murthylytics 0.1.0__tar.gz

murthylytics-0.1.0/.gitignore

@@ -0,0 +1,41 @@
+# Byte-compiled / optimized
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+
+# Distribution / packaging
+.Python
+build/
+dist/
+*.egg-info/
+.eggs/
+wheels/
+
+# Testing / coverage
+.pytest_cache/
+.coverage
+.coverage.*
+htmlcov/
+.mypy_cache/
+.ruff_cache/
+
+# Environments
+.venv/
+venv/
+env/
+ENV/
+
+# IDE / OS
+.vscode/
+.idea/
+.DS_Store
+
+# Murthylytics artifacts
+*.mlt
+reports/
+*.log
+
+# Local tooling / self-hosted index (not part of the package)
+.claude/
+public/

murthylytics-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Pranav Murthy
+
+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.

murthylytics-0.1.0/PKG-INFO

@@ -0,0 +1,168 @@
+Metadata-Version: 2.4
+Name: murthylytics
+Version: 0.1.0
+Summary: Production-grade, AI-powered machine learning data-analysis and preparation library.
+Project-URL: Homepage, https://github.com/pranavmurthy/murthylytics
+Project-URL: Repository, https://github.com/pranavmurthy/murthylytics
+Project-URL: Issues, https://github.com/pranavmurthy/murthylytics/issues
+Author: Pranav Murthy
+License: MIT
+License-File: LICENSE
+Keywords: autoeda,automl,data-cleaning,data-science,eda,feature-engineering,feature-selection,machine-learning,preprocessing
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Requires-Dist: numpy>=1.23
+Requires-Dist: pandas>=1.5
+Provides-Extra: all
+Requires-Dist: charset-normalizer>=3.0; extra == 'all'
+Requires-Dist: jinja2>=3.1; extra == 'all'
+Requires-Dist: lightgbm>=3.3; extra == 'all'
+Requires-Dist: matplotlib>=3.6; extra == 'all'
+Requires-Dist: openpyxl>=3.1; extra == 'all'
+Requires-Dist: pyarrow>=10.0; extra == 'all'
+Requires-Dist: scikit-learn>=1.1; extra == 'all'
+Requires-Dist: scipy>=1.9; extra == 'all'
+Requires-Dist: seaborn>=0.12; extra == 'all'
+Requires-Dist: sqlalchemy>=2.0; extra == 'all'
+Requires-Dist: xgboost>=1.7; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: black>=23.0; extra == 'dev'
+Requires-Dist: mypy>=1.5; extra == 'dev'
+Requires-Dist: pre-commit>=3.4; extra == 'dev'
+Requires-Dist: pytest-cov>=4.1; extra == 'dev'
+Requires-Dist: pytest>=7.4; extra == 'dev'
+Requires-Dist: ruff>=0.1; extra == 'dev'
+Provides-Extra: io
+Requires-Dist: charset-normalizer>=3.0; extra == 'io'
+Requires-Dist: openpyxl>=3.1; extra == 'io'
+Requires-Dist: pyarrow>=10.0; extra == 'io'
+Requires-Dist: sqlalchemy>=2.0; extra == 'io'
+Provides-Extra: ml
+Requires-Dist: lightgbm>=3.3; extra == 'ml'
+Requires-Dist: xgboost>=1.7; extra == 'ml'
+Provides-Extra: polars
+Requires-Dist: polars>=0.20; extra == 'polars'
+Provides-Extra: report
+Requires-Dist: jinja2>=3.1; extra == 'report'
+Provides-Extra: stats
+Requires-Dist: scikit-learn>=1.1; extra == 'stats'
+Requires-Dist: scipy>=1.9; extra == 'stats'
+Provides-Extra: viz
+Requires-Dist: matplotlib>=3.6; extra == 'viz'
+Requires-Dist: seaborn>=0.12; extra == 'viz'
+Description-Content-Type: text/markdown
+
+# Murthylytics
+
+**Production-grade, AI-powered machine-learning data analysis & preparation for Python.**
+
+Murthylytics turns hundreds of lines of exploratory-data-analysis and preprocessing
+boilerplate into a handful of intuitive commands — while staying transparent,
+configurable and production-quality. Think of it as a next-generation companion to
+pandas, ydata-profiling, Sweetviz and scikit-learn's preprocessing tools, unified
+behind one stateful API.
+
+```python
+import murthylytics as mlt
+
+mlt.read_csv("data.csv")   # auto-detects encoding, delimiter, dtypes, datetimes
+
+mlt.summary()              # compact overview
+mlt.inspect()              # intelligent profiling: roles, targets, leakage, issues
