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 | |
| # Load the knowledge base | |
| 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 | |
| def preprocess_text(text): | |
| text = text.lower() # Lowercase | |
| text = re.sub(r'[^a-zA-Z\s]', '', text) # Remove special characters | |
| return text | |
| # Function to generate graphs for stories with similarity > 0.8 | |
| def generate_graphs(new_story): | |
| # Preprocess the new story | |
| new_story = preprocess_text(new_story) | |
| # Encode the new story | |
| new_story_vector = model.encode([new_story])[0] | |
| # Calculate similarity with knowledge base stories | |
| knowledge_base_vectors = encoded_df.iloc[:, :-7].values # Exclude 'likesCount' | |
| similarities = cosine_similarity([new_story_vector], knowledge_base_vectors)[0] | |
| # Filter indices with similarity > 0.8 | |
| similar_indexes = np.where(similarities > 0.85)[0] | |
| if len(similar_indexes) == 0: | |
| return None, "No stories have a similarity > 0.85." | |
| # Get likesCount for stories with similarity > 0.8 | |
| likes_distribution = encoded_df.iloc[similar_indexes]['likesCount'].values | |
| story_labels = [f"Story {i+1}" for i in similar_indexes] | |
| # Plot similarity distribution for all similar stories | |
| plt.figure(figsize=(10, 6)) | |
| sns.kdeplot(new_story_vector, shade=False, label="New Story", color='blue', linewidth=2) | |
| for idx in similar_indexes: | |
| most_similar_vector = encoded_df.iloc[idx, :-7].values | |
| sns.kdeplot(most_similar_vector, shade=False, label=f"Story {idx+1}", alpha=0.5) | |
| plt.title("Similarity Distribution: New Story vs Similar Stories", fontsize=14) | |
| plt.xlabel("Vector Values", fontsize=12) | |
| plt.ylabel("Density", fontsize=12) | |
| plt.legend(title="Stories") | |
| sim_dist_plot = plt.gcf() | |
| # Create a bar graph for likes distribution | |
| plt.figure(figsize=(10, 6)) | |
| sns.barplot(x=story_labels, y=likes_distribution, palette="viridis") | |
| plt.title("LikesCount Distribution for Similar Stories", fontsize=14) | |
| plt.xlabel("Story Index (Similarity > 0.8)", fontsize=12) | |
| plt.ylabel("LikesCount", fontsize=12) | |
| plt.xticks(rotation=90) | |
| likes_dist_plot = plt.gcf() | |
| return sim_dist_plot, likes_dist_plot | |
| # Gradio interface | |
| def gradio_interface(new_story): | |
| sim_dist_plot, likes_dist_plot = generate_graphs(new_story) | |
| if sim_dist_plot is None: | |
| return "No stories have a similarity > 0.8.", None | |
| return sim_dist_plot, likes_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(label="Similarity Distribution"), gr.Plot(label="Likes Distribution")], | |
| title="Story Similarity and Likes Analysis", | |
| description="Enter a new story to compare with the knowledge base. " | |
| "View similarity distributions and likes of stories with similarity > 0.8." | |
| ) | |
| # Launch the interface | |
| iface.launch(share=True) | |