import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier, plot_tree
import matplotlib.pyplot as plt

#Load dataset
iris = load_iris()
X, y = iris.data, iris.target

# Split dataset
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.3, random_state = 42)

# Build Decision Tree
clf = DecisionTreeClassifier(criterion="gini", max_depth=3, random_state=42)
clf.fit(X_train, y_train)

DecisionTreeClassifier(max_depth=3, random_state=42)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

# Evaluate
print("Accuracy", clf.score(X_test, y_test))

Accuracy 1.0

# Test with 3 example samples. Start continueing lab 4 record from here
samples = [
    [5.1, 3.5, 1.4, 0.2], # Setosa
    [6.0, 2.9, 4.5, 1.5], # Versicolor
    [6.9, 3.1, 5.4, 2.1], # Virginica
]

predictions = clf.predict(samples)

for i, pred in enumerate(predictions):
    print(f"Sample {i+1}: Predicted class -> {iris.target_names[pred]}")

Sample 1: Predicted class -> setosa
Sample 2: Predicted class -> versicolor
Sample 3: Predicted class -> virginica

# Visualize the decision tree
plt.figure(figsize=(12, 8))
plot_tree(clf, feature_names=iris.feature_names, class_names=iris.target_names, filled = True)
plt.show()

Class	Sepal Length	Sepal Width	Petal Length	Petal Width
Setosa	4.3-5.8	2.3-4.4	1.0-1.9	0.1-0.6
Versicolor	4.9-7.0	2.0-3.4	3.0-5.1	1.0-1.8
Virginica	4.0-7.9	2.2-3.8	4.5-6.9	1.4-2.5