First release - Initial implementation

.env.example

@@ -0,0 +1,3 @@
+#### IDEALISTA ####
+IDEALISTA_API_KEY=myApiKey
+IDEALISTA_SECRET=mySecret

.gitignore

@@ -1,7 +1,6 @@
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
-*$py.class
 
 # C extensions
 *.so
@@ -19,12 +18,9 @@ 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
@@ -39,87 +35,27 @@ 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
+# DotEnv configuration
 .env
 .venv
 env/
@@ -128,17 +64,34 @@ ENV/
 env.bak/
 venv.bak/
 
-# Spyder project settings
-.spyderproject
-.spyproject
+# Database
+*.db
+*.rdb
+
+# Pycharm
+.idea
+
+# VS Code
+.vscode/
 
-# Rope project settings
-.ropeproject
+# Spyder
+.spyproject/
 
-# mkdocs documentation
-/site
+# Jupyter NB Checkpoints
+.ipynb_checkpoints/
 
-# mypy
+# exclude specific folders from source control by default
+/data/
+/results/
+
+# Mac OS-specific storage files
+.DS_Store
+
+# vim
+*.swp
+*.swo
+
+# Mypy
 .mypy_cache/
 .dmypy.json
 dmypy.json
@@ -151,10 +104,3 @@ dmypy.json
 
 # 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/

CHANGELOG.md

@@ -0,0 +1,11 @@
+# Changelog
+
+## 0.1.0 (2024-04-01)
+#### New Features
+
+* defined project structure
+* added scripts for generating data
+* added scripts for training and prediction
+
+#### Docs
+* added README

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 $(MAKEFILE_LIST))))
+BUCKET = [OPTIONAL] your-bucket-for-syncing-data (do not include 's3://')
+PROFILE = default
+PROJECT_NAME = house-finder
+PYTHON_INTERPRETER = python3
+
+ifeq (,$(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')