← All projects

Personal portfolio application · 2026

Automated Data Cleaning and EDA

A Streamlit application that identifies common data-quality problems, supports cleaning decisions and produces a clear exploratory overview of uploaded datasets.

PythonPandasStreamlitPlotlyExcel / CSV
Launch live app Opens the interactive Streamlit application in a new tab.
DATA QUALITY REPORTIN BUILD
92/100Illustrative quality score
Completeness94%
Consistency88%
Validity96%
01 Upload02 Inspect03 Clean04 Export

Central question

How can repetitive data-cleaning and exploratory-analysis tasks become a transparent, reusable workflow?

01

Project overview

Clean My Data is designed as a practical first stop for CSV and Excel datasets. It brings inspection, cleaning, visual exploration and export into one guided interface.

The objective is not to hide analytical judgement. The application surfaces data-quality issues and explains proposed actions so that the user remains in control of the final dataset.

02

Core workflow

The application follows a consistent sequence from upload to export. Each stage produces information that supports the next decision rather than applying unexplained transformations automatically.

  • Upload CSV or Excel data and inspect its structure.
  • Profile missing values, duplicates, data types and potential outliers.
  • Review distributions, correlations and date-aware summaries.
  • Apply selected cleaning actions and export the revised dataset.
03

Design priorities

The interface is being developed for users who need a fast overview without losing traceability. Clear labels, before-and-after summaries and downloadable outputs make each transformation easier to evaluate.

The visual system uses concise cards and diagnostic views to keep the experience useful on desktop and smaller screens.

04

Live application and next iteration

The application is now deployed as an interactive Streamlit experience and can be tested directly from this report. The next iteration will expand end-to-end testing across varied datasets, refine recommendations for mixed data types and document performance with verified screenshots and before-and-after examples.

People behind the project

Project contributors

Creator and developer

Toni Cata

Next project

Fear Patterns with CCA

View report