itertoolkit 1.4.9__tar.gz

itertoolkit-1.4.9/.gitignore

@@ -0,0 +1,225 @@
+# 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
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# 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
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+*.png
+*.jpg
+*.pdf
+*.jpeg
+
+CMDS.md
+
+*.code-workspace

itertoolkit-1.4.9/PKG-INFO

@@ -0,0 +1,120 @@
+Metadata-Version: 2.4
+Name: itertoolkit
+Version: 1.4.9
+Summary: An itertools-inspired toolkit for cached iterator and data-structure processing
+Requires-Python: >=3.11
+Requires-Dist: gsppy>=5.3.0
+Requires-Dist: matplotlib>=3.10.8
+Requires-Dist: networkx>=3.6.1
+Requires-Dist: numpy>=2.4.4
+Requires-Dist: pandas>=3.0.2
+Requires-Dist: plotly>=6.6.0
+Requires-Dist: scikit-learn>=1.8.0
+Requires-Dist: scipy>=1.17.1
+Requires-Dist: seaborn>=0.13.2
+Description-Content-Type: text/markdown
+
+# itertoolkit
+
+Functions creating iterators and cached data pipelines for efficient looping.
+
+`itertoolkit` is an `itertools`-inspired wrapper focused on practical data processing. It keeps the lazy, composable style of iterator algebra, then adds cache-aware helpers so repeated list and data-structure transformations run faster.
+
+The goal is simple:
+
+- Keep memory usage low with lazy iterators.
+- Speed up repeated workloads with caching.
+- Make iterator pipelines readable and reusable.
+
+## Installation
+
+```bash
+pip install itertoolkit
+```
+
+## Quick Start
+
+```python
+from itertools import count, islice
+
+# Install name: itertoolkit
+# Current import path in this repo remains bm_preprocessing
+from bm_preprocessing import IR, DM
+
+# Example: base itertools stream
+stream = (x * x for x in count(1))
+print(list(islice(stream, 5)))  # [1, 4, 9, 16, 25]
+
+# Example: cached computation workflow (concept)
+# result = itertoolkit.cached_map(expensive_fn, dataset, cache_key="v1")
+```
+
+## Why It Is Faster
+
+`itertoolkit` performance comes from combining:
+
+- Lazy iteration, so intermediate materialization is avoided.
+- Cache-first wrappers, so repeated transformations are reused.
+- Composable pipelines, so complex loops stay compact and optimized.
+
+In repeated analytics or feature-building jobs, the first pass computes and stores results, and later passes can fetch from cache instead of recomputing every step.
+
+## Core Iterator Families
+
+### General iterators
+
+| Iterator concept | Input | Output shape | Typical use |
+| --- | --- | --- | --- |
+| Running reduction | iterable, func | incremental totals | rolling stats |
+| Batching | iterable, n | tuples of size n | chunk processing |
+| Chaining | multiple iterables | one continuous stream | merging sources |
+| Selection | data + selectors | filtered stream | mask-based filtering |
+| Windowing | iterable | adjacent pairs/windows | transition analysis |
+| Truncation | predicate/slice | bounded output | safe handling of infinite streams |
+
+### Combinatoric iterators
+
+| Iterator concept | Output |
+| --- | --- |
+| Cartesian products | all pairings across inputs |
+| Permutations | order-sensitive tuples |
+| Combinations | order-insensitive unique tuples |
+| Combinations with replacement | tuples allowing repeated values |
+
+## Pipeline Pattern
+
+Use this pattern when processing large lists, tables, graphs, or text records:
+
+1. Start from one or more iterables.
+2. Chain filtering, mapping, grouping, and batching.
+3. Add cache boundaries around expensive stages.
+4. Materialize only where needed (`list`, `tuple`, `DataFrame`, model input).
+
+```python
+from itertools import chain
+
+sources = [[1, 2, 3], [4, 5], [6]]
+pipeline = (x * 10 for x in chain.from_iterable(sources) if x % 2 == 0)
+print(list(pipeline))  # [20, 40, 60]
+```
+
+## Caching Strategy
+
+Recommended caching behavior for data-heavy workloads:
+
+- Key by transformation signature and input fingerprint.
+- Keep deterministic steps cacheable.
+- Invalidate cache on function/version changes.
+- Persist long-running results between sessions.
+
+This makes repeated preprocessing and feature extraction significantly cheaper.
+
+## Compatibility Note
+
+Package distribution name is `itertoolkit`.
+
+Current code in this repository still exposes the import path `bm_preprocessing` for compatibility with existing users. If needed, a follow-up release can add a top-level `itertoolkit` import alias as well.
+
+## License
+
+MIT

