first

.dvc/.gitignore

@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache

.dvcignore

@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

.gitignore

@@ -0,0 +1,92 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# 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/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# DotEnv configuration
+.env
+
+# Database
+*.db
+*.rdb
+
+# Pycharm
+.idea
+
+# VS Code
+.vscode/
+
+# Spyder
+.spyproject/
+
+# Jupyter NB Checkpoints
+.ipynb_checkpoints/
+
+# exclude data from source control by default
+/data/
+
+# Mac OS-specific storage files
+.DS_Store
+
+# vim
+*.swp
+*.swo
+
+# Mypy cache
+.mypy_cache/
+
+/models
+/dvclive

LICENSE

@@ -0,0 +1 @@
+

Makefile

@@ -0,0 +1,144 @@
+.PHONY: clean data lint requirements sync_data_to_s3 sync_data_from_s3
+
+#################################################################################
+# GLOBALS                                                                       #
+#################################################################################
+
+PROJECT_DIR := $(shell dirname $(realpath $(lastword $(MAKEFILE_LIST))))
+BUCKET = [OPTIONAL] your-bucket-for-syncing-data (do not include 's3://')
+PROFILE = default
+PROJECT_NAME = dummy
+PYTHON_INTERPRETER = python3
+
+ifeq (,$(shell which conda))
+HAS_CONDA=False
+else
+HAS_CONDA=True
+endif
+
+#################################################################################
+# COMMANDS                                                                      #
+#################################################################################
+
+## Install Python Dependencies
+requirements: test_environment
+	$(PYTHON_INTERPRETER) -m pip install -U pip setuptools wheel
+	$(PYTHON_INTERPRETER) -m pip install -r requirements.txt
+
+## Make Dataset
+data: requirements
+	$(PYTHON_INTERPRETER) src/data/make_dataset.py data/raw data/processed
+
+## Delete all compiled Python files
+clean:
+	find . -type f -name "*.py[co]" -delete
+	find . -type d -name "__pycache__" -delete
+
+## Lint using flake8
+lint:
+	flake8 src
+
+## Upload Data to S3
+sync_data_to_s3:
+ifeq (default,$(PROFILE))
+	aws s3 sync data/ s3://$(BUCKET)/data/
+else
+	aws s3 sync data/ s3://$(BUCKET)/data/ --profile $(PROFILE)
+endif
+
+## Download Data from S3
+sync_data_from_s3:
+ifeq (default,$(PROFILE))
+	aws s3 sync s3://$(BUCKET)/data/ data/
+else
+	aws s3 sync s3://$(BUCKET)/data/ data/ --profile $(PROFILE)
+endif
+
+## Set up python interpreter environment
+create_environment:
+ifeq (True,$(HAS_CONDA))
+		@echo ">>> Detected conda, creating conda environment."
+ifeq (3,$(findstring 3,$(PYTHON_INTERPRETER)))
+	conda create --name $(PROJECT_NAME) python=3
+else
+	conda create --name $(PROJECT_NAME) python=2.7
+endif
+		@echo ">>> New conda env created. Activate with:\nsource activate $(PROJECT_NAME)"
+else
+	$(PYTHON_INTERPRETER) -m pip install -q virtualenv virtualenvwrapper
+	@echo ">>> Installing virtualenvwrapper if not already installed.\nMake sure the following lines are in shell startup file\n\
+	export WORKON_HOME=$$HOME/.virtualenvs\nexport PROJECT_HOME=$$HOME/Devel\nsource /usr/local/bin/virtualenvwrapper.sh\n"
+	@bash -c "source `which virtualenvwrapper.sh`;mkvirtualenv $(PROJECT_NAME) --python=$(PYTHON_INTERPRETER)"
+	@echo ">>> New virtualenv created. Activate with:\nworkon $(PROJECT_NAME)"
+endif
+
+## Test python environment is setup correctly
+test_environment:
+	$(PYTHON_INTERPRETER) test_environment.py
+
+#################################################################################
+# PROJECT RULES                                                                 #
+#################################################################################
+
+
+
+#################################################################################
+# Self Documenting Commands                                                     #
+#################################################################################
+
+.DEFAULT_GOAL := help
+
+# Inspired by <http://marmelab.com/blog/2016/02/29/auto-documented-makefile.html>
+# sed script explained:
+# /^##/:
+# 	* save line in hold space
+# 	* purge line
+# 	* Loop:
+# 		* append newline + line to hold space
+# 		* go to next line
+# 		* if line starts with doc comment, strip comment character off and loop
+# 	* remove target prerequisites
+# 	* append hold space (+ newline) to line
+# 	* replace newline plus comments by `---`
+# 	* print line
+# Separate expressions are necessary because labels cannot be delimited by
+# semicolon; see <http://stackoverflow.com/a/11799865/1968>
+.PHONY: help
+help:
+	@echo "$$(tput bold)Available rules:$$(tput sgr0)"
+	@echo
+	@sed -n -e "/^## / { \
+		h; \
+		s/.*//; \
+		:doc" \
+		-e "H; \
+		n; \
+		s/^## //; \
+		t doc" \
+		-e "s/:.*//; \
+		G; \
+		s/\\n## /---/; \
+		s/\\n/ /g; \
+		p; \
+	}" ${MAKEFILE_LIST} \
+	| LC_ALL='C' sort --ignore-case \
+	| awk -F '---' \
+		-v ncol=$$(tput cols) \
+		-v indent=19 \
+		-v col_on="$$(tput setaf 6)" \
+		-v col_off="$$(tput sgr0)" \
+	'{ \
+		printf "%s%*s%s ", col_on, -indent, $$1, col_off; \
+		n = split($$2, words, " "); \
+		line_length = ncol - indent; \
+		for (i = 1; i <= n; i++) { \
+			line_length -= length(words[i]) + 1; \
+			if (line_length <= 0) { \
+				line_length = ncol - indent - length(words[i]) - 1; \
+				printf "\n%*s ", -indent, " "; \
+			} \
+			printf "%s ", words[i]; \
+		} \
+		printf "\n"; \
+	}' \
+	| more $(shell test $(shell uname) = Darwin && echo '--no-init --raw-control-chars')

