Create app.py

app.py

@@ -0,0 +1,330 @@
+import os
+import pandas as pd
+import numpy as np
+import seaborn as sns
+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
+
+def main():
+    st.set_page_config(layout="wide")
+
+    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, width=150) #,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
+                        )
+
+        # Additional section below the option menu
+        # st.markdown("---")  # Add a separator line
+        st.header("Settings")
+        
+        num_lines = st.number_input("% of lines to be processed:", min_value=0, max_value=100, value=100)
+        graph_select = st.checkbox("Show Graphics", value= True)
+        feat_imp_select = st.checkbox("Feature Importance", value= False)
+
+        # Define the options for the dropdown list
+        numclusters = [2, 3, 4, 5, 6]
+        selected_clusters = st.slider("Choose a number of clusters", min_value=2, max_value=10, value=4)
+        
+        p_remove_multicollinearity = st.checkbox("Remove Multicollinearity", value=False)
+        p_multicollinearity_threshold = st.slider("Choose multicollinearity thresholds", min_value=0.0, max_value=1.0, value=0.9)
+        # p_remove_outliers = st.checkbox("Remove Outliers", value=False)
+        # p_outliers_method = st.selectbox ("Choose an Outlier Method", ["iforest", "ee", "lof"])
+        p_transformation = st.checkbox("Choose Power Transform", value = False)
+        p_normalize = st.checkbox("Choose Normalize", value = False)
+        p_pca = st.checkbox("Choose PCA", value = False)
+        p_pca_method = st.selectbox ("Choose a PCA Method", ["linear", "kernel", "incremental"])
+
+    st.title('ITACA Insurance Core AI Module')
+
+    #col1, col2 = st.columns(2)
+
+    if page == "Clustering Analysis":
+        #with col1:
+        st.header('Clustering Analysis')
+
+        st.write(
+            """
+            """
+        )
+        # import pycaret unsupervised models
+        from pycaret.clustering import setup, create_model, assign_model, pull, plot_model
+        # import ClusteringExperiment
+        from pycaret.clustering import ClusteringExperiment
+
+        # Display the list of CSV files
+        directory = "./"
+        all_files = os.listdir(directory)
+        # Filter files to only include CSV files
+        csv_files = [file for file in all_files if file.endswith(".csv")]
+        # Select a CSV file from the list
+        selected_csv = st.selectbox("Select a CSV file from the list", ["None"] + csv_files)
+
+        # 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)
+
+        # Read and display the CSV file
+        if selected_csv != "None" or uploaded_file is not None:
+            if uploaded_file:
+                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')
+            else:
+                insurance_claims = pd.read_csv(selected_csv)
+
+            num_rows = int(insurance_claims.shape[0]*(num_lines)/100)
+            insurance_claims_reduced = insurance_claims.head(num_rows)
+            st.write("Rows to be processed: " + str(num_rows))
+
+            all_columns = insurance_claims_reduced.columns.tolist()
+            selected_columns = st.multiselect("Choose columns", all_columns, default=all_columns)
+            insurance_claims_reduced = insurance_claims_reduced[selected_columns].copy()
+        
+            with st.expander("Inference Description", expanded=True):
+                insurance_claims_reduced.describe().T
+
+            with st.expander("Head Map", expanded=True):
+                cat_col = insurance_claims_reduced.select_dtypes(include=['object']).columns
+                num_col = insurance_claims_reduced.select_dtypes(exclude=['object']).columns
+
+                # insurance_claims[num_col].hist(bins=15, figsize=(20, 15), layout=(5, 4))
+                # Calculate the correlation matrix
+                corr_matrix = insurance_claims_reduced[num_col].corr()
+                # Create a Matplotlib figure
+                fig, ax = plt.subplots(figsize=(12, 8))
+                # Create a heatmap using seaborn
+                #st.header("Heat Map")
+                sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt='.2f', ax=ax)
+                # Set the title for the heatmap
+                ax.set_title('Correlation Heatmap')
+                # Display the heatmap in Streamlit
+                st.pyplot(fig)
+
+            if st.button("Prediction"):
+                #insurance_claims_reduced = insurance_claims_reduced[selected_columns].copy()
+                
