Spaces:
Runtime error
Runtime error
| 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 | |
| with open('kmeans_model.pkl', 'rb') as file: | |
| kmeans = pickle.load(file) | |
| with open('scaler.pkl', 'rb') as file: | |
| scaler = pickle.load(file) | |
| 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=cluster_summary, | |
| inputs=[], | |
| outputs=[ | |
| gr.Dataframe(label="Cluster Summary"), | |
| gr.Image(label="Customer Distribution Across Clusters"), | |
| gr.Image(label="Spending Score Distribution Across Clusters") | |
| ], | |
| live=True | |
| ) | |
| # Launch the interface | |
| iface.launch() | |