+
+mlt.clean_data()           # roadmap: intelligent cleaning & imputation
+mlt.auto_eda()             # roadmap: HTML / Markdown / PDF / JSON reports
+mlt.preprocess()           # roadmap: task detection + preprocessing pipeline
+mlt.recommend_model()      # roadmap: model recommendations with justification
+```
+
+## Why Murthylytics
+
+- **One stateful facade.** Load a dataset once; every call operates on the active
+  session — no handle passing.
+- **Intelligent by default.** Encoding/delimiter/dtype detection, column-role
+  inference, target detection, class-imbalance and data-leakage checks, all automatic.
+- **Lightweight core, optional power.** Base install is just pandas + numpy. Heavy
+  tooling (plots, XGBoost, SHAP, Parquet…) is lazy-loaded behind extras.
+- **Engineered to last.** `src/` layout, full type hints, SOLID modules, a pure
+  stateless engine under the facade, and a test suite.
+
+## Installation
+
+```bash
+pip install murthylytics            # core (pandas + numpy)
+pip install 'murthylytics[stats]'   # scipy + scikit-learn powered analysis
+pip install 'murthylytics[viz]'     # matplotlib + seaborn plotting
+pip install 'murthylytics[all]'     # everything
+```
+
+> Develop locally: `pip install -e '.[dev,stats]'`
+
+## Quick start
+
+```python
+import murthylytics as mlt
+
+mlt.read_csv("titanic.csv")
+
+mlt.shape()          # {'rows': 891, 'columns': 12}
+mlt.missing()        # per-column missing counts & %
+report = mlt.inspect()
+print(report)                    # human-readable summary
+print(report.recommendations)    # actionable next steps
+report.to_dict()                 # JSON-serialisable
+```
+
+## Feature status
+
+| Area | API | Status |
+|------|-----|--------|
+| Data I/O (CSV/Excel/JSON/Parquet/SQL) | `read_*` | ✅ available |
+| Exploration | `show/top/bottom/shape/columns/summary/describe/info/types/missing/duplicates/memory` | ✅ available |
+| Intelligent inspection | `inspect` | ✅ available |
+| Intelligent cleaning | `clean_data` | 🚧 roadmap (iteration 2) |
+| Visualization | `cleaned_pyplot` | 🚧 roadmap (iteration 3) |
+| AutoEDA reports | `auto_eda` | 🚧 roadmap (iteration 4) |
+| Preprocessing | `preprocess` | 🚧 roadmap (iteration 5) |
+| Feature engineering / selection | `engineer_features` / `select_features` | 🚧 roadmap (iteration 6) |
+| Model recommendation | `recommend_model` | 🚧 roadmap (iteration 7) |
+| Pipeline export | `export_pipeline` | 🚧 roadmap (iteration 8) |
+| Plugins (malware, finance, …) | `use_plugin` | 🚧 roadmap (iteration 9) |
+
+The roadmap functions are already part of the public surface with stable
+signatures; calling one today raises a clear `NotImplementedError` pointing at the
+iteration that delivers it.
+
+## Architecture
+
+```
+murthylytics/
+├── core/          config · session/context · logging · exceptions · types
+├── io/            smart readers · encoding/delimiter/dtype detection · memory opt
+├── exploration/   display helpers · intelligent inspection
+├── cleaning/      (roadmap) duplicates · imputation · outliers · text fixes
+├── viz/           (roadmap) auto-plot dispatcher
+├── eda/           (roadmap) HTML/MD/PDF/JSON reports
+├── preprocess/    (roadmap) task detection · scaling · encoding · pipelines
+├── features/      (roadmap) engineering · selection
+├── modeling/      (roadmap) model recommendation
+├── pipeline/      (roadmap) save/load/export
+└── plugins/       (roadmap) domain plugins
+```
+
+All mutable state lives in a single `Session`; the engine modules are pure
+functions, which keeps them independently testable and reusable.
+
+## License
+
+MIT © Pranav Murthy