+                s = setup(insurance_claims_reduced, session_id = 123, remove_multicollinearity=p_remove_multicollinearity, multicollinearity_threshold=p_multicollinearity_threshold,
+                        # remove_outliers=p_remove_outliers, outliers_method=p_outliers_method, 
+                        transformation=p_transformation, 
+                        normalize=p_normalize, pca=p_pca, pca_method=p_pca_method)
+                exp_clustering = ClusteringExperiment()
+                # init setup on exp
+                exp_clustering.setup(insurance_claims_reduced, session_id = 123)
+
+                with st.spinner("Analyzing..."):
+                    #with col2:
+                    #st.markdown("<br><br><br><br>", unsafe_allow_html=True)
+                    # train kmeans model
+                    cluster_model = create_model(selected_model, num_clusters = selected_clusters)
+
+                    cluster_model_2 = assign_model(cluster_model)
+                    # Calculate summary statistics for each cluster
+                    cluster_summary = cluster_model_2.groupby('Cluster').agg(['count', 'mean', 'median', 'min', 'max', 
+                                                                                'std', 'var', 'sum', ('quantile_25', lambda x: x.quantile(0.25)), 
+                                                                                ('quantile_75', lambda x: x.quantile(0.75)), 'skew'])
+                    
+                    with st.expander("Cluster Summary", expanded=False):
+                        #st.header("Cluster Summary")
+                        cluster_summary
+
+                    with st.expander("Model Assign", expanded=False):
+                        #st.header("Assign Model")
+                        cluster_model_2
+
+                    # all_metrics = get_metrics()
+                    # all_metrics
+
+                    with st.expander("Clustering Metrics", expanded=False):
+                        #st.header("Clustering Metrics")
+                        cluster_results = pull()
+                        cluster_results
+
+                    with st.expander("Clustering Plots", expanded=False):
+                        if graph_select:
+                            #st.header("Clustering Plots")
+                            # 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')  
+
+                    with st.expander("Feature Importance", expanded=False):
+                        # Create a Classification Model to extract feature importance
+                        if graph_select and feat_imp_select:
+                            #st.header("Feature Importance")
+                            from pycaret.classification import setup, create_model, get_config
+                            s = setup(cluster_model_2, target = 'Cluster')
+                            lr = create_model('lr')
+                            
+                            # this is how you can recreate the table
+                            feat_imp = pd.DataFrame({'Feature': get_config('X_train').columns, 'Value' : abs(lr.coef_[0])}).sort_values(by='Value', ascending=False)
+                            # sort by feature importance value and filter top 10
+                            feat_imp = feat_imp.sort_values(by='Value', ascending=False).head(10)
+                            # Display the filtered table in Streamlit
+                            # st.dataframe(feat_imp)
+                            # Display the filtered table as a bar chart in Streamlit
+                            st.bar_chart(feat_imp.set_index('Feature'))
+
+    elif page == "Anomaly Detection":
+        #with col1:
+        st.header('Anomaly Detection')
+
+        st.write(
+            """
+            """
+        )
+
+        # import pycaret anomaly
+        from pycaret.anomaly import setup, create_model, assign_model, pull, plot_model
+        # import AnomalyExperiment
+        from pycaret.anomaly import AnomalyExperiment
+
+        # Display the list of CSV files
+        directory = "./"
+        all_files = os.listdir(directory)
+        # Filter files to only include CSV files
+        csv_files = [file for file in all_files if file.endswith(".csv")]
+        # Select a CSV file from the list
+        selected_csv = st.selectbox("Select a CSV file from the list", ["None"] + csv_files)
+        
+        # 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 selected_csv != "None" or uploaded_file is not None:
+            if uploaded_file:
+                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')
+            else:
+                insurance_claims = pd.read_csv(selected_csv)
