Create app.py

app.py

@@ -0,0 +1,87 @@
+import streamlit as st
+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
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics import classification_report, accuracy_score
+import matplotlib.pyplot as plt
+
+st.set_page_config(page_title="Explore Decision Tree Algorithm", layout="wide")
+st.title("🌳 Decision Tree Classifier Demystified")
+
+st.markdown("""
+## 🧠 What is a Decision Tree?
+
+A Decision Tree is a flowchart-like tree structure where each internal node represents a test on a feature,
+each branch represents an outcome of that test, and each leaf node represents a class label.
+
+Think of it like *20 Questions*, but for data.
+
+---
+## ⚙️ How Decision Trees Work
+
+1. Split the dataset based on feature values.
+2. Choose the best feature using criteria like *Gini Index, **Entropy, or **Information Gain*.
+3. Repeat recursively until leaf nodes are pure or max depth is reached.
+
+Decision Trees are:
+- Easy to understand and interpret
+- Able to handle both numerical and categorical data
+- Prone to overfitting if not pruned
+
+---
+""")
+
+st.subheader("🌼 Try Decision Tree on the Iris Dataset")
+
+iris = load_iris()
+df = pd.DataFrame(iris.data, columns=iris.feature_names)
+df['target'] = iris.target
+
+st.dataframe(df.head(), use_container_width=True)
+
+criterion = st.radio("Select the Splitting Criterion", ["gini", "entropy"])
+max_depth = st.slider("Select Max Depth of Tree", 1, 10, value=3)
+
+X = df.drop('target', axis=1)
+y = df['target']
+
+# Standardize features
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+
+X_train, X_test, y_train, y_test = train_test_split(X_scaled, y, test_size=0.2, random_state=42)
+
+model = DecisionTreeClassifier(criterion=criterion, max_depth=max_depth, random_state=42)
+model.fit(X_train, y_train)
+y_pred = model.predict(X_test)
+
+acc = accuracy_score(y_test, y_pred)
+st.success(f"✅ Model Accuracy: {acc*100:.2f}%")
+
+st.markdown("### 📊 Classification Report")
+st.text(classification_report(y_test, y_pred, target_names=iris.target_names))
+
+st.markdown("### 🌳 Visualizing the Decision Tree")
+fig, ax = plt.subplots(figsize=(10, 6))
+plot_tree(model, filled=True, feature_names=iris.feature_names, class_names=iris.target_names, fontsize=10)
+st.pyplot(fig)
+
+st.markdown("""
+---
+## 💡 Highlights of Decision Trees:
+- Visual and easy to explain.
+- No need for feature scaling.
+- Can model non-linear relationships.
+- Can easily overfit — use pruning or set max depth.
+
+## 🔧 When to Use Decision Trees?
+Use them when:
+- You need a quick, explainable model.
+- Feature relationships are non-linear.
+- Interpretability is more important than performance.
+
+---
+🎯 *Tip:* Watch out for overfitting. Decision Trees love to memorize the training data if left unchecked.
+""")