smartml-assistant 0.2.0__tar.gz

smartml_assistant-0.2.0/LICENSE

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

smartml_assistant-0.2.0/PKG-INFO

@@ -0,0 +1,130 @@
+Metadata-Version: 2.4
+Name: smartml-assistant
+Version: 0.2.0
+Summary: A production-grade AutoML engine with a conversational Assistant interface.
+Author-email: SmartML Contributors <contributors@smartml.org>
+License: MIT
+Project-URL: Homepage, https://github.com/smartml-contributors/smartml-assistant
+Project-URL: Repository, https://github.com/smartml-contributors/smartml-assistant
+Project-URL: Documentation, https://github.com/smartml-contributors/smartml-assistant#readme
+Project-URL: Bug Tracker, https://github.com/smartml-contributors/smartml-assistant/issues
+Keywords: automl,machine-learning,assistant,sklearn,explainable-ai
+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: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=2.0
+Requires-Dist: numpy>=1.24
+Requires-Dist: scikit-learn>=1.3
+Requires-Dist: matplotlib>=3.7
+Requires-Dist: joblib>=1.3
+Provides-Extra: boosting
+Requires-Dist: xgboost>=2.0; extra == "boosting"
+Requires-Dist: lightgbm>=4.0; extra == "boosting"
+Requires-Dist: catboost>=1.2; extra == "boosting"
+Provides-Extra: tuning
+Requires-Dist: optuna>=3.0; extra == "tuning"
+Provides-Extra: explain
+Requires-Dist: shap>=0.43; extra == "explain"
+Provides-Extra: viz
+Requires-Dist: plotly>=5.0; extra == "viz"
+Requires-Dist: seaborn>=0.12; extra == "viz"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Provides-Extra: all
+Requires-Dist: xgboost>=2.0; extra == "all"
+Requires-Dist: lightgbm>=4.0; extra == "all"
+Requires-Dist: catboost>=1.2; extra == "all"
+Requires-Dist: optuna>=3.0; extra == "all"
+Requires-Dist: shap>=0.43; extra == "all"
+Requires-Dist: plotly>=5.0; extra == "all"
+Requires-Dist: seaborn>=0.12; extra == "all"
+Dynamic: license-file
+
+# SmartML
+
+**SmartML** is a production-grade, enterprise-level Machine Learning Automation Library for Python. It combines data preprocessing, feature engineering, feature selection, AutoML model training, explainable AI, visualization, and a conversational Assistant interface into a single unified framework.
+
+## Installation
+
+```bash
+pip install smartml-assistant
+```
+
+To install with optional boosting algorithms (XGBoost, LightGBM, CatBoost) and visualization libraries (Plotly, Seaborn):
+
+```bash
+pip install "smartml-assistant[all]"
+```
+
+## Quick Start
+
+### The One-Line Auto-Pilot
+Provide your DataFrame and the target column, and SmartML will do the rest: profiling, cleaning, feature engineering, model comparison, training, and evaluation.
+
+```python
+import smartml as sml
+
+# Load data (auto-detects CSV, Parquet, JSON, Excel, etc.)
+df = sml.load("data/house_prices.csv")
+
+# Run the complete AutoML pipeline
+result = sml.auto(df, target="SalePrice", output_dir="my_project")
+
+# Explain the best model
+print(result.explain())
+
+# Make predictions on new data
+preds = result.predict(new_df)
+
+# Save the model
+result.save("my_model")
+
+# Generate an HTML report
+result.report(fmt="html")
+```
+
+### Unsupervised Clustering
+```python
+df = sml.load("data/customer_segments.csv")
+result = sml.clustering_pipeline(df, algorithm="auto")
+print(f"Found {result.clustering_result.n_clusters} clusters!")
+```
+
+### Conversational Assistant
+Interact with your data using natural language:
+
+```python
+import smartml as sml
+
+assistant = sml.Assistant(df, target="SalePrice")
+
+assistant.ask("Clean my dataset")
+assistant.ask("Engineer some new features")
+assistant.ask("Train the best regression model")
+assistant.ask("Why did you choose this algorithm?")
+assistant.ask("Show feature importance")
+assistant.ask("Generate a report")
+```
+
+## Features
+
+- **Automated Data Cleaning:** Imputation, deduplication, low-cardinality one-hot encoding, and scaling.
+- **Advanced Feature Engineering:** Polynomial interactions, date decomposition, frequency encoding, and pairwise ratios.
+- **Smart Feature Selection:** Variance thresholding, correlation filtering, univariate selection, and model-based feature importance thresholding.
+- **Multi-Model Leaderboard:** Automatically cross-validates Logistic/Linear Regression, Random Forest, Gradient Boosting, SVM, XGBoost, LightGBM, CatBoost, and more.
+- **Unsupervised Learning:** Full clustering (KMeans, DBSCAN, GMM, Agglomerative) and Anomaly Detection (IsolationForest, LOF, OneClassSVM).
+- **Explainable AI:** Natural-language justifications for algorithm selection and feature importance.
+- **Safe & Headless:** Safe for interactive environments. No global state side-effects.
+
+## License
+MIT License. See `LICENSE` for more information.

