README.md

metadata

title: SimpleClean
emoji: 🧹
colorFrom: yellow
colorTo: pink
sdk: docker
app_port: 8501
tags:
  - streamlit
  - data-cleaning
  - preprocessing
  - imputation
  - encoding
pinned: false
short_description: Clean your data interactively — no code required.

SimpleClean

Interactive Streamlit dashboard to clean and preprocess your datasets: handle missing values, encode categories, scale features, remove duplicates.

Author

Eduardo Nacimiento García
📧 enacimie@ull.edu.es
📜 Apache 2.0 License

Features

• Upload CSV or use built-in demo dataset
• Data quality report: missing values, duplicates, data types
• Interactive cleaning:
  • 🧹 Remove duplicate rows
  • 🩹 Impute missing values (Mean, Median, Mode, Constant, KNN)
  • 🔠 Encode categorical variables (Label Encoding, One-Hot Encoding)
  • 📏 Scale numeric variables (StandardScaler, MinMaxScaler)
• Visualize missing data with Plotly
• Download cleaned dataset as CSV
• Reset to original anytime

Demo Dataset

Includes sample data with:

• Numeric columns: Age, Income, Satisfaction
• Categorical columns: City, Gender, Has_Children
• Intentional missing values and duplicates

Deployment

Ready for Hugging Face Spaces (free tier).

⚠️ Uses sdk: docker — include Dockerfile.

Requirements

• Python 3.8+
• Streamlit, pandas, numpy, scikit-learn, plotly

---

💡 Tip: Clean step-by-step → preview changes → download when ready!