Upload 7 files

app.py

@@ -0,0 +1,104 @@
+import gradio as gr
+import pickle
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Load model and data
+with open("course_emb.pkl", "rb") as f:
+    course_emb = pickle.load(f)
+
+df = pd.read_excel("analytics_vidhya_courses_Final.xlsx")
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def search_courses(query, top_n=5):
+    if not query.strip():
+        return "Please enter a search query."
+    
+    query_embedding = model.encode([query])
+    similarities = cosine_similarity(query_embedding, course_emb)
+    top_n_idx = similarities[0].argsort()[-top_n:][::-1]
+    
+    results = []
+    for idx in top_n_idx:
+        course = df.iloc[idx]
+        results.append({
+            "title": course["Course Title"],
+            "description": course["Course Description"],
+            "similarity": float(similarities[0][idx])
+        })
+    return results
+
+def gradio_interface(query):
+    results = search_courses(query)
+    if isinstance(results, str):
+        return results
+    
+    # Format results as HTML with updated styling
+    html_output = "<div style='font-family: Inter, sans-serif;'>"
+    
+    for i, course in enumerate(results, 1):
+        relevance = int(course['similarity'] * 100)
+        html_output += f"""
+        <div style='background: #f8f9fa; padding: 20px; margin: 15px 0; border-radius: 12px; box-shadow: 0 2px 6px rgba(0,0,0,0.05);'>
+            <h3 style='color: #1a237e; margin: 0 0 12px 0; font-weight: 600;'>#{i}. {course['title']}</h3>
+            <div style='color: #3949ab; font-size: 0.9em; margin-bottom: 10px; font-weight: 500;'>Match Score: {relevance}%</div>
+            <p style='color: #424242; margin: 0; line-height: 1.6;'>{course['description']}</p>
+        </div>
+        """
+    
+    html_output += "</div>"
+    return html_output
+
+# Create Gradio interface with improved styling
+css = """
+.gradio-container {
+    font-family: 'Inter', sans-serif;
+}
+.gradio-button {
+    background: linear-gradient(135deg, #3949ab, #1a237e) !important;
+}
+.gradio-button:hover {
+    background: linear-gradient(135deg, #1a237e, #3949ab) !important;
+}
+"""
+
+with gr.Blocks(css=css, theme="soft") as iface:
+    gr.Markdown(
+        """
+        # 😻 Smart Learning Pathfinder
+        Unlock your learning potential with AI-powered course recommendations tailored just for you!
+        """
+    )
+    
+    with gr.Row():
+        query_input = gr.Textbox(
+            label="What would you like to master?",
+            placeholder="Tell us your learning interests (e.g., 'AI fundamentals' or 'data science for beginners')",
+            scale=4
+        )
+    
+    with gr.Row():
+        search_button = gr.Button("✨ Discover Courses", variant="primary")
+    
+    with gr.Row():
+        output = gr.HTML(label="Personalized Recommendations")
+    
+    search_button.click(
+        fn=gradio_interface,
+        inputs=query_input,
+        outputs=output,
+    )
+    
+    gr.Markdown(
+        """
+        ### 💡 Optimization Tips:
+        - Share your current knowledge level
+        - Mention specific skills you want to develop
+        - Include your learning preferences
+        - Specify your target outcomes
+        """
+    )
+
+# Launch the interface
+iface.launch(share=True)

course_emb.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50af6e24422db342f6af21bbb5f495590a2cedb6f5cae013bd41ce5a64177c84
+size 100003

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

main.py

@@ -0,0 +1,73 @@
+import requests
+from bs4 import BeautifulSoup
+import pandas as pd
+import time
+
+base_url = "https://courses.analyticsvidhya.com/collections?page="
+course_url_base = "https://courses.analyticsvidhya.com"
+
+course_data = []
+
+for page in range(1,9):
+    print(f"Scraping page {page}...")
+    response = requests.get(base_url + str(page))
+    soup = BeautifulSoup(response.text, 'html.parser')
+    
+    course_section = soup.find_all('div', class_="collections__product-cards collections__product-cards___0b9ab")
+    if not course_section:
+        print("No course section found, skipping this page.")
+        continue
+    
+    courses = course_section[0].find_all('li')
+    
+    for course in courses:
+        link_tag = course.find('a', href=True)
+        if not link_tag:
+            continue
+        course_relative_link = link_tag['href']
+        course_link = course_url_base + course_relative_link
+        
+        course_response = requests.get(course_link)
+        course_soup = BeautifulSoup(course_response.text, 'html.parser')
+        
+        title_tag = course_soup.find('h1', class_="section__heading")
+        if title_tag:
+            course_title = title_tag.get_text(strip=True)
+        else:
+            course_title = "N/A"
+        
+        description_tag = course_soup.find_all('div', class_="rich-text__container")
+        course_description = " ".join([p.get_text(strip=True) for tag in description_tag for p in tag.find_all('p')]) if description_tag else "N/A"
+        
+        curriculum_section = course_soup.find('div', class_="course-curriculum__container")
+        if curriculum_section:
+            curriculum_content = []
+            
+            chapters = curriculum_section.find_all('li', class_="course-curriculum__chapter")
+            for chapter in chapters:
+                title = chapter.find('h5', class_="course-curriculum__chapter-title")
+                if title:
+                    curriculum_content.append(title.get_text(strip=True))
+                    
+                    chapter_content = chapter.find('ul', class_="course-curriculum__chapter-content")
+                    if chapter_content:
+                        curriculum_content.extend(
+                            [f"  - {item.get_text(strip=True)}" for item in chapter_content.find_all('li')]
+                        )
+            course_curriculum = "\n".join(curriculum_content) if curriculum_content else "N/A"
+        else:
+            course_curriculum = "N/A"
+        
+        course_data.append({
+            "Course Title": course_title,
+            "Course Description": course_description,
+            "Course Curriculum": course_curriculum,
+            "Link": course_link
+        })
+        
+        time.sleep(1)
+
+df = pd.DataFrame(course_data)
+file_path = r"C:\Users\rachi\OneDrive\Desktop\Analytics VIdya - Gen AI\analytics_vidhya_courses.xlsx"
+df.to_excel(file_path, index=False)
+print(f"Data saved to {file_path}")

requirements.txt

@@ -0,0 +1,9 @@
+requests>=2.31.0
+beautifulsoup4>=4.12.0
+pandas>=2.0.0
+openpyxl>=3.1.2
+sentence-transformers>=2.2.2
+torch>=2.0.0
+gradio>=5.9.1
+numpy>=1.24.0
+tqdm>=4.65.0

search.py

@@ -0,0 +1,28 @@
+import pickle
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+
+with open("course_emb.pkl", "rb") as f:
+    course_emb = pickle.load(f)
+
+df = pd.read_excel("analytics_vidhya_courses_Final.xlsx")
+
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def search_courses(query, top_n=5):
+    query_embedding = model.encode([query])
+    
+    similarities = cosine_similarity(query_embedding, course_emb)
+    
+    top_n_idx = similarities[0].argsort()[-top_n:][::-1]
+    
+    return df.iloc[top_n_idx][["Course Title", "Course Description"]]
+
+query = input("Enter your search query: ")
+top_courses = search_courses(query)
+
+print("\nTop relevant courses:")
+for idx, row in top_courses.iterrows():
+    print(f"Title: {row['Course Title']}")
+    print(f"Description: {row['Course Description']}\n")