app.py

import numpy as np
import matplotlib.pyplot as plt
from threading import Thread
from matplotlib.colors import ListedColormap
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.datasets import make_blobs, make_circles, make_moons
import gradio as gr
import math
from functools import partial
import time

import matplotlib

from sklearn import svm
from sklearn.datasets import make_moons, make_blobs
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

def get_groundtruth_model(X, labels):
    # dummy model to show true label distribution
    class Dummy:
        def __init__(self, y):
            self.labels_ = labels

    return Dummy(labels)

#### PLOT
FIGSIZE = 10,10
figure = plt.figure(figsize=(25, 10))


def train_models(input_data,  outliers_fraction, n_samples, clf_name):
    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)
    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),
    }   
    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),
    }
    DATASETS = [
    make_blobs(centers=[[0, 0], [0, 0]], cluster_std=0.5, **blobs_params)[0],
    make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[0.5, 0.5], **blobs_params)[0],
    make_blobs(centers=[[2, 2], [-2, -2]], cluster_std=[1.5, 0.3], **blobs_params)[0],
    4.0
    * (
        make_moons(n_samples=n_samples, noise=0.05, random_state=0)[0]
        - np.array([0.5, 0.25])
    ),
    14.0 * (np.random.RandomState(42).rand(n_samples, 2) - 0.5),
    ]
    
    xx, yy = np.meshgrid(np.linspace(-7, 7, 150), np.linspace(-7, 7, 150))
    clf = NAME_CLF_MAPPING[clf_name]
    plt.figure(figsize=(len(NAME_CLF_MAPPING) * 2 + 4, 12.5))


    plot_num = 1
    rng = np.random.RandomState(42)
    X = DATA_MAPPING[input_data]
    X = np.concatenate([X, rng.uniform(low=-6, high=6, size=(n_outliers, 2))], axis=0)
    
    t0 = time.time()
    clf.fit(X)
    t1 = time.time()
    # fit the data and tag outliers
    if clf_name == "Local Outlier Factor":
        y_pred = clf.fit_predict(X)
    else:
        y_pred = clf.fit(X).predict(X)

    # plot the levels lines and the points
    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=10, colors="black")

    colors = np.array(["#377eb8", "#ff7f00"])
    plt.scatter(X[:, 0], X[:, 1], s=100, color=colors[(y_pred + 1) // 2])

    plt.xlim(-7, 7)
    plt.ylim(-7, 7)
    plt.xticks(())
    plt.yticks(())
    plt.text(
        0.99,
        0.01,
        ("%.2fs" % (t1 - t0)).lstrip("0"),
        transform=plt.gca().transAxes,
        size=60,
        horizontalalignment="right",
    )
    plot_num += 1

    return plt

description = "Learn how different anomaly detection algorithms perform in different datasets."

def iter_grid(n_rows, n_cols):
    # create a grid using gradio Block
    for _ in range(n_rows):
        with gr.Row():
            for _ in range(n_cols):
                with gr.Column():
                    yield

title = "🕵️‍♀️ compare anomaly detection algorithms 🕵️‍♂️"
with gr.Blocks() as demo:
    gr.Markdown(f"## {title}")
    gr.Markdown(description)

    input_models = ["Robust covariance","One-Class SVM","One-Class SVM (SGD)","Isolation Forest",
    "Local Outlier Factor"]
    input_data = gr.Radio(
        choices=["Central Blob", "Two Blobs", "Blob with Noise", "Moons", "Noise"],
        value="Moons"
    )
    n_samples = gr.Slider(minimum=100, maximum=500, step=25, label="Number of Samples")
    outliers_fraction = gr.Slider(minimum=0.1, maximum=0.9, step=0.1, label="Fraction of Outliers")
    counter = 0


    for _ in iter_grid(5, 5):
        if counter >= len(input_models):
            break

        input_model = input_models[counter]
        plot = gr.Plot(label=input_model)
        fn = partial(train_models, clf_name=input_model)
        input_data.change(fn=fn, inputs=[input_data, outliers_fraction, n_samples], outputs=plot)
        n_samples.change(fn=fn, inputs=[input_data, outliers_fraction, n_samples], outputs=plot)
        outliers_fraction.change(fn=fn, inputs=[input_data, outliers_fraction, n_samples], outputs=plot)
        counter += 1

demo.launch(enable_queue=True, debug=True)