Create app.py

app.py

@@ -0,0 +1,73 @@
+import pandas as pd
+import gradio as gr
+import matplotlib.pyplot as plt
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+
+# Load dataset
+df = pd.read_csv('/content/nlp_test_data_final.csv')
+
+def recommend_courses(user_skills, user_level, df):
+    # Combine prerequisites and difficulty into a single feature
+    df['combined_features'] = df['Prerequisites'].fillna('') + ', ' + df['course_difficulty'].fillna('')
+    
+    # Convert text data into numerical format using TF-IDF
+    vectorizer = TfidfVectorizer()
+    tfidf_matrix = vectorizer.fit_transform(df['combined_features'])
+    
+    # Transform user input into the same format
+    user_input = ', '.join(user_skills) + ', ' + user_level
+    user_vector = vectorizer.transform([user_input])
+    
+    # Compute cosine similarity using TF-IDF
+    similarities_tfidf = cosine_similarity(user_vector, tfidf_matrix).flatten()
+    
+    # Sentence BERT model for embeddings
+    model = SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2')
+    course_embeddings = model.encode(df['combined_features'].tolist(), convert_to_numpy=True)
+    user_embedding = model.encode([user_input], convert_to_numpy=True)
+    
+    # FAISS for vector similarity search
+    index = faiss.IndexFlatL2(course_embeddings.shape[1])
+    index.add(course_embeddings)
+    _, similarities_faiss = index.search(user_embedding, len(df))
+    similarities_faiss = 1 / (1 + similarities_faiss.flatten())  # Convert distances to similarity scores
+    
+    # Store similarity scores
+    df['similarity_tfidf'] = similarities_tfidf
+    df['similarity_bert'] = similarities_bert = cosine_similarity(user_embedding, course_embeddings).flatten()
+    df['similarity_faiss'] = similarities_faiss
+    
+    # Sort by highest similarity score from any model
+    recommended_courses = df.sort_values(by=['similarity_tfidf', 'similarity_bert', 'similarity_faiss'], ascending=False).head(5)
+    
+    # Plot similarity scores
+    plt.figure(figsize=(8, 5))
+    plt.bar(['TF-IDF', 'Sentence-BERT', 'FAISS'], [max(similarities_tfidf), max(similarities_bert), max(similarities_faiss)])
+    plt.xlabel('Model')
+    plt.ylabel('Max Similarity Score')
+    plt.title('Comparison of Similarity Scores Across Models')
+    plt.savefig('/content/similarity_comparison.png')
+    
+    return recommended_courses[['course_title', 'course_organization', 'course_difficulty', 'course_rating', 'similarity_tfidf', 'similarity_bert', 'similarity_faiss']]
+
+def gradio_interface(user_skills, user_level):
+    user_skills_list = user_skills.split(', ')
+    recommended_courses = recommend_courses(user_skills_list, user_level, df)
+    return recommended_courses
+
+# Gradio UI
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.Textbox(label="Enter your skills (comma-separated)"), 
+        gr.Dropdown(["Beginner", "Intermediate", "Mixed"], label="Select Difficulty Level")
+    ],
+    outputs=gr.Dataframe(headers=["Course Title", "Organization", "Difficulty", "Rating", "TF-IDF Score", "BERT Score", "FAISS Score"], label="Recommended Courses")
+)
+
+if __name__ == "__main__":
+    iface.launch()