Update app.py

app.py

@@ -27,12 +27,15 @@ def prepare_data(input_data, n_samples, outliers_fraction=0.0):
     }
     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)
-    return X
+    outliers = rng.uniform(low=-6, high=6, size=(n_outliers, 2))
+    X = np.concatenate([X, outliers], axis=0)
+    labels = np.array(["Normal"] * len(X))
+    labels[-len(outliers):] = "Anomaly"
+    return X, labels
 
 # Function to train models and generate plots
 def train_models(input_data, outliers_fraction, n_samples, clf_name):
-    X = prepare_data(input_data, n_samples, outliers_fraction)
+    X, _ = prepare_data(input_data, n_samples, outliers_fraction)
 
     # Define classifiers
     NAME_CLF_MAPPING = {
@@ -81,9 +84,7 @@ def train_models(input_data, outliers_fraction, n_samples, clf_name):
 
 # 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
+    data, _ = prepare_data(input_data, n_samples)
     x_data = data[:, 0] if feature_x == "Feature1" else data[:, 1]
     y_data = data[:, 1] if feature_y == "Feature2" else data[:, 0]
 
@@ -97,24 +98,35 @@ def plot_interactive_feature_scatter(input_data, feature_x, feature_y, n_samples
     return plt.gcf()
 
 # Function to simulate anomaly samples
-def get_anomaly_samples():
-    # Simulated dataframe
-    data = {
-        "Anomaly_Score": np.random.random(100),
-        "Anomaly_Label": np.random.choice(["Anomaly", "Normal"], size=100, p=[0.2, 0.8]),
-    }
-    df = pd.DataFrame(data)
+def get_anomaly_samples(input_data, n_samples, outliers_fraction):
+    # Prepare data with labels
+    X, labels = prepare_data(input_data, n_samples, outliers_fraction)
+
+    # Assign anomaly scores (simulated here)
+    scores = np.random.random(len(X))
+
+    # Create a DataFrame
+    df = pd.DataFrame({
+        "Feature1": X[:, 0],
+        "Feature2": X[:, 1],
+        "Anomaly_Score": scores,
+        "Anomaly_Label": labels,
+    })
+
+    # Round values to 3 decimal places
+    df = df.round({"Feature1": 3, "Feature2": 3, "Anomaly_Score": 3})
 
     # Top 10 anomalies
-    top_10 = df.sort_values("Anomaly_Score", ascending=False).head(10)
+    top_10 = df[df["Anomaly_Label"] == "Anomaly"].nlargest(10, "Anomaly_Score")
 
-    # Middle 10
-    middle = df.iloc[len(df) // 2 - 5 : len(df) // 2 + 5]
+    # Middle 10 (mixed)
+    mid_start = len(df) // 2 - 5
+    middle_10 = df.iloc[mid_start: mid_start + 10]
 
     # Bottom 10 normals
-    bottom_10 = df[df["Anomaly_Label"] == "Normal"].tail(10)
+    bottom_10 = df[df["Anomaly_Label"] == "Normal"].nsmallest(10, "Anomaly_Score")
 
-    return top_10, middle, bottom_10
+    return top_10, middle_10, bottom_10
 
 # Gradio Interface
 with gr.Blocks() as demo:
@@ -122,7 +134,7 @@ with gr.Blocks() as demo:
     gr.Markdown("## 🕵️‍♀️ Anomaly Detection App 🕵️‍♂️")
     gr.Markdown("Explore anomaly detection models, feature interactions, and anomaly examples.")
 
-    # Anomaly Detection Comparison
+    # Compare Anomaly Detection Algorithms
     gr.Markdown("### 1. Compare Anomaly Detection Algorithms")
     input_data = gr.Radio(
         choices=["Central Blob", "Two Blobs", "Blob with Noise", "Moons", "Noise"],
@@ -166,16 +178,16 @@ with gr.Blocks() as demo:
     )
 
     # Anomaly Samples Tab
-    with gr.Tab("Anomaly Samples"):
-        gr.Markdown("### Example Anomaly Records")
-        top_table = gr.Dataframe(label="Top 10 Anomalies")
-        middle_table = gr.Dataframe(label="Middle 10 Records")
-        bottom_table = gr.Dataframe(label="Bottom 10 Normals")
-        anomaly_samples_button = gr.Button("Show Anomaly Samples")
-
-        anomaly_samples_button.click(
-            fn=get_anomaly_samples, 
-            outputs=[top_table, middle_table, bottom_table]
-        )
+    gr.Markdown("### 3. Example Anomaly Records")
+    top_table = gr.Dataframe(label="Top 10 Anomalies")
+    middle_table = gr.Dataframe(label="Middle 10 Records")
+    bottom_table = gr.Dataframe(label="Bottom 10 Normals")
+    anomaly_samples_button = gr.Button("Show Anomaly Samples")
+
+    anomaly_samples_button.click(
+        fn=get_anomaly_samples, 
+        inputs=[input_data, n_samples, outliers_fraction],
+        outputs=[top_table, middle_table, bottom_table],
+    )
 
 demo.launch(debug=True)