decision_tree.py

# -*- coding: utf-8 -*-
"""Decision Tree.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1Ho399oSWvvbOABhO33zJsVsRXP79rzxg
"""

# CODTECH Internship - TASK 1
# Decision Tree Classifier with Visualization and Evaluation
# Dataset: Iris (built-in from sklearn)
# ===============================================================

# Step 1: Import Required Libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

# Step 2: Load and Explore the Dataset
iris = load_iris()
X = pd.DataFrame(iris.data, columns=iris.feature_names)
y = pd.Series(iris.target, name="species")

print("✅ Feature sample:")
print(X.head())
print("\n✅ Target classes:", iris.target_names)
print("\n✅ Dataset shape:", X.shape)

# Step 3: Check for Null Values
print("\n🔍 Null value check:")
print(X.isnull().sum())

# Step 4: Train-Test Split
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3, random_state=42, stratify=y
)

print("\n✅ Data split:")
print("Training samples:", len(X_train))
print("Testing samples:", len(X_test))

# Step 5: Model Initialization and Training
clf = DecisionTreeClassifier(criterion="entropy", max_depth=4, random_state=42)
clf.fit(X_train, y_train)

# Step 6: Prediction
y_pred = clf.predict(X_test)

# Step 7: Model Evaluation
acc = accuracy_score(y_test, y_pred)
print(f"\n🎯 Accuracy of the model: {acc:.2f}")

print("\n📊 Classification Report:")
print(classification_report(y_test, y_pred, target_names=iris.target_names))

print("📉 Confusion Matrix:")
cm = confusion_matrix(y_test, y_pred)
sns.heatmap(cm, annot=True, cmap="Blues", xticklabels=iris.target_names, yticklabels=iris.target_names)
plt.title("Confusion Matrix")
plt.xlabel("Predicted")
plt.ylabel("Actual")
plt.show()

# Step 8: Visualize the Decision Tree
plt.figure(figsize=(16, 10))
plot_tree(
    clf,
    feature_names=iris.feature_names,
    class_names=iris.target_names,
    filled=True,
    rounded=True,
    fontsize=12
)
plt.title("🌳 Decision Tree Visualization")
plt.show()

# Step 9: Feature Importance
feature_importance = pd.Series(clf.feature_importances_, index=X.columns).sort_values(ascending=False)
print("\n🔥 Feature Importances:")
print(feature_importance)

# Plot Feature Importance
feature_importance.plot(kind="bar", color="green")
plt.title("Feature Importance")
plt.ylabel("Importance Score")
plt.xlabel("Features")
plt.show()