SagarAnalysis

A production-ready, beginner-friendly Python package designed for one-line data cleaning, one-line Exploratory Data Analysis (EDA), and stunning, glassmorphic HTML reporting.

Features

• One-line Cleaning (clean(df)):
  • Automatically standardizes column names to snake_case.
  • Removes duplicate rows.
  • Detects and drops constant/highly missing columns.
  • Imputes missing values intelligently (median/mean/mode/unknown).
  • Handles numerical outliers via clipping.
  • Coerces data types (string to numeric, string to datetime, Yes/No to boolean).
• One-line EDA & Report (analysis(df)):
  • Generates a comprehensive overview of the dataset.
  • Performs descriptive statistics and missingness analysis.
  • Discovers high correlations and skewness.
  • Auto-detects the target column and runs target profiling.
• Stunning HTML Reports (report.save()):
  • Interactive, modern Glassmorphism design.
  • Supports light/dark theme toggles.
  • Fully responsive layout with embedded Base64 charts.
  • Searchable variables, collapsible details, and clear data insights.

Installation

pip install sagaranalysis

Quick Start

import pandas as pd
import sagaranalysis as sa

# Load your dirty dataset
df = pd.read_csv("dirty_data.csv")

# Clean your data in one line
cleaned_df = sa.clean(df)

# Perform automatic EDA and generate insights
report = sa.analysis(cleaned_df)

# View or save the report
report.show()                  # Opens in local browser or renders in Jupyter Notebook
report.save("report.html")     # Saves self-contained report to disk

License

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