Update app.py

app.py

@@ -9,15 +9,15 @@ 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 time
 
-# Function to train models and generate plots
-def train_models(input_data, outliers_fraction, n_samples, clf_name):
-    # Prepare data
+# Helper function to prepare data
+def prepare_data(input_data, n_samples, outliers_fraction):
     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)
-    
+
     DATA_MAPPING = {
         "Central Blob": make_blobs(centers=[[0, 0], [0, 0]], cluster_std=0.5, **blobs_params)[0],
         "Two Blobs": make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[0.5, 0.5], **blobs_params)[0],
@@ -26,6 +26,16 @@ def train_models(input_data, outliers_fraction, n_samples, clf_name):
         "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)
+    return X
+
+# 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)
+
+    # Define classifiers
     NAME_CLF_MAPPING = {
         "Robust covariance": EllipticEnvelope(contamination=outliers_fraction),
         "One-Class SVM": svm.OneClassSVM(nu=outliers_fraction, kernel="rbf", gamma=0.1),
@@ -42,13 +52,9 @@ def train_models(input_data, outliers_fraction, n_samples, clf_name):
         "Isolation Forest": IsolationForest(contamination=outliers_fraction, random_state=42),
         "Local Outlier Factor": LocalOutlierFactor(n_neighbors=35, contamination=outliers_fraction),
     }
-    
-    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)
 
-    xx, yy = np.meshgrid(np.linspace(-7, 7, 150), np.linspace(-7, 7, 150))
     clf = NAME_CLF_MAPPING[clf_name]
+    xx, yy = np.meshgrid(np.linspace(-7, 7, 150), np.linspace(-7, 7, 150))
 
     t0 = time.time()
     if clf_name == "Local Outlier Factor":
@@ -58,7 +64,7 @@ def train_models(input_data, outliers_fraction, n_samples, clf_name):
         y_pred = clf.predict(X)
     t1 = time.time()
 
-    # Plot
+    # Plotting
     plt.figure(figsize=(5, 5))
     if clf_name != "Local Outlier Factor":
         Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
@@ -74,91 +80,25 @@ def train_models(input_data, outliers_fraction, n_samples, clf_name):
     plt.yticks(())
     return plt.gcf()
 
-# Gradio Interface
-description = "Compare how different anomaly detection algorithms perform on various datasets."
-title = "🕵️‍♀️ Compare Anomaly Detection Algorithms 🕵️‍♂️"
-
-with gr.Blocks() as demo:
-    gr.Markdown(f"## {title}")
-    gr.Markdown(description)
-    
-    # Inputs
-    input_data = gr.Radio(
-        choices=["Central Blob", "Two Blobs", "Blob with Noise", "Moons", "Noise"],
-        value="Moons",
-        label="Dataset"
-    )
-    n_samples = gr.Slider(minimum=10, maximum=10000, step=25, value=500, label="Number of Samples")
-    outliers_fraction = gr.Slider(minimum=0.001, maximum=0.999, step=0.1, value=0.2, label="Fraction of Outliers")
-    
-    # Models and their plots in a row
-    input_models = ["Robust covariance", "One-Class SVM", "One-Class SVM (SGD)", "Isolation Forest", "Local Outlier Factor"]
-    plots = []
-
-    with gr.Row():
-        for model_name in input_models:
-            plot = gr.Plot(label=model_name)
-            plots.append((model_name, plot))
-
-    # Update function
-    def update(input_data, outliers_fraction, n_samples):
-        results = []
-        for clf_name, plot in plots:
-            fig = train_models(input_data, outliers_fraction, n_samples, clf_name)
-            results.append(fig)
-        return results
-
-    # Set change triggers
-    inputs = [input_data, outliers_fraction, n_samples]
-    demo_outputs = [plot for _, plot in plots]
-    input_data.change(fn=update, inputs=inputs, outputs=demo_outputs)
-    n_samples.change(fn=update, inputs=inputs, outputs=demo_outputs)
-    outliers_fraction.change(fn=update, inputs=inputs, outputs=demo_outputs)
-
-
+# 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)
 
