Added free subscription tutorial

JaumeAmoresDS · Mar 27, 2024 · 514a6c7 · 514a6c7
1 parent 203a841
commit 514a6c7
Show file tree

Hide file tree

Showing 5 changed files with 321 additions and 45 deletions.
diff --git a/_site/search.json b/_site/search.json
diff --git a/additional/data_science/aml/free_subscription.ipynb b/additional/data_science/aml/free_subscription.ipynb
diff --git a/gpull.sh b/gpull.sh
@@ -0,0 +1,4 @@
+eval "$(ssh-agent -s)"
+ssh-add ~/.ssh/id_ed25519_home
+sudo hwclock -s
+git pull $1
diff --git a/posts/data_science/hello_world.ipynb b/posts/data_science/hello_world.ipynb
@@ -1,5 +1,21 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "38534efa-75c0-4aca-941c-e396f2976d46",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "title: \"Hello World AML pipeline with component\"\n",
+    "subtitle: Exploring AML through Hello World components.\n",
+    "author: \"Jaume Amores\"\n",
+    "date: 2024-03-22\n",
+    "toc: true\n",
+    "categories:\n",
+    "  - Data Science\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "5045fb3a-c4d6-4530-9d24-f935c9b9a9d4",
@@ -8,6 +24,32 @@
     "# Hello World AML pipeline with components"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f3961630-1375-4d89-8ac6-8513fa597a98",
+   "metadata": {},
+   "source": [
+    "The purpose of this tutorial is to show how to incrementally build a pipeline from simple and debuggable \"Hello World\" components. In order to run this at home, you may find it useful to create a free Azure ML subscription as described in the how-to guide I have [here](../../additional/data_science/aml/free_subscription.html)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b4403853-efc1-4aa2-b99f-4530447b3141",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "free_subscription.ipynb\n"
+     ]
+    }
+   ],
+   "source": [
+    "ls ../../additional/data_science/aml"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "24c97d77-c8a3-4859-8ef0-e3e8fa88aa8b",
@@ -36,7 +78,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "b4a67b25-46e9-40af-8755-35c548160a3b",
    "metadata": {},
    "outputs": [
@@ -67,7 +109,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "0b2a7fdb-b52f-4240-a031-c6bd8bfb886f",
    "metadata": {},
    "outputs": [
@@ -130,7 +172,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "fc48978f-363a-482e-a4d3-57d85c315243",
    "metadata": {},
    "outputs": [
@@ -245,7 +287,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "794b917b-a4aa-430a-96b2-cd375a0efe97",
    "metadata": {},
    "outputs": [
@@ -273,9 +315,7 @@
   {
    "cell_type": "markdown",
    "id": "439b43fd-1fd6-422a-9420-59af3aab027a",
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "source": [
     "## Running script as a job\n",
     "\n",
@@ -294,7 +334,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "904b3dc3-4abf-4509-8874-52e5c9f9600d",
    "metadata": {},
    "outputs": [
@@ -337,7 +377,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "2ee8efea-d7f4-4a5c-9d60-010fcd9bfdd1",
    "metadata": {},
    "outputs": [],
@@ -373,7 +413,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "id": "8184260b-bc9a-4dd8-a916-e593d4590d6d",
    "metadata": {},
    "outputs": [
@@ -398,10 +438,10 @@
        "<table style=\"width:100%\"><tr><th>Experiment</th><th>Name</th><th>Type</th><th>Status</th><th>Details Page</th></tr><tr><td>hello_world</td><td>clever_spade_sq4jwcg67r</td><td>command</td><td>Starting</td><td><a href=\"https://ml.azure.com/runs/clever_spade_sq4jwcg67r?wsid=/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourcegroups/helloworld/workspaces/helloworld&amp;tid=369b25b1-777a-484a-8b5b-52d79bc83015\" target=\"_blank\" rel=\"noopener\">Link to Azure Machine Learning studio</a></td></tr></table>"
       ],
       "text/plain": [
