cleanflow-kit 1.1.0__tar.gz

cleanflow_kit-1.1.0/LICENSE

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

cleanflow_kit-1.1.0/PKG-INFO

@@ -0,0 +1,119 @@
+Metadata-Version: 2.4
+Name: cleanflow-kit
+Version: 1.1.0
+Summary: A comprehensive, modular Python tool for automated data cleaning, EDA, and feature engineering.
+Author: DataClean Contributors
+License: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: numpy>=1.20.0
+Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: matplotlib>=3.5.0
+Requires-Dist: joblib>=1.1.0
+Provides-Extra: smote
+Requires-Dist: imbalanced-learn>=0.9.0; extra == "smote"
+Provides-Extra: drift
+Requires-Dist: scipy>=1.7.0; extra == "drift"
+Provides-Extra: all
+Requires-Dist: imbalanced-learn>=0.9.0; extra == "all"
+Requires-Dist: scipy>=1.7.0; extra == "all"
+Provides-Extra: web
+Requires-Dist: Flask; extra == "web"
+Requires-Dist: Flask-SQLAlchemy; extra == "web"
+Requires-Dist: PyJWT; extra == "web"
+Requires-Dist: gunicorn; extra == "web"
+Requires-Dist: openpyxl; extra == "web"
+Provides-Extra: api
+Requires-Dist: FastAPI; extra == "api"
+Requires-Dist: uvicorn; extra == "api"
+Requires-Dist: pydantic; extra == "api"
+Dynamic: license-file
+
+# DataClean
+
+A comprehensive, modular Python tool for automated **data cleaning**, **exploratory data analysis (EDA)**, and **feature engineering**.
+
+## 🚀 Quick Start
+
+```python
+from dataclean import DataPipeline
+
+# Initialize and load data
+pipeline = DataPipeline()
+pipeline.load("data.csv")
+
+# Run full pipeline
+cleaned_df, final_df = pipeline.run_full_pipeline(
+    target_col="target_column",
+    problem_type="classification"  # or "regression"
+)
+
+# Save results
+pipeline.save_data("./output")
+```
+
+## 📦 Installation
+
+Install via pip:
+
+```bash
+pip install dataclean
+```
+
+For optional features (SMOTE for class imbalance handling and Drift detection):
+```bash
+pip install dataclean[all]
+```
+
+## 📋 Features
+
+### 1. Data Loading & Validation
+- Load CSV, Excel, JSON, Parquet files or pandas DataFrames directly.
+- Detect duplicates, missing values, data types.
+- Identify constant/near-constant and potential ID columns.
+
+### 2. Data Cleaning
+- Remove duplicate rows.
+- Handle missing values (mean/median/mode/drop).
+- Fix incorrect data types.
+- Handle outliers (IQR/Z-score).
+- Clean categorical values (whitespace, case).
+
+### 3. Exploratory Data Analysis (EDA)
+- Summary statistics, Correlation analysis, Distribution analysis.
+- Visualizations: Histograms, Boxplots, Heatmaps, Feature-target scatter plots.
+
+### 4. Feature Engineering
+- Categorical encoding (One-Hot, Label).
+- Feature scaling (Standard, MinMax).
+- Datetime feature extraction.
+- Polynomial and interaction features.
+- Handling class imbalance (SMOTE).
+
+### 5. ML Model Training
+- Auto-train classification (RandomForest, LogisticRegression) or regression models (RandomForest, Ridge).
+- Reliability scoring, cross-validation, and metrics comparison.
+
+## 🎯 Supported Problem Types
+- **Classification**
+- **Regression**
+*(Clustering is a planned future feature)*
+
+## 🌐 Optional Web Application
+The repository includes an optional Flask web application to interact with the pipeline via a browser.
+Install web dependencies:
+```bash
+pip install dataclean[web,api]
+```
+Run the web application:
+```bash
+python app.py
+```
+
+## 📝 License
+MIT License