README.md

@@ -0,0 +1,57 @@
+dummy
+==============================
+
+A short description of the project.
+
+Project Organization
+------------
+
+    ├── LICENSE
+    ├── Makefile           <- Makefile with commands like `make data` or `make train`
+    ├── README.md          <- The top-level README for developers using this project.
+    ├── data
+    │   ├── external       <- Data from third party sources.
+    │   ├── interim        <- Intermediate data that has been transformed.
+    │   ├── processed      <- The final, canonical data sets for modeling.
+    │   └── raw            <- The original, immutable data dump.
+    │
+    ├── docs               <- A default Sphinx project; see sphinx-doc.org for details
+    │
+    ├── models             <- Trained and serialized models, model predictions, or model summaries
+    │
+    ├── notebooks          <- Jupyter notebooks. Naming convention is a number (for ordering),
+    │                         the creator's initials, and a short `-` delimited description, e.g.
+    │                         `1.0-jqp-initial-data-exploration`.
+    │
+    ├── references         <- Data dictionaries, manuals, and all other explanatory materials.
+    │
+    ├── reports            <- Generated analysis as HTML, PDF, LaTeX, etc.
+    │   └── figures        <- Generated graphics and figures to be used in reporting
+    │
+    ├── requirements.txt   <- The requirements file for reproducing the analysis environment, e.g.
+    │                         generated with `pip freeze > requirements.txt`
+    │
+    ├── setup.py           <- makes project pip installable (pip install -e .) so src can be imported
+    ├── src                <- Source code for use in this project.
+    │   ├── __init__.py    <- Makes src a Python module
+    │   │
+    │   ├── data           <- Scripts to download or generate data
+    │   │   └── make_dataset.py
+    │   │
+    │   ├── features       <- Scripts to turn raw data into features for modeling
+    │   │   └── build_features.py
+    │   │
+    │   ├── models         <- Scripts to train models and then use trained models to make
+    │   │   │                 predictions
+    │   │   ├── predict_model.py
+    │   │   └── train_model.py
+    │   │
+    │   └── visualization  <- Scripts to create exploratory and results oriented visualizations
+    │       └── visualize.py
+    │
+    └── tox.ini            <- tox file with settings for running tox; see tox.readthedocs.io
+
+
+--------
+
+<p><small>Project based on the <a target="_blank" href="https://drivendata.github.io/cookiecutter-data-science/">cookiecutter data science project template</a>. #cookiecutterdatascience</small></p>