Update app.py

app.py

@@ -7,81 +7,78 @@ 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 (if required)
+
+# Function to preprocess text
 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)
+    text = text.lower()  # Lowercase
+    text = re.sub(r'[^a-zA-Z\s]', '', text)  # Remove special characters
     return text
 
-# Function to generate the graphs
+# 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)
 
-    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
+    # Calculate similarity with knowledge base stories
     knowledge_base_vectors = encoded_df.iloc[:, :-7].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)
+    similarities = cosine_similarity([new_story_vector], knowledge_base_vectors)[0]
 
-    # Find the indices of the 5 most similar stories
-    top_5_indices = np.argsort(similarities[0])[::-1][:5]  # Sort similarities and get top 5
+    # Filter indices with similarity > 0.8
+    similar_indexes = np.where(similarities > 0.8)[0]
 
-    likes_distribution=[]
-    for i in top_5_indices:
-        print(f"Row {i+1}: Similarity = {similarities[0][i]:.4f}, LikesCount = {encoded_df.iloc[i]['likesCount']}")
-        likes_distribution.append(encoded_df.iloc[i]['likesCount'].astype(int))
-
-    # 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')
+    if len(similar_indexes) == 0:
+        return None, "No stories have a similarity > 0.85."
 
-    for i in top_5_indices:
-        most_similar_vector = encoded_df.iloc[i, :-7].values
-        sns.kdeplot(most_similar_vector, shade=False, label=f"Most Similar Story: {top_5_indices.tolist().index(i)+1}", alpha=0.5)
+    # 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]
 
-    plt.title("Similarity Distribution of New Story and Top 5 Similar Stories", fontsize=14)
-    plt.xlabel("Value", fontsize=12)
+    # 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 the distribution of the 5 most similar stories
-    # top_5_stories = [0,1,2,3,4]
+
+    # Create a bar graph for likes distribution
     plt.figure(figsize=(10, 6))
-    sns.barplot(x=[f"Story {i+1}" for i in range(5)], y=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)
+    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
+    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
+    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(), 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."
+    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