cleanflow_kit-1.1.0/README.md

@@ -0,0 +1,83 @@
+# DataClean
+
+A comprehensive, modular Python tool for automated **data cleaning**, **exploratory data analysis (EDA)**, and **feature engineering**.
+
+## 🚀 Quick Start
+
+```python
+from dataclean import DataPipeline
+
+# Initialize and load data
+pipeline = DataPipeline()
+pipeline.load("data.csv")
+
+# Run full pipeline
+cleaned_df, final_df = pipeline.run_full_pipeline(
+    target_col="target_column",
+    problem_type="classification"  # or "regression"
+)
+
+# Save results
+pipeline.save_data("./output")
+```
+
+## 📦 Installation
+
+Install via pip:
+
+```bash
+pip install dataclean
+```
+
+For optional features (SMOTE for class imbalance handling and Drift detection):
+```bash
+pip install dataclean[all]
+```
+
+## 📋 Features
+
+### 1. Data Loading & Validation
+- Load CSV, Excel, JSON, Parquet files or pandas DataFrames directly.
+- Detect duplicates, missing values, data types.
+- Identify constant/near-constant and potential ID columns.
+
+### 2. Data Cleaning
+- Remove duplicate rows.
+- Handle missing values (mean/median/mode/drop).
+- Fix incorrect data types.
+- Handle outliers (IQR/Z-score).
+- Clean categorical values (whitespace, case).
+
+### 3. Exploratory Data Analysis (EDA)
+- Summary statistics, Correlation analysis, Distribution analysis.
+- Visualizations: Histograms, Boxplots, Heatmaps, Feature-target scatter plots.
+
+### 4. Feature Engineering
+- Categorical encoding (One-Hot, Label).
+- Feature scaling (Standard, MinMax).
+- Datetime feature extraction.
+- Polynomial and interaction features.
+- Handling class imbalance (SMOTE).
+
+### 5. ML Model Training
+- Auto-train classification (RandomForest, LogisticRegression) or regression models (RandomForest, Ridge).
+- Reliability scoring, cross-validation, and metrics comparison.
+
+## 🎯 Supported Problem Types
+- **Classification**
+- **Regression**
+*(Clustering is a planned future feature)*
+
+## 🌐 Optional Web Application
+The repository includes an optional Flask web application to interact with the pipeline via a browser.
+Install web dependencies:
+```bash
+pip install dataclean[web,api]
+```
+Run the web application:
+```bash
+python app.py
+```
+
+## 📝 License
+MIT License

cleanflow_kit-1.1.0/cleanflow_kit.egg-info/PKG-INFO

@@ -0,0 +1,119 @@
+Metadata-Version: 2.4
+Name: cleanflow-kit
+Version: 1.1.0
+Summary: A comprehensive, modular Python tool for automated data cleaning, EDA, and feature engineering.
+Author: DataClean Contributors
+License: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: numpy>=1.20.0
+Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: matplotlib>=3.5.0
+Requires-Dist: joblib>=1.1.0
+Provides-Extra: smote
+Requires-Dist: imbalanced-learn>=0.9.0; extra == "smote"
+Provides-Extra: drift
+Requires-Dist: scipy>=1.7.0; extra == "drift"
+Provides-Extra: all
+Requires-Dist: imbalanced-learn>=0.9.0; extra == "all"
+Requires-Dist: scipy>=1.7.0; extra == "all"
+Provides-Extra: web
+Requires-Dist: Flask; extra == "web"
+Requires-Dist: Flask-SQLAlchemy; extra == "web"
+Requires-Dist: PyJWT; extra == "web"
+Requires-Dist: gunicorn; extra == "web"
+Requires-Dist: openpyxl; extra == "web"
+Provides-Extra: api
+Requires-Dist: FastAPI; extra == "api"
+Requires-Dist: uvicorn; extra == "api"
+Requires-Dist: pydantic; extra == "api"
+Dynamic: license-file
+
+# DataClean
+
+A comprehensive, modular Python tool for automated **data cleaning**, **exploratory data analysis (EDA)**, and **feature engineering**.
+
+## 🚀 Quick Start
+
+```python
+from dataclean import DataPipeline
+
+# Initialize and load data
+pipeline = DataPipeline()
+pipeline.load("data.csv")
+
+# Run full pipeline
+cleaned_df, final_df = pipeline.run_full_pipeline(
+    target_col="target_column",
+    problem_type="classification"  # or "regression"
+)
+
+# Save results
+pipeline.save_data("./output")
+```
+
+## 📦 Installation
+
+Install via pip:
+
+```bash
+pip install dataclean
+```
+
+For optional features (SMOTE for class imbalance handling and Drift detection):
+```bash
+pip install dataclean[all]
+```
+
+## 📋 Features
+
+### 1. Data Loading & Validation
+- Load CSV, Excel, JSON, Parquet files or pandas DataFrames directly.
+- Detect duplicates, missing values, data types.
+- Identify constant/near-constant and potential ID columns.
+
+### 2. Data Cleaning
+- Remove duplicate rows.
+- Handle missing values (mean/median/mode/drop).
+- Fix incorrect data types.
+- Handle outliers (IQR/Z-score).
+- Clean categorical values (whitespace, case).
+
+### 3. Exploratory Data Analysis (EDA)
+- Summary statistics, Correlation analysis, Distribution analysis.
+- Visualizations: Histograms, Boxplots, Heatmaps, Feature-target scatter plots.
+
+### 4. Feature Engineering
+- Categorical encoding (One-Hot, Label).
+- Feature scaling (Standard, MinMax).
+- Datetime feature extraction.
+- Polynomial and interaction features.
+- Handling class imbalance (SMOTE).
+
+### 5. ML Model Training
+- Auto-train classification (RandomForest, LogisticRegression) or regression models (RandomForest, Ridge).
+- Reliability scoring, cross-validation, and metrics comparison.
+
+## 🎯 Supported Problem Types
+- **Classification**
+- **Regression**
+*(Clustering is a planned future feature)*
+
+## 🌐 Optional Web Application
+The repository includes an optional Flask web application to interact with the pipeline via a browser.
+Install web dependencies:
+```bash
+pip install dataclean[web,api]
+```
+Run the web application:
+```bash
+python app.py
+```
+
+## 📝 License
+MIT License

