From 449c8ed83b6bad8ce33ea8c14d5f1e7184b6ed2c Mon Sep 17 00:00:00 2001
From: Hamza Tahir <hamza@zenml.io>
Date: Sat, 24 Aug 2024 13:30:14 +0200
Subject: [PATCH] Added github and scripts

---
 .github/workflows/update-tutorials.yml       | 12 ++-
 tutorials/starter-guide-2/introduction.ipynb | 80 ++++++++++++++++++++
 2 files changed, 91 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/update-tutorials.yml b/.github/workflows/update-tutorials.yml
index 1bfca6b436a..7b0b0b7619b 100644
--- a/.github/workflows/update-tutorials.yml
+++ b/.github/workflows/update-tutorials.yml
@@ -86,7 +86,17 @@ jobs:
           changedFiles.forEach(file => {
             commentBody += `- \`${file}\`\n`;
           });
-          commentBody += '\nPlease review these changes.';
+          commentBody += '\nPlease review these changes.\n\n';
+          
+          // Add suggested TOC for each guide type
+          const guideTypes = ['starter_guide', 'advanced_guide']; // Add all your guide types here
+          guideTypes.forEach(guideType => {
+            const suggestedToc = process.env[`suggested_toc_${guideType}`];
+            if (suggestedToc) {
+              commentBody += `### Suggested TOC for ${guideType.replace('_', ' ').replace(/\b\w/g, l => l.toUpperCase())}:\n\n`;
+              commentBody += '```\n' + suggestedToc + '\n```\n\n';
+            }
+          });
           
           try {
             await github.rest.issues.createComment({
diff --git a/tutorials/starter-guide-2/introduction.ipynb b/tutorials/starter-guide-2/introduction.ipynb
index 29d0912e664..56fc655aedd 100644
--- a/tutorials/starter-guide-2/introduction.ipynb
+++ b/tutorials/starter-guide-2/introduction.ipynb
@@ -135,6 +135,86 @@
     "    # You can now use the `run` object to see steps, outputs, etc."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from zenml import pipeline, step\n",
+    "\n",
+    "@step\n",
+    "def load_data() -> dict:\n",
+    "    \"\"\"Simulates loading of training data and labels.\"\"\"\n",
+    "\n",
+    "    training_data = [[1, 2], [3, 4], [5, 6]]\n",
+    "    labels = [0, 1, 0]\n",
+    "    \n",
+    "    return {'features': training_data, 'labels': labels}\n",
+    "\n",
+    "@step\n",
+    "def train_model(data: dict) -> None:\n",
+    "    \"\"\"\n",
+    "    A mock 'training' process that also demonstrates using the input data.\n",
+    "    In a real-world scenario, this would be replaced with actual model fitting logic.\n",
+    "    \"\"\"\n",
+    "    total_features = sum(map(sum, data['features']))\n",
+    "    total_labels = sum(data['labels'])\n",
+    "    \n",
+    "    print(f\"Trained model using {len(data['features'])} data points. \"\n",
+    "          f\"Feature sum is {total_features}, label sum is {total_labels}\")\n",
+    "\n",
+    "@pipeline\n",
+    "def simple_ml_pipeline():\n",
+    "    \"\"\"Define a pipeline that connects the steps.\"\"\"\n",
+    "    dataset = load_data()\n",
+    "    train_model(dataset)\n",
+    "\n",
+    "if __name__ == \"__main__\":\n",
+    "    run = simple_ml_pipeline()\n",
+    "    # You can now use the `run` object to see steps, outputs, etc."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from zenml import pipeline, step\n",
+    "\n",
+    "@step\n",
+    "def load_data() -> dict:\n",
+    "    \"\"\"Simulates loading of training data and labels.\"\"\"\n",
+    "\n",
+    "    training_data = [[1, 2], [3, 4], [5, 6]]\n",
+    "    labels = [0, 1, 0]\n",
+    "    \n",
+    "    return {'features': training_data, 'labels': labels}\n",
+    "\n",
+    "@step\n",
+    "def train_model(data: dict) -> None:\n",
+    "    \"\"\"\n",
+    "    A mock 'training' process that also demonstrates using the input data.\n",
+    "    In a real-world scenario, this would be replaced with actual model fitting logic.\n",
+    "    \"\"\"\n",
+    "    total_features = sum(map(sum, data['features']))\n",
+    "    total_labels = sum(data['labels'])\n",
+    "    \n",
+    "    print(f\"Trained model using {len(data['features'])} data points. \"\n",
+    "          f\"Feature sum is {total_features}, label sum is {total_labels}\")\n",
+    "\n",
+    "@pipeline\n",
+    "def simple_ml_pipeline():\n",
+    "    \"\"\"Define a pipeline that connects the steps.\"\"\"\n",
+    "    dataset = load_data()\n",
+    "    train_model(dataset)\n",
+    "\n",
+    "if __name__ == \"__main__\":\n",
+    "    run = simple_ml_pipeline()\n",
+    "    # You can now use the `run` object to see steps, outputs, etc."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},