clearspark 0.1.0__tar.gz

clearspark-0.1.0/.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

clearspark-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Vinicius de Oliveira
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

clearspark-0.1.0/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.4
+Name: clearspark
+Version: 0.1.0
+Summary: A curated collection of essential PySpark functions for daily data engineering. Featuring quality-of-life enhancements for DataFrames.
+Author-email: Seu Nome <seu.email@example.com>
+License: MIT
+License-File: LICENSE
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.8
+Requires-Dist: pyspark>=3.5.0
+Provides-Extra: dev
+Requires-Dist: black; extra == 'dev'
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# clearspark
+A curated collection of essential PySpark functions for daily data engineering. Featuring quality-of-life enhancements for DataFrames.

clearspark-0.1.0/README.md

@@ -0,0 +1,2 @@
+# clearspark
+A curated collection of essential PySpark functions for daily data engineering. Featuring quality-of-life enhancements for DataFrames.

clearspark-0.1.0/pyproject.toml

@@ -0,0 +1,35 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "clearspark"
+version = "0.1.0"
+description = "A curated collection of essential PySpark functions for daily data engineering. Featuring quality-of-life enhancements for DataFrames."
+readme = "README.md"
+requires-python = ">=3.8"
+license = {text = "MIT"}
+authors = [
+    {name = "Seu Nome", email = "seu.email@example.com"},
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "pyspark>=3.5.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest",
+    "black",
+    "mypy",
+]
+
+[tool.hatch.build.targets.sdist]
+include = ["/src"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/clearspark"]

clearspark-0.1.0/src/clearspark/functions.py

@@ -0,0 +1,80 @@
+from pyspark.sql.functions import\
+     when, \
+     col, \
+     lit
+
+from clearspark.validation import\
+     _validate_with_buckets_params
+
+__all__ = ["with_buckets"]
+
+def with_buckets(spark_df, value_column_name: str, bucket_column_name: str, buckets: list):
+     """
+    Adds a categorical column to a PySpark DataFrame that classifies numeric values into labeled ranges (buckets).
+
+    The resulting labels are prefixed with a zero-padded index to preserve natural sort order,
+    making them suitable for ordering in charts and reports.
+
+    Args:
+        spark_df (DataFrame): Input PySpark DataFrame.
+        value_column_name (str): Name of the numeric column to classify.
+        bucket_column_name (str): Name of the new column to be added with the bucket labels.
+        buckets (list): List of numeric boundary values that define the bucket edges.
+                        Does not need to be sorted. Must contain at least one value.
+
+    Returns:
+        DataFrame: A new DataFrame with an additional string column containing the bucket label
+                   for each row.
+
+    Raises:
+        IndexError: If `buckets` is an empty list.
+
+    Label format:
+        "00. no info"       → null values
+        "01. <{min}"        → values below the smallest boundary
+        "0N. {low}-{high}"  → values within a boundary range (inclusive)
+        "0N. >{max}"        → values above the largest boundary
+
+    Example:
+        >>> with_buckets(df, "revenue", "revenue_range", [100, 500, 1000])
+
+        Resulting labels in "revenue_range":
+            "00. no info"    → null
+            "01. <100"       → revenue < 100
+            "02. 100-500"    → 100 <= revenue <= 500
+            "03. 500-1000"   → 500 <= revenue <= 1000
+            "04. >1000"      → revenue > 1000
+     """
+     _validate_with_buckets_params(spark_df, value_column_name, bucket_column_name, buckets)
+
+     value_col = col(value_column_name)
+     sorted_buckets = sorted(buckets) 
+     n = len(sorted_buckets)
+
+     expr = when(
+        value_col.isNull(), 
+        lit("00. no info")
+     )
+    
+     expr = expr.when(
+        value_col < sorted_buckets[0], 
+        lit(f"01. <{sorted_buckets[0]}")
+     )
+
+     for i in range(len(sorted_buckets) - 1):
+          low, high = sorted_buckets[i], sorted_buckets[i + 1]
+
+          label = f"{(i + 2):02d}. {low}-{high}"
+
+          expr = expr\
+               .when(
+                    (value_col >= low) & (value_col <= high), 
+                    lit(label)
+               )
+
+     expr = expr\
+          .otherwise(
+              lit(f"{(n + 1):02d}. >{sorted_buckets[-1]}")
+          )
+
+     return spark_df.withColumn(bucket_column_name, expr)

clearspark-0.1.0/src/clearspark/validation.py

@@ -0,0 +1,38 @@
+
+__all__ = ["_validate_with_buckets_params"]
+
+def _validate_with_buckets_params(spark_df, value_column_name: str, bucket_column_name: str, buckets: list):
+    """
+    Validates the parameters for the `with_buckets` function.
+
+    Args:
+        spark_df (DataFrame): Input PySpark DataFrame.
+        value_column_name (str): Name of the numeric column to classify.
+        bucket_column_name (str): Name of the new bucket column to be created.
+        buckets (list): List of numeric boundary values.
+
+    Raises:
+        TypeError: If any parameter has an unexpected type.
+        ValueError: If `buckets` is empty, contains duplicates, or `value_column_name`
+                    does not exist in the DataFrame.
+    """
+    if not isinstance(value_column_name, str):
+        raise TypeError(f"'value_column_name' must be a string, got {type(value_column_name).__name__}.")
+
+    if not isinstance(bucket_column_name, str):
+        raise TypeError(f"'bucket_column_name' must be a string, got {type(bucket_column_name).__name__}.")
+
+    if not isinstance(buckets, list):
+        raise TypeError(f"'buckets' must be a list, got {type(buckets).__name__}.")
+
+    if len(buckets) == 0:
+        raise ValueError("'buckets' must contain at least one boundary value.")
+
+    if not all(isinstance(b, (int, float)) for b in buckets):
+        raise TypeError("All values in 'buckets' must be numeric (int or float).")
+
+    if len(buckets) != len(set(buckets)):
+        raise ValueError("'buckets' must not contain duplicate values.")
+
+    if value_column_name not in spark_df.columns:
+        raise ValueError(f"Column '{value_column_name}' not found in DataFrame. Available columns: {spark_df.columns}.")