cleanflow_kit-1.1.0/cleanflow_kit.egg-info/SOURCES.txt

@@ -0,0 +1,20 @@
+LICENSE
+README.md
+pyproject.toml
+cleanflow_kit.egg-info/PKG-INFO
+cleanflow_kit.egg-info/SOURCES.txt
+cleanflow_kit.egg-info/dependency_links.txt
+cleanflow_kit.egg-info/requires.txt
+cleanflow_kit.egg-info/top_level.txt
+dataclean/__init__.py
+dataclean/_compat.py
+dataclean/data_cleaner.py
+dataclean/data_loader.py
+dataclean/drift_detector.py
+dataclean/eda.py
+dataclean/feature_engineer.py
+dataclean/model_trainer.py
+dataclean/pipeline.py
+dataclean/py.typed
+dataclean/report_generator.py
+dataclean/synthetic_generator.py

cleanflow_kit-1.1.0/cleanflow_kit.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

cleanflow_kit-1.1.0/cleanflow_kit.egg-info/requires.txt

@@ -0,0 +1,27 @@
+pandas>=2.0.0
+numpy>=1.20.0
+scikit-learn>=1.0.0
+matplotlib>=3.5.0
+joblib>=1.1.0
+
+[all]
+imbalanced-learn>=0.9.0
+scipy>=1.7.0
+
+[api]
+FastAPI
+uvicorn
+pydantic
+
+[drift]
+scipy>=1.7.0
+
+[smote]
+imbalanced-learn>=0.9.0
+
+[web]
+Flask
+Flask-SQLAlchemy
+PyJWT
+gunicorn
+openpyxl

cleanflow_kit-1.1.0/cleanflow_kit.egg-info/top_level.txt

@@ -0,0 +1 @@
+dataclean

cleanflow_kit-1.1.0/dataclean/__init__.py

@@ -0,0 +1,44 @@
+"""
+Data Pipeline Tool
+==================
+A comprehensive, modular Python tool for automated data cleaning, 
+exploratory data analysis (EDA), and feature engineering.
+
+Modules:
+- data_loader: Load and validate datasets
+- data_cleaner: Clean and preprocess data
+- eda: Exploratory data analysis and visualizations
+- feature_engineer: Feature engineering and transformation
+- pipeline: Main orchestrator combining all modules
+"""
+
+import logging
+logger = logging.getLogger(__name__)
+from .data_loader import DataLoader
+from .data_cleaner import DataCleaner
+from .model_trainer import ModelTrainer
+
+# Lazy imports to avoid loading matplotlib/seaborn/scipy at import time
+# Use: from .eda import EDAAnalyzer
+# Use: from .feature_engineer import FeatureEngineer
+# Use: from .pipeline import DataPipeline
+
+def _get_pipeline():
+    from .pipeline import DataPipeline as _DP
+    return _DP
+
+# Make DataPipeline available but lazy
+import importlib
+def __getattr__(name):
+    if name == "DataPipeline":
+        return _get_pipeline()
+    if name == "EDAAnalyzer":
+        from .eda import EDAAnalyzer
+        return EDAAnalyzer
+    if name == "FeatureEngineer":
+        from .feature_engineer import FeatureEngineer
+        return FeatureEngineer
+    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+__version__ = "1.1.0"
+__all__ = ["DataPipeline", "DataLoader", "DataCleaner", "EDAAnalyzer", "FeatureEngineer", "ModelTrainer"]

cleanflow_kit-1.1.0/dataclean/_compat.py

@@ -0,0 +1,24 @@
+"""Pandas dtype compatibility helpers.
+
+Pandas 3 infers text columns as the dedicated ``str`` dtype. Unlike the
+legacy ``object`` dtype, it rejects non-string assignments. The data-cleaning
+and ML code intentionally converts some text columns to numeric values, so we
+normalise inferred string columns to ``object`` at each public entry point.
+
+This module intentionally does not import pandas. Importing it from ``app.py``
+therefore preserves the app's lazy-loading behaviour for data libraries.
+"""
+
+
+def normalize_string_columns(df):
+    """Convert pandas string extension columns to object columns in-place.
+
+    The dtype names cover pandas 2.x's optional ``StringDtype`` and pandas
+    3.x's default ``str`` dtype. ``object`` is appropriate because a column
+    can later be transformed from text into numeric values.
+    """
+    for column in df.columns:
+        series = df[column]
+        if getattr(series.dtype, "name", None) in {"str", "string", "String"}:
+            df[column] = series.astype(object)
+    return df