Add application file

1app.py

@@ -0,0 +1,98 @@
+# -*- coding: utf-8 -*-
+"""Skill Transformation Journey.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/11XAXUP2fzy553V9v0x-gxJXcXL3uHJcw
+"""
+
+import gradio as gr
+import re
+import openai
+from openai import OpenAI
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import linear_kernel
+
+client = OpenAI(
+    # defaults to os.environ.get("OPENAI_API_KEY")
+    api_key="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",
+)
+
+# Specify the sheet name in the Excel file
+excel_file_path = "1.csv"
+sheet_name = "Shortlisted Courses"  # Replace with the actual sheet name
+
+# Read the Excel file into a Pandas DataFrame
+courses_df = pd.read_csv(excel_file_path)
+
+# Create a TF-IDF vectorizer
+tfidf_vectorizer = TfidfVectorizer(stop_words='english')
+tfidf_matrix = tfidf_vectorizer.fit_transform(courses_df['Course Name'].fillna(''))
+
+def html_coversion(gpt_content):
+
+  # Provided data in text format
+  data_text = gpt_content
+
+  # Extract course details using a modified regular expression
+  courses = re.findall(r'(\d+)\. (.*?):\n\s*- Course Link: \[([^\]]+)\]\(([^)]+)\)\n\s*- Description: ([^\n]+)', data_text)
+
+  # Process each tuple to remove the second occurrence of the course link
+  processed_courses = []
+  for course_tuple in courses:
+      # Find the index of the second occurrence of the course link
+      index_of_second_occurrence = course_tuple.index(course_tuple[2], course_tuple.index(course_tuple[2]) + 1)
+      # Remove the second occurrence of the course link from the tuple
+      processed_tuple = course_tuple[:index_of_second_occurrence] + course_tuple[index_of_second_occurrence + 1:]
+      processed_courses.append(processed_tuple)
+
+  # Convert the processed list of tuples into a DataFrame
+  df = pd.DataFrame(processed_courses, columns=['Course Name', 'Course Link'])
+
+  # Convert the DataFrame to an HTML table
+  html_table = df.to_html(index=False, escape=False)
+
+  # Print or save the HTML table
+  return html_table
+
+# Function to recommend courses based on user input using GPT and TF-IDF
+def recommend_courses(user_skill):
+    # Combine user's input into a single string for TF-IDF
+    user_input = f"{user_skill}"
+
+    # Use TF-IDF and cosine similarity for initial course recommendations
+    user_vector = tfidf_vectorizer.transform([user_input])
+    cosine_similarities = linear_kernel(user_vector, tfidf_matrix)
+
+    # Get initial course recommendations based on similarity scores
+    recommendations = courses_df.copy()
+    recommendations['Similarity'] = cosine_similarities[0]
+
+    # Sort by similarity and get top recommendations
+    top_recommendations = recommendations.sort_values(by='Similarity', ascending=False).head(5)
+
+    # Generate a text summary of the initial recommendations
+    initial_recommendations_text = top_recommendations[['Course Name', 'Course Link']].to_string(index=False)
+
+    
+    # Assume GPT generates HTML-formatted final recommendations
+    final_recommendations_html = html_coversion(initial_recommendations_text)
+
+    return final_recommendations_html
+
+# Gradio Interface with dynamically generated dropdown options
+iface = gr.Interface(
+    fn=recommend_courses,
+    inputs=[
+        gr.Textbox("text", label="Enter expected skill"),
+        #gr.Dropdown(["B.Tech/B.Sc", "M.Tech/M.Sc", "Management"], label="Highest Educational Qualification"),
+    ],
+    outputs="html",
+    live=True
+)
+
+# Launch the Gradio interface and save the output to an HTML file
+iface.launch(share=True)
+

app.py

@@ -1,98 +1,106 @@
 # -*- coding: utf-8 -*-
-"""Skill Transformation Journey.ipynb
+"""[DRAFT]SWAYAM_CHATBOT SYSTEM_Course Recommendation System.ipynb
 
 Automatically generated by Colaboratory.
 
