app.py

# ==========================================================
# 👨‍💻 K. Siddhartha — Python Developer | AI / NLP Developer
# Product Category Prediction using Decision Tree
# ==========================================================

import numpy as np
import pandas as pd
import streamlit as st
import matplotlib.pyplot as plt

from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, classification_report

# ==========================================================
# PAGE CONFIG
# ==========================================================
st.set_page_config(
    page_title="Product Category Prediction | Decision Tree",
    layout="centered"
)

st.title("🛍️ Product Category Prediction using Decision Tree")
st.caption(
    "Supervised Machine Learning • Explainable AI • Decision Tree Visualization"
)

# ==========================================================
# DATASET (CACHED)
# ==========================================================
@st.cache_data
def load_data():
    data = {
        "price": [1000, 1200, 900, 50, 60, 40, 10, 15, 8],
        "weight": [1.5, 1.3, 1.8, 0.5, 0.6, 0.4, 0.3, 0.2, 0.1],
        "rating": [4.5, 4.2, 4.7, 3.8, 4.0, 3.5, 4.8, 4.6, 4.9],
        "category": [
            "Electronics", "Electronics", "Electronics",
            "Clothing", "Clothing", "Clothing",
            "Grocery", "Grocery", "Grocery"
        ]
    }
    return pd.DataFrame(data)

df = load_data()

st.subheader("📊 Training Dataset")
st.dataframe(df, use_container_width=True)

# ==========================================================
# SPLIT DATA
# ==========================================================
X = df[["price", "weight", "rating"]]
y = df["category"]

X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.3,
    random_state=42,
    stratify=y
)

# ==========================================================
# MODEL TRAINING (CACHED RESOURCE)
# ==========================================================
@st.cache_resource
def train_model(X_train, y_train):
    model = DecisionTreeClassifier(
        max_depth=3,
        random_state=42
    )
    model.fit(X_train, y_train)
    return model

model = train_model(X_train, y_train)

# ==========================================================
# MODEL PERFORMANCE
# ==========================================================
st.subheader("📈 Model Performance")

y_pred = model.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)

st.metric("Model Accuracy", f"{accuracy:.2f}")

with st.expander("📄 Classification Report"):
    report = classification_report(y_test, y_pred, output_dict=True)
    st.dataframe(pd.DataFrame(report).transpose())

# ==========================================================
# USER INPUT
# ==========================================================
st.subheader("🔮 Predict Product Category")

col1, col2 = st.columns(2)

with col1:
    price = st.number_input("Price", 1.0, 2000.0, 100.0)

with col2:
    weight = st.number_input("Weight (kg)", 0.1, 5.0, 0.5)

rating = st.slider("Rating", 1.0, 5.0, 4.0)

if st.button("Predict Category"):
    pred = model.predict([[price, weight, rating]])[0]
    prob = model.predict_proba([[price, weight, rating]])[0]

    st.success(f"Predicted Category: **{pred}**")
    st.info(f"Confidence: {np.max(prob)*100:.2f}%")

# ==========================================================
# DECISION TREE VISUALIZATION (XAI)
# ==========================================================
st.subheader("🌳 Decision Tree Explainability")

fig, ax = plt.subplots(figsize=(10, 5))

plot_tree(
    model,
    feature_names=["Price", "Weight", "Rating"],
    class_names=model.classes_,
    filled=True,
    rounded=True,
    impurity=False,
    ax=ax
)

ax.set_axis_off()
st.pyplot(fig)

# ==========================================================
# FOOTER
# ==========================================================
st.markdown("---")
st.markdown(
    "Built with **Streamlit**, **Scikit-learn**, and **Matplotlib**"
)