Add default_python example (#3)

This adds a default_python project based on the template of databricks/cli#686:
```
The 'default_python' project was generated by using the default-python template.
```

It also adds a LICENSE and removes the original stub example.

LICENSE

@@ -0,0 +1,51 @@
+DB license
+
+Copyright (2022) Databricks, Inc.
+
+Definitions.
+
+Agreement: The agreement between Databricks, Inc., and you governing the use of the Databricks Services, which shall 
+be, with respect to Databricks, the Databricks Terms of Service located at www.databricks.com/termsofservice, and with 
+respect to Databricks Community Edition, the Community Edition Terms of Service located at 
+www.databricks.com/ce-termsofuse, in each case unless you have entered into a separate written agreement with 
+Databricks governing the use of the applicable Databricks Services.
+
+Software: The source code and object code to which this license applies.
+
+Scope of Use. You may not use this Software except in connection with your use of the Databricks Services pursuant to 
+the Agreement. Your use of the Software must comply at all times with any restrictions applicable to the Databricks 
+Services, generally, and must be used in accordance with any applicable documentation. You may view, use, copy, 
+modify, publish, and/or distribute the Software solely for the purposes of using the code within or connecting to the 
+Databricks Services. If you do not agree to these terms, you may not view, use, copy, modify, publish, and/or 
+distribute the Software.
+
+Redistribution. You may redistribute and sublicense the Software so long as all use is in compliance with these terms. 
+In addition:
+
+You must give any other recipients a copy of this License;
+You must cause any modified files to carry prominent notices stating that you changed the files;
+You must retain, in the source code form of any derivative works that you distribute, all copyright, patent, 
+trademark, and attribution notices from the source code form, excluding those notices that do not pertain to any part 
+of the derivative works; and
+If the source code form includes a "NOTICE" text file as part of its distribution, then any derivative works that you 
+distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those 
+notices that do not pertain to any part of the derivative works.
+You may add your own copyright statement to your modifications and may provide additional license terms and conditions 
+for use, reproduction, or distribution of your modifications, or for any such derivative works as a whole, provided 
+your use, reproduction, and distribution of the Software otherwise complies with the conditions stated in this 
+License.
+
+Termination. This license terminates automatically upon your breach of these terms or upon the termination of your 
+Agreement. Additionally, Databricks may terminate this license at any time on notice. Upon termination, you must 
+permanently delete the Software and all copies thereof.
+
+DISCLAIMER; LIMITATION OF LIABILITY.
+
+THE SOFTWARE IS PROVIDED “AS-IS” AND WITH ALL FAULTS. DATABRICKS, ON BEHALF OF ITSELF AND ITS LICENSORS, SPECIFICALLY 
+DISCLAIMS ALL WARRANTIES RELATING TO THE SOURCE CODE, EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, IMPLIED 
+WARRANTIES, CONDITIONS AND OTHER TERMS OF MERCHANTABILITY, SATISFACTORY QUALITY OR FITNESS FOR A PARTICULAR PURPOSE, 
+AND NON-INFRINGEMENT. DATABRICKS AND ITS LICENSORS TOTAL AGGREGATE LIABILITY RELATING TO OR ARISING OUT OF YOUR USE OF 
+OR DATABRICKS’ PROVISIONING OF THE SOURCE CODE SHALL BE LIMITED TO ONE THOUSAND ($1,000) DOLLARS. IN NO EVENT SHALL 
+THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF 
+CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN 
+THE SOFTWARE.

default_python/.gitignore

@@ -0,0 +1,9 @@
+
+.databricks/
+build/
+dist/
+__pycache__/
+*.egg-info
+.venv/
+scratch/**
+!scratch/README.md

default_python/.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 *

default_python/.vscode/extensions.json

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

default_python/.vscode/settings.json

@@ -0,0 +1,14 @@
+{
+    "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,
+    "files.exclude": {
+        "**/*.egg-info": true
+    },
+}

default_python/README.md

@@ -0,0 +1,37 @@
+# default_python
+
+The 'default_python' 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] default_python-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. 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.
+
+6. 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.