 Original file is located at
-    https://colab.research.google.com/drive/11XAXUP2fzy553V9v0x-gxJXcXL3uHJcw
+    https://colab.research.google.com/drive/1s4_kZDgJcvRr7kfnw12oFNus45E2oOr9
 """
 
-import gradio as gr
-import re
+# Commented out IPython magic to ensure Python compatibility.
+# %pip install openai
+
 import openai
-from openai import OpenAI
 import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import linear_kernel
 
-client = OpenAI(
-    # defaults to os.environ.get("OPENAI_API_KEY")
-    api_key="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",
-)
-
-# Specify the sheet name in the Excel file
-excel_file_path = "1.csv"
-sheet_name = "Shortlisted Courses"  # Replace with the actual sheet name
-
-# Read the Excel file into a Pandas DataFrame
-courses_df = pd.read_csv(excel_file_path)
-
-# Create a TF-IDF vectorizer
-tfidf_vectorizer = TfidfVectorizer(stop_words='english')
-tfidf_matrix = tfidf_vectorizer.fit_transform(courses_df['Course Name'].fillna(''))
-
-def html_coversion(gpt_content):
-
-  # Provided data in text format
-  data_text = gpt_content
-
-  # Extract course details using a modified regular expression
-  courses = re.findall(r'(\d+)\. (.*?):\n\s*- Course Link: \[([^\]]+)\]\(([^)]+)\)\n\s*- Description: ([^\n]+)', data_text)
-
-  # Process each tuple to remove the second occurrence of the course link
-  processed_courses = []
-  for course_tuple in courses:
-      # Find the index of the second occurrence of the course link
-      index_of_second_occurrence = course_tuple.index(course_tuple[2], course_tuple.index(course_tuple[2]) + 1)
-      # Remove the second occurrence of the course link from the tuple
-      processed_tuple = course_tuple[:index_of_second_occurrence] + course_tuple[index_of_second_occurrence + 1:]
-      processed_courses.append(processed_tuple)
-
-  # Convert the processed list of tuples into a DataFrame
-  df = pd.DataFrame(processed_courses, columns=['Course Name', 'Course Link'])
-
-  # Convert the DataFrame to an HTML table
-  html_table = df.to_html(index=False, escape=False)
-
-  # Print or save the HTML table
-  return html_table
-
-# Function to recommend courses based on user input using GPT and TF-IDF
-def recommend_courses(user_skill):
-    # Combine user's input into a single string for TF-IDF
-    user_input = f"{user_skill}"
-
-    # Use TF-IDF and cosine similarity for initial course recommendations
-    user_vector = tfidf_vectorizer.transform([user_input])
+# Set your OpenAI API key
+openai.api_key = "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"  # Replace with your actual API key
+
+# Sample course data
+data = {
+    'CourseID': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16],
+    'Title': ['Python Programming',
+              'Data Science with Python',
+              'Machine Learning',
+              'Web Development',
+              'Environmental Studies',
+              'Business Communication (Language-English/ Hindi/ MIL)',
+              'Management Principles and Applications',
+              'Analytical Geometry',
+              'Cost Accounting',
+              'Principles of Micro Economics',
+              'Human Resource Management',
+              'Fundamentals of Financial Management',
+              'Classical Political Philosophy',
+              'Differential Calculus',
+              'Sociology of Health and Medicine',
+              'Economic History of India (1857-1947)'],
+    'Description': [
+        'Start your journey in programming by learning Python from scratch.',
+        'Start your journey in Data Science and become data scientist by learning python and other data science libraries.',
+        'Master your programming skills and dive into the world of machine learning with python and other machine learning libraries',
+        'Start your journey in web development using python programming and Django library.',
+        'Explore the intricate relationship between humanity and the environment, and learn how to make informed decisions to preserve and protect our planet.',
+        'Enhance your communication skills in English, Hindi, or your mother tongue (MIL) to excel in the business world. Learn the art of effective written and verbal communication.',
+        'Gain a comprehensive understanding of the fundamental principles of management and their real-world applications to thrive in today\'s dynamic business environment.',
+        'Delve into the world of analytical geometry and master the mathematical techniques and concepts that underlie this fascinating branch of mathematics.',
+        'Learn the essentials of cost accounting and financial analysis to make sound business decisions and optimize financial performance.',
+        'Explore the principles of microeconomics, the study of individual economic behavior, and understand how economic decisions impact businesses and society.',
+        'Gain insight into the management of human resources, from recruitment to employee development, and learn how effective HR practices drive organizational success.',
+        'Understand the core principles of financial management, including budgeting, investment, and risk analysis, to make strategic financial decisions.',
+        'Dive into the world of classical political philosophy and explore the influential works of thinkers like Plato, Aristotle, and more, to understand the foundations of political thought.',
+        'Master the fundamental concepts of differential calculus, a branch of mathematics that deals with rates of change, and its applications in various fields.',
+        'Explore the sociological aspects of health, illness, and healthcare systems. Understand how society shapes healthcare practices and policies.',
+        'Take a journey through the economic history of India during a critical period of change and transformation, from 1857 to 1947, and understand the economic forces that shaped the nation.'
+    ]
+}
+
+# Create a DataFrame from the course data
+courses_df = pd.DataFrame(data)
+
+# Function to recommend courses based on user skills
+def recommend_courses(user_skills):
+    # Combine the user's skills into a single string
+    user_skills = ', '.join(user_skills.split())
+
+    # Create a TF-IDF vectorizer to convert course descriptions into vectors
+    tfidf_vectorizer = TfidfVectorizer(stop_words='english')
+    tfidf_matrix = tfidf_vectorizer.fit_transform(courses_df['Description'])
+
+    # Calculate cosine similarity between user skills and course descriptions
+    user_vector = tfidf_vectorizer.transform([user_skills])
     cosine_similarities = linear_kernel(user_vector, tfidf_matrix)
 