-       "Command({'parameters': {}, 'init': False, 'name': 'clever_spade_sq4jwcg67r', 'type': 'command', 'status': 'Starting', 'log_files': None, 'description': None, 'tags': {}, 'properties': {'_azureml.ComputeTargetType': 'amlctrain', '_azureml.ClusterName': None, 'ContentSnapshotId': '59fd973d-6cab-4386-a4a8-f1ea1676287f'}, 'print_as_yaml': True, 'id': '/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourceGroups/helloworld/providers/Microsoft.MachineLearningServices/workspaces/helloworld/jobs/clever_spade_sq4jwcg67r', 'Resource__source_path': None, 'base_path': '/mnt/batch/tasks/shared/LS_root/mounts/clusters/jaumecpu/code/Users/jau.m/hello_world', 'creation_context': <azure.ai.ml.entities._system_data.SystemData object at 0x7f8aa0317e80>, 'serialize': <msrest.serialization.Serializer object at 0x7f8aa27ca590>, 'allowed_keys': {}, 'key_restriction': False, 'logger': <Logger attr_dict (WARNING)>, 'display_name': 'Simplest Hello World', 'experiment_name': 'hello_world', 'compute': None, 'services': {'Tracking': {'endpoint': 'azureml://eastus2.api.azureml.ms/mlflow/v1.0/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourceGroups/helloworld/providers/Microsoft.MachineLearningServices/workspaces/helloworld?', 'type': 'Tracking'}, 'Studio': {'endpoint': 'https://ml.azure.com/runs/clever_spade_sq4jwcg67r?wsid=/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourcegroups/helloworld/workspaces/helloworld&tid=369b25b1-777a-484a-8b5b-52d79bc83015', 'type': 'Studio'}}, 'comment': None, 'job_inputs': {'name': 'Jaume'}, 'job_outputs': {'default': {'type': 'uri_folder', 'path': 'azureml://datastores/workspaceartifactstore/ExperimentRun/dcid.clever_spade_sq4jwcg67r', 'mode': 'rw_mount'}}, 'inputs': {'name': <azure.ai.ml.entities._job.pipeline._io.base.NodeInput object at 0x7f8aa27ca290>}, 'outputs': {'default': <azure.ai.ml.entities._job.pipeline._io.base.NodeOutput object at 0x7f8aa04f0340>}, 'component': CommandComponent({'intellectual_property': None, 'auto_increment_version': True, 'source': 'REMOTE.WORKSPACE.JOB', 'is_anonymous': False, 'auto_delete_setting': None, 'name': 'clever_spade_sq4jwcg67r', 'description': None, 'tags': {}, 'properties': {}, 'print_as_yaml': True, 'id': None, 'Resource__source_path': None, 'base_path': PosixPath('.'), 'creation_context': <azure.ai.ml.entities._system_data.SystemData object at 0x7f8aa0317e80>, 'serialize': <msrest.serialization.Serializer object at 0x7f8aa27ca980>, 'command': 'python hello_world_core.py --name ${{inputs.name}}', 'code': '/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourceGroups/helloworld/providers/Microsoft.MachineLearningServices/workspaces/helloworld/codes/6ac1a0d9-2ea6-48d4-be76-c738397c29f9/versions/1', 'environment_variables': {}, 'environment': 'azureml:AzureML-sklearn-1.0-ubuntu20.04-py38-cpu@latest', 'distribution': None, 'resources': None, 'queue_settings': None, 'version': None, 'latest_version': None, 'schema': None, 'type': 'command', 'display_name': 'Simplest Hello World', 'is_deterministic': True, 'inputs': {'name': {'type': 'string', 'default': 'Jaume'}}, 'outputs': {'default': {'type': 'uri_folder', 'path': 'azureml://datastores/workspaceartifactstore/ExperimentRun/dcid.clever_spade_sq4jwcg67r', 'mode': 'rw_mount'}}, 'yaml_str': None, 'other_parameter': {'status': 'Starting', 'parameters': {}}, 'additional_includes': [], 'CommandComponent__additional_includes_obj': None}), 'referenced_control_flow_node_instance_id': None, 'kwargs': {'services': {'Tracking': {'endpoint': 'azureml://eastus2.api.azureml.ms/mlflow/v1.0/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourceGroups/helloworld/providers/Microsoft.MachineLearningServices/workspaces/helloworld?', 'type': 'Tracking'}, 'Studio': {'endpoint': 'https://ml.azure.com/runs/clever_spade_sq4jwcg67r?wsid=/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourcegroups/helloworld/workspaces/helloworld&tid=369b25b1-777a-484a-8b5b-52d79bc83015', 'type': 'Studio'}}, 'status': 'Starting', 'creation_context': <azure.ai.ml.entities._system_data.SystemData object at 0x7f8aa0317e80>}, 'instance_id': 'fdfea982-8943-4733-8292-f47d663f5e5d', 'source': 'BUILDER', 'validate_required_input_not_provided': True, 'limits': None, 'identity': None, 'distribution': None, 'environment_variables': {}, 'environment': 'azureml:AzureML-sklearn-1.0-ubuntu20.04-py38-cpu@latest', 'resources': {'instance_count': 1, 'shm_size': '2g'}, 'queue_settings': {'job_tier': 'standard'}, 'swept': False})"
