cleanflow-kit 1.1.0__tar.gz → 1.2.0__tar.gz

{cleanflow_kit-1.1.0 → cleanflow_kit-1.2.0}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: cleanflow-kit
-Version: 1.1.0
+Version: 1.2.0
 Summary: A comprehensive, modular Python tool for automated data cleaning, EDA, and feature engineering.
-Author: DataClean Contributors
+Author: CleanFlow Contributors
 License: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
@@ -34,14 +34,14 @@ Requires-Dist: uvicorn; extra == "api"
 Requires-Dist: pydantic; extra == "api"
 Dynamic: license-file
 
-# DataClean
+# CleanFlow
 
 A comprehensive, modular Python tool for automated **data cleaning**, **exploratory data analysis (EDA)**, and **feature engineering**.
 
 ## 🚀 Quick Start
 
 ```python
-from dataclean import DataPipeline
+from cleanflow import DataPipeline
 
 # Initialize and load data
 pipeline = DataPipeline()
@@ -62,12 +62,12 @@ pipeline.save_data("./output")
 Install via pip:
 
 ```bash
-pip install dataclean
+pip install cleanflow
 ```
 
 For optional features (SMOTE for class imbalance handling and Drift detection):
 ```bash
-pip install dataclean[all]
+pip install cleanflow[all]
 ```
 
 ## 📋 Features
@@ -108,7 +108,7 @@ pip install dataclean[all]
 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]
+pip install cleanflow[web,api]
 ```
 Run the web application:
 ```bash

{cleanflow_kit-1.1.0 → cleanflow_kit-1.2.0}/README.md

@@ -1,11 +1,11 @@
-# DataClean
+# CleanFlow
 
 A comprehensive, modular Python tool for automated **data cleaning**, **exploratory data analysis (EDA)**, and **feature engineering**.
 
 ## 🚀 Quick Start
 
 ```python
-from dataclean import DataPipeline
+from cleanflow import DataPipeline
 
 # Initialize and load data
 pipeline = DataPipeline()
@@ -26,12 +26,12 @@ pipeline.save_data("./output")
 Install via pip:
 
 ```bash
-pip install dataclean
+pip install cleanflow
 ```
 
 For optional features (SMOTE for class imbalance handling and Drift detection):
 ```bash
-pip install dataclean[all]
+pip install cleanflow[all]
 ```
 
 ## 📋 Features
@@ -72,7 +72,7 @@ pip install dataclean[all]
 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]
+pip install cleanflow[web,api]
 ```
 Run the web application:
 ```bash

{cleanflow_kit-1.1.0/dataclean → cleanflow_kit-1.2.0/cleanflow}/__init__.py

@@ -15,7 +15,7 @@ Modules:
 import logging
 logger = logging.getLogger(__name__)
 from .data_loader import DataLoader
-from .data_cleaner import DataCleaner
+from .data_cleaner import CleanFlower
 from .model_trainer import ModelTrainer
 
 # Lazy imports to avoid loading matplotlib/seaborn/scipy at import time
@@ -41,4 +41,4 @@ def __getattr__(name):
     raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
 
 __version__ = "1.1.0"
-__all__ = ["DataPipeline", "DataLoader", "DataCleaner", "EDAAnalyzer", "FeatureEngineer", "ModelTrainer"]
+__all__ = ["DataPipeline", "DataLoader", "CleanFlower", "EDAAnalyzer", "FeatureEngineer", "ModelTrainer"]

{cleanflow_kit-1.1.0/dataclean → cleanflow_kit-1.2.0/cleanflow}/data_cleaner.py

@@ -16,7 +16,7 @@ import re
 from ._compat import normalize_string_columns
 
 
-class DataCleaner:
+class CleanFlower:
     """Clean and preprocess datasets."""
     
     def __init__(self, df: pd.DataFrame):
@@ -45,7 +45,7 @@ class DataCleaner:
         self, 
         subset: Optional[List[str]] = None,
         keep: str = 'first'
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Remove duplicate rows.
         
@@ -93,7 +93,7 @@ class DataCleaner:
         categorical_strategy: str = 'mode',
         drop_threshold: float = 0.4,
         fill_value: Optional[Any] = None
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Handle missing values in the dataset.
         
@@ -224,7 +224,7 @@ class DataCleaner:
         self,
         type_mapping: Optional[Dict[str, str]] = None,
         infer_types: bool = True
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Fix and optimize data types.
         
@@ -292,7 +292,7 @@ class DataCleaner:
         columns: Optional[List[str]] = None,
         threshold: float = 1.5,
         action: str = 'clip'
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Detect and handle outliers in numeric columns.
         
@@ -393,7 +393,7 @@ class DataCleaner:
         lowercase: bool = True,
         strip_whitespace: bool = True,
         replace_mapping: Optional[Dict[str, Dict[str, str]]] = None
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Clean and standardize categorical values.
         
@@ -467,7 +467,7 @@ class DataCleaner:
         self,
         method: str = 'standard',
         columns: Optional[List[str]] = None
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Scale numerical features.
         
@@ -518,7 +518,7 @@ class DataCleaner:
         method: str = 'onehot',
         columns: Optional[List[str]] = None,
         max_categories: int = 20
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Encode categorical features.
         
@@ -585,7 +585,7 @@ class DataCleaner:
         columns: Optional[List[str]] = None,
         remove_symbols: bool = True,
         handle_shorthand: bool = True
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Clean text columns containing numbers (e.g. '$1,200', '1.5k').
         
@@ -707,7 +707,7 @@ class DataCleaner:
     def rename_columns(
         self,
         mapping: Dict[str, str]
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Rename columns.
         
