my-databricks-project/
├── src/
│   ├── __init__.py
│   ├── pipelines/
│   │   ├── __init__.py
│   │   ├── bronze.py       # Raw data ingestion
│   │   ├── silver.py       # Data cleansing
│   │   └── gold.py         # Business aggregations
│   └── utils/
│       ├── __init__.py
│       └── helpers.py
├── tests/
│   ├── __init__.py
│   ├── unit/
│   │   └── test_helpers.py
│   └── integration/
│       └── test_pipelines.py
├── notebooks/              # Databricks notebooks
│   └── exploration.py
├── resources/              # Asset Bundle configs
│   └── jobs.yml
├── databricks.yml          # Asset Bundle project config
├── .env.local              # Local secrets (git-ignored)
├── .env.example            # Template for team
├── pyproject.toml
└── requirements.txt

# Install Databricks SDK and CLI
pip install databricks-sdk databricks-cli

# Install dbx for deployment
pip install dbx

# Install Databricks Connect v2 (for local Spark)
pip install databricks-connect==14.3.*

# Install testing tools
pip install pytest pytest-cov

# Configure Databricks Connect for local development
databricks-connect configure

# Or set environment variables
export DATABRICKS_HOST="https://adb-1234567890.1.azuredatabricks.net"
export DATABRICKS_TOKEN="dapi..."
export DATABRICKS_CLUSTER_ID="1234-567890-abcde123"

# databricks.yml
bundle:
  name: my-databricks-project

workspace:
  host: ${DATABRICKS_HOST}

variables:
  catalog:
    description: Unity Catalog name
    default: main
  schema:
    description: Schema name
    default: default

targets:
  dev:
    default: true
    mode: development
    workspace:
      root_path: /Users/${workspace.current_user.userName}/.bundle/${bundle.name}/dev

  staging:
    mode: development
    workspace:
      root_path: /Shared/.bundle/${bundle.name}/staging

  prod:
    mode: production
    workspace:
      root_path: /Shared/.bundle/${bundle.name}/prod

# tests/conftest.py
import pytest
from pyspark.sql import SparkSession

@pytest.fixture(scope="session")
def spark():
    """Create local SparkSession for unit tests."""
    return SparkSession.builder \
        .master("local[*]") \
        .appName("unit-tests") \
        .config("spark.sql.extensions", "io.delta.sql.DeltaSparkSessionExtension") \
        .config("spark.sql.catalog.spark_catalog", "org.apache.spark.sql.delta.catalog.DeltaCatalog") \
        .getOrCreate()

@pytest.fixture(scope="session")
def dbx_spark():
    """Connect to Databricks cluster for integration tests."""
    from databricks.connect import DatabricksSession
    return DatabricksSession.builder.getOrCreate()

// .vscode/settings.json
{
  "python.defaultInterpreterPath": "${workspaceFolder}/.venv/bin/python",
  "python.testing.pytestEnabled": true,
  "python.testing.pytestArgs": ["tests"],
  "python.linting.enabled": true,
  "python.linting.pylintEnabled": true,
  "editor.formatOnSave": true,
  "[python]": {
    "editor.defaultFormatter": "ms-python.black-formatter"
  },
  "databricks.python.envFile": "${workspaceFolder}/.env.local"
}

// .vscode/launch.json
{
  "version": "0.2.0",
  "configurations": [
    {
      "name": "Python: Current File (Databricks Connect)",
      "type": "python",
      "request": "launch",
      "program": "${file}",
      "console": "integratedTerminal",
      "env": {
        "DATABRICKS_HOST": "${env:DATABRICKS_HOST}",
        "DATABRICKS_TOKEN": "${env:DATABRICKS_TOKEN}",
        "DATABRICKS_CLUSTER_ID": "${env:DATABRICKS_CLUSTER_ID}"
      }
    }
  ]
}

# Unit tests (local Spark)
pytest tests/unit/ -v

# Integration tests (Databricks Connect)
pytest tests/integration/ -v --tb=short

# With coverage
pytest tests/ --cov=src --cov-report=html

# Validate bundle
databricks bundle validate

# Deploy to dev
databricks bundle deploy -t dev

# Run job
databricks bundle run -t dev my-job

# src/pipelines/bronze.py
from pyspark.sql import SparkSession, DataFrame

def ingest_raw_data(spark: SparkSession, source_path: str) -> DataFrame:
    """Ingest raw data from source."""
    return spark.read.format("json").load(source_path)

if __name__ == "__main__":
    # Works locally with Databricks Connect
    from databricks.connect import DatabricksSession
    spark = DatabricksSession.builder.getOrCreate()

    df = ingest_raw_data(spark, "/mnt/raw/events")
    df.show()

# Watch for changes and sync
dbx sync --watch

# Or use Asset Bundles
databricks bundle sync -t dev --watch