feat: add dbt project from other repository

Author: jaanli

.gitignore

@@ -3,4 +3,178 @@ dist/
 docs/.observablehq/cache/
 node_modules/
 yarn-error.log
-.vscode/
+.vscode/
+
+# Duckdb
+*.duckdb
+*.duckdb.tmp/
+*.duckdb.wal
+
+.gitkeep
+
+# MacOS 
+.DS_Store
+
+# Venv
+.venv/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

data_processing/.gitignore

@@ -0,0 +1,4 @@
+
+target/
+dbt_packages/
+logs/

data_processing/dbt_project.yml

@@ -0,0 +1,47 @@
+# Name your project! Project names should contain only lowercase characters
+# and underscores. A good package name should reflect your organization's
+# name or the intended use of these models
+name: "american_community_survey"
+version: "1.0.0"
+config-version: 2
+
+# This setting configures which "profile" dbt uses for this project.
+profile: "american_community_survey"
+
+# Variables that can be changed from the command line using the `--vars` flag:
+# example: dbt run --vars 'my_variable: my_value'
+vars:
+  # The URL of the American Community Survey PUMS data
+  public_use_microdata_sample_url: "https://www2.census.gov/programs-surveys/acs/data/pums/2022/1-Year/"
+  public_use_microdata_sample_data_dictionary_url: "https://www2.census.gov/programs-surveys/acs/tech_docs/pums/data_dict/PUMS_Data_Dictionary_2022.csv"
+  microdata_area_shapefile_url: "https://www2.census.gov/geo/tiger/TIGER2010/PUMA5/2010/" # https://www2.census.gov/geo/tiger/TIGER2010/PUMA5/2010/ # https://www2.census.gov/geo/tiger/TIGER2020/PUMA20/
+  output_path: "~/data/american_community_survey"
+
+# These configurations specify where dbt should look for different types of files.
+# The `model-paths` config, for example, states that models in this project can be
+# found in the "models/" directory. You probably won't need to change these!
+model-paths: ["models"]
+analysis-paths: ["analyses"]
+test-paths: ["tests"]
+seed-paths: ["seeds"]
+macro-paths: ["macros"]
+snapshot-paths: ["snapshots"]
+
+clean-targets: # directories to be removed by `dbt clean`
+  - "target"
+  - "dbt_packages"
+
+# Configuring models
+# Full documentation: https://docs.getdbt.com/docs/configuring-models
+
+# In this example config, we tell dbt to build all models in the example/
+# directory as views. These settings can be overridden in the individual model
+# files using the `{{ config(...) }}` macro.
+models:
+  american_community_survey:
+    # Config indicated by + and applies to all files under models/example/
+    # example:
+    +materialized: view
+    public_use_microdata_sample:
+      generated:
+        +tags: "generated"

data_processing/macros/generate_industry_mapping_2003_onwards.sql

@@ -0,0 +1,9 @@
+{% macro generate_industry_mapping_2003_onwards_sql(input_field) %}
+{% set industry_mappings = get_industry_mappings_2003_onwards() %}
+
+CASE {{ input_field }}
+    {% for code, description in industry_mappings.items() %}
+    WHEN '{{ code }}' THEN '{{ description }}'
+    {% endfor %}
+END::ENUM ({% for description in industry_mappings.values() | unique %}'{{ description }}'{{ "," if not loop.last }}{% endfor %})
+{% endmacro %}

data_processing/macros/generate_industry_mapping_before_2003.sql

@@ -0,0 +1,9 @@
+{% macro generate_industry_mapping_before_2003_sql(input_field) %}
+{% set industry_mappings = get_industry_mappings_before_2003() %}
+
+CASE {{ input_field }}
+    {% for code, description in industry_mappings.items() %}
+    WHEN '{{ code }}' THEN '{{ description }}'
+    {% endfor %}
+END::ENUM ({% for description in industry_mappings.values() | unique %}'{{ description }}'{{ "," if not loop.last }}{% endfor %})
+{% endmacro %}