default_python/databricks.yml

@@ -0,0 +1,43 @@
+# This is a Databricks asset bundle definition for default_python.
+# See https://docs.databricks.com/dev-tools/bundles/index.html for documentation.
+bundle:
+  name: default_python
+
+include:
+  - resources/*.yml
+
+targets:
+  # The 'dev' target, used development purposes.
+  # Whenever a developer deploys using 'dev', they get their own copy.
+  dev:
+    # We use 'mode: development' to make everything deployed to this target gets a prefix
+    # like '[dev my_user_name]'. Setting this mode also disables any schedules and
+    # automatic triggers for jobs and enables the 'development' mode for Delta Live Tables pipelines.
+    mode: development
+    default: true
+    workspace:
+      host: https://myworkspace.databricks.com
+
+  # 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://myworkspace.databricks.com
+
+  # The 'prod' target, used for production deployment.
+  prod:
+    # For production deployments, we only have a single copy, so we override the
+    # workspace.root_path default of
+    # /Users/${workspace.current_user.userName}/.bundle/${bundle.target}/${bundle.name}
+    # to a path that is not specific to the current user.
+    mode: production
+    workspace:
+      host: https://myworkspace.databricks.com
+      root_path: /Shared/.bundle/prod/${bundle.name}
+    run_as:
+      # This runs as [email protected] in production. Alternatively,
+      # a service principal could be used here using service_principal_name
+      # (see Databricks documentation).
+      user_name: [email protected]
+

default_python/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 os.path.join("/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)
+```

default_python/pytest.ini

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

default_python/resources/default_python_job.yml

@@ -0,0 +1,48 @@
+# The main job for default_python
+resources:
+  jobs:
+    default_python_job:
+      name: default_python_job
+
+      schedule:
+        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.default_python_pipeline.id}
+
+        - task_key: main_task
+          depends_on:
+            - task_key: refresh_pipeline
+          job_cluster_key: job_cluster
+          python_wheel_task:
+            package_name: default_python
+            entry_point: main
+          libraries:
+            - whl: ../dist/*.whl
+
+      job_clusters:
+        - job_cluster_key: job_cluster
+          new_cluster:
+            spark_version: 13.3.x-scala2.12
+            # node_type_id is the cluster node type to use.
+            # Typical node types on AWS include i3.xlarge; 
+            # Standard_D3_v2 on Azure;
+            # n1-standard-4 on Google Cloud.
+            node_type_id: i3.xlarge
+            autoscale:
+                min_workers: 1
+                max_workers: 4

default_python/resources/default_python_pipeline.yml

@@ -0,0 +1,12 @@
+# The main pipeline for default_python
+resources:
+  pipelines:
+    default_python_pipeline:
+      name: "default_python_pipeline"
+      target: "default_python_${bundle.environment}"
+      libraries:
+        - notebook:
+            path: ../src/dlt_pipeline.ipynb
+
+      configuration:
+        "bundle.sourcePath": "/Workspace/${workspace.file_path}/src"

default_python/scratch/README.md

@@ -0,0 +1,4 @@
+# scratch
+
+This folder is reserved for personal, exploratory notebooks.
+By default these are not committed to Git, as 'scratch' is listed in .gitignore.

default_python/scratch/exploration.ipynb

@@ -0,0 +1,50 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "application/vnd.databricks.v1+cell": {
+     "cellMetadata": {
+      "byteLimit": 2048000,
+      "rowLimit": 10000
+     },
+     "inputWidgets": {},
+     "nuid": "6bca260b-13d1-448f-8082-30b60a85c9ae",
+     "showTitle": false,
+     "title": ""
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "sys.path.append('../src')\n",
+    "from default_python import main\n",
+    "\n",
+    "main.get_taxis().show(10)"
+   ]
+  }
+ ],
+ "metadata": {
+  "application/vnd.databricks.v1+notebook": {
+   "dashboards": [],
+   "language": "python",
+   "notebookMetadata": {
+    "pythonIndentUnit": 2
+   },
+   "notebookName": "ipynb-notebook",
+   "widgets": {}
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

default_python/setup.py

@@ -0,0 +1,24 @@
+"""
+Setup script for default_python.
+
+This script packages and distributes the associated wheel file(s).
+Source code is in ./src/. Run 'python setup.py sdist bdist_wheel' to build.
+"""
+from setuptools import setup, find_packages
+
+import sys
+sys.path.append('./src')
+
+import default_python
+
+setup(
+    name="default_python",
+    version=default_python.__version__,
+    url="https://databricks.com",
+    author="<no value>",
+    description="my test wheel",
+    packages=find_packages(where='./src'),
+    package_dir={'': 'src'},
+    entry_points={"entry_points": "main=default_python.main:main"},
+    install_requires=["setuptools"],
+)

default_python/src/default_python/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.1"

default_python/src/default_python/main.py

@@ -0,0 +1,11 @@
+from pyspark.sql import SparkSession
+
+def get_taxis():
+  spark = SparkSession.builder.getOrCreate()
+  return spark.read.table("samples.nyctaxi.trips")
+
+def main():
+  get_taxis().show(5)
+
+if __name__ == '__main__':
+  main()