Code Editor for app.py

import streamlit as st
import numpy as np
import plotly.graph_objects as go
from sklearn.datasets import make_blobs

# Set page config
st.set_page_config(page_title="3D Visualization Explorer", layout="wide")

# Utility functions
def generate_spiral():
    t = np.linspace(0, 10*np.pi, 100)
    x = t * np.cos(t)
    y = t * np.sin(t)
    z = t + np.random.normal(0, 0.5, 100)
    return x, y, z

def generate_surface(a=1, b=1):
    x = np.linspace(-5, 5, 100)
    y = np.linspace(-5, 5, 100)
    X, Y = np.meshgrid(x, y)
    Z = a * np.sin(X) * np.cos(b * Y)
    return X, Y, Z

def generate_clusters():
    X, y = make_blobs(n_samples=150, n_features=3, centers=3, cluster_std=1.0, random_state=42)
    return X[:, 0], X[:, 1], X[:, 2], y

# Main app
st.title("3D Data Visualization Explorer")

# Sidebar controls
st.sidebar.header("Visualization Controls")
viz_type = st.sidebar.selectbox(
    "Select Visualization",
    ["Spiral Helix", "Surface Plot", "3D Clusters"]
)

# Common plot settings
point_size = st.sidebar.slider("Point Size", 1, 20, 5)
opacity = st.sidebar.slider("Opacity", 0.0, 1.0, 0.8)
colorscale = st.sidebar.selectbox("Color Scheme", ["Viridis", "Plasma", "Magma", "Inferno"])

# Create figure based on selection
fig = go.Figure()

if viz_type == "Spiral Helix":
    x, y, z = generate_spiral()
    animation_speed = st.sidebar.slider("Animation Speed", 0, 100, 50)
    
    fig.add_trace(go.Scatter3d(
        x=x, y=y, z=z,
        mode='markers',
        marker=dict(
            size=point_size,
            opacity=opacity,
            colorscale=colorscale.lower(),
            color=z,
        )
    ))

elif viz_type == "Surface Plot":
    st.sidebar.subheader("Surface Plot Controls")
    a = st.sidebar.slider("Sine multiplier", 0.1, 5.0, 1.0)
    b = st.sidebar.slider("Cosine multiplier", 0.1, 5.0, 1.0)
    show_contours = st.sidebar.checkbox("Show Contours", True)
    
    X, Y, Z = generate_surface(a, b)
    
    fig.add_trace(go.Surface(
        x=X, y=Y, z=Z,
        colorscale=colorscale.lower(),
        opacity=opacity,
        contours=dict(
            z=dict(
                show=show_contours,
                usecolormap=True,
                project_z=True
            )
        )
    ))

else:  # 3D Clusters
    x, y, z, labels = generate_clusters()
    
    fig.add_trace(go.Scatter3d(
        x=x, y=y, z=z,
        mode='markers',
        marker=dict(
            size=point_size,
            opacity=opacity,
            color=labels,
            colorscale=colorscale.lower(),
        )
    ))

# Common figure settings
fig.update_layout(
    scene=dict(
        xaxis_title="X",
        yaxis_title="Y",
        zaxis_title="Z",
        aspectmode='cube'
    ),
    width=800,
    height=800,
    margin=dict(l=0, r=0, b=0, t=30)
)

# Display plot
st.plotly_chart(fig, use_container_width=True)

# Info section
with st.expander("About this visualization"):
    if viz_type == "Spiral Helix":
        st.write("""
        This visualization shows a 3D spiral helix with added random noise. 
        The color of each point corresponds to its z-coordinate.
        """)
    elif viz_type == "Surface Plot":
        st.write("""
        This visualization shows a surface plot of the function z = sin(ax)cos(by).
        Use the sliders to adjust the parameters a and b to see how they affect the surface.
        """)
    else:
        st.write("""
        This visualization shows three 3D clusters generated using scikit-learn's make_blobs function.
        Each color represents a different cluster.
        """)