Iris Dataset Exploration

Task Objective

Explore and visualize the Iris dataset using Python to understand feature relationships, distributions, and potential outliers.

Dataset

The Iris dataset contains 150 samples of iris flowers, with 4 numerical features and 1 categorical target variable:

• sepal_length
• sepal_width
• petal_length
• petal_width
• species (target variable: Setosa, Versicolor, Virginica)

Dataset source: Seaborn Repository

Tools Used

• Python
• Pandas
• Matplotlib
• Seaborn

Steps Performed

1. Loaded dataset using pandas.
2. Inspected dataset using head(), info(), and describe().
3. Visualized data using:
   • Scatter plots to analyze feature correlations.
   • Histograms to check distributions.
   • Box plots to detect outliers.

Models Applied

• None (exploratory data analysis only)

Key Results and Findings

• Dataset shape: (150, 5)
• 3 species: Setosa, Versicolor, Virginica
• Petal length & width show clear clusters (best for classification)
• Setosa does not overlap with other species
• Few outliers detected in sepal width
• All features are numerical; no missing values

Project Files

• main.py – Python code for dataset exploration
• iris.csv – Dataset file

Outputs & Results

Dataset Shape

Dataset Info

Scatter Plot: Sepal Length vs Petal Length

Histograms: Feature Distributions

Box Plots: Outlier Detection

Summary Statistics