Add application file

app.py

@@ -27,6 +27,36 @@ 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=['Sr No', 'Course Name', 'Course Link', 'Description'])
+
+  # 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, ed_qual):
     # Combine user's input into a single string for TF-IDF
@@ -72,44 +102,6 @@ def recommend_courses(user_skill, ed_qual):
 
     return final_recommendations_html
 
-# Create a TF-IDF vectorizer
-tfidf_vectorizer = TfidfVectorizer(stop_words='english')
-tfidf_matrix = tfidf_vectorizer.fit_transform(courses_df['Course Name'].fillna(''))
-
-user_skill = "psychology"
-
-ed_qual = "B.Tech/B.Sc"
-
-html = recommend_courses(user_skill, ed_qual)
-
-html
-
-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=['Sr No', 'Course Name', 'Course Link', 'Description'])
-
-  # 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
-
 # Gradio Interface with dynamically generated dropdown options
 iface = gr.Interface(
     fn=recommend_courses,