Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import numpy as np | |
| import seaborn as sns | |
| import matplotlib.pyplot as plt | |
| from sklearn.metrics.pairwise import cosine_similarity | |
| from sentence_transformers import SentenceTransformer | |
| import pandas as pd | |
| import re | |
| encoded_df = pd.read_csv('encoded_df.csv').drop(columns=['Unnamed: 0']) | |
| # Initialize the Sentence Transformer model | |
| model = SentenceTransformer('all-MiniLM-L6-v2') | |
| # Function to preprocess text (if required) | |
| def preprocess_text(text): | |
| # Your text preprocessing logic here (e.g., lowercasing, removing special characters) | |
| text.lower() # Placeholder for text preprocessing | |
| text = re.sub(r'[^a-zA-Z\s]', '', text) | |
| return text | |
| # Function to generate the graphs | |
| def generate_graphs(new_story): | |
| # Preprocess the new story | |
| new_story = preprocess_text(new_story) | |
| global model | |
| # Encode the new story | |
| new_story_vector = model.encode([new_story])[0] | |
| # Calculate the similarity with all existing stories in the knowledge base | |
| knowledge_base_vectors = encoded_df.iloc[:, :-1].values # Exclude 'likesCount' | |
| print(f"New Story Vector Shape: {new_story_vector.shape}") | |
| print(f"Knowledge Base Vector Shape: {knowledge_base_vectors.shape}") | |
| similarities = cosine_similarity([new_story_vector], knowledge_base_vectors) | |
| # Find the indices of the 5 most similar stories | |
| top_5_indices = np.argsort(similarities[0])[::-1][:5] # Sort similarities and get top 5 | |
| # Retrieve the LikesCount for the top 5 most similar stories | |
| likes_distribution = encoded_df.iloc[top_5_indices]['likesCount'].values | |
| sorted_likes_distribution = sorted(likes_distribution, reverse=True) | |
| # Create a bar graph for the distribution of the 5 most similar stories | |
| plt.figure(figsize=(10, 6)) | |
| sns.barplot(x=[f"Story {i+1}" for i in range(5)], y=sorted_likes_distribution, palette="viridis") | |
| plt.title("LikesCount Distribution for the 5 Most Similar Stories", fontsize=14) | |
| plt.xlabel("Story Similarity (Most Similar to Least)", fontsize=12) | |
| plt.ylabel("LikesCount", fontsize=12) | |
| likes_dist_plot = plt.gcf() | |
| # Plot the similarity distribution for the 5 most similar stories | |
| plt.figure(figsize=(10, 6)) | |
| sns.kdeplot([new_story_vector], shade=False, label="New Story", color='blue') | |
| for i in top_5_indices: | |
| most_similar_vector = encoded_df.iloc[i, :-1].values | |
| sns.kdeplot(most_similar_vector, shade=False, label=f"Most Similar Story: {top_5_indices.tolist().index(i)+1}", alpha=0.5) | |
| plt.title("Similarity Distribution of New Story and Top 5 Similar Stories", fontsize=14) | |
| plt.xlabel("Value", fontsize=12) | |
| plt.ylabel("Density", fontsize=12) | |
| plt.legend(title="Stories") | |
| sim_dist_plot = plt.gcf() | |
| return sim_dist_plot,likes_dist_plot | |
| # Gradio interface | |
| def gradio_interface(new_story): | |
| # Generate and return both plots | |
| likes_dist_plot, sim_dist_plot = generate_graphs(new_story) | |
| return likes_dist_plot, sim_dist_plot | |
| # Create the Gradio interface | |
| iface = gr.Interface( | |
| fn=gradio_interface, | |
| inputs=gr.Textbox(label="Enter a story", lines=10, placeholder="Enter the story here..."), | |
| outputs=[gr.Plot(), gr.Plot()], | |
| title="Story Similarity and Likes Distribution", | |
| description="Enter a new story to compare it with the knowledge base and get analytics on similarity and likes distribution of the most similar stories." | |
| ) | |
| # Launch the interface | |
| iface.launch(share=True) | |