|
31 | 31 | "id": "9Ku6cXXnwATV" |
32 | 32 | }, |
33 | 33 | "source": [ |
34 | | - "# Multimodal Analysis and Vector Search with BigQuery ML\n", |
| 34 | + "# AI-Assisted Data Science Workflows in BigQuery\n", |
35 | 35 | "\n", |
36 | 36 | "<table align=\"left\">\n", |
37 | 37 | " <td style=\"text-align: center\">\n", |
|
334 | 334 | }, |
335 | 335 | "source": [ |
336 | 336 | "---\n", |
337 | | - "## 1. Data Preparation and Feature Engineering\n", |
| 337 | + "## Data Preparation and Feature Engineering\n", |
338 | 338 | "\n", |
339 | 339 | "### Create a BigQuery dataset\n", |
340 | 340 | "\n", |
|
443 | 443 | "SELECT\n", |
444 | 444 | " *,\n", |
445 | 445 | " EXTRACT(YEAR FROM CURRENT_DATE()) - year_built AS property_age,\n", |
446 | | - " OBJ.FETCH_METADATA(OBJ.MAKE_REF(house_uri, 'us.ai_connection')) as image_ref\n", |
| 446 | + " OBJ.FETCH_METADATA(OBJ.MAKE_REF(house_uri, 'us.ai_connection')) AS image_ref\n", |
447 | 447 | "FROM\n", |
448 | 448 | " `housing_dataset.listings`\n", |
449 | 449 | "WHERE sale_status = 'For Sale';" |
|
457 | 457 | }, |
458 | 458 | "source": [ |
459 | 459 | "---\n", |
460 | | - "## 2. Multimodal Enrichment with AI Functions\n", |
| 460 | + "## Multimodal Enrichment with AI Functions\n", |
461 | 461 | "\n", |
462 | 462 | "### Create a remote model for Gemini\n", |
463 | 463 | "\n", |
|
578 | 578 | }, |
579 | 579 | "source": [ |
580 | 580 | "---\n", |
581 | | - "## 3. Model Training with K-Means Clustering\n", |
| 581 | + "## Model Training with K-Means Clustering\n", |
582 | 582 | "\n", |
583 | 583 | "With your enriched and feature-engineered dataset, you can now build a machine learning model. Your goal is to segment the house listings into distinct groups based on their characteristics. K-means clustering is an unsupervised learning algorithm that groups data points based on their similarity.\n", |
584 | 584 | "\n", |
|
621 | 621 | }, |
622 | 622 | "source": [ |
623 | 623 | "---\n", |
624 | | - "## 4. Model Evaluation and Prediction\n", |
| 624 | + "## Model Evaluation and Prediction\n", |
625 | 625 | "\n", |
626 | 626 | "### Evaluate the clustering model\n", |
627 | 627 | "\n", |
|
713 | 713 | "---\n", |
714 | 714 | "\n", |
715 | 715 | "\n", |
716 | | - "## 5. Visualize and Interpret Clusters\n", |
| 716 | + "## Visualize and Interpret Clusters\n", |
717 | 717 | "\n", |
718 | 718 | "With each property now assigned to a cluster, you can visualize the results to better understand the distinct housing segments." |
719 | 719 | ] |
|
824 | 824 | }, |
825 | 825 | "source": [ |
826 | 826 | "---\n", |
827 | | - "## 6. Generate Cluster Descriptions with Gemini\n", |
| 827 | + "## Generate Cluster Descriptions with Gemini\n", |
828 | 828 | "\n", |
829 | 829 | "While the centroids and visualizations are useful, you can use generative AI to create human-readable descriptions for each cluster.\n", |
830 | 830 | "\n", |
|
997 | 997 | }, |
998 | 998 | "source": [ |
999 | 999 | "---\n", |
1000 | | - "## 7. Automate Modeling with the Data Science Agent\n", |
| 1000 | + "## Automate Modeling with the Data Science Agent\n", |
1001 | 1001 | "\n", |
1002 | 1002 | "Now, you'll explore a different approach to the same problem. Instead of writing SQL and Python code manually, you will use the integrated [**Data Science Agent**](https://cloud.google.com/bigquery/docs/colab-data-science-agent) to automatically generate code for a K-means clustering model.\n", |
1003 | 1003 | "\n", |
|
1021 | 1021 | }, |
1022 | 1022 | "source": [ |
1023 | 1023 | "---\n", |
1024 | | - "## 8. Multimodal Search with Embeddings and Vector Search\n", |
| 1024 | + "## Multimodal Search with Embeddings and Vector Search\n", |
1025 | 1025 | "\n", |
1026 | 1026 | "In this final section, you will use a multimodal embedding model to convert images into [vector embeddings](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-generate-embedding#embeddings) and then use BigQuery's built-in [vector search](https://cloud.google.com/bigquery/docs/vector-search-intro) capabilities to find similar houses based on a text description or another image." |
1027 | 1027 | ] |
|
1313 | 1313 | "---\n", |
1314 | 1314 | "\n", |
1315 | 1315 | "\n", |
1316 | | - "## 9. Cleaning Up\n", |
| 1316 | + "## Cleaning Up\n", |
1317 | 1317 | "\n", |
1318 | 1318 | "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n", |
1319 | 1319 | "\n", |
|
0 commit comments