import streamlit as st
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs
import time

st.set_page_config(layout="wide")

st.markdown("#### Clustering in AI - (unsupervised modeling)")

# Section 1: What is clustering?
with st.expander("🔍 What is clustering, and why is it relevant in business?"):
    st.markdown("""
    Clustering is an **unsupervised machine learning technique** that groups similar data points together.  
    It's commonly used in:
    - **Customer segmentation** (e.g., marketing campaigns)
    - **Anomaly detection** (e.g., fraud or system failures)
    - **Document categorization**  
      
    Clustering helps discover **patterns** without labeled data, making it extremely useful in business scenarios where manual labeling is costly or infeasible.
    """)
    
    from sklearn.datasets import make_blobs
    from sklearn.cluster import KMeans
    import matplotlib.pyplot as plt
    import seaborn as sns

    # Set plot style
    sns.set(style="whitegrid")
        
    # --- 1. Customer Segmentation ---
    st.markdown("###### 📊 1. Customer Segmentation")
    st.write("Imagine customers represented by their **age** and **spending score**. Clustering reveals distinct customer groups.")

    X_seg, _ = make_blobs(n_samples=300, centers=4, cluster_std=1.0, random_state=42)
    kmeans_seg = KMeans(n_clusters=4, random_state=42).fit(X_seg)
    labels_seg = kmeans_seg.labels_

    fig1, ax1 = plt.subplots(figsize=(9,4))
    scatter1 = ax1.scatter(X_seg[:, 0], X_seg[:, 1], c=labels_seg, cmap='Accent')
    ax1.set_xlabel("Age")
    ax1.set_ylabel("Spending Score")
    ax1.set_title("Customer Segmentation Clusters")
    st.pyplot(fig1)

    st.markdown("""
    **Interpretation:**  
    Each cluster corresponds to a distinct customer segment, like:
    - High spenders vs budget-conscious
    - Young vs older demographics  
    This allows targeted marketing and better personalization.
    """)

    # --- 2. Anomaly Detection ---
    st.markdown("###### 🚨 2. Anomaly Detection")
    st.write("Let’s simulate normal system activity with a few injected anomalies.")

    X_anom, _ = make_blobs(n_samples=290, centers=1, cluster_std=1.0, random_state=42)
    anomalies = np.random.uniform(low=-6, high=6, size=(10, 2))
    X_anom_combined = np.vstack([X_anom, anomalies])

    kmeans_anom = KMeans(n_clusters=1, random_state=42).fit(X_anom_combined)
    distances = np.linalg.norm(X_anom_combined - kmeans_anom.cluster_centers_[0], axis=1)
    threshold = np.percentile(distances, 95)
    outliers = distances > threshold

    fig2, ax2 = plt.subplots(figsize=(9,4))
    ax2.scatter(X_anom_combined[~outliers, 0], X_anom_combined[~outliers, 1], label="Normal", alpha=0.6)
    ax2.scatter(X_anom_combined[outliers, 0], X_anom_combined[outliers, 1], color='red', label="Anomaly")
    ax2.set_title("Anomaly Detection using Clustering")
    ax2.legend()
    st.pyplot(fig2)

    st.markdown("""
    **Interpretation:**  
    Data points that are **far from the cluster center** are flagged as anomalies.  
    Great for:
    - Fraud detection
    - Network intrusion
    - Fault detection in systems
    """)

    # --- 3. Document Categorization ---
    st.markdown("###### 📚 3. Document Categorization")
    st.write("Assume each document is reduced to 2D space using techniques like TF-IDF + PCA.")

    X_docs, _ = make_blobs(n_samples=300, centers=3, cluster_std=1.2, random_state=7)
    kmeans_docs = KMeans(n_clusters=3, random_state=7).fit(X_docs)

    fig3, ax3 = plt.subplots(figsize=(9,4))
    ax3.scatter(X_docs[:, 0], X_docs[:, 1], c=kmeans_docs.labels_, cmap='Set2')
    ax3.set_title("Clustering Documents into Categories")
    ax3.set_xlabel("Topic Vector 1")
    ax3.set_ylabel("Topic Vector 2")
    st.pyplot(fig3)

    st.markdown("""
    **Interpretation:**  
    Clustering helps group similar documents or articles (e.g., tech, sports, health) without prior labels.  
    It's used in:
    - News aggregation
    - Content recommendation
    - Automated document organization
    """)
    
    
# Section 2: Key characteristics
with st.expander("🧠 Key characteristics of clustering (Human-in-the-loop)"):
    st.markdown("""
    - No predefined labels — clustering is exploratory.
    - Requires defining **number of clusters (K)** manually in many algorithms like K-Means.
    - Human input is essential for:
      - **Interpreting cluster meanings**
      - **Validating business relevance**
      - **Tuning parameters like K or distance metrics**
      
    This is where **"human-in-the-loop"** comes in — domain experts make sense of the clusters produced.
    """)
    
    # --- 1. Standard Numeric Dataset ---
    st.markdown("###### 🧮 1. Standard Numeric Dataset (e.g., Customer Features)")

    import pandas as pd
    import numpy as np

    df_numeric = pd.DataFrame({
        "Age": np.random.randint(18, 65, size=5),
        "Annual Income ($)": np.random.randint(20000, 100000, size=5),
        "Spending Score": np.random.randint(1, 100, size=5),
        "Cluster_Label": ["" for _ in range(5)]
    })
    st.dataframe(df_numeric)

