transformplan 0.1.0__tar.gz

transformplan-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 TransformPlan Contributors
+
+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.

transformplan-0.1.0/PKG-INFO

@@ -0,0 +1,151 @@
+Metadata-Version: 2.4
+Name: transformplan
+Version: 0.1.0
+Summary: Safe, reproducible data transformations with built-in auditing and validation
+License: MIT
+Project-URL: Homepage, https://github.com/limebit/transformplan
+Project-URL: Repository, https://github.com/limebit/transformplan
+Keywords: data,transformation,polars,pandas,audit,validation
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Software Development
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: polars
+Requires-Dist: pandas
+Requires-Dist: pyarrow
+Dynamic: license-file
+
+<div align="center">
+  <img src="docs/assets/images/logo_wordmark_black.png" alt="TransformPlan" width="600">
+</div>
+
+<h1 align="center">TransformPlan: Auditable Data Transformation Pipelines</h1>
+
+<div align="center">
+  <img src="https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue" alt="Python 3.10+">
+  <img src="./coverage.svg" alt="Coverage">
+</div>
+
+## Features
+
+- **Declarative transformations**: Build transformation pipelines using method chaining
+- **Schema validation**: Validate operations before execution with dry-run capability
+- **Audit trails**: Generate complete audit protocols with deterministic DataFrame hashing
+- **Multi-backend support**: Works with both Polars (primary) and Pandas DataFrames
+- **Serializable pipelines**: Save and load transformation plans as JSON
+
+## Quick Example
+
+```python
+from transformplan import TransformPlan, Col
+
+# Build readable pipelines with 75+ chainable operations
+plan = (
+    TransformPlan()
+    # Standardize column names
+    .col_rename(column="PatientID", new_name="patient_id")
+    .col_rename(column="DOB", new_name="date_of_birth")
+    .str_strip(column="patient_id")
+
+    # Calculate derived values
+    .dt_age_years(column="date_of_birth", new_column="age")
+    .math_clamp(column="age", min_value=0, max_value=120)
+
+    # Categorize patients age
+    .map_discretize(column="age", bins=[18, 40, 65], labels=["young", "adult", "senior"], new_column="age_group")
+
+    # Filter and clean
+    .rows_filter(Col("age") >= 18)
+    .rows_drop_nulls(columns=["patient_id", "age"])
+    .col_drop(column="date_of_birth")
+)
+
+# Execute with schema validation — catch errors before they hit production
+df_result, protocol = plan.process(df, validate=True)
+
+# Serialize pipelines to JSON — version control your transformations
+plan.to_json("patient_transform.json")
+
+# Reload and reapply — reproducible results across environments
+plan = TransformPlan.from_json("patient_transform.json")
+df_result, protocol = plan.process(new_data)
+```
+
+### Full Audit Trail — Every Step Tracked and Hashed
+
+```python
+protocol.print(show_params=False)
+```
+
+```
+======================================================================
+TRANSFORM PROTOCOL
+======================================================================
+Input:  1000 rows × 5 cols  [a4f8b2c1]
+Output: 847 rows × 5 cols   [e7d3f9a2]
+Total time: 0.0247s
+----------------------------------------------------------------------
+
+#    Operation            Rows         Cols         Time       Hash
+----------------------------------------------------------------------
+0    input                1000         5            -          a4f8b2c1
+1    col_rename           1000         5            0.0012s    b2e4a7f3
+2    col_rename           1000         5            0.0008s    c9d1e5b8
+3    str_strip            1000         5            0.0013s    c9d1e5b8        ○
+4    dt_age_years         1000         6 (+1)       0.0041s    d4f2c8a1
+5    math_clamp           1000         6            0.0015s    e1b7d3f9
+6    map_discretize       1000         7 (+1)       0.0028s    f8a4c2e6
+7    rows_filter          858 (-142)   7            0.0037s    a2e9f4b7
+8    rows_drop_nulls      847 (-11)    7            0.0019s    b5c1d8e3
+9    col_drop             847          6 (-1)       0.0006s    e7d3f9a2
+======================================================================
+○ = no effect (steps 3 did not change data)
+```
+
+## Available Operations
+
+| Category   | Description               | Examples                                                                     |
+| ---------- | ------------------------- | ---------------------------------------------------------------------------- |
+| **col\_**  | Column operations         | `col_rename`, `col_drop`, `col_cast`, `col_add`, `col_select`                |
+| **math\_** | Arithmetic & scaling      | `math_add`, `math_multiply`, `math_standardize`, `math_minmax`, `math_clamp` |
+| **rows\_** | Row filtering & reshaping | `rows_filter`, `rows_drop_nulls`, `rows_sort`, `rows_unique`, `rows_pivot`   |
+| **str\_**  | String operations         | `str_lower`, `str_upper`, `str_strip`, `str_replace`, `str_split`            |
+| **dt\_**   | Datetime operations       | `dt_year`, `dt_month`, `dt_parse`, `dt_age_years`, `dt_diff_days`            |
+| **map\_**  | Value mapping & encoding  | `map_values`, `map_discretize`, `map_onehot`, `map_ordinal`                  |
+
+## Installation
+
+```bash
+pip install transformplan
+```
+
+Or with uv:
+
+```bash
+uv add transformplan
+```
+
+## Development Setup
+
+```bash
+make install-dev   # Install with dev dependencies
+make test          # Run the test suite
+make lint          # Run ruff linting and pyright type checking
+make format        # Fix import sorting and format code
+```
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.

