Update app.py

app.py

@@ -8,14 +8,13 @@ from sklearn.linear_model import SGDOneClassSVM
 from sklearn.kernel_approximation import Nystroem
 from sklearn.pipeline import make_pipeline
 from sklearn.datasets import make_blobs, make_moons
-import gradio as gr
-import tensorflow as tf
 from tensorflow.keras.models import Sequential
-from tensorflow.keras.layers import Dense, Input
+from tensorflow.keras.layers import Dense
 from tensorflow.keras.optimizers import Adam
+import gradio as gr
 import time
 
-# 1. Helper function: Prepare data
+# Helper function: Prepare data
 def prepare_data(input_data, n_samples, outliers_fraction=0.01):
     n_outliers = max(int(outliers_fraction * n_samples), 1)
     n_inliers = n_samples - n_outliers
@@ -33,7 +32,7 @@ def prepare_data(input_data, n_samples, outliers_fraction=0.01):
     X = np.concatenate([X, outliers], axis=0)
     return X
 
-# 2. Autoencoder Anomaly Detection
+# Autoencoder Anomaly Detection
 def build_autoencoder(input_dim):
     model = Sequential([
         Dense(64, activation='relu', input_dim=input_dim),
@@ -53,7 +52,18 @@ def autoencoder_anomaly_detection(X, outliers_fraction=0.01, epochs=50):
     y_pred = (reconstruction_error > threshold).astype(int)
     return y_pred
 
-# 3. Function to train models and generate plots
+# Function to generate scatter plots
+def plot_interactive_feature_scatter(input_data, feature_x, feature_y, n_samples):
+    X = prepare_data(input_data, n_samples)
+    plt.figure(figsize=(6, 6))
+    plt.scatter(X[:, 0], X[:, 1], alpha=0.8, c="blue", s=20, label="Data Points")
+    plt.title(f"Feature Interaction Scatter Plot - {feature_x} vs {feature_y}")
+    plt.xlabel(feature_x)
+    plt.ylabel(feature_y)
+    plt.legend()
+    return plt.gcf()
+
+# Function to train models and generate comparison plots
 def train_models(input_data, outliers_fraction, n_samples, clf_name):
     X = prepare_data(input_data, n_samples, outliers_fraction)
     NAME_CLF_MAPPING = {
@@ -67,34 +77,57 @@ def train_models(input_data, outliers_fraction, n_samples, clf_name):
         "Local Outlier Factor": LocalOutlierFactor(n_neighbors=35, contamination=outliers_fraction),
         "Autoencoders": autoencoder_anomaly_detection(X, outliers_fraction)
     }
+    clf = NAME_CLF_MAPPING.get(clf_name, None)
     if clf_name == "Autoencoders":
-        y_pred = NAME_CLF_MAPPING[clf_name]
+        y_pred = clf
     else:
-        clf = NAME_CLF_MAPPING[clf_name]
         if clf_name == "Local Outlier Factor":
             y_pred = clf.fit_predict(X)
         else:
             clf.fit(X)
             y_pred = clf.predict(X)
+
+    # Plot results
     plt.figure(figsize=(5, 5))
     colors = np.array(["#377eb8", "#ff7f00"])
     plt.scatter(X[:, 0], X[:, 1], c=colors[(y_pred + 1) // 2], s=20)
     plt.title(clf_name)
     return plt.gcf()
 
-# 4. Gradio Interface
+# Gradio Interface
 with gr.Blocks() as demo:
     gr.Markdown("## Anomaly Detection Comparison App")
+    
+    # Interactive Scatter Plot
+    gr.Markdown("### Interactive Feature Scatter Plot")
     input_data = gr.Radio(choices=["Central Blob", "Two Blobs", "Blob with Noise", "Moons", "Noise"], value="Moons", label="Dataset")
+    feature_x = gr.Dropdown(choices=["Feature1", "Feature2"], value="Feature1", label="Feature 1")
+    feature_y = gr.Dropdown(choices=["Feature1", "Feature2"], value="Feature2", label="Feature 2")
     n_samples = gr.Slider(minimum=50, maximum=2000, step=50, value=500, label="Number of Samples")
+    scatter_plot_button = gr.Button("Generate Scatter Plot")
+    scatter_plot = gr.Plot(label="Feature Scatter Plot")
+
+    scatter_plot_button.click(
+        fn=plot_interactive_feature_scatter,
+        inputs=[input_data, feature_x, feature_y, n_samples],
+        outputs=scatter_plot,
+    )
+    
+    # Compare Anomaly Detection Algorithms
+    gr.Markdown("### Compare Anomaly Detection Algorithms")
     outliers_fraction = gr.Slider(minimum=0.01, maximum=0.5, step=0.01, value=0.05, label="Fraction of Outliers")
     input_models = gr.Radio(
         choices=["Robust covariance", "One-Class SVM", "One-Class SVM (SGD)", "Isolation Forest", "Local Outlier Factor", "Autoencoders"],
         value="Isolation Forest",
         label="Select Model"
     )
-    plot = gr.Plot(label="Model Results")
-    generate_plot = gr.Button("Generate Plot")
-    generate_plot.click(fn=train_models, inputs=[input_data, outliers_fraction, n_samples, input_models], outputs=plot)
+    comparison_plot = gr.Plot(label="Model Comparison Results")
+    generate_comparison_plot = gr.Button("Generate Comparison Plot")
+
+    generate_comparison_plot.click(
+        fn=train_models,
+        inputs=[input_data, outliers_fraction, n_samples, input_models],
+        outputs=comparison_plot,
+    )
 
 demo.launch()