<<<<<<< HEAD Pandas Data Cleaning Practice – Iris Dataset

This notebook demonstrates data cleaning and preprocessing using Pandas on a modified version of the classic Iris dataset (iris_dirty.csv). The dataset intentionally contains inconsistencies, missing values, and formatting issues to simulate real-world messy data.

Objectives

Practice data inspection and exploration

Handle missing values

Fix incorrect data types

Detect and manage duplicate records

Clean inconsistent categorical values

Prepare the dataset for data analysis or machine learning

Tools Used

Python

Jupyter Notebook

Pandas

NumPy

Workflow

Load the dataset

Explore dataset structure and statistics

Identify data quality issues

Clean and preprocess the data

Validate the cleaned dataset

Dataset

iris_dirty.csv is a deliberately corrupted version of the classic Iris dataset used for data cleaning exercises.

Purpose

This notebook was created as part of AI / Data Science training, focusing on developing practical data preprocessing skills using Pandas, a fundamental step in any machine learning workflow.

AI-University-course

This repository contains Jupyter Notebooks from my Artificial Intelligence university coursework.

58dcf6f23d2d775ed6205768188d777975fa3f0e