transformplan-0.1.0/README.md

@@ -0,0 +1,122 @@
+<div align="center">
+  <img src="docs/assets/images/logo_wordmark_black.png" alt="TransformPlan" width="600">
+</div>
+
+<h1 align="center">TransformPlan: Auditable Data Transformation Pipelines</h1>
+
+<div align="center">
+  <img src="https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue" alt="Python 3.10+">
+  <img src="./coverage.svg" alt="Coverage">
+</div>
+
+## Features
+
+- **Declarative transformations**: Build transformation pipelines using method chaining
+- **Schema validation**: Validate operations before execution with dry-run capability
+- **Audit trails**: Generate complete audit protocols with deterministic DataFrame hashing
+- **Multi-backend support**: Works with both Polars (primary) and Pandas DataFrames
+- **Serializable pipelines**: Save and load transformation plans as JSON
+
+## Quick Example
+
+```python
+from transformplan import TransformPlan, Col
+
+# Build readable pipelines with 75+ chainable operations
+plan = (
+    TransformPlan()
+    # Standardize column names
+    .col_rename(column="PatientID", new_name="patient_id")
+    .col_rename(column="DOB", new_name="date_of_birth")
+    .str_strip(column="patient_id")
+
+    # Calculate derived values
+    .dt_age_years(column="date_of_birth", new_column="age")
+    .math_clamp(column="age", min_value=0, max_value=120)
+
+    # Categorize patients age
+    .map_discretize(column="age", bins=[18, 40, 65], labels=["young", "adult", "senior"], new_column="age_group")
+
+    # Filter and clean
+    .rows_filter(Col("age") >= 18)
+    .rows_drop_nulls(columns=["patient_id", "age"])
+    .col_drop(column="date_of_birth")
+)
+
+# Execute with schema validation — catch errors before they hit production
+df_result, protocol = plan.process(df, validate=True)
+
+# Serialize pipelines to JSON — version control your transformations
+plan.to_json("patient_transform.json")
+
+# Reload and reapply — reproducible results across environments
+plan = TransformPlan.from_json("patient_transform.json")
+df_result, protocol = plan.process(new_data)
+```
+
+### Full Audit Trail — Every Step Tracked and Hashed
+
+```python
+protocol.print(show_params=False)
+```
+
+```
+======================================================================
+TRANSFORM PROTOCOL
+======================================================================
+Input:  1000 rows × 5 cols  [a4f8b2c1]
+Output: 847 rows × 5 cols   [e7d3f9a2]
+Total time: 0.0247s
+----------------------------------------------------------------------
+
+#    Operation            Rows         Cols         Time       Hash
+----------------------------------------------------------------------
+0    input                1000         5            -          a4f8b2c1
+1    col_rename           1000         5            0.0012s    b2e4a7f3
+2    col_rename           1000         5            0.0008s    c9d1e5b8
+3    str_strip            1000         5            0.0013s    c9d1e5b8        ○
+4    dt_age_years         1000         6 (+1)       0.0041s    d4f2c8a1
+5    math_clamp           1000         6            0.0015s    e1b7d3f9
+6    map_discretize       1000         7 (+1)       0.0028s    f8a4c2e6
+7    rows_filter          858 (-142)   7            0.0037s    a2e9f4b7
+8    rows_drop_nulls      847 (-11)    7            0.0019s    b5c1d8e3
+9    col_drop             847          6 (-1)       0.0006s    e7d3f9a2
+======================================================================
+○ = no effect (steps 3 did not change data)
+```
+
+## Available Operations
+
+| Category   | Description               | Examples                                                                     |
+| ---------- | ------------------------- | ---------------------------------------------------------------------------- |
+| **col\_**  | Column operations         | `col_rename`, `col_drop`, `col_cast`, `col_add`, `col_select`                |
+| **math\_** | Arithmetic & scaling      | `math_add`, `math_multiply`, `math_standardize`, `math_minmax`, `math_clamp` |
+| **rows\_** | Row filtering & reshaping | `rows_filter`, `rows_drop_nulls`, `rows_sort`, `rows_unique`, `rows_pivot`   |
+| **str\_**  | String operations         | `str_lower`, `str_upper`, `str_strip`, `str_replace`, `str_split`            |
+| **dt\_**   | Datetime operations       | `dt_year`, `dt_month`, `dt_parse`, `dt_age_years`, `dt_diff_days`            |
+| **map\_**  | Value mapping & encoding  | `map_values`, `map_discretize`, `map_onehot`, `map_ordinal`                  |
+
+## Installation
+
+```bash
+pip install transformplan
+```
+
+Or with uv:
+
+```bash
+uv add transformplan
+```
+
+## Development Setup
+
+```bash
+make install-dev   # Install with dev dependencies
+make test          # Run the test suite
+make lint          # Run ruff linting and pyright type checking
+make format        # Fix import sorting and format code
+```
+
+## License
+
+MIT License - see [LICENSE](LICENSE) for details.

