Iris Dataset — Data Cleaning & Exploratory Data Analysis 🌸📊

Overview

This project focuses on cleaning and exploring the Iris dataset using Python. The analysis covers data inspection, data quality checks, missing-value treatment, duplicate handling, outlier detection, and exploratory data analysis through visualizations.

The project was completed as part of my Machine Learning internship at Internship Studio.

Objectives

• Understand the structure and characteristics of the Iris dataset
• Identify missing values and duplicate records
• Check for inconsistent or unwanted values
• Perform exploratory data analysis
• Detect and treat outliers
• Prepare the dataset for further analysis or machine learning

Dataset

• Source: Kaggle — Iris Dataset
• Format: CSV
• Features: Sepal Length, Sepal Width, Petal Length, Petal Width
• Target: Iris Species

The dataset contains measurements of iris flowers and was used for data cleaning, preprocessing, and exploratory data analysis.

Tools & Technologies

• Programming Language: Python
• Libraries: Pandas, NumPy, Matplotlib, Seaborn
• Environment: Jupyter Notebook / Google Colab

Project Workflow

1. Data Loading & Inspection

• Loaded the Iris dataset using Pandas.
• Examined the first and last records.
• Checked dataset dimensions, data types, and overall structure.

2. Data Quality Checks

• Checked for missing values.
• Identified duplicate records.
• Checked for potential inconsistent or unwanted values.
• Generated descriptive statistics for numerical features.

3. Exploratory Data Analysis

• Analyzed numerical feature distributions.
• Created histograms and boxplots.
• Visualized relationships between features using scatter plots.
• Analyzed feature correlations using a correlation matrix and heatmap.

4. Missing Value Treatment

• Identified missing values in numerical features.
• Applied median imputation to handle missing numerical values.
• Verified that missing values were successfully handled.

5. Outlier Detection & Treatment

• Used the Interquartile Range (IQR) method to identify potential outliers.
• Applied outlier treatment to the relevant numerical feature.

6. Duplicate Handling

• Checked the dataset for duplicate observations.
• Removed duplicate records where applicable.

Key Learning Outcomes

• Practiced data cleaning and preprocessing using Pandas.
• Learned to identify and handle common data-quality issues.
• Performed exploratory data analysis using Matplotlib and Seaborn.
• Applied median imputation for missing numerical values.
• Used the IQR method for outlier detection and treatment.
• Developed a basic understanding of preparing datasets for further analysis.

Project Structure

Internship-Studio-Machine-Learning-Internship/
│
├── Iris-Data-Cleaning-and-EDA/
│   └── IRIS_DATASET.ipynb
│
└── README.md