🌳 Decision Tree — Flower Type Classifier (Unit 9)

🔍 Overview

A beginner-friendly Decision Tree classifier built with scikit-learn that predicts the flower type (Type1, Type2, Type3) from two simple features: sepal length and petal length.

This was originally an in-class Unit 9 activity used to introduce supervised learning, train/test splits, and tree-based classifiers in a hands-on way.

---

📦 Features

• Loads a small flower dataset from flower.csv
• Trains a DecisionTreeClassifier with a configurable depth
• Splits data into train/test sets
• Reports accuracy on the test set
• NEW: Optional tree visualization saved as a PNG (--save-plot)
• NEW: Configurable random seed for reproducible runs
• NEW: All key hyperparameters available as command-line options

---

🧠 Dataset

Property	Details
File	flower.csv
Features	sepal_length, petal_length
Label	class (Type1, Type2, Type3)
Samples	~50 rows
Task	Multi-class classification

---

🧰 Requirements

pip install pandas scikit-learn matplotlib

matplotlib is only needed if you use --save-plot.

---

⚙️ How to Run

Default run (uses flower.csv in the same folder):

python DecisionTree_Unit9.py

With options:

python DecisionTree_Unit9.py --csv flower.csv --max-depth 4 --test-size 0.30 --seed 42 --save-plot tree.png

---

🛠️ Command-Line Options

Flag	Default	Description
--csv	flower.csv	Path to the CSV dataset
--max-depth	3	Max depth of the decision tree
--test-size	0.30	Fraction of data used for testing (0.0–1.0)
--seed	None	Random seed for reproducible splits
--save-plot	off	If set, saves a tree visualization to the given path

---

📊 Example Output

The dataset:
   sepal_length  petal_length  class
0           5.1           1.5  Type1
1           4.8           1.4  Type1
...

The actual flower type:    ['Type2' 'Type1' 'Type3' ...]
The predicted flower type: ['Type2' 'Type1' 'Type3' ...]

My decision tree accuracy = 0.9333

---

🎓 Learning Goals

1. Read a CSV into a pandas DataFrame
2. Separate features from the label
3. Use train_test_split to create train/test sets
4. Train a DecisionTreeClassifier and tune max_depth
5. Evaluate the model with accuracy_score

---

📁 Project Structure

Decision_Tree_G10/
├── DecisionTree_Unit9.py     # Main training script
├── flower.csv                # Dataset
├── Unit9_Decision_Tree_Activity.zip  # Original classroom activity
└── README.md

---

📄 License

Educational use — Credits to CS42.org.