    # --- 2. Text Dataset ---
    st.markdown("###### ✍️ 2. Text Dataset (e.g., Customer Reviews)")

    df_text = pd.DataFrame({
        "Review_Text": [
            "Great product, loved the quality!",
            "Terrible support. Never buying again.",
            "Okay-ish experience. Could be better.",
            "Fast delivery and nice packaging.",
            "Didn't meet my expectations."
        ],
        "Cluster_Label": ["" for _ in range(5)]
    })
    st.dataframe(df_text)

    # --- 3. Image Dataset ---
    st.markdown("###### 🖼️ 3. Image Dataset (e.g., Pixel Vectors)")

    df_image = pd.DataFrame(np.random.randint(0, 256, size=(5, 10)), columns=[f"Pixel_{i}" for i in range(10)])
    df_image["Cluster_Label"] = ""
    st.dataframe(df_image)

    st.markdown("""
    **Notice:**  
    There are **no predefined labels** (`Cluster_Label` is empty).  
    Clustering algorithms group the rows based on internal patterns, and **humans interpret what those groupings mean**.
    """)
    
# Section 3: Custom K-Means visualization
with st.expander("📊 Visualizing K-Means Clustering (Custom Implementation)"):
    st.markdown("K-Means Clustering Demonstration (Custom Implementation)")

    # Sidebar parameters
    num_points  = st.sidebar.slider("Number of points per cluster", 10, 100, 50)
    cluster_sep = st.sidebar.slider("Cluster separation", 0.5, 5.0, 2.0)
    sleep_interval = st.sidebar.slider("Sleep interval (seconds)", 0.1, 2.0, 0.5)
    show_table = st.sidebar.checkbox("Show cluster table")

    # Generate synthetic data
    @st.cache_data
    def generate_data(num_points, cluster_sep):
        points, _ = make_blobs(n_samples=num_points*3, centers=3, cluster_std=cluster_sep, n_features=2, random_state=42)
        return points

    points = generate_data(num_points, cluster_sep)

    # Random centers
    np.random.seed(42)
    centers = np.column_stack((
        np.random.uniform(-10, 10, 3),
        np.random.uniform(-10, 5, 3)
    ))

    def calculate_distances(points, centers):
        return np.linalg.norm(points[:, np.newaxis] - centers, axis=2)

    fig, axes = plt.subplots(4, 3, figsize=(12, 16))
    num_iterations = 12

    for iteration in range(num_iterations):
        distances = calculate_distances(points, centers)
        closest = np.argmin(distances, axis=1)
        df = pd.DataFrame(points, columns=['x1', 'x2'])
        for i in range(3):
            df[f'dist_to_center_{i+1}'] = distances[:, i]
        df['closest_center'] = closest

        row, col = divmod(iteration, 3)
        ax = axes[row, col]
        colors = ['red', 'green', 'blue']
        for i in range(3):
            cluster = df[df['closest_center'] == i]
            ax.scatter(cluster['x1'], cluster['x2'], color=colors[i], s=5, label=f'Cluster {i+1}')
            ax.scatter(centers[i][0], centers[i][1], color='black', marker='x', s=50, linewidths=2)
        ax.set_title(f"Iteration {iteration + 1}", fontsize=8)
        ax.set_xlabel("x1", fontsize=8)
        ax.set_ylabel("x2", fontsize=8)
        ax.tick_params(labelsize=6)
        ax.legend(fontsize=6)

        # Update centers
        centers = np.array([df[df['closest_center'] == i][['x1', 'x2']].mean() for i in range(3)])

        time.sleep(sleep_interval)

    st.pyplot(fig)

    if show_table:
        def highlight_min(s): return ['background-color: lightgreen' if v == s.min() else '' for v in s]
        st.dataframe(df.style.apply(highlight_min, subset=[f'dist_to_center_{i+1}' for i in range(3)]))
        
# Section 4: Evaluating with the Elbow Method
with st.expander("📉 How do we know if clustering worked well (Elbow Method)?"):
    st.markdown("""
    The **Elbow Method** helps identify the optimal number of clusters (K).  
    - Plot the **inertia** (sum of squared distances from points to their cluster center) for different K.
    - The 'elbow' point in the curve is the ideal number of clusters.

    A sharp drop followed by a plateau indicates the elbow.
    
    This technique avoids both under- and over-clustering.
    """)

    from sklearn.cluster import KMeans

    X = generate_data(100, 1.5)
    inertias = []
    Ks = range(1, 10)
    for k in Ks:
        km = KMeans(n_clusters=k, n_init="auto", random_state=42)
        km.fit(X)
        inertias.append(km.inertia_)

    fig2, ax2 = plt.subplots()
    ax2.plot(Ks, inertias, marker='o')
    ax2.set_title("Elbow Method for Optimal K")
    ax2.set_xlabel("Number of Clusters (K)")
    ax2.set_ylabel("Inertia")
    st.pyplot(fig2)

# Section 5: Challenges and Alternatives
with st.expander("⚠️ Challenges with K-Means & Alternatives"):
    st.markdown("""
    **K-Means limitations:**
    - Requires choosing K manually
    - Assumes clusters are spherical and equal-sized
    - Sensitive to outliers and initial center placement

    **Variants / Alternatives:**
    - **K-Medoids**: More robust to outliers
    - **DBSCAN**: Density-based, no need to specify K
    - **Hierarchical Clustering**: Builds a tree of clusters
    - **Gaussian Mixture Models (GMM)**: Probabilistic soft clustering
    
    Use-case and data characteristics often guide which method to choose.
    """)