smartml_assistant-0.2.0/README.md

@@ -0,0 +1,78 @@
+# SmartML
+
+**SmartML** is a production-grade, enterprise-level Machine Learning Automation Library for Python. It combines data preprocessing, feature engineering, feature selection, AutoML model training, explainable AI, visualization, and a conversational Assistant interface into a single unified framework.
+
+## Installation
+
+```bash
+pip install smartml-assistant
+```
+
+To install with optional boosting algorithms (XGBoost, LightGBM, CatBoost) and visualization libraries (Plotly, Seaborn):
+
+```bash
+pip install "smartml-assistant[all]"
+```
+
+## Quick Start
+
+### The One-Line Auto-Pilot
+Provide your DataFrame and the target column, and SmartML will do the rest: profiling, cleaning, feature engineering, model comparison, training, and evaluation.
+
+```python
+import smartml as sml
+
+# Load data (auto-detects CSV, Parquet, JSON, Excel, etc.)
+df = sml.load("data/house_prices.csv")
+
+# Run the complete AutoML pipeline
+result = sml.auto(df, target="SalePrice", output_dir="my_project")
+
+# Explain the best model
+print(result.explain())
+
+# Make predictions on new data
+preds = result.predict(new_df)
+
+# Save the model
+result.save("my_model")
+
+# Generate an HTML report
+result.report(fmt="html")
+```
+
+### Unsupervised Clustering
+```python
+df = sml.load("data/customer_segments.csv")
+result = sml.clustering_pipeline(df, algorithm="auto")
+print(f"Found {result.clustering_result.n_clusters} clusters!")
+```
+
+### Conversational Assistant
+Interact with your data using natural language:
+
+```python
+import smartml as sml
+
+assistant = sml.Assistant(df, target="SalePrice")
+
+assistant.ask("Clean my dataset")
+assistant.ask("Engineer some new features")
+assistant.ask("Train the best regression model")
+assistant.ask("Why did you choose this algorithm?")
+assistant.ask("Show feature importance")
+assistant.ask("Generate a report")
+```
+
+## Features
+
+- **Automated Data Cleaning:** Imputation, deduplication, low-cardinality one-hot encoding, and scaling.
+- **Advanced Feature Engineering:** Polynomial interactions, date decomposition, frequency encoding, and pairwise ratios.
+- **Smart Feature Selection:** Variance thresholding, correlation filtering, univariate selection, and model-based feature importance thresholding.
+- **Multi-Model Leaderboard:** Automatically cross-validates Logistic/Linear Regression, Random Forest, Gradient Boosting, SVM, XGBoost, LightGBM, CatBoost, and more.
+- **Unsupervised Learning:** Full clustering (KMeans, DBSCAN, GMM, Agglomerative) and Anomaly Detection (IsolationForest, LOF, OneClassSVM).
+- **Explainable AI:** Natural-language justifications for algorithm selection and feature importance.
+- **Safe & Headless:** Safe for interactive environments. No global state side-effects.
+
+## License
+MIT License. See `LICENSE` for more information.

smartml_assistant-0.2.0/pyproject.toml

@@ -0,0 +1,68 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "smartml-assistant"
+version = "0.2.0"
+description = "A production-grade AutoML engine with a conversational Assistant interface."
+readme = "README.md"
+requires-python = ">=3.10"
+license = { text = "MIT" }
+authors = [{ name = "SmartML Contributors", email = "contributors@smartml.org" }]
+keywords = ["automl", "machine-learning", "assistant", "sklearn", "explainable-ai"]
+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",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "pandas>=2.0",
+    "numpy>=1.24",
+    "scikit-learn>=1.3",
+    "matplotlib>=3.7",
+    "joblib>=1.3",
+]
+
+[project.urls]
+Homepage = "https://github.com/smartml-contributors/smartml-assistant"
+Repository = "https://github.com/smartml-contributors/smartml-assistant"
+Documentation = "https://github.com/smartml-contributors/smartml-assistant#readme"
+"Bug Tracker" = "https://github.com/smartml-contributors/smartml-assistant/issues"
+
+
+[project.optional-dependencies]
+boosting = ["xgboost>=2.0", "lightgbm>=4.0", "catboost>=1.2"]
+tuning   = ["optuna>=3.0"]
+explain  = ["shap>=0.43"]
+viz      = ["plotly>=5.0", "seaborn>=0.12"]
+dev = [
+    "pytest>=7.4",
+    "pytest-cov>=4.0",
+]
+all = [
+    "xgboost>=2.0",
+    "lightgbm>=4.0",
+    "catboost>=1.2",
+    "optuna>=3.0",
+    "shap>=0.43",
+    "plotly>=5.0",
+    "seaborn>=0.12",
+]
+
+[tool.setuptools.packages.find]
+include = ["smartml*"]
+
+[tool.pytest.ini_options]
+filterwarnings = [
+    "ignore::DeprecationWarning",
+    "ignore::PendingDeprecationWarning",
+    "ignore::FutureWarning",
+]
+testpaths = ["tests"]

smartml_assistant-0.2.0/setup.cfg

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