Merge pull request #11 from MicrosoftCloudEssentials-LearningHub/fixing-pipelines

no push needed

Author: brown9804

.github/workflows/validate_and_fix_markdown.yml

@@ -4,9 +4,6 @@ on:
   pull_request:
     branches:
       - main
-  push:
-    branches:
-      - main
 
 permissions:
   contents: write

.github/workflows/validate_and_fix_notebook.yml

@@ -4,9 +4,6 @@ on:
   pull_request:
     branches:
       - main
-  push:
-    branches:
-      - main
 
 permissions:
   contents: write
@@ -35,12 +32,15 @@ jobs:
           python -c "
           import nbformat
           import glob
-          for file in glob.glob('**/*.ypyb', recursive=True):
+          for file in glob.glob('**/*.ipynb', recursive=True):
               with open(file, 'r') as f:
                   nb = nbformat.read(f, as_version=4)
               nbformat.validate(nb)
-              if 'application/vnd.beylor-adapt+notebook' not in nb.metadata:
-                  nb.metadata['application/vnd.beylor-adapt+notebook'] = {'version': '1.0'}
+              if 'widgets' in nb.metadata:
+                  if 'application/vnd.jupyter.widget-state+json' not in nb.metadata['widgets']:
+                      nb.metadata['widgets']['application/vnd.jupyter.widget-state+json'] = {'version': '1.0', 'state': {}}
+                  elif 'state' not in nb.metadata['widgets']['application/vnd.jupyter.widget-state+json']:
+                      nb.metadata['widgets']['application/vnd.jupyter.widget-state+json']['state'] = {}
               with open(file, 'w') as f:
                   nbformat.write(nb, f)
           "

Monitoring-Observability/FabricActivatorRulePipeline/GeneratesRandomData.ipynb

@@ -1 +1,107 @@
-{"cells":[{"cell_type":"code","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}'.\")"],"outputs":[],"execution_count":null,"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"8d820f25-3c2e-45b3-8a08-af78f0d45e1d"}],"metadata":{"kernel_info":{"name":"synapse_pyspark"},"kernelspec":{"name":"synapse_pyspark","language":"Python","display_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"}}},"dependencies":{}},"nbformat":4,"nbformat_minor":5}
+{
+ "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
+}

Workloads-Specific/DataScience/AI_integration/src/fabric-llms-overview_sample.ipynb

@@ -1152,6 +1152,9 @@
   }
  ],
  "metadata": {
+  "application/vnd.jupyter.widget-state+json": {
+   "version": "1.0"
+  },
   "dependencies": {
    "environment": {
     "environmentId": "766562be-9e21-456c-b270-cac7e4bf8d18",
@@ -1187,7 +1190,12 @@
     }
    }
   },
-  "widgets": {}
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version": "1.0"
+   }
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 5