Update app.py

app.py

@@ -4,26 +4,12 @@ import seaborn as sns
 import numpy as np
 import pickle
 import matplotlib.pyplot as plt
-from data_preparation import preprocess_data
-from clustering import perform_clustering, plot_clusters
+from data_preparation import preprocess_data,data_imp
+from clustering import perform_clustering, plot_clusters,,summarize_cluster_characteristics
 from feature_selection import select_features_pca, select_features_rfe, select_features_rf
 from sklearn.preprocessing import StandardScaler
-feature_descriptions = {
-    "CustID": "Unique identifier for each customer.",
-    "FirstPolYear": "Year when the customer first bought an insurance policy.",
-    "BirthYear": "Birth year of the customer, used to calculate age.",
-    "EducDeg": "Highest educational degree obtained by the customer.",
-    "MonthSal": "Monthly salary of the customer. (Numerical, float64)",
-    "GeoLivArea": "Geographical area where the customer lives.",
-    "Children": "Number of children the customer has.",
-    "CustMonVal": "Total monetary value of the customer to the company.",
-    "ClaimsRate": "Rate at which the customer files insurance claims.",
-    "PremMotor": "Premium amount for motor insurance.",
-    "PremHousehold": "Premium amount for household insurance.",
-    "PremHealth": "Premium amount for health insurance.",
-    "PremLife": "Premium amount for life insurance.",
-    "PremWork": "Premium amount for work insurance."
-}
+
+feature_descriptions,insurance_defaults,banking_defaults,retail_defaults=data_imp()
 
 def load_data(dataset_choice):
     if dataset_choice == "Insurance":
@@ -33,13 +19,6 @@ def load_data(dataset_choice):
     elif dataset_choice == "Banking":
         data = pd.read_csv('bankingdata.csv', encoding='latin1')
     return data
-    
-    return data
-# Function to summarize cluster characteristics
-def summarize_cluster_characteristics(clustered_data, labels, cluster_number):
-    cluster_data = clustered_data[labels == cluster_number]
-    summary = cluster_data.mean().to_dict()
-    return summary
 
 # Function to display Business Understanding section
 def display_business_understanding():
@@ -70,8 +49,9 @@ def display_dataset_selection():
     if dataset_choice=="Insurance":
         st.write(feature_descriptions)
     return data
+    
 # Function to display Modeling & Evaluation section
-def display_modeling_evaluation():
+def display_modeling_evaluation(insurance_defaults,banking_defaults,retail_defaults):
     dataset_choice = st.selectbox("Select Dataset", ("Insurance", "Retail", "Banking"))
     data = load_data(dataset_choice)
     data = preprocess_data(data)
@@ -119,7 +99,18 @@ def display_modeling_evaluation():
         with st.form(key='prediction_form'):
             user_input = {}
             for feature in st.session_state.selected_features:
-                user_input[feature] = st.number_input(f'Enter {feature}', value=0.0)
+                
+                # Set default values based on the dataset choice
+                if dataset_choice == "Insurance":
+                    default_value = insurance_defaults.get(feature, 0.0)
+                elif dataset_choice == "Banking":
+                    default_value = banking_defaults.get(feature, 0.0)
+                elif dataset_choice == "Retail":
+                    default_value = retail_defaults.get(feature, 0.0)
+                else:
+                    default_value = 0.0
+
+                user_input[feature] = st.number_input(f'Enter {feature}', value=default_value)
 
             submit_button = st.form_submit_button(label='Predict')