murthylytics-0.1.0/README.md

@@ -0,0 +1,104 @@
+# Murthylytics
+
+**Production-grade, AI-powered machine-learning data analysis & preparation for Python.**
+
+Murthylytics turns hundreds of lines of exploratory-data-analysis and preprocessing
+boilerplate into a handful of intuitive commands — while staying transparent,
+configurable and production-quality. Think of it as a next-generation companion to
+pandas, ydata-profiling, Sweetviz and scikit-learn's preprocessing tools, unified
+behind one stateful API.
+
+```python
+import murthylytics as mlt
+
+mlt.read_csv("data.csv")   # auto-detects encoding, delimiter, dtypes, datetimes
+
+mlt.summary()              # compact overview
+mlt.inspect()              # intelligent profiling: roles, targets, leakage, issues
+
+mlt.clean_data()           # roadmap: intelligent cleaning & imputation
+mlt.auto_eda()             # roadmap: HTML / Markdown / PDF / JSON reports
+mlt.preprocess()           # roadmap: task detection + preprocessing pipeline
+mlt.recommend_model()      # roadmap: model recommendations with justification
+```
+
+## Why Murthylytics
+
+- **One stateful facade.** Load a dataset once; every call operates on the active
+  session — no handle passing.
+- **Intelligent by default.** Encoding/delimiter/dtype detection, column-role
+  inference, target detection, class-imbalance and data-leakage checks, all automatic.
+- **Lightweight core, optional power.** Base install is just pandas + numpy. Heavy
+  tooling (plots, XGBoost, SHAP, Parquet…) is lazy-loaded behind extras.
+- **Engineered to last.** `src/` layout, full type hints, SOLID modules, a pure
+  stateless engine under the facade, and a test suite.
+
+## Installation
+
+```bash
+pip install murthylytics            # core (pandas + numpy)
+pip install 'murthylytics[stats]'   # scipy + scikit-learn powered analysis
+pip install 'murthylytics[viz]'     # matplotlib + seaborn plotting
+pip install 'murthylytics[all]'     # everything
+```
+
+> Develop locally: `pip install -e '.[dev,stats]'`
+
+## Quick start
+
+```python
+import murthylytics as mlt
+
+mlt.read_csv("titanic.csv")
+
+mlt.shape()          # {'rows': 891, 'columns': 12}
+mlt.missing()        # per-column missing counts & %
+report = mlt.inspect()
+print(report)                    # human-readable summary
+print(report.recommendations)    # actionable next steps
+report.to_dict()                 # JSON-serialisable
+```
+
+## Feature status
+
+| Area | API | Status |
+|------|-----|--------|
+| Data I/O (CSV/Excel/JSON/Parquet/SQL) | `read_*` | ✅ available |
+| Exploration | `show/top/bottom/shape/columns/summary/describe/info/types/missing/duplicates/memory` | ✅ available |
+| Intelligent inspection | `inspect` | ✅ available |
+| Intelligent cleaning | `clean_data` | 🚧 roadmap (iteration 2) |
+| Visualization | `cleaned_pyplot` | 🚧 roadmap (iteration 3) |
+| AutoEDA reports | `auto_eda` | 🚧 roadmap (iteration 4) |
+| Preprocessing | `preprocess` | 🚧 roadmap (iteration 5) |
+| Feature engineering / selection | `engineer_features` / `select_features` | 🚧 roadmap (iteration 6) |
+| Model recommendation | `recommend_model` | 🚧 roadmap (iteration 7) |
+| Pipeline export | `export_pipeline` | 🚧 roadmap (iteration 8) |
+| Plugins (malware, finance, …) | `use_plugin` | 🚧 roadmap (iteration 9) |
+
+The roadmap functions are already part of the public surface with stable
+signatures; calling one today raises a clear `NotImplementedError` pointing at the
+iteration that delivers it.
+
+## Architecture
+
+```
+murthylytics/
+├── core/          config · session/context · logging · exceptions · types
+├── io/            smart readers · encoding/delimiter/dtype detection · memory opt
+├── exploration/   display helpers · intelligent inspection
+├── cleaning/      (roadmap) duplicates · imputation · outliers · text fixes
+├── viz/           (roadmap) auto-plot dispatcher
+├── eda/           (roadmap) HTML/MD/PDF/JSON reports
+├── preprocess/    (roadmap) task detection · scaling · encoding · pipelines
+├── features/      (roadmap) engineering · selection
+├── modeling/      (roadmap) model recommendation
+├── pipeline/      (roadmap) save/load/export
+└── plugins/       (roadmap) domain plugins
+```
+
+All mutable state lives in a single `Session`; the engine modules are pure
+functions, which keeps them independently testable and reusable.
+
+## License
+
+MIT © Pranav Murthy

