Decision Trees

# DECISION TREE BASICS

import numpy as np
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.datasets import make_classification
import matplotlib.pyplot as plt

# Create sample data
# Features: [Temperature, Humidity, Wind Speed, Ground Wetness]
# Label: Play Cricket (1) or Not (0)
np.random.seed(42)

X = np.array([
    [35, 80, 10, 0],   # Hot, Humid, Low Wind, Dry
    [25, 60, 5, 0],    # Pleasant weather
    [28, 50, 8, 0],    # Good conditions
    [42, 40, 15, 0],   # Too hot
    [20, 90, 20, 1],   # Cold, very humid, wet ground
    [30, 70, 5, 0],    # Nice weather
    [38, 85, 12, 1],   # Hot and wet
    [22, 55, 6, 0],    # Perfect
    [40, 75, 18, 0],   # Too hot, windy
    [26, 65, 7, 0],    # Good weather
])

y = np.array([1, 1, 1, 0, 0, 1, 0, 1, 0, 1])  # 1=Play, 0=Don't Play

# Build Decision Tree
tree = DecisionTreeClassifier(max_depth=3, random_state=42)
tree.fit(X, y)

# Visualize the tree
plt.figure(figsize=(20, 10))
feature_names = ['Temperature', 'Humidity', 'Wind', 'Ground_Wet']
class_names = ['No Play', 'Play']

plot_tree(tree, 
          feature_names=feature_names, 
          class_names=class_names,
          filled=True, 
          rounded=True,
          fontsize=12)
plt.title('Decision Tree: Should I Play Cricket?', fontsize=16)
plt.tight_layout()
plt.show()

# Make predictions
test_conditions = np.array([
    [28, 60, 8, 0],   # Pleasant day
    [41, 85, 20, 1],  # Bad conditions
])

predictions = tree.predict(test_conditions)
print("\nPredictions:")
print(f"Pleasant day (28°C, 60% humidity): {'PLAY!' if predictions[0] else 'Stay Home'}")
print(f"Bad weather (41°C, wet ground): {'PLAY!' if predictions[1] else 'Stay Home'}")

# Feature Importance
print("\nFeature Importance:")
for name, importance in zip(feature_names, tree.feature_importances_):
    print(f"  {name}: {importance:.2%}")