Attribute Selection Algorithm : Decision Tree Visualizer

A Python-based implementation of Decision Trees built from scratch, complete with Entropy (Information Gain) and Gini Index as splitting criteria. The project also includes a Graphviz-powered visualizer to generate crisp, interpretable tree diagrams.

🚀 Features

• Custom Entropy & Gini Functions – Implemented from scratch, no external ML libraries.
• Dynamic Tree Builder – Recursively constructs decision trees using chosen impurity measures.
• Dual Criteria Support
  • Entropy (Information Gain) → ID3-style splitting
  • Gini Index → CART-style splitting
• Interactive Visualizations – Trees are exported as PNGs with Graphviz.
• Human-readable structure – Leaf nodes represent final decisions, internal nodes show feature splits.

📂 Project Structure

DecisionTreeVisualizer/
│── Dataset.csv          # Input dataset
│── Tree.py     # Main script with tree logic + visualization
│── tree_entropy.png     # Tree built using entropy
│── tree_gini.png        # Tree built using gini index
│── README.md            # You are here

⚙️ How It Works

1. Entropy & Gini Calculation

   • Computes uncertainty of class labels.
   • Lower impurity ⇒ better split.

2. Attribute Selection

   • Recursively selects the best feature based on chosen metric (Entropy or Gini).

3. Tree Construction

   • Splits dataset into subsets by feature values.
   • Continues until pure leaves or no features remain.

4. Visualization

   • Uses Graphviz (Digraph) to generate interpretable flowchart-like trees.

🛠 Installation

Install the required Python libraries:

pip install pandas numpy graphviz

Also, install the Graphviz system package (needed for rendering images):

Debian/Ubuntu

sudo apt-get update && sudo apt-get install -y graphviz

macOS (Homebrew)

brew install graphviz

Windows

Download from Graphviz.org and add it to your PATH.

📊 Usage

Run the script with your dataset (weekend.csv as default):

python Tree.py

This will generate:

tree_entropy.png   # Decision tree using Information Gain
tree_gini.png      # Decision tree using Gini Index

Both trees will be saved in the working directory and usually open automatically.

Sure! Here’s the input part formatted as a table that you can directly paste into your README:

📊 Example Input Data

Here is an example of the input dataset used in the project:

Weekend	Weather	Parents	Financial Condition	Decision
W1	Sunny	Yes	Rich	Cinema
W2	Sunny	No	Rich	Play Tennis
W3	Windy	Yes	Rich	Cinema
W4	Rainy	Yes	Poor	Cinema
W5	Rainy	No	Rich	Stay in
W6	Rainy	Yes	Poor	Cinema
W7	Windy	No	Poor	Cinema
W8	Windy	No	Rich	Shopping
W9	Windy	Yes	Rich	Cinema
W10	Sunny	No	Rich	Play Tennis

🔍 Example Output

• 🟦 Feature Nodes → Light-blue rounded boxes
• 🟩 Leaf Nodes → Green ellipses (final decision)

📌 Entropy-based trees maximize information gain

📌 Gini-based trees minimize class impurity