+
+            num_rows = int(insurance_claims.shape[0]*(num_lines)/100)
+            insurance_claims_reduced = insurance_claims.head(num_rows)
+            st.write("Rows to be processed: " + str(num_rows))
+
+            all_columns = insurance_claims_reduced.columns.tolist()
+            selected_columns = st.multiselect("Choose columns", all_columns, default=all_columns)
+            insurance_claims_reduced = insurance_claims_reduced[selected_columns].copy()
+
+            with st.expander("Inference Description", expanded=True):
+                insurance_claims_reduced.describe().T
+
+            with st.expander("Head Map", expanded=True):
+                cat_col = insurance_claims_reduced.select_dtypes(include=['object']).columns
+                num_col = insurance_claims_reduced.select_dtypes(exclude=['object']).columns
+
+                # insurance_claims[num_col].hist(bins=15, figsize=(20, 15), layout=(5, 4))
+                # Calculate the correlation matrix
+                corr_matrix = insurance_claims_reduced[num_col].corr()
+                # Create a Matplotlib figure
+                fig, ax = plt.subplots(figsize=(12, 8))
+                # Create a heatmap using seaborn
+                #st.header("Heat Map")
+                sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt='.2f', ax=ax)
+                # Set the title for the heatmap
+                ax.set_title('Correlation Heatmap')
+                # Display the heatmap in Streamlit
+                st.pyplot(fig)
+            
+            if st.button("Prediction"):
+            
+                s = setup(insurance_claims_reduced, session_id = 123, remove_multicollinearity=p_remove_multicollinearity, multicollinearity_threshold=p_multicollinearity_threshold,
+                            # remove_outliers=p_remove_outliers, outliers_method=p_outliers_method, 
+                            transformation=p_transformation, 
+                            normalize=p_normalize, pca=p_pca, pca_method=p_pca_method)
+
+                exp_anomaly = AnomalyExperiment()
+                # init setup on exp
+                exp_anomaly.setup(insurance_claims_reduced, session_id = 123)
+            
+                with st.spinner("Analyzing..."):
+                    #with col2:
+                    #st.markdown("<br><br><br><br>", unsafe_allow_html=True)
+                    # train model
+                    anomaly_model = create_model(selected_model)
+
+                    with st.expander("Assign Model", expanded=False):
+                        #st.header("Assign Model")
+                        anomaly_model_2 = assign_model(anomaly_model)
+                        anomaly_model_2
+
+                    with st.expander("Anomaly Metrics", expanded=False):
+                        #st.header("Anomaly Metrics")
+                        anomaly_results = pull()
+                        anomaly_results
+
+                    with st.expander("Anomaly Plots", expanded=False):
+                        if graph_select:
+                            # plot
+                            #st.header("Anomaly Plots")
+                            plot_model(anomaly_model, plot = 'tsne', display_format = 'streamlit')
+                            plot_model(anomaly_model, plot = 'umap', display_format = 'streamlit')
+
+                    with st.expander("Feature Importance", expanded=False):
+                        if graph_select and feat_imp_select:
+                            # Create a Classification Model to extract feature importance
+                            #st.header("Feature Importance")
+                            from pycaret.classification import setup, create_model, get_config
+                            s = setup(anomaly_model_2, target = 'Anomaly')
+                            lr = create_model('lr')
+                            # this is how you can recreate the table
+                            feat_imp = pd.DataFrame({'Feature': get_config('X_train').columns, 'Value' : abs(lr.coef_[0])}).sort_values(by='Value', ascending=False)
+                            # sort by feature importance value and filter top 10
+                            feat_imp = feat_imp.sort_values(by='Value', ascending=False).head(10)
+                            # Display the filtered table in Streamlit
+                            # st.dataframe(feat_imp)
+                            # Display the filtered table as a bar chart in Streamlit
+                            st.bar_chart(feat_imp.set_index('Feature'))
+try:
+    main()
+except Exception as e:
+    st.sidebar.error(f"An error occurred: {e}")