First commit

.gitignore

@@ -0,0 +1,8 @@
+.databricks/
+build/
+dist/
+__pycache__/
+*.egg-info
+.venv/
+scratch/**
+!scratch/README.md

.vscode/__builtins__.pyi

@@ -0,0 +1,3 @@
+# Typings for Pylance in Visual Studio Code
+# see https://github.com/microsoft/pyright/blob/main/docs/builtins.md
+from databricks.sdk.runtime import *

.vscode/extensions.json

@@ -0,0 +1,7 @@
+{
+    "recommendations": [
+        "databricks.databricks",
+        "ms-python.vscode-pylance",
+        "redhat.vscode-yaml"
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,17 @@
+{
+    "python.analysis.stubPath": ".vscode",
+    "databricks.python.envFile": "${workspaceFolder}/.env",
+    "jupyter.interactiveWindow.cellMarker.codeRegex": "^# COMMAND ----------|^# Databricks notebook source|^(#\\s*%%|#\\s*\\<codecell\\>|#\\s*In\\[\\d*?\\]|#\\s*In\\[ \\])",
+    "jupyter.interactiveWindow.cellMarker.default": "# COMMAND ----------",
+    "python.testing.pytestArgs": [
+        "."
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "python.analysis.extraPaths": ["src"],
+    "files.exclude": {
+        "**/*.egg-info": true,
+        "**/__pycache__": true,
+        ".pytest_cache": true,
+    },
+}

README.md

@@ -0,0 +1,42 @@
+# marcin_project
+
+The 'marcin_project' project was generated by using the default-python template.
+
+## Getting started
+
+1. Install the Databricks CLI from https://docs.databricks.com/dev-tools/cli/databricks-cli.html
+
+2. Authenticate to your Databricks workspace:
+    ```
+    $ databricks configure
+    ```
+
+3. To deploy a development copy of this project, type:
+    ```
+    $ databricks bundle deploy --target dev
+    ```
+    (Note that "dev" is the default target, so the `--target` parameter
+    is optional here.)
+
+    This deploys everything that's defined for this project.
+    For example, the default template would deploy a job called
+    `[dev yourname] marcin_project_job` to your workspace.
+    You can find that job by opening your workpace and clicking on **Workflows**.
+
+4. Similarly, to deploy a production copy, type:
+   ```
+   $ databricks bundle deploy --target prod
+   ```
+
+5. To run a job or pipeline, use the "run" command:
+   ```
+   $ databricks bundle run
+   ```
+
+6. Optionally, install developer tools such as the Databricks extension for Visual Studio Code from
+   https://docs.databricks.com/dev-tools/vscode-ext.html. Or read the "getting started" documentation for
+   **Databricks Connect** for instructions on running the included Python code from a different IDE.
+
+7. For documentation on the Databricks asset bundles format used
+   for this project, and for CI/CD configuration, see
+   https://docs.databricks.com/dev-tools/bundles/index.html.

databricks.yml

@@ -0,0 +1,41 @@
+# This is a Databricks asset bundle definition for marcin_project.
+# See https://docs.databricks.com/dev-tools/bundles/index.html for documentation.
+bundle:
+  name: marcin_project
+
+include:
+  - resources/*.yml
+
+targets:
+  # The 'dev' target, for development purposes. This target is the default.
+  dev:
+    # We use 'mode: development' to indicate this is a personal development copy:
+    # - Deployed resources get prefixed with '[dev my_user_name]'
+    # - Any job schedules and triggers are paused by default
+    # - The 'development' mode is used for Delta Live Tables pipelines
+    mode: development
+    default: true
+    workspace:
+      host: https://adb-8870486534760962.2.azuredatabricks.net
+
+  ## Optionally, there could be a 'staging' target here.
+  ## (See Databricks docs on CI/CD at https://docs.databricks.com/dev-tools/bundles/index.html.)
+  #
+  # staging:
+  #   workspace:
+  #     host: https://adb-8870486534760962.2.azuredatabricks.net
+
+  # The 'prod' target, used for production deployment.
+  prod:
+    # We use 'mode: production' to indicate this is a production deployment.
+    # Doing so enables strict verification of the settings below.
+    mode: production
+    workspace:
+      host: https://adb-8870486534760962.2.azuredatabricks.net
+      # We only have a single deployment copy for production, so we use a shared path.
+      root_path: /Shared/.bundle/prod/${bundle.name}
+    run_as:
+      # This runs as [email protected] in production. We could also use a service principal here
+      # using service_principal_name (see https://docs.databricks.com/dev-tools/bundles/permissions.html).
+      user_name: [email protected]
+