-# Function to generate interactive feature scatter plots
-def plot_interactive_feature_scatter(input_data, feature_x, feature_y, n_samples):
-    # Generate data based on the selected dataset
-    if input_data == "Moons":
-        data, _ = make_moons(n_samples=n_samples, noise=0.05)
-    else:
-        data, _ = make_blobs(n_samples=n_samples, random_state=0)
-
-    # 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()
+    # Top 10 anomalies
+    top_10 = df.sort_values("Anomaly_Score", ascending=False).head(10)
 
+    # Middle 10
+    middle = df.iloc[len(df) // 2 - 5 : len(df) // 2 + 5]
 
-# Function for anomaly examples (Optional feature row)
-def get_anomaly_samples():
-    """Returns formatted top, middle, and bottom 10 records based on anomaly score."""
-    sorted_df = df.sort_values("Anomaly_Score", ascending=False)
-    
-    # Top 10 anomalies
-    top_10 = sorted_df[sorted_df["Anomaly_Label"] == "Anomaly"].head(10)
-    
-    # Middle 10 (mix of anomalies and normal)
-    mid_start = len(sorted_df) // 2 - 50  # Get a broader middle slice
-    middle_section = sorted_df.iloc[mid_start: mid_start + 100]  # Consider a larger middle slice
-    middle_anomalies = middle_section[middle_section["Anomaly_Label"] == "Anomaly"].sample(n=5, random_state=42)
-    middle_normals = middle_section[middle_section["Anomaly_Label"] == "Normal"].sample(n=5, random_state=42)
-    middle_10 = pd.concat([middle_anomalies, middle_normals]).sort_values("Anomaly_Score", ascending=False)
-    
-    # Bottom 10 normal records
-    bottom_10 = sorted_df[sorted_df["Anomaly_Label"] == "Normal"].tail(10)
-    
-    return top_10, middle_10, bottom_10
+    # Bottom 10 normals
+    bottom_10 = df[df["Anomaly_Label"] == "Normal"].tail(10)
 
+    return top_10, middle, bottom_10
 
 # Gradio Interface
 with gr.Blocks() as demo:
@@ -173,12 +113,8 @@ with gr.Blocks() as demo:
         value="Moons",
         label="Dataset"
     )
-    n_samples = gr.Slider(
-        minimum=10, maximum=10000, step=25, value=500, label="Number of Samples"
-    )
-    outliers_fraction = gr.Slider(
-        minimum=0.001, maximum=0.999, step=0.1, value=0.2, label="Fraction of Outliers"
-    )
+    n_samples = gr.Slider(minimum=10, maximum=10000, step=25, value=500, label="Number of Samples")
+    outliers_fraction = gr.Slider(minimum=0.001, maximum=0.999, step=0.1, value=0.2, label="Fraction of Outliers")
 
     input_models = ["Robust covariance", "One-Class SVM", "One-Class SVM (SGD)", "Isolation Forest", "Local Outlier Factor"]
     plots = []
@@ -200,34 +136,17 @@ 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.HTML("<h3 style='text-align: center; font-size: 18px; font-weight: bold;'>Top 10 Records (Anomalies)</h3>")
-        top_table = gr.Dataframe(label="Top 10 Records")
-        
-        gr.HTML("<h3 style='text-align: center; font-size: 18px; font-weight: bold;'>Middle 10 Records (Mixed)</h3>")
+        gr.Markdown("### Example Anomaly Records")
+        top_table = gr.Dataframe(label="Top 10 Anomalies")
         middle_table = gr.Dataframe(label="Middle 10 Records")
-        
-        gr.HTML("<h3 style='text-align: center; font-size: 18px; font-weight: bold;'>Bottom 10 Records (Normal)</h3>")
-        bottom_table = gr.Dataframe(label="Bottom 10 Records")
-        
+        bottom_table = gr.Dataframe(label="Bottom 10 Normals")
         anomaly_samples_button = gr.Button("Show Anomaly Samples")
+
         anomaly_samples_button.click(
-            get_anomaly_samples, 
+            fn=get_anomaly_samples, 
             outputs=[top_table, middle_table, bottom_table]
         )
-    )
 
 demo.launch(debug=True)