Upload folder using huggingface_hub

main.py

@@ -5,9 +5,9 @@ import cohere
 import requests
 from bs4 import BeautifulSoup
 from sklearn.cluster import KMeans
-import matplotlib.pyplot as plt
 from sklearn.decomposition import PCA
 import numpy as np
+import plotly.express as px
 
 # Load the API key from the .env file
 load_dotenv()
@@ -54,43 +54,31 @@ def cluster_urls(urls, num_clusters):
         clusters[empty_cluster].append(clusters[max_cluster].pop())
 
     # Plotting the clusters
-    plot_path = plot_clusters(embeddings, labels, url_list, num_clusters)
+    plot = plot_clusters(embeddings, labels, url_list, num_clusters)
 
-    return clusters, plot_path
+    return clusters, plot
 
 def plot_clusters(embeddings, labels, url_list, num_clusters):
     # Reduce dimensions for visualization using PCA
     pca = PCA(n_components=2)
     reduced_embeddings = pca.fit_transform(embeddings)
 
-    # Create a scatter plot
-    plt.figure(figsize=(10, 7))
-    colors = plt.cm.rainbow(np.linspace(0, 1, num_clusters))
+    # Create a scatter plot using Plotly
+    fig = px.scatter(
+        x=reduced_embeddings[:, 0],
+        y=reduced_embeddings[:, 1],
+        color=labels,
+        labels={'color': 'Cluster'},
+        hover_data={'URL': url_list},
+        title='URL Clustering',
+    )
 
-    for i in range(num_clusters):
-        cluster_points = reduced_embeddings[np.array(labels) == i]
-        plt.scatter(cluster_points[:, 0], cluster_points[:, 1], label=f'Cluster {i+1}', color=colors[i])
-
-    for i, url in enumerate(url_list):
-        plt.annotate(f'URL {i+1}', (reduced_embeddings[i, 0], reduced_embeddings[i, 1]))
-
-    plt.title('URL Clustering')
-    plt.xlabel('PCA Component 1')
-    plt.ylabel('PCA Component 2')
-    plt.legend()
-    plt.grid(True)
-    
-    # Save the plot to a file
-    plot_path = 'clustering_plot.png'
-    plt.savefig(plot_path)
-    plt.close()
-
-    return plot_path
+    return fig
 
 # Create a Gradio interface
 def gradio_interface(urls, num_clusters):
-    clusters, plot_path = cluster_urls(urls, num_clusters)
-    return clusters, plot_path
+    clusters, plot = cluster_urls(urls, num_clusters)
+    return clusters, plot
 
 inputs = [
     gr.Textbox(label='URLs', lines=5, 
@@ -107,7 +95,7 @@ inputs = [
 ]
 output = [
     gr.JSON(label='Clusters'),
-    gr.Image(label='Clustering Plot')
+    gr.Plot(label='Clustering Plot')
 ]
 
 interface = gr.Interface(