@@ -735,7 +735,7 @@ class DataCleaner:
         source_col: str,
         pattern: str,
         new_col_name: str
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         r"""
         Extract text using regex capture group.
         
@@ -778,7 +778,7 @@ class DataCleaner:
         columns: Optional[List[str]] = None,
         drop_constant: bool = True,
         drop_id_like: bool = False
-    ) -> 'DataCleaner':
+    ) -> 'CleanFlower':
         """
         Drop specified or problematic columns.
         

{cleanflow_kit-1.1.0/dataclean → cleanflow_kit-1.2.0/cleanflow}/model_trainer.py

@@ -18,7 +18,7 @@ import warnings
 from datetime import datetime
 from typing import Optional, Dict, Any, List, Tuple
 from .feature_engineer import FeatureEngineer
-from .data_cleaner import DataCleaner
+from .data_cleaner import CleanFlower
 
 from sklearn.model_selection import (
     cross_validate, StratifiedKFold, KFold, RandomizedSearchCV

{cleanflow_kit-1.1.0/dataclean → cleanflow_kit-1.2.0/cleanflow}/pipeline.py

@@ -16,7 +16,7 @@ from typing import Optional, Dict, Any, List, Tuple
 from pathlib import Path
 
 from .data_loader import DataLoader
-from .data_cleaner import DataCleaner
+from .data_cleaner import CleanFlower
 # EDAAnalyzer and FeatureEngineer are imported lazily inside methods
 # to avoid loading matplotlib/seaborn/scipy at module import time
 from .model_trainer import ModelTrainer
@@ -42,7 +42,7 @@ class DataPipeline:
     def __init__(self):
         """Initialize the data pipeline."""
         self.loader: Optional[DataLoader] = None
-        self.cleaner: Optional[DataCleaner] = None
+        self.cleaner: Optional[CleanFlower] = None
         self.eda: Optional['EDAAnalyzer'] = None
         self.engineer: Optional['FeatureEngineer'] = None
         self.trainer: Optional[ModelTrainer] = None
@@ -115,12 +115,12 @@ class DataPipeline:
         
         Parameters:
         -----------
-        (See DataCleaner for parameter descriptions)
+        (See CleanFlower for parameter descriptions)
         """
         if self.raw_df is None:
             raise ValueError("No data loaded. Call load() first.")
         
-        self.cleaner = DataCleaner(self.raw_df)
+        self.cleaner = CleanFlower(self.raw_df)
         
         if remove_duplicates:
             self.cleaner.remove_duplicates()

{cleanflow_kit-1.1.0 → cleanflow_kit-1.2.0}/cleanflow_kit.egg-info/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: cleanflow-kit
-Version: 1.1.0
+Version: 1.2.0
 Summary: A comprehensive, modular Python tool for automated data cleaning, EDA, and feature engineering.
-Author: DataClean Contributors
+Author: CleanFlow Contributors
 License: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
@@ -34,14 +34,14 @@ Requires-Dist: uvicorn; extra == "api"
 Requires-Dist: pydantic; extra == "api"
 Dynamic: license-file
 
-# DataClean
+# CleanFlow
 
 A comprehensive, modular Python tool for automated **data cleaning**, **exploratory data analysis (EDA)**, and **feature engineering**.
 
 ## 🚀 Quick Start
 
 ```python
-from dataclean import DataPipeline
+from cleanflow import DataPipeline
 
 # Initialize and load data
 pipeline = DataPipeline()
@@ -62,12 +62,12 @@ pipeline.save_data("./output")
 Install via pip:
 
 ```bash
-pip install dataclean
+pip install cleanflow
 ```
 
 For optional features (SMOTE for class imbalance handling and Drift detection):
 ```bash
-pip install dataclean[all]
+pip install cleanflow[all]
 ```
 
 ## 📋 Features
@@ -108,7 +108,7 @@ pip install dataclean[all]
 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]
+pip install cleanflow[web,api]
 ```
 Run the web application:
 ```bash

cleanflow_kit-1.2.0/cleanflow_kit.egg-info/SOURCES.txt

@@ -0,0 +1,20 @@
+LICENSE
+README.md
+pyproject.toml
+cleanflow/__init__.py
+cleanflow/_compat.py
+cleanflow/data_cleaner.py
+cleanflow/data_loader.py
+cleanflow/drift_detector.py
+cleanflow/eda.py
+cleanflow/feature_engineer.py
+cleanflow/model_trainer.py
+cleanflow/pipeline.py
+cleanflow/py.typed
+cleanflow/report_generator.py
+cleanflow/synthetic_generator.py
+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

cleanflow_kit-1.2.0/cleanflow_kit.egg-info/top_level.txt

@@ -0,0 +1 @@
+cleanflow

{cleanflow_kit-1.1.0 → cleanflow_kit-1.2.0}/pyproject.toml

@@ -4,11 +4,11 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "cleanflow-kit"
-version = "1.1.0"
+version = "1.2.0"
 description = "A comprehensive, modular Python tool for automated data cleaning, EDA, and feature engineering."
 readme = "README.md"
 authors = [
-  { name = "DataClean Contributors" }
+  { name = "CleanFlow Contributors" }
 ]
 license = { text = "MIT License" }
 requires-python = ">=3.8"
@@ -33,7 +33,7 @@ web = ["Flask", "Flask-SQLAlchemy", "PyJWT", "gunicorn", "openpyxl"]
 api = ["FastAPI", "uvicorn", "pydantic"]
 
 [tool.setuptools.packages.find]
-include = ["dataclean*"]
+include = ["cleanflow*"]
 
 [tool.pytest.ini_options]
 minversion = "6.0"

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

@@ -1,20 +0,0 @@
-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/top_level.txt

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