murthylytics-0.1.0/examples/quickstart.py

@@ -0,0 +1,63 @@
+"""Murthylytics quickstart.
+
+Run with:  python examples/quickstart.py
+
+Generates a small synthetic dataset, then walks through the currently available
+facade API: reading, exploration and intelligent inspection.
+"""
+
+from __future__ import annotations
+
+import json
+import tempfile
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+
+import murthylytics as mlt
+
+
+def make_dataset(path: Path) -> None:
+    rng = np.random.default_rng(42)
+    n = 400
+    df = pd.DataFrame(
+        {
+            "user_id": range(1, n + 1),
+            "age": rng.integers(18, 75, n),
+            "monthly_spend": rng.gamma(3.0, 40.0, n).round(2),
+            "plan": rng.choice(["free", "pro", "enterprise"], n, p=[0.6, 0.3, 0.1]),
+            "signup": pd.date_range("2022-01-01", periods=n, freq="D").astype(str),
+            "churned": rng.choice([0, 1], n, p=[0.82, 0.18]),
+        }
+    )
+    df.loc[rng.choice(n, 25, replace=False), "monthly_spend"] = np.nan
+    df.to_csv(path, index=False)
+
+
+def main() -> None:
+    with tempfile.TemporaryDirectory() as tmp:
+        csv = Path(tmp) / "subscriptions.csv"
+        make_dataset(csv)
+
+        mlt.enable_logging("INFO")
+        mlt.read_csv(csv)
+
+        print("\n== shape ==", mlt.shape())
+        print("== dtypes ==", mlt.types())
+        print("\n== summary ==")
+        print(json.dumps(mlt.summary(), indent=2))
+        print("\n== missing ==")
+        print(mlt.missing())
+
+        print("\n== intelligent inspection ==")
+        report = mlt.inspect()
+        print(report)
+        print("\nPotential targets:", report.potential_targets)
+        print("Recommendations:")
+        for rec in report.recommendations:
+            print("  -", rec)
+
+
+if __name__ == "__main__":
+    main()

murthylytics-0.1.0/pyproject.toml

@@ -0,0 +1,102 @@
+[build-system]
+requires = ["hatchling>=1.21"]
+build-backend = "hatchling.build"
+
+[project]
+name = "murthylytics"
+dynamic = ["version"]
+description = "Production-grade, AI-powered machine learning data-analysis and preparation library."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "MIT" }
+authors = [{ name = "Pranav Murthy" }]
+keywords = [
+    "machine-learning", "data-science", "eda", "autoeda", "preprocessing",
+    "feature-engineering", "feature-selection", "automl", "data-cleaning",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Typing :: Typed",
+]
+
+# Core dependencies are intentionally minimal. Everything heavy is optional.
+dependencies = [
+    "pandas>=1.5",
+    "numpy>=1.23",
+]
+
+[project.optional-dependencies]
+stats = ["scipy>=1.9", "scikit-learn>=1.1"]
+viz = ["matplotlib>=3.6", "seaborn>=0.12"]
+io = ["pyarrow>=10.0", "openpyxl>=3.1", "charset-normalizer>=3.0", "sqlalchemy>=2.0"]
+ml = ["xgboost>=1.7", "lightgbm>=3.3"]
+report = ["jinja2>=3.1"]
+polars = ["polars>=0.20"]
+all = [
+    "scipy>=1.9", "scikit-learn>=1.1",
+    "matplotlib>=3.6", "seaborn>=0.12",
+    "pyarrow>=10.0", "openpyxl>=3.1", "charset-normalizer>=3.0", "sqlalchemy>=2.0",
+    "xgboost>=1.7", "lightgbm>=3.3",
+    "jinja2>=3.1",
+]
+dev = [
+    "pytest>=7.4", "pytest-cov>=4.1",
+    "black>=23.0", "ruff>=0.1", "mypy>=1.5",
+    "pre-commit>=3.4",
+]
+
+[project.urls]
+Homepage = "https://github.com/pranavmurthy/murthylytics"
+Repository = "https://github.com/pranavmurthy/murthylytics"
+Issues = "https://github.com/pranavmurthy/murthylytics/issues"
+
+[tool.hatch.version]
+path = "src/murthylytics/_version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/murthylytics"]
+
+[tool.hatch.build.targets.sdist]
+# Explicit allowlist so build artifacts (public/, dist/) and local settings
+# (.claude/) never leak into the published source distribution.
+include = [
+    "src/murthylytics",
+    "tests",
+    "examples",
+    "README.md",
+    "LICENSE",
+    "pyproject.toml",
+]
+
+[tool.black]
+line-length = 100
+target-version = ["py39"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py39"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "W", "UP", "B", "C4", "SIM"]
+ignore = ["E501"]  # line length handled by black
+
+[tool.mypy]
+python_version = "3.9"
+warn_unused_configs = true
+disallow_untyped_defs = false
+ignore_missing_imports = true
+files = ["src/murthylytics"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-q"
+filterwarnings = ["ignore::DeprecationWarning"]