File size: 3,910 Bytes
ae4467e 586e301 ae4467e 586e301 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
import pandas as pd
from sentence_transformers import SentenceTransformer, util
from transformers import pipeline
import torch
import gradio as gr
import os
# Load the dataset
csv_file_path = os.path.join(os.getcwd(), 'Analytics_Vidhya_Free_Course_data.csv')
df = pd.read_csv(csv_file_path, encoding='Windows-1252')
df.fillna('', inplace=True)
# Load the pre-trained model for embeddings
model = SentenceTransformer('multi-qa-mpnet-base-dot-v1')
# Combine title and description to create a full text for each course
df['full_text'] = df.iloc[:, 0] + " " + df.iloc[:, 1] + " " + df['Instructor Name'] + " " + df['Rating'].astype(str) + " " + df['Category']
# Convert full course texts into embeddings
course_embeddings = model.encode(df['full_text'].tolist(), convert_to_tensor=True)
# Load a model for text generation (e.g., BART)
generator = pipeline('text2text-generation', model='facebook/bart-large-cnn')
def expand_query(query):
paraphraser = pipeline('text2text-generation', model='Vamsi/T5_Paraphrase_Paws')
expanded_queries = paraphraser(query, num_return_sequences=3, max_length=50, do_sample=True)
return [q['generated_text'] for q in expanded_queries]
def generate_description(query):
response = generator(query, max_length=100, num_return_sequences=1)
return response[0]['generated_text']
def search_courses(query, level_filter=None, category_filter=None, top_k=3):
expanded_queries = expand_query(query)
all_similarities = []
for expanded_query in expanded_queries:
query_embedding = model.encode(expanded_query, convert_to_tensor=True)
similarities = util.pytorch_cos_sim(query_embedding, course_embeddings)[0]
all_similarities.append(similarities)
aggregated_similarities = torch.max(torch.stack(all_similarities), dim=0)[0]
filtered_df = df.copy()
if level_filter and level_filter != "Nil":
filtered_df = filtered_df[filtered_df['Level of Difficulty'] == level_filter]
if category_filter and category_filter != "NIL":
filtered_df = filtered_df[filtered_df['Category'] == category_filter]
if filtered_df.empty:
return "<p>No matching courses found.</p>"
filtered_similarities = aggregated_similarities[filtered_df.index]
top_results = filtered_similarities.topk(k=min(top_k, len(filtered_similarities)))
results = []
for idx in top_results.indices:
idx = int(idx)
course_title = filtered_df.iloc[idx]['Course Title']
course_description = filtered_df.iloc[idx, 1]
course_url = filtered_df.iloc[idx, -1]
generated_description = generate_description(course_title + " " + course_description)
course_link = f'<a href="{course_url}" target="_blank">{course_title}</a>'
results.append(f"<strong>{course_link}</strong><br>{course_description}<br>{generated_description}<br><br>")
return "<ol>" + "".join([f"<li>{result}</li>" for result in results]) + "</ol>"
def create_gradio_interface():
with gr.Blocks() as demo:
gr.Markdown("# Analytics Vidhya Free Courses")
gr.Markdown("Enter your query and use filters to narrow down the search.")
query = gr.Textbox(label=" Search for a course", placeholder="Enter course topic or description")
with gr.Accordion(" Filters", open=False):
level_filter = gr.Dropdown(choices=["Beginner", "Intermediate", "Advanced", "Nil"], label=" Course Level", multiselect=False)
category_filter = gr.Dropdown(choices=["Data Science", "Machine Learning", "Deep Learning", "AI", "NLP", "NIL"], label=" Category", multiselect=False)
search_button = gr.Button("Search")
output = gr.HTML(label="Search Results")
search_button.click(fn=search_courses, inputs=[query, level_filter, category_filter], outputs=output)
return demo
# Launch Gradio interface
demo = create_gradio_interface()
demo.launch() |