itertoolkit-1.4.9/README.md

@@ -0,0 +1,104 @@
+# itertoolkit
+
+Functions creating iterators and cached data pipelines for efficient looping.
+
+`itertoolkit` is an `itertools`-inspired wrapper focused on practical data processing. It keeps the lazy, composable style of iterator algebra, then adds cache-aware helpers so repeated list and data-structure transformations run faster.
+
+The goal is simple:
+
+- Keep memory usage low with lazy iterators.
+- Speed up repeated workloads with caching.
+- Make iterator pipelines readable and reusable.
+
+## Installation
+
+```bash
+pip install itertoolkit
+```
+
+## Quick Start
+
+```python
+from itertools import count, islice
+
+# Install name: itertoolkit
+# Current import path in this repo remains bm_preprocessing
+from bm_preprocessing import IR, DM
+
+# Example: base itertools stream
+stream = (x * x for x in count(1))
+print(list(islice(stream, 5)))  # [1, 4, 9, 16, 25]
+
+# Example: cached computation workflow (concept)
+# result = itertoolkit.cached_map(expensive_fn, dataset, cache_key="v1")
+```
+
+## Why It Is Faster
+
+`itertoolkit` performance comes from combining:
+
+- Lazy iteration, so intermediate materialization is avoided.
+- Cache-first wrappers, so repeated transformations are reused.
+- Composable pipelines, so complex loops stay compact and optimized.
+
+In repeated analytics or feature-building jobs, the first pass computes and stores results, and later passes can fetch from cache instead of recomputing every step.
+
+## Core Iterator Families
+
+### General iterators
+
+| Iterator concept | Input | Output shape | Typical use |
+| --- | --- | --- | --- |
+| Running reduction | iterable, func | incremental totals | rolling stats |
+| Batching | iterable, n | tuples of size n | chunk processing |
+| Chaining | multiple iterables | one continuous stream | merging sources |
+| Selection | data + selectors | filtered stream | mask-based filtering |
+| Windowing | iterable | adjacent pairs/windows | transition analysis |
+| Truncation | predicate/slice | bounded output | safe handling of infinite streams |
+
+### Combinatoric iterators
+
+| Iterator concept | Output |
+| --- | --- |
+| Cartesian products | all pairings across inputs |
+| Permutations | order-sensitive tuples |
+| Combinations | order-insensitive unique tuples |
+| Combinations with replacement | tuples allowing repeated values |
+
+## Pipeline Pattern
+
+Use this pattern when processing large lists, tables, graphs, or text records:
+
+1. Start from one or more iterables.
+2. Chain filtering, mapping, grouping, and batching.
+3. Add cache boundaries around expensive stages.
+4. Materialize only where needed (`list`, `tuple`, `DataFrame`, model input).
+
+```python
+from itertools import chain
+
+sources = [[1, 2, 3], [4, 5], [6]]
+pipeline = (x * 10 for x in chain.from_iterable(sources) if x % 2 == 0)
+print(list(pipeline))  # [20, 40, 60]
+```
+
+## Caching Strategy
+
+Recommended caching behavior for data-heavy workloads:
+
+- Key by transformation signature and input fingerprint.
+- Keep deterministic steps cacheable.
+- Invalidate cache on function/version changes.
+- Persist long-running results between sessions.
+
+This makes repeated preprocessing and feature extraction significantly cheaper.
+
+## Compatibility Note
+
+Package distribution name is `itertoolkit`.
+
+Current code in this repository still exposes the import path `bm_preprocessing` for compatibility with existing users. If needed, a follow-up release can add a top-level `itertoolkit` import alias as well.
+
+## License
+
+MIT

itertoolkit-1.4.9/bm_preprocessing/__init__.py

@@ -0,0 +1,14 @@
+"""bm_preprocessing package."""
+
+# Keep legacy module paths working, e.g. ``import bm_preprocessing.DM``.
+import sys
+
+from .importer import DM, IR, PY, Finals
+
+sys.modules[__name__ + ".DM"] = DM
+sys.modules[__name__ + ".PY"] = PY
+sys.modules[__name__ + ".IR"] = IR
+sys.modules[__name__ + ".Finals"] = Finals
+
+
+__all__ = ["DM", "PY", "IR"]

itertoolkit-1.4.9/bm_preprocessing/importer/DM/__init__.py

@@ -0,0 +1,7 @@
+from .agg import agg
+from .dbscan import dbscan
+from .finals import finals
+from .gsp import gsp
+from .test import test
+
+__all__ = ["finals", "test", "agg", "dbscan", "gsp"]