transformplan-0.1.0/pyproject.toml

@@ -0,0 +1,138 @@
+[project]
+name = "transformplan"
+version = "0.1.0"
+description = "Safe, reproducible data transformations with built-in auditing and validation"
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "MIT" }
+keywords = ["data", "transformation", "polars", "pandas", "audit", "validation"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Topic :: Scientific/Engineering",
+    "Topic :: Software Development",
+    "Typing :: Typed",
+]
+dependencies = ["polars", "pandas", "pyarrow"]
+
+[project.urls]
+Homepage = "https://github.com/limebit/transformplan"
+Repository = "https://github.com/limebit/transformplan"
+
+[dependency-groups]
+tests = ["pytest>=8.2.2", "pytest-cov>=7.0.0"]
+docs = [
+    "mkdocs>=1.6.0",
+    "mkdocs-material>=9.5.0",
+    "mkdocstrings[python]>=0.24.0",
+]
+dev = [
+    { include-group = "docs" },
+    { include-group = "tests" },
+    "ruff>=0.4.9",
+    "pyright==1.1.408",
+]
+
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools]
+packages = ["transformplan"]
+
+[tool.ruff]
+exclude = ["__pycache__", ".git", ".github", ".ruff_cache", ".venv"]
+line-length = 88
+
+[tool.ruff.lint]
+select = [
+    "E",    # PEP 8 codestyle errors
+    "F",    # pyflakes
+    "I",    # isort
+    "N",    # PEP 8 naming
+    "DOC",  # Pydoc Linting (preview); complementary to "D"
+    "D",    # Pydoc Style; PEP 257
+    "FA",   # future annotations linting; PEP 563
+    "W",    # pycodestyle warnings; PEP 8
+    "SIM",  # flake8 simplify; simplify code
+    "ANN",  # flake8 function annotations; PEP 3107
+    "B",    # bugbear extension for flake8; opinionated, not based on any PEP
+    "C4",   # list/set/dict comprehensions
+    "T10",  # Check for debugging leftovers: pdb;idbp imports and set traces
+    "EM",   # error messages
+    "LOG",  # logging module usage linting
+    "G",    # logging format strings
+    "T20",  # print statements
+    "PYI",  # lint stub files .pyi
+    "PT",   # pytest linting
+    "RET",  # return values
+    "TCH",  # type checking
+    "PTH",  # pathlib usage
+    "PERF", # performance linting
+    "FURB", # modern python code patterns
+    "RUF",  # ruff specific rules
+    "FBT",  # no bool as function param
+    "TD",   # todo linting
+    "C90",  # mccabe complexity
+]
+preview = true
+ignore = [
+    "E501", # Line length managed by formatter
+    # indentation linters conflicting with formatter:
+    "W191",
+    "E111",
+    "E114",
+    "E117",
+    "D206",
+    # quotation linters conflicting with formatter:
+    "D300",
+    "Q000",
+    "Q001",
+    "Q002",
+    "Q003",
+    # comma linters conflicting with formatter:
+    "COM812",
+    "COM819",
+    # string concatenation linters conflicting with formatter:
+    "ISC001",
+    "ISC002",
+]
+
+[tool.ruff.lint.per-file-ignores]
+"*/__init__.py" = ["D", "DOC"]
+"tests/**" = ["D", "DOC", "ANN", "PT009", "FBT", "B905", "W505", "PT017"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.pycodestyle]
+max-doc-length = 88
+
+[tool.ruff.format]
+docstring-code-format = true
+docstring-code-line-length = 88
+
+[tool.pyright]
+typeCheckingMode = "strict"
+reportPrivateUsage = false
+reportIncompatibleMethodOverride = false
+reportUnknownArgumentType = false
+reportUnknownVariableType = false
+reportUnknownMemberType = false
+reportMissingModuleSource = false
+reportMissingTypeStubs = false
+enableTypeIgnoreComments = false
+
+[tool.pytest.ini_options]
+filterwarnings = [
+    "error",
+    "ignore:.*`default` parameter for `replace` is deprecated.*:DeprecationWarning",
+]

transformplan-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+