Upload src/streamlit_app.py with huggingface_hub

src/streamlit_app.py

@@ -1,40 +1,202 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import numpy as np
+import plotly.express as px
+from sklearn.decomposition import PCA
+from sklearn.datasets import load_iris, load_wine, load_breast_cancer
+from sklearn.preprocessing import StandardScaler
+import plotly.graph_objects as go
+
+# Set page config
+st.set_page_config(
+    page_title="PCA Visualization App",
+    page_icon="📊",
+    layout="wide"
+)
+
+# Title and description
+st.title("📊 PCA Visualization Dashboard")
+st.markdown("""
+This app demonstrates Principal Component Analysis (PCA) visualization using different datasets.
+Use the controls in the sidebar to customize your analysis.
+""")
+
+# Sidebar controls
+st.sidebar.header("🎛️ Controls")
+
+# Dataset selection
+dataset_name = st.sidebar.selectbox(
+    "Select Dataset",
+    ("Iris", "Wine", "Breast Cancer")
+)
+
+# Number of components
+n_components = st.sidebar.slider(
+    "Number of Components",
+    min_value=2,
+    max_value=3,
+    value=2,
+    help="Select 2D or 3D visualization"
+)
+
+# Load selected dataset
+@st.cache_data
+def load_data(dataset_name):
+    if dataset_name == "Iris":
+        data = load_iris()
+    elif dataset_name == "Wine":
+        data = load_wine()
+    else:
+        data = load_breast_cancer()
+    
+    df = pd.DataFrame(data.data, columns=data.feature_names)
+    df['target'] = data.target
+    df['target_names'] = [data.target_names[i] for i in data.target]
+    return df, data.target_names
+
+# Load data
+df, target_names = load_data(dataset_name)
+
+# Display dataset info
+st.subheader(f"Dataset: {dataset_name}")
+st.write(f"Shape: {df.shape[0]} rows, {df.shape[1]-2} features")
+st.write(f"Target classes: {', '.join(target_names)}")
+
+# Show raw data toggle
+if st.checkbox("Show raw data"):
+    st.write(df.head())
+
+# Prepare data for PCA
+X = df.drop(['target', 'target_names'], axis=1)
+y = df['target']
+target_names = df['target_names'].unique()
+
+# Standardize the data
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(X)
+
+# Apply PCA
+pca = PCA(n_components=n_components)
+X_pca = pca.fit_transform(X_scaled)
+
+# Create DataFrame with PCA results
+pca_columns = [f"PC{i+1}" for i in range(n_components)]
+df_pca = pd.DataFrame(X_pca, columns=pca_columns)
+df_pca['target'] = y
+df_pca['target_names'] = df['target_names']
+
+# Display PCA info
+st.subheader("PCA Analysis")
+col1, col2 = st.columns(2)
+with col1:
+    st.write(f"Explained Variance Ratio: {[f'{val:.2%}' for val in pca.explained_variance_ratio_]}")
+    st.write(f"Total Variance Explained: {pca.explained_variance_ratio_.sum():.2%}")
+
+with col2:
+    st.write(f"Cumulative Variance Explained: {[f'{val:.2%}' for val in pca.explained_variance_ratio_.cumsum()]}")
+
+# Create visualization
+if n_components == 2:
+    fig = px.scatter(
+        df_pca,
+        x='PC1',
+        y='PC2',
+        color='target_names',
+        title=f"PCA Visualization - {dataset_name} Dataset (2D)",
+        labels={
+            'PC1': f'PC1 ({pca.explained_variance_ratio_[0]:.1%} variance)',
+            'PC2': f'PC2 ({pca.explained_variance_ratio_[1]:.1%} variance)'
+        },
+        hover_data=['target_names']
+    )
+    
+    fig.update_traces(marker=dict(size=8, opacity=0.8))
+    fig.update_layout(
+        width=800,
+        height=600,
+        legend_title_text='Classes'
+    )
+    
+else:  # 3D visualization
+    fig = px.scatter_3d(
+        df_pca,
+        x='PC1',
+        y='PC2',
+        z='PC3',
+        color='target_names',
+        title=f"PCA Visualization - {dataset_name} Dataset (3D)",
+        labels={
+            'PC1': f'PC1 ({pca.explained_variance_ratio_[0]:.1%} variance)',
+            'PC2': f'PC2 ({pca.explained_variance_ratio_[1]:.1%} variance)',
+            'PC3': f'PC3 ({pca.explained_variance_ratio_[2]:.1%} variance)'
+        },
+        hover_data=['target_names']
+    )
+    
+    fig.update_traces(marker=dict(size=5, opacity=0.8))
+    fig.update_layout(
+        width=800,
+        height=600,
+        legend_title_text='Classes'
+    )
+
+# Display plot
+st.plotly_chart(fig, use_container_width=True)
+
+# Feature contribution to principal components
+st.subheader("Feature Contributions to Principal Components")
+feature_importance = pd.DataFrame(
+    pca.components_.T,
+    columns=pca_columns,
+    index=X.columns
+)
+
+# Display feature importance as a heatmap
+fig_importance = px.imshow(
+    feature_importance.T,
+    labels=dict(x="Features", y="Principal Components", color="Contribution"),
+    color_continuous_scale='RdBu_r',
+    aspect="auto",
+    title="Feature Contributions to Principal Components"
+)
+
+fig_importance.update_layout(
+    width=800,
+    height=400
+)
+
+st.plotly_chart(fig_importance, use_container_width=True)
+
+# Show top contributing features
+st.subheader("Top Contributing Features")
+for i in range(n_components):
+    st.write(f"**PC{i+1}**:")
+    pc_features = feature_importance[f'PC{i+1}'].abs().sort_values(ascending=False)
+    top_features = pc_features.head(5)
+    for feature, value in top_features.items():
+        st.write(f"- {feature}: {value:.3f}")
+    st.write("")
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+# Information about PCA
+with st.expander("ℹ️ About PCA"):
+    st.markdown("""
+    **Principal Component Analysis (PCA)** is a dimensionality reduction technique that transforms 
+    high-dimensional data into a lower-dimensional space while preserving as much variance as possible.
+    
+    **Key Concepts:**
+    - **Principal Components**: New axes that capture maximum variance in the data
+    - **Explained Variance Ratio**: Proportion of total variance explained by each component
+    - **Standardization**: Important preprocessing step to ensure all features contribute equally
+    
+    **Benefits:**
+    - Reduces computational complexity
+    - Removes multicollinearity
+    - Helps with data visualization
+    - Can improve model performance by reducing noise
+    
+    **Applications:**
+    - Data visualization
+    - Feature extraction
+    - Noise reduction
+    - Data compression
+    """)