+       "Command({'parameters': {}, 'init': False, 'name': 'clever_spade_sq4jwcg67r', 'type': 'command', 'status': 'Starting', 'log_files': None, 'description': None, 'tags': {}, 'properties': {'_azureml.ComputeTargetType': 'amlctrain', '_azureml.ClusterName': None, 'ContentSnapshotId': '59fd973d-6cab-4386-a4a8-f1ea1676287f'}, 'print_as_yaml': True, 'id': '/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourceGroups/helloworld/providers/Microsoft.MachineLearningServices/workspaces/helloworld/jobs/clever_spade_sq4jwcg67r', 'Resource__source_path': None, 'base_path': '/mnt/batch/tasks/shared/LS_root/mounts/clusters/jaumecpu/code/Users/jau.m/hello_world', 'creation_context': <azure.ai.ml.entities._system_data.SystemData object>, 'serialize': <msrest.serialization.Serializer object>, 'allowed_keys': {}, 'key_restriction': False, 'logger': <Logger attr_dict (WARNING)>, 'display_name': 'Simplest Hello World', 'experiment_name': 'hello_world', 'compute': None, 'services': {'Tracking': {'endpoint': 'azureml://eastus2.api.azureml.ms/mlflow/v1.0/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourceGroups/helloworld/providers/Microsoft.MachineLearningServices/workspaces/helloworld?', 'type': 'Tracking'}, 'Studio': {'endpoint': 'https://ml.azure.com/runs/clever_spade_sq4jwcg67r?wsid=/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourcegroups/helloworld/workspaces/helloworld&tid=369b25b1-777a-484a-8b5b-52d79bc83015', 'type': 'Studio'}}, 'comment': None, 'job_inputs': {'name': 'Jaume'}, 'job_outputs': {'default': {'type': 'uri_folder', 'path': 'azureml://datastores/workspaceartifactstore/ExperimentRun/dcid.clever_spade_sq4jwcg67r', 'mode': 'rw_mount'}}, 'inputs': {'name': <azure.ai.ml.entities._job.pipeline._io.base.NodeInput object>}, 'outputs': {'default': <azure.ai.ml.entities._job.pipeline._io.base.NodeOutput object>}, 'component': CommandComponent({'intellectual_property': None, 'auto_increment_version': True, 'source': 'REMOTE.WORKSPACE.JOB', 'is_anonymous': False, 'auto_delete_setting': None, 'name': 'clever_spade_sq4jwcg67r', 'description': None, 'tags': {}, 'properties': {}, 'print_as_yaml': True, 'id': None, 'Resource__source_path': None, 'base_path': PosixPath('.'), 'creation_context': <azure.ai.ml.entities._system_data.SystemData object>, 'serialize': <msrest.serialization.Serializer object>, 'command': 'python hello_world_core.py --name ${{inputs.name}}', 'code': '/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourceGroups/helloworld/providers/Microsoft.MachineLearningServices/workspaces/helloworld/codes/6ac1a0d9-2ea6-48d4-be76-c738397c29f9/versions/1', 'environment_variables': {}, 'environment': 'azureml:AzureML-sklearn-1.0-ubuntu20.04-py38-cpu@latest', 'distribution': None, 'resources': None, 'queue_settings': None, 'version': None, 'latest_version': None, 'schema': None, 'type': 'command', 'display_name': 'Simplest Hello World', 'is_deterministic': True, 'inputs': {'name': {'type': 'string', 'default': 'Jaume'}}, 'outputs': {'default': {'type': 'uri_folder', 'path': 'azureml://datastores/workspaceartifactstore/ExperimentRun/dcid.clever_spade_sq4jwcg67r', 'mode': 'rw_mount'}}, 'yaml_str': None, 'other_parameter': {'status': 'Starting', 'parameters': {}}, 'additional_includes': [], 'CommandComponent__additional_includes_obj': None}), 'referenced_control_flow_node_instance_id': None, 'kwargs': {'services': {'Tracking': {'endpoint': 'azureml://eastus2.api.azureml.ms/mlflow/v1.0/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourceGroups/helloworld/providers/Microsoft.MachineLearningServices/workspaces/helloworld?', 'type': 'Tracking'}, 'Studio': {'endpoint': 'https://ml.azure.com/runs/clever_spade_sq4jwcg67r?wsid=/subscriptions/6af6741b-f140-48c2-84ca-027a27365026/resourcegroups/helloworld/workspaces/helloworld&tid=369b25b1-777a-484a-8b5b-52d79bc83015', 'type': 'Studio'}}, 'status': 'Starting', 'creation_context': <azure.ai.ml.entities._system_data.SystemData object>}, 'instance_id': 'fdfea982-8943-4733-8292-f47d663f5e5d', 'source': 'BUILDER', 'validate_required_input_not_provided': True, 'limits': None, 'identity': None, 'distribution': None, 'environment_variables': {}, 'environment': 'azureml:AzureML-sklearn-1.0-ubuntu20.04-py38-cpu@latest', 'resources': {'instance_count': 1, 'shm_size': '2g'}, 'queue_settings': {'job_tier': 'standard'}, 'swept': False})"
