Create app_copy.py

app_copy.py

@@ -0,0 +1,160 @@
+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')