app.py

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.covariance import EllipticEnvelope
from sklearn.ensemble import IsolationForest
from sklearn.neighbors import LocalOutlierFactor
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 pandas as pd
import time

# Helper function to prepare data
def prepare_data(input_data, n_samples, outliers_fraction=0.01):
    n_outliers = max(int(outliers_fraction * n_samples), 1)  # At least 1 outlier
    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],
        "Blob with Noise": make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[1.5, 0.3], **blobs_params)[0],
        "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)
    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):
    # Ensure contamination is valid
    outliers_fraction = max(outliers_fraction, 0.01)  # At least 0.01

    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),
        "One-Class SVM (SGD)": make_pipeline(
            Nystroem(gamma=0.1, random_state=42, n_components=150),
            SGDOneClassSVM(
                nu=outliers_fraction,
                shuffle=True,
                fit_intercept=True,
                random_state=42,
                tol=1e-6,
            ),
        ),
        "Isolation Forest": IsolationForest(contamination=outliers_fraction, random_state=42),
        "Local Outlier Factor": LocalOutlierFactor(n_neighbors=35, contamination=outliers_fraction),
    }

    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":
        y_pred = clf.fit_predict(X)
    else:
        clf.fit(X)
        y_pred = clf.predict(X)
    t1 = time.time()

    # Plotting
    plt.figure(figsize=(5, 5))
    if clf_name != "Local Outlier Factor":
        Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
        Z = Z.reshape(xx.shape)
        plt.contour(xx, yy, Z, levels=[0], linewidths=2, colors="black")

    colors = np.array(["#377eb8", "#ff7f00"])
    plt.scatter(X[:, 0], X[:, 1], s=30, color=colors[(y_pred + 1) // 2])
    plt.title(f"{clf_name} ({t1 - t0:.2f}s)")
    plt.xlim(-7, 7)
    plt.ylim(-7, 7)
    plt.xticks(())
    plt.yticks(())
    return plt.gcf()

# Function to detect anomalies and generate anomaly records
def detect_anomalies(input_data, n_samples, outliers_fraction, model_name):
    X, labels = 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),
        "One-Class SVM (SGD)": make_pipeline(
            Nystroem(gamma=0.1, random_state=42, n_components=150),
            SGDOneClassSVM(
                nu=outliers_fraction,
                shuffle=True,
                fit_intercept=True,
                random_state=42,
                tol=1e-6,
            ),
        ),
        "Isolation Forest": IsolationForest(contamination=outliers_fraction, random_state=42),
        "Local Outlier Factor": LocalOutlierFactor(n_neighbors=35, contamination=outliers_fraction),
    }

    clf = NAME_CLF_MAPPING[model_name]
    if model_name == "Local Outlier Factor":
        clf.fit(X)
        scores = -clf.negative_outlier_factor_
    else:
        clf.fit(X)
        scores = -clf.decision_function(X)

    # Normalize scores to a consistent range
    scores = (scores - scores.min()) / (scores.max() - scores.min())

    # Create DataFrame
    df = pd.DataFrame({
        "Feature1": X[:, 0],
        "Feature2": X[:, 1],
        "Anomaly_Score": scores,
        "Anomaly_Label": labels,
    })

    # Sort by anomaly score in descending order
    df = df.sort_values("Anomaly_Score", ascending=False).reset_index(drop=True)

    return df

# Function to get anomaly samples
def get_anomaly_samples(input_data, n_samples, outliers_fraction, model_name):
    outliers_fraction = max(outliers_fraction, 0.01)  # Ensure fraction is valid
    df = detect_anomalies(input_data, n_samples, outliers_fraction, model_name)

    # Debugging: Check anomaly label counts
    print("Anomaly Label Counts:", df["Anomaly_Label"].value_counts())

    # Top 10 anomalies
    top_10 = df[df["Anomaly_Label"] == "Anomaly"].head(10)

    if top_10.empty:
        print("No anomalies found in Top 10 Anomalies.")
        top_10 = pd.DataFrame({"Message": ["No anomalies found"]})

    # Middle 10 (mixed records)
    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)

    return top_10, middle_10, bottom_10

# Function to plot scatter plots
def plot_interactive_feature_scatter(input_data, feature_x, feature_y, n_samples):
    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]

    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()

# Gradio Interface
with gr.Blocks() as demo:
    gr.Markdown("## 🕵️‍♀️ Anomaly Detection App 🕵️‍♂️")

    # Interactive Feature Scatter Plot
    gr.Markdown("### 1. 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=10, maximum=10000, step=25, 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("### 2. Compare Anomaly Detection Algorithms")
    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 = []
    with gr.Row():
        for model_name in input_models:
            plot = gr.Plot(label=model_name)
            plots.append((model_name, plot))

    def update_anomaly_comparison(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

    anomaly_inputs = [input_data, outliers_fraction, n_samples]
    anomaly_outputs = [plot for _, plot in plots]
    input_data.change(fn=update_anomaly_comparison, inputs=anomaly_inputs, outputs=anomaly_outputs)
    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)

    # Example Anomaly Records
    gr.Markdown("### 3. Example Anomaly Records")
    model_dropdown = gr.Dropdown(choices=input_models, value="Isolation Forest", label="Select Model")
    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, model_dropdown],
        outputs=[top_table, middle_table, bottom_table],
    )

demo.launch(debug=True)