├── data └── .gitkeep ├── analysis └── .gitkeep ├── macros ├── .gitkeep └── incremental_watermark.sql ├── snapshots └── .gitkeep ├── tests └── .gitkeep ├── .gitignore ├── README.md ├── .pre-commit-config.yaml ├── models ├── schema.yml ├── revenue.sql ├── order_lines.sql └── orders.sql ├── dbt_project.yml └── LICENSE /data/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /analysis/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /macros/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /snapshots/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .idea/ 2 | 3 | target/ 4 | dbt_modules/ 5 | logs/ 6 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # DBT + Azure Databricks 2 | 3 | This is the repository that contains all the code that was used for the demo at the [Data + AI Summit Europe](https://databricks.com/session_eu20/3d-dbt-using-databricks-and-delta). 4 | -------------------------------------------------------------------------------- /macros/incremental_watermark.sql: -------------------------------------------------------------------------------- 1 | {% macro incremental_watermark(column_name='changed_at') %} 2 | -- We use this to only incrementally load changes, 3 | -- based on the watermark 4 | WHERE {{ column_name }} > (SELECT MAX({{ column_name }}) FROM {{ this }}) 5 | {% endmacro %} 6 | -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- 1 | # See https://pre-commit.com for more information 2 | # See https://pre-commit.com/hooks.html for more hooks 3 | repos: 4 | - repo: https://github.com/pre-commit/pre-commit-hooks 5 | rev: v2.5.0 6 | hooks: 7 | - id: trailing-whitespace 8 | - id: end-of-file-fixer 9 | - id: check-docstring-first 10 | - id: debug-statements 11 | - id: check-yaml 12 | - id: check-ast 13 | -------------------------------------------------------------------------------- /models/schema.yml: -------------------------------------------------------------------------------- 1 | 2 | version: 2 3 | 4 | models: 5 | - name: revenue 6 | description: Table containing the realised revenue 7 | columns: 8 | - name: order_no 9 | description: The unique indentifier of the column 10 | tests: 11 | - not_null 12 | - unique 13 | - name: revenue 14 | description: The revenue generated by the specific order 15 | - name: changed_at 16 | description: When the order was changed for the last time -------------------------------------------------------------------------------- /models/revenue.sql: -------------------------------------------------------------------------------- 1 | {{ 2 | config( 3 | materialized='incremental', 4 | file_format='delta', 5 | incremental_strategy='merge', 6 | unique_key='order_no', 7 | post_hook=[ 8 | 'ANALYZE TABLE {{ this }} COMPUTE STATISTICS' 9 | ] 10 | ) 11 | }} 12 | 13 | SELECT /*+ BROADCAST(orders) */ 14 | orders.order_no order_no, 15 | SUM(order_lines.price * order_lines.quantity) revenue, 16 | MAX(orders.changed_at) changed_at 17 | FROM {{ ref('orders') }} orders 18 | JOIN {{ ref('order_lines') }} order_lines USING (order_no) 19 | 20 | {% if is_incremental() %} 21 | -- this filter will only be applied on an incremental run 22 | WHERE changed_at > (SELECT MAX(changed_at) FROM {{ this }}) 23 | {% endif %} 24 | 25 | GROUP BY order_no 26 | -------------------------------------------------------------------------------- /models/order_lines.sql: -------------------------------------------------------------------------------- 1 | {{ 2 | config( 3 | materialized='table', 4 | file_format='delta' 5 | ) 6 | }} 7 | 8 | 9 | -- Usually this would be an external table or so, that will read the data 10 | -- from some landing zone that is, for example being fed by CDC 11 | 12 | -- Right now just make up some data :) 13 | 14 | {% for order_number in range(100) %} 15 | 16 | {% for order_line in range(5) %} 17 | SELECT {{ order_number }} AS order_no, 18 | {{ order_line }} AS order_line, 19 | {{ range(1, 5) | random }} AS quantity, 20 | {{ range(1, 51) | random }} AS price 21 | 22 | {% if not loop.last %} 23 | UNION ALL 24 | {% endif %} 25 | {% endfor %} 26 | 27 | {% if not loop.last %} 28 | UNION ALL 29 | {% endif %} 30 | {% endfor %} 31 | -------------------------------------------------------------------------------- /models/orders.sql: -------------------------------------------------------------------------------- 1 | {{ 2 | config( 3 | materialized='table', 4 | file_format='delta' 5 | ) 6 | }} 7 | 8 | -- Usually this would be an external table or so, that will read the data 9 | -- from some landing zone that is, for example being fed by CDC 10 | 11 | -- Right now just make up some data :) 12 | 13 | {% for order_number in range(100) %} 14 | 15 | SELECT 16 | {{ order_number }} AS order_no, 17 | {% if order_number is divisibleby 2 %} 18 | -- Half of the records will be updated each run 19 | current_timestamp AS changed_at 20 | {% else %} 21 | timestamp( 22 | '2020-01-20 12:22:19' 23 | ) AS changed_at 24 | {% endif %} 25 | {% if not loop.last %} 26 | UNION ALL 27 | {% endif %} 28 | {% endfor %} 29 | -------------------------------------------------------------------------------- /dbt_project.yml: -------------------------------------------------------------------------------- 1 | 2 | # Name your project! Project names should contain only lowercase characters 3 | # and underscores. A good package name should reflect your organization's 4 | # name or the intended use of these models 5 | name: 'DataAISummit' 6 | version: '1.0.0' 7 | 8 | config-version: 2 9 | 10 | # This setting configures which "profile" dbt uses for this project. 11 | profile: 'default' 12 | 13 | # These configurations specify where dbt should look for different types of files. 14 | # The `source-paths` config, for example, states that models in this project can be 15 | # found in the "models/" directory. You probably won't need to change these! 16 | source-paths: ["models"] 17 | analysis-paths: ["analysis"] 18 | test-paths: ["tests"] 19 | data-paths: ["data"] 20 | macro-paths: ["macros"] 21 | snapshot-paths: ["snapshots"] 22 | 23 | target-path: "target" # directory which will store compiled SQL files 24 | clean-targets: # directories to be removed by `dbt clean` 25 | - "target" 26 | - "dbt_modules" 27 | 28 | # Configuring models 29 | # Full documentation: https://docs.getdbt.com/docs/configuring-models 30 | 31 | # In this example config, we tell dbt to build all models in the example/ directory 32 | # as tables. These settings can be overridden in the individual model files 33 | # using the `{{ config(...) }}` macro. 34 | models: 35 | dbtpresentation: 36 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------