fixtures/.gitkeep

@@ -0,0 +1,22 @@
+# Fixtures
+
+This folder is reserved for fixtures, such as CSV files.
+
+Below is an example of how to load fixtures as a data frame:
+
+```
+import pandas as pd
+import os
+
+def get_absolute_path(*relative_parts):
+    if 'dbutils' in globals():
+        base_dir = os.path.dirname(dbutils.notebook.entry_point.getDbutils().notebook().getContext().notebookPath().get()) # type: ignore
+        path = os.path.normpath(os.path.join(base_dir, *relative_parts))
+        return path if path.startswith("/Workspace") else "/Workspace" + path
+    else:
+        return os.path.join(*relative_parts)
+
+csv_file = get_absolute_path("..", "fixtures", "mycsv.csv")
+df = pd.read_csv(csv_file)
+display(df)
+```

pytest.ini

@@ -0,0 +1,3 @@
+[pytest]
+testpaths = tests
+pythonpath = src

requirements-dev.txt

@@ -0,0 +1,26 @@
+## requirements-dev.txt: dependencies for local development.
+##
+## For defining dependencies used by jobs in Databricks Workflows, see
+## https://docs.databricks.com/dev-tools/bundles/library-dependencies.html
+
+## pytest is the default package used for testing
+pytest
+
+## Dependencies for building wheel files
+setuptools
+wheel
+
+## databricks-connect can be used to run parts of this project locally.
+## See https://docs.databricks.com/dev-tools/databricks-connect.html.
+##
+## databricks-connect is automatically installed if you're using Databricks
+## extension for Visual Studio Code
+## (https://docs.databricks.com/dev-tools/vscode-ext/dev-tasks/databricks-connect.html).
+##
+## To manually install databricks-connect, either follow the instructions
+## at https://docs.databricks.com/dev-tools/databricks-connect.html
+## to install the package system-wide. Or uncomment the line below to install a
+## version of db-connect that corresponds to the Databricks Runtime version used
+## for this project.
+#
+databricks-connect>=13.3,<13.4

resources/marcin_project_job.yml

@@ -0,0 +1,48 @@
+# The main job for marcin_project.
+resources:
+  jobs:
+    marcin_project_job:
+      name: marcin_project_job
+
+      schedule:
+        # Run every day at 8:37 AM
+        quartz_cron_expression: '44 37 8 * * ?'
+        timezone_id: Europe/Amsterdam
+
+      email_notifications:
+        on_failure:
+          - [email protected]
+
+      tasks:
+        - task_key: notebook_task
+          job_cluster_key: job_cluster
+          notebook_task:
+            notebook_path: ../src/notebook.ipynb
+
+        - task_key: refresh_pipeline
+          depends_on:
+            - task_key: notebook_task
+          pipeline_task:
+            pipeline_id: ${resources.pipelines.marcin_project_pipeline.id}
+
+        - task_key: main_task
+          depends_on:
+            - task_key: refresh_pipeline
+          job_cluster_key: job_cluster
+          python_wheel_task:
+            package_name: marcin_project
+            entry_point: main
+          libraries:
+            # By default we just include the .whl file generated for the marcin_project package.
+            # See https://docs.databricks.com/dev-tools/bundles/library-dependencies.html
+            # for more information on how to add other libraries.
+            - whl: ../dist/*.whl
+
+      job_clusters:
+        - job_cluster_key: job_cluster
+          new_cluster:
+            spark_version: 13.3.x-scala2.12
+            node_type_id: Standard_D3_v2
+            autoscale:
+                min_workers: 1
+                max_workers: 4