itertoolkit-1.4.9/bm_preprocessing/importer/DM/agg.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "DM" / "agg.py"
+agg = SourceCodeModule("bm_preprocessing.DM.agg", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/DM/dbscan.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "DM" / "dbscan.py"
+dbscan = SourceCodeModule("bm_preprocessing.DM.dbscan", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/DM/finals.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "DM" / "finals.py"
+finals = SourceCodeModule("bm_preprocessing.DM.finals", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/DM/gsp.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "DM" / "gsp.py"
+gsp = SourceCodeModule("bm_preprocessing.DM.gsp", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/DM/test.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "DM" / "test.py"
+test = SourceCodeModule("bm_preprocessing.DM.test", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/Finals/__init__.py

@@ -0,0 +1,7 @@
+"""Finals source snippets."""
+from .kaadhal import kaadhal
+from .raaka import raaka
+from .seedan import seedan
+from .vikram import vikram
+
+__all__ = ["kaadhal", "raaka", "seedan", "vikram"]

itertoolkit-1.4.9/bm_preprocessing/importer/Finals/kaadhal.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "Finals" / "kaadhal.py"
+kaadhal = SourceCodeModule("bm_preprocessing.Finals.kaadhal", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/Finals/raaka.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "Finals" / "raaka.py"
+raaka = SourceCodeModule("bm_preprocessing.Finals.raaka", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/Finals/seedan.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "Finals" / "seedan.py"
+seedan = SourceCodeModule("bm_preprocessing.Finals.seedan", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/Finals/vikram.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "Finals" / "vikram.py"
+vikram = SourceCodeModule("bm_preprocessing.Finals.vikram", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/IR/__init__.py

@@ -0,0 +1,6 @@
+from .finals import finals
+from .pagerank import pagerank
+from .recommenders_pca import recommenders_pca
+from .test import test
+
+__all__ = ["finals", "test", "pagerank", "recommenders_pca"]

itertoolkit-1.4.9/bm_preprocessing/importer/IR/finals.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "IR" / "finals.py"
+finals = SourceCodeModule("bm_preprocessing.IR.finals", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/IR/pagerank.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "IR" / "pagerank.py"
+pagerank = SourceCodeModule("bm_preprocessing.IR.pagerank", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/IR/recommenders_pca.py

@@ -0,0 +1,8 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "IR" / "recommenders_pca.py"
+recommenders_pca = SourceCodeModule(
+    "bm_preprocessing.IR.recommenders_pca", _source_file
+)

itertoolkit-1.4.9/bm_preprocessing/importer/IR/test.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "IR" / "test.py"
+test = SourceCodeModule("bm_preprocessing.IR.test", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/PY/__init__.py

@@ -0,0 +1,4 @@
+from .lib_doc import lib_doc
+from .python_doc import python_doc
+
+__all__ = ["lib_doc", "python_doc"]

itertoolkit-1.4.9/bm_preprocessing/importer/PY/lib_doc.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "PY" / "lib_doc.py"
+lib_doc = SourceCodeModule("bm_preprocessing.PY.lib_doc", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/PY/python_doc.py

@@ -0,0 +1,6 @@
+from pathlib import Path
+
+from .._module_printer import SourceCodeModule
+
+_source_file = Path(__file__).parents[2] / "src" / "PY" / "python_doc.py"
+python_doc = SourceCodeModule("bm_preprocessing.PY.python_doc", _source_file)

itertoolkit-1.4.9/bm_preprocessing/importer/__init__.py

@@ -0,0 +1,8 @@
+"""Importer layer that exposes printable source wrappers."""
+
+from .DM import *
+from .IR import *
+from .PY import *
+from .Finals import *
+
+__all__ = ["DM", "PY", "IR", "Finals"]

itertoolkit-1.4.9/bm_preprocessing/importer/_module_printer.py

@@ -0,0 +1,23 @@
+from pathlib import Path
+
+
+class SourceCodeModule:
+    """A class that displays source code when printed."""
+
+    def __init__(self, name: str, source_path: Path):
+        self.name = name
+        self._source_path = source_path
+        self._source_code = None
+
+    @property
+    def source_code(self) -> str:
+        """Lazily load source code."""
+        if self._source_code is None:
+            self._source_code = self._source_path.read_text(encoding="utf-8")
+        return self._source_code
+
+    def __repr__(self) -> str:
+        return self.source_code
+
+    def __str__(self) -> str:
+        return self.source_code

itertoolkit-1.4.9/bm_preprocessing/src/DM/__init__.py

@@ -0,0 +1 @@
+"""Data-mining source snippets."""