-    # Get initial course recommendations based on similarity scores
+    # Get course recommendations based on similarity scores
     recommendations = courses_df.copy()
     recommendations['Similarity'] = cosine_similarities[0]
 
-    # Sort by similarity and get top recommendations
-    top_recommendations = recommendations.sort_values(by='Similarity', ascending=False).head(5)
-
-    # Generate a text summary of the initial recommendations
-    initial_recommendations_text = top_recommendations[['Course Name', 'Course Link']].to_string(index=False)
-
-    
-    # Assume GPT generates HTML-formatted final recommendations
-    final_recommendations_html = html_coversion(initial_recommendations_text)
-
-    return final_recommendations_html
-
-# Gradio Interface with dynamically generated dropdown options
-iface = gr.Interface(
-    fn=recommend_courses,
-    inputs=[
-        gr.Textbox("text", label="Enter expected skill"),
-        #gr.Dropdown(["B.Tech/B.Sc", "M.Tech/M.Sc", "Management"], label="Highest Educational Qualification"),
-    ],
-    outputs="html",
-    live=True
-)
-
-# Launch the Gradio interface and save the output to an HTML file
-iface.launch(share=True)
-
+    # Sort courses by similarity and recommend the top matches
+    recommendations = recommendations.sort_values(by='Similarity', ascending=False)
+    recommended_courses = recommendations[['CourseID', 'Title', 'Similarity']]
+
+    return recommended_courses
+
+# Function to interact with GPT-3 and provide recommendations
+def gpt_recommend_courses(user_input):
+    response = openai.Completion.create(
+        engine="text-davinci-002",
+        prompt=f"I have skills in {user_input}. What courses do you recommend?",
+        max_tokens=100,
+        n=1,
+        stop=None,
+        temperature=0.7,
+    )
+    recommendation_prompt = response.choices[0].text.strip()
+
+    return recommend_courses(recommendation_prompt)
+
+# User input for skills
+user_input = input("Enter your skills: ")
+
+# Get course recommendations using GPT-3
+recommended_courses = gpt_recommend_courses(user_input)
+print("\nRecommended Courses:")
+print(recommended_courses)