datax-analytics 1.0.0

Advanced Data Analytics Package with cleaning, statistics, and visualization

DataX - Advanced Data Analytics Package

DataX is a comprehensive Python package for data analytics that provides powerful tools for data cleaning, statistical analysis, and visualization. Built with modern Python practices, it offers both programmatic and command-line interfaces for maximum flexibility.

🚀 Features

Core Functionality

• Advanced Data Cleaning: Missing value handling, outlier detection, data validation, type conversion
• Comprehensive Statistics: Descriptive statistics, correlation analysis, hypothesis testing, regression analysis
• Rich Visualizations: Statistical plots, interactive charts, customizable themes, export capabilities
• Command Line Interface: Full CLI support with interactive mode and batch processing
• High Performance: Optimized for large datasets with efficient memory usage

Advanced Features

• Interactive Mode: Jupyter notebook integration and interactive plotting
• Statistical Modeling: Linear regression, ANOVA, normality testing
• Data Validation: Custom rule-based validation with comprehensive reporting
• Export Capabilities: Multiple output formats (CSV, Excel, JSON, Parquet)
• Extensible Architecture: Plugin system for custom analyzers and visualizers

📦 Installation

From PyPI (Recommended)

pip install datax

From Source

git clone https://github.com/datax/datax.git
cd datax
pip install -e .

With Optional Dependencies

# For development
pip install datax[dev]

# For documentation
pip install datax[docs]

# For Jupyter integration
pip install datax[jupyter]

# All optional dependencies
pip install datax[all]

🎯 Quick Start

Python API

import pandas as pd
from datax import DataCleaner, DataAnalyzer, DataVisualizer

# Load your data
df = pd.read_csv('your_data.csv')

# Data Cleaning
cleaner = DataCleaner(df)
cleaner.handle_missing_values(method='auto')
cleaner.remove_duplicates()
cleaner.handle_outliers(method='iqr', action='cap')
cleaned_data = cleaner.data

# Statistical Analysis
analyzer = DataAnalyzer(cleaned_data)
desc_stats = analyzer.get_descriptive_stats()
correlation = analyzer.get_correlation_matrix()
regression = analyzer.regression_analysis('target_column', ['feature1', 'feature2'])

# Visualization
visualizer = DataVisualizer(cleaned_data)
visualizer.plot_distribution('column_name')
visualizer.plot_correlation_heatmap()
visualizer.plot_multiple_distributions(['col1', 'col2', 'col3'])

Command Line Interface

# Load data and get information
datax load data.csv info

# Clean data with auto missing value handling
datax load data.csv clean --missing auto --remove-duplicates

# Perform statistical analysis
datax load data.csv stats --descriptive --correlation

# Create visualizations
datax load data.csv viz --distributions --correlation-heatmap

# Interactive mode
datax interactive --file data.csv

📊 Examples

Data Cleaning Pipeline

from datax import DataCleaner
import pandas as pd

# Load data
df = pd.read_csv('messy_data.csv')

# Initialize cleaner
cleaner = DataCleaner(df)

# Comprehensive cleaning pipeline
cleaner.handle_missing_values(method='auto') \
       .remove_duplicates() \
       .handle_outliers(method='iqr', action='cap') \
       .convert_data_types(auto_convert=True) \
       .validate_data()

# Get cleaning summary
summary = cleaner.get_cleaning_summary()
print(f"Original shape: {summary['original_shape']}")
print(f"Final shape: {summary['current_shape']}")

# Save cleaned data
cleaner.save_cleaned_data('cleaned_data.csv')

Statistical Analysis

from datax import DataAnalyzer

analyzer = DataAnalyzer(df)

# Descriptive statistics
desc_stats = analyzer.get_descriptive_stats()

# Correlation analysis
correlation = analyzer.get_correlation_matrix(method='pearson')

# Hypothesis testing
ttest_result = analyzer.hypothesis_test('ttest', 
                                       column1='group1', 
                                       column2='group2')

# Regression analysis
regression = analyzer.regression_analysis('target', 
                                        ['feature1', 'feature2', 'feature3'])

# ANOVA analysis
anova = analyzer.anova_analysis('value_column', 'group_column')

# Export results
analyzer.export_results('analysis_results.json')

Advanced Visualizations

from datax import DataVisualizer

visualizer = DataVisualizer(df, style='colorful')

# Distribution plots
visualizer.plot_distribution('numeric_column', plot_type='histogram', kde=True)

# Correlation heatmap
visualizer.plot_correlation_heatmap(annot=True)

# Multiple distributions
numeric_cols = df.select_dtypes(include=['number']).columns.tolist()
visualizer.plot_multiple_distributions(numeric_cols[:6])

# Interactive plots
interactive_fig = visualizer.create_interactive_plot('scatter',
                                                   x_column='x',
                                                   y_column='y',
                                                   color_column='category')

# Save plots
visualizer.save_plot(fig, 'output.png', format='png', dpi=300)

🛠️ CLI Usage

Basic Commands

# Show help
datax --help

# Load and analyze data
datax load data.csv info
datax load data.csv clean --missing auto
datax load data.csv stats --descriptive --correlation
datax load data.csv viz --distributions --correlation-heatmap

# Interactive mode
datax interactive --file data.csv

Advanced CLI Features

# Batch processing
datax batch config.json

# Custom output formats
datax load data.csv clean --output cleaned_data.xlsx --format excel

# Verbose output
datax load data.csv stats --descriptive --verbose

# Save plots
datax load data.csv viz --distributions --save-plots ./plots/

📈 Performance

DataX is optimized for performance with large datasets:

• Memory Efficient: Uses pandas' efficient data structures
• Vectorized Operations: Leverages NumPy and pandas vectorization
• Lazy Evaluation: Computes statistics only when needed
• Parallel Processing: Supports multiprocessing for large datasets
• Caching: Intelligent caching of computed results

🔧 Configuration

Custom Themes and Styles

# Set custom visualization style
visualizer = DataVisualizer(df, style='dark')
visualizer.set_style('minimal')

# Custom color palettes
import seaborn as sns
sns.set_palette("Set2")

Advanced Configuration

# Custom validation rules
validation_rules = {
    "age_range": {
        "type": "range",
        "column": "age",
        "min": 0,
        "max": 120
    },
    "unique_id": {
        "type": "unique",
        "column": "id"
    }
}

cleaner.validate_data(rules=validation_rules, strict=True)

📚 Documentation

• Full Documentation
• API Reference
• Examples Gallery
• Contributing Guide

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Setup

git clone https://github.com/datax/datax.git
cd datax
pip install -e ".[dev]"
pre-commit install
pytest

Running Tests

# Run all tests
pytest

# Run with coverage
pytest --cov=datax --cov-report=html

# Run specific test categories
pytest -m "not slow"
pytest -m integration

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Built on top of the amazing pandas library
• Visualization powered by matplotlib and seaborn
• Statistical functions from scipy and scikit-learn
• Interactive plots with plotly

📞 Support

• Documentation: https://datax.readthedocs.io
• Issues: GitHub Issues
• Discussions: GitHub Discussions
• Email: [e-mail]

🗺️ Roadmap

• Machine learning integration
• Time series analysis
• Geospatial data support
• Web dashboard interface
• Real-time data processing
• Cloud deployment support

---

DataX - Making data analytics accessible, powerful, and enjoyable! 🚀