Update app.py

app.py

@@ -1,6 +1,9 @@
 import gradio as gr
 import pickle
 import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
 from sklearn.preprocessing import StandardScaler
 from sklearn.cluster import KMeans
 
@@ -9,32 +12,56 @@ with open('kmeans_model.pkl', 'rb') as file:
 with open('scaler.pkl', 'rb') as file:
     scaler = pickle.load(file)
 
-def predict_spending_score(annual_income, family_size, work_experience):
-    df = pd.DataFrame({
-        'Annual Income ($)': [annual_income],
-        'Family Size': [family_size],
-        'Work Experience': [work_experience]
-    })
-    
-    df['Family_Income_Product'] = df['Family Size'] * df['Annual Income ($)']
-    df['Family_Income_Ratio'] = df['Family Size'] / (df['Annual Income ($)'] + 1e-5)
-    
-    features = df[['Annual Income ($)', 'Family Size', 'Family_Income_Product', 'Family_Income_Ratio']]
-    features_scaled = scaler.transform(features)
-    
-    
-    cluster = kmeans.predict(features_scaled)
-    return f'Cluster: {int(cluster[0])}'
+dataset_path = 'Customers.csv' 
+data = pd.read_csv(dataset_path)
+
+
+data['Family_Income_Product'] = data['Family Size'] * data['Annual Income ($)']
+data['Family_Income_Ratio'] = data['Family Size'] / (data['Annual Income ($)'] + 1e-5)
+
+features = data[['Annual Income ($)', 'Family Size', 'Family_Income_Product', 'Family_Income_Ratio']]
+features_scaled = scaler.transform(features)
+clusters = kmeans.predict(features_scaled)
+data['Cluster'] = clusters
+
+def plot_cluster_distribution():
+    plt.figure(figsize=(10, 6))
+    sns.countplot(data=data, x='Cluster', palette='viridis')
+    plt.title('Customer Distribution Across Clusters')
+    plt.xlabel('Cluster')
+    plt.ylabel('Number of Customers')
+    plt.tight_layout()
+    plt.savefig('/kaggle/working/cluster_distribution.png')
+    return '/kaggle/working/cluster_distribution.png'
+
+def plot_spending_score_distribution():
+    plt.figure(figsize=(10, 6))
+    sns.boxplot(data=data, x='Cluster', y='Spending Score (1-100)', palette='viridis')
+    plt.title('Spending Score Distribution Across Clusters')
+    plt.xlabel('Cluster')
+    plt.ylabel('Spending Score (1-100)')
+    plt.tight_layout()
+    plt.savefig('/kaggle/working/spending_score_distribution.png')
+    return '/kaggle/working/spending_score_distribution.png'
+
+def cluster_summary():
+    summary = data.groupby('Cluster').agg({
+        'Annual Income ($)': ['mean', 'std'],
+        'Family Size': ['mean', 'std'],
+        'Spending Score (1-100)': ['mean', 'std']
+    }).reset_index()
+    return summary.to_dict()
 
 iface = gr.Interface(
-    fn=predict_spending_score,
-    inputs=[
-        gr.Number(label="Annual Income ($)", value=50000),
-        gr.Number(label="Family Size", value=2),
-        gr.Number(label="Work Experience (years)", value=5)
+    fn=cluster_summary,
+    inputs=[],
+    outputs=[
+        gr.Dataframe(label="Cluster Summary"),
+        gr.Image(label="Customer Distribution Across Clusters"),
+        gr.Image(label="Spending Score Distribution Across Clusters")
     ],
-    outputs="text",
     live=True
 )
 
+# Launch the interface
 iface.launch()