Update app.py

app.py

@@ -9,11 +9,11 @@ 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 pandas as pd  # Needed for dataframe operations
+import pandas as pd
 import time
 
 # Helper function to prepare data
-def prepare_data(input_data, n_samples, outliers_fraction):
+def prepare_data(input_data, n_samples, outliers_fraction=0.0):
     n_outliers = int(outliers_fraction * n_samples)
     n_inliers = n_samples - n_outliers
     blobs_params = dict(random_state=0, n_samples=n_inliers, n_features=2)
@@ -25,7 +25,6 @@ def prepare_data(input_data, n_samples, outliers_fraction):
         "Moons": 4.0 * (make_moons(n_samples=n_samples, noise=0.05, random_state=0)[0] - np.array([0.5, 0.25])),
         "Noise": 14.0 * (np.random.RandomState(42).rand(n_samples, 2) - 0.5),
     }
-    
     X = DATA_MAPPING[input_data]
     rng = np.random.RandomState(42)
     X = np.concatenate([X, rng.uniform(low=-6, high=6, size=(n_outliers, 2))], axis=0)
@@ -80,6 +79,23 @@ def train_models(input_data, outliers_fraction, n_samples, clf_name):
     plt.yticks(())
     return plt.gcf()
 
+# Function to generate feature scatter plots
+def plot_interactive_feature_scatter(input_data, feature_x, feature_y, n_samples):
+    data = prepare_data(input_data, n_samples)
+
+    # Simulate feature selection by indexing
+    x_data = data[:, 0] if feature_x == "Feature1" else data[:, 1]
+    y_data = data[:, 1] if feature_y == "Feature2" else data[:, 0]
+
+    # Generate scatter plot
+    plt.figure(figsize=(6, 6))
+    plt.scatter(x_data, y_data, alpha=0.8, c="blue", s=20, label="Features")
+    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 simulate anomaly samples
 def get_anomaly_samples():
     # Simulated dataframe
@@ -136,6 +152,19 @@ with gr.Blocks() as demo:
     n_samples.change(fn=update_anomaly_comparison, inputs=anomaly_inputs, outputs=anomaly_outputs)
     outliers_fraction.change(fn=update_anomaly_comparison, inputs=anomaly_inputs, outputs=anomaly_outputs)
 
+    # Interactive Feature Scatter Plot
+    gr.Markdown("### 2. Interactive Feature Scatter Plot")
+    feature_x = gr.Dropdown(choices=["Feature1", "Feature2"], value="Feature1", label="Feature 1")
+    feature_y = gr.Dropdown(choices=["Feature1", "Feature2"], value="Feature2", label="Feature 2")
+    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,
+    )
+
     # Anomaly Samples Tab
     with gr.Tab("Anomaly Samples"):
         gr.Markdown("### Example Anomaly Records")