File size: 5,657 Bytes
def2fa3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib as mpl
import pycaret
import streamlit as st
from streamlit_option_menu import option_menu
import PIL
from PIL import Image
from PIL import ImageColor
from PIL import ImageDraw
from PIL import ImageFont

hide_streamlit_style = """
            <style>
            #MainMenu {visibility: hidden;}
            footer {visibility: hidden;}
            </style>
            """
st.markdown(hide_streamlit_style, unsafe_allow_html=True)

with st.sidebar:
    image = Image.open('./itaca_logo.png')
    st.image(image,use_column_width=True)
    page = option_menu(menu_title='Menu',
                       menu_icon="robot",
                       options=["Clustering Analysis",
                                "Anomaly Detection"],
                       icons=["chat-dots",
                              "key"],
                       default_index=0
                       )

st.title('ITACA Insurance Core AI Module')

if page == "Clustering Analysis":
    st.header('Clustering Analysis')

    st.write(
        """
        """
    )

    # import pycaret unsupervised models
    from pycaret.clustering import *
    # import ClusteringExperiment
    from pycaret.clustering import ClusteringExperiment

    # Upload the CSV file
    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")

    # Define the unsupervised model
    clusteringmodel = ['kmeans', 'ap', 'meanshift', 'sc', 'hclust', 'dbscan', 'optics', 'birch']
    selected_model = st.selectbox("Choose a clustering model", clusteringmodel)

    # Define the options for the dropdown list
    numclusters = [2, 3, 4, 5, 6]
    # selected_clusters = st.selectbox("Choose a number of clusters", numclusters)
    selected_clusters = st.slider("Choose a number of clusters", min_value=2, max_value=10, value=4)

    
    # Read and display the CSV file
    if uploaded_file is not None:
        try:
            delimiter = ','
            insurance_claims = pd.read_csv (uploaded_file, sep=delimiter)
        except ValueError:
            delimiter = '|'
            insurance_claims = pd.read_csv (uploaded_file, sep=delimiter, encoding='latin-1')
        
        s = setup(insurance_claims, session_id = 123, log_experiment='mlflow', experiment_name='fraud_detection')

        exp_clustering = ClusteringExperiment()

        # init setup on exp
        exp_clustering.setup(insurance_claims, session_id = 123)

        if st.button("Prediction"):
            with st.spinner("Analyzing..."):
                # train kmeans model
                cluster_model = create_model(selected_model, num_clusters = selected_clusters)

                cluster_model_2 = assign_model(cluster_model)
                cluster_model_2

                all_metrics = get_metrics()
                all_metrics

                cluster_results = pull()
                cluster_results

                # plot pca cluster plot 
                plot_model(cluster_model, plot = 'cluster', display_format = 'streamlit')
                
                if selected_model != 'ap':
                    plot_model(cluster_model, plot = 'tsne', display_format = 'streamlit')
                
                if selected_model not in ('ap', 'meanshift', 'dbscan', 'optics'):
                    plot_model(cluster_model, plot = 'elbow', display_format = 'streamlit')
                
                if selected_model not in ('ap', 'meanshift', 'sc', 'hclust', 'dbscan', 'optics'):
                    plot_model(cluster_model, plot = 'silhouette', display_format = 'streamlit')
                
                if selected_model not in ('ap', 'sc', 'hclust', 'dbscan', 'optics', 'birch'):
                    plot_model(cluster_model, plot = 'distance', display_format = 'streamlit')
                
                if selected_model != 'ap':
                    plot_model(cluster_model, plot = 'distribution', display_format = 'streamlit')  

elif page == "Anomaly Detection":
    st.header('Anomaly Detection')

    st.write(
        """
        """
    )

    # import pycaret anomaly
    from pycaret.anomaly import *
    # import AnomalyExperiment
    from pycaret.anomaly import AnomalyExperiment

        # Upload the CSV file
    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")

    # Define the unsupervised model
    anomalymodel = ['abod', 'cluster', 'cof', 'iforest', 'histogram', 'knn', 'lof', 'svm', 'pca', 'mcd', 'sod', 'sos']
    selected_model = st.selectbox("Choose an anomaly model", anomalymodel)

    # Read and display the CSV file
    if uploaded_file is not None:
        try:
            delimiter = ','
            insurance_claims = pd.read_csv (uploaded_file, sep=delimiter)
        except ValueError:
            delimiter = '|'
            insurance_claims = pd.read_csv (uploaded_file, sep=delimiter, encoding='latin-1')
        
        s = setup(insurance_claims, session_id = 123)

        exp_anomaly = AnomalyExperiment()

        # init setup on exp
        exp_anomaly.setup(insurance_claims, session_id = 123)

        if st.button("Prediction"):
            with st.spinner("Analyzing..."):
                # train model
                anomaly_model = create_model(selected_model)

                anomaly_model_2 = assign_model(anomaly_model)
                anomaly_model_2

                anomaly_results = pull()
                anomaly_results

                # plot
                plot_model(anomaly_model, plot = 'tsne', display_format = 'streamlit')
                plot_model(anomaly_model, plot = 'umap', display_format = 'streamlit')