File size: 2,977 Bytes
303f2f6
 
 
 
 
 
 
 
783a1d4
64eb9a6
 
fd886b3
64eb9a6
303f2f6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1fddda
6c5daeb
 
 
 
a1fddda
 
 
 
 
 
 
303f2f6
 
783a1d4
 
 
 
 
 
 
 
a1fddda
783a1d4
303f2f6
fd886b3
64eb9a6
 
 
 
783a1d4
6c5daeb
 
 
303f2f6
783a1d4
 
6c5daeb
 
 
 
303f2f6
783a1d4
a1fddda
 
303f2f6
a1fddda
6c5daeb
 
303f2f6
a1fddda
6c5daeb
a1fddda
 
6c5daeb
 
96f4763
64eb9a6
783a1d4
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
import os

import pandas as pd
from sklearn.ensemble import IsolationForest

import numpy as np
from sklearn.model_selection import train_test_split
import gradio as gr
import matplotlib.pyplot as plt
from skops import hub_utils
import pickle
import time



#Data preparation
n_samples, n_outliers = 120, 40
rng = np.random.RandomState(0)
covariance = np.array([[0.5, -0.1], [0.7, 0.4]])
cluster_1 = 0.4 * rng.randn(n_samples, 2) @ covariance + np.array([2, 2])  # general deformed cluster
cluster_2 = 0.3 * rng.randn(n_samples, 2) + np.array([-2, -2])  # spherical cluster
outliers = rng.uniform(low=-4, high=4, size=(n_outliers, 2))

X = np.concatenate([cluster_1, cluster_2, outliers]) #120+120+40 = 280 with 2D
y = np.concatenate(
    [np.ones((2 * n_samples), dtype=int), -np.ones((n_outliers), dtype=int)]
)

def load_hf_model_hub():
    '''
    Load the directory containing pretrained model  
    and files from the model repository
    '''
    repo_id="sklearn-docs/anomaly-detection"
    download_repo = "downloaded-model"
    hub_utils.download(repo_id=repo_id, dst=download_repo)
    time.sleep(2)
    loaded_model = pickle.load(open('./downloaded-model/isolation_forest.pkl', 'rb'))
    return loaded_model

#Visualize the data as a scatter plot

def visualize_input_data():
    fig = plt.figure(1, facecolor="w", figsize=(5, 5))
    scatter = plt.scatter(X[:, 0], X[:, 1], c=y, s=20, edgecolor="k")
    handles, labels = scatter.legend_elements()
    plt.axis("square")
    plt.legend(handles=handles, labels=["outliers", "inliers"], title="true class")
    plt.title("Gaussian inliers with \nuniformly distributed outliers")
    # plt.show()
    # plt.clear()
    return fig






title = " An example using IsolationForest for anomaly detection."
description1 = "The isolation forest is an Ensemble of Isolation trees and it isolates the datapoints using recursive random partitioning."
description2 = "In case of outliers the number of splits required is greater than those required for inliers."
description3 = "We will use the toy dataset as given in the scikit-learn page for Isolation Forest."

with gr.Blocks(title=title) as demo:
    
    gr.Markdown(f"# {title}")
    gr.Markdown(f"# {description1}")
    gr.Markdown(f"# {description2}")
    gr.Markdown(f"# {description3}")

    gr.Markdown(" **https://scikit-learn.org/stable/auto_examples/ensemble/plot_isolation_forest.html#sphx-glr-auto-examples-ensemble-plot-isolation-forest-py**")
    
    loaded_model = load_hf_model_hub()

    with gr.Tab("Visualize Input dataset"):
        btn = gr.Button(value="Visualize input dataset")
        btn.click(visualize_input_data, outputs= gr.Plot(label='Visualizing input dataset') )

    with gr.Tab("Plot Decision Boundary"):
        image_decision = gr.Image('./downloaded-model/decision_boundary.png')
    
    with gr.Tab("Plot Path"):
        image_path = gr.Image('./downloaded-model/plot_path.png')

    
    gr.Markdown( f"## Success")
demo.launch()