+   "name": "python"
+  },
+  "microsoft": {
+   "language": "python",
+   "language_group": "synapse_pyspark",
+   "ms_spell_check": {
+    "ms_spell_check_language": "en"
+   }
+  },
+  "nteract": {
+   "version": "[email protected]"
+  },
+  "spark_compute": {
+   "compute_id": "/trident/default",
+   "session_options": {
+    "conf": {
+     "spark.synapse.nbs.session.timeout": "1200000"
+    }
+   }
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version": "1.0"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}