init repo

Author: donny-son

.gitignore

@@ -0,0 +1,162 @@
+.datatoys
+
+# 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/

.pre-commit-config.yaml

@@ -0,0 +1,11 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v2.3.0
+    hooks:
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/psf/black
+    rev: "22.6.0"
+    hooks:
+      - id: black

datatoys/__init__.py

@@ -0,0 +1,118 @@
+import os
+
+import pandas as pd
+import pyreadr
+
+
+class Datatoy:
+    """Easily install & load curated Republic of Korea public datasets from https://github.com/statgarten/datatoys"""
+
+    DATATOYS_URL = "https://github.com/statgarten/datatoys"
+    README_POSTFIX = "/blob/main/README.md"
+    DOWNLOAD_DIR = f"{os.path.join(os.getcwd(), '.datatoys')}"
+    DATASET_HEADER_KO = "데이터셋"
+
+    def __init__(self):
+        self.__create_download_directory()
+        self.manifest = self.get_manifest()
+
+    def __create_download_directory(self):
+        os.makedirs(self.DOWNLOAD_DIR, exist_ok=True)
+        assert os.path.exists(self.DOWNLOAD_DIR)
+
+    def _dataset_downloaded(self, dataset_nm: str) -> bool:
+        return os.path.exists(f"{self.DOWNLOAD_DIR}/{dataset_nm}.rda")
+
+    def _dataset_in_manifest(self, dataset_nm: str) -> bool:
+        return dataset_nm in self.get_manifest_dataset_names()
+
+    def get_manifest(self) -> pd.DataFrame:
+        url = self.DATATOYS_URL + self.README_POSTFIX
+        response = pd.read_html(url)
+        assert len(response) == 1 and isinstance(response[0], pd.DataFrame)
+        return response.pop()
+
+    def get_manifest_dataset_names(self) -> list:
+        return self.manifest.loc[:, self.DATASET_HEADER_KO].tolist()
+
+    def show_manifest(self):
+        print(self.get_manifest())
+
+    def install(self, dataset_nm: str) -> bool:
+        """Install the dataset to the download directory.
+
+        Args:
+                dataset_nm (str): The name of the dataset to be deleted.
+
+        Returns:
+                return: return True if successfully installed otherwise false.
+
+        Raises:
+                raise ValueError: raise ValueError if the dataset is not in the manifest.
+        """
+
+        remote_url = f"{self.DATATOYS_URL}/blob/main/data/{dataset_nm}.rda?raw=true"
+        dst_path = f"{self.DOWNLOAD_DIR}/{dataset_nm}.rda"
+        if not self._dataset_in_manifest(dataset_nm):
+            raise ValueError(
+                f"Dataset `{dataset_nm}` is not in the manifest. Check the manifest with `Datatoy().show_manifest()`."
+            )
+        try:
+            pyreadr.download_file(remote_url, dst_path)
+        except Exception as e:
+            print(f"Exception occured while downloading {remote_url}", e)
+            return False
+        assert self._dataset_downloaded(dataset_nm)
+        return True
+
+    def load(self, dataset_nm: str) -> pd.DataFrame:
+        """Load the dataset from the download directory.
+
+        Calls `Datatoy().install()` if the dataset is not downloaded.
+
+        Args:
+                dataset_nm (str): The name of the dataset to be deleted.
+
+        Returns:
+                return: pandas.DataFrame
+        """
+
+        dst_path = f"{self.DOWNLOAD_DIR}/{dataset_nm}.rda"
+        if not self._dataset_downloaded(dataset_nm):
+            print(f"Dataset `{dataset_nm}` is not installed. Installing it first.")
+            self.install(dataset_nm)
+        res = pyreadr.read_r(dst_path)
+        data = res.get(dataset_nm)
+        assert isinstance(data, pd.DataFrame)
+        return data
+
+    def clean(self, dataset_nm: str) -> bool:
+        """Delete the dataset from the download directory.
+
+        Args:
+                dataset_nm (str): The name of the dataset to be deleted.
+
+        Returns:
+                return: return True if the dataset is deleted successfully otherwise false.
+        """
+
+        dst_path = f"{self.DOWNLOAD_DIR}/{dataset_nm}.rda"
+        if self._dataset_downloaded(dataset_nm):
+            os.remove(dst_path)
+            return True
+        return False
+
+    def clean_all(self):
+        """Cleanup all datasets within the download directory."""
+
+        for dataset_nm in self.get_manifest_dataset_names():
+            self.clean(dataset_nm)
+
+
+if __name__ == "__main__":
+    dt = Datatoy()
+    dt.show_manifest()
+    dataset_nm = "karaoke"
+    df = dt.load("karaoke")
+    print(df.head())
+    dt.clean(dataset_nm)