       ]
      },
-     "execution_count": 10,
+     "execution_count": null,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -609,7 +649,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "08db4dd6-a562-4c1f-ad7e-375564f09288",
    "metadata": {},
    "outputs": [
@@ -629,7 +669,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "id": "b3c3df45-e03e-4e0f-b753-e8d5be1dab5b",
    "metadata": {},
    "outputs": [],
@@ -652,7 +692,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "id": "431f9e20-53a9-4468-af9d-f05d85e17162",
    "metadata": {},
    "outputs": [],
@@ -665,7 +705,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
    "id": "c79ff2bb-7e75-4aba-a1c1-d6e577e764f6",
    "metadata": {},
    "outputs": [
@@ -734,7 +774,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": null,
    "id": "f787c906-5349-4dfe-81cc-57a351ed6903",
    "metadata": {},
    "outputs": [
@@ -766,7 +806,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": null,
    "id": "dcf92501-5694-42f5-9515-cb4869609693",
    "metadata": {},
    "outputs": [],
@@ -789,7 +829,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": null,
    "id": "8d2783f1-9ef3-45eb-be8b-a54f86c4a914",
    "metadata": {},
    "outputs": [
@@ -876,7 +916,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": null,
    "id": "ecaadb90-1e81-4d0a-b8fa-a401a190965a",
    "metadata": {},
    "outputs": [
@@ -984,7 +1024,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": null,
    "id": "3f4c35dd-826d-4478-b360-c9e7d647de16",
    "metadata": {},
    "outputs": [],
@@ -994,7 +1034,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": null,
    "id": "bc85b398-20b4-4655-a3ed-79c43e66cb1d",
    "metadata": {},
    "outputs": [
@@ -1097,7 +1137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": null,
    "id": "c58b92f4-3232-4f17-a3e0-eb44931cf3a3",
    "metadata": {},
    "outputs": [],
@@ -1111,7 +1151,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": null,
    "id": "41065e75-75f9-4f81-a2a7-5d2c5ece6b41",
    "metadata": {},
    "outputs": [],
@@ -1138,7 +1178,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": null,
    "id": "1eb04804-991f-4c25-89e7-bf4b4901813c",
    "metadata": {},
    "outputs": [
@@ -1196,7 +1236,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": null,
    "id": "24b74e38-eba1-4ab6-a5df-6faa3f55c19a",
    "metadata": {},
    "outputs": [
@@ -1238,7 +1278,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": null,
    "id": "6afcb989-5c77-4ed3-9d43-87dc83d51d00",
    "metadata": {},
    "outputs": [
@@ -1296,7 +1336,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 60,
+   "execution_count": null,
    "id": "3b4f6fb0-26a4-471e-96c7-511673015eda",
    "metadata": {},
    "outputs": [
@@ -1352,7 +1392,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": null,
    "id": "314cb640-e9ad-4fc2-b651-bf8d54cc8fbb",
    "metadata": {},
    "outputs": [
@@ -1419,7 +1459,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": null,
    "id": "55196b04-892c-4e33-8c17-2ccf40fcdaf6",
    "metadata": {},
    "outputs": [
@@ -1512,21 +1552,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.10 - SDK v2",
+   "display_name": "tabularml",
    "language": "python",
-   "name": "python310-sdkv2"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.11"
+   "name": "tabularml"
   }
  },
  "nbformat": 4,

diff --git a/posts/data_science/index.qmd b/posts/data_science/index.qmd
@@ -0,0 +1,16 @@
+---
+title: "Data Science"
+author: "Jaume Amores"
+#date: 2024-03-22
+#toc: true
+listing:
+  - id: talks
+    #contents: "**/*/index.qmd"
+    #fields: [date, title]
+    fields: [title]
+    sort: "date desc"
+    categories: true
+categories:
+  - Data Science
+---
+