Update app.py

app.py

@@ -1,5 +1,6 @@
 import streamlit as st
 from datasets import load_dataset
+import pandas as pd
 from transformers import pipeline
 
 # Constants
@@ -10,9 +11,12 @@ universities_url = "https://www.4icu.org/top-universities-world/"
 def load_datasets():
     ds_jobs = load_dataset("lukebarousse/data_jobs")
     ds_courses = load_dataset("azrai99/coursera-course-dataset")
-    return ds_jobs, ds_courses
+    ds_custom_courses = pd.read_csv("final_cleaned_merged_coursera_courses.csv")
+    ds_custom_jobs = pd.read_csv("merged_data_science_jobs.csv")
+    ds_custom_universities = pd.read_csv("merged_university_data_cleaned (1).csv")
+    return ds_jobs, ds_courses, ds_custom_courses, ds_custom_jobs, ds_custom_universities
 
-ds_jobs, ds_courses = load_datasets()
+ds_jobs, ds_courses, ds_custom_courses, ds_custom_jobs, ds_custom_universities = load_datasets()
 
 # Initialize the pipeline with caching, using an accessible model like 'google/flan-t5-large'
 @st.cache_resource
@@ -42,6 +46,30 @@ if st.sidebar.button("Save Profile"):
     }
     st.sidebar.success("Profile saved successfully!")
 
+# Questions Section (Appears after profile submission)
+if "profile_data" in st.session_state:
+    st.header("Answer the Following Questions:")
+    questions = [
+        "What do you see yourself achieving in the next five years?",
+        "Which skills would you like to develop further? (Examples: leadership, technical expertise, communication, etc.)",
+        "Do you prefer a structured routine or a more flexible, varied work environment?",
+        "What’s most important to you in a job? (e.g., work-life balance, job stability, opportunities for growth, impact on society)",
+        "What types of projects or tasks energize you? (e.g., solving complex problems, helping others, creating something new)",
+        "Are you comfortable with roles that may involve public speaking or presenting ideas?",
+        "How do you handle stress or pressure in a work setting? (Select options: I thrive under pressure, I manage well, I prefer lower-stress environments)",
+        "Would you be open to relocation or travel for your job?",
+        "Do you prioritize high salary potential or job satisfaction when considering a career?",
+        "What kind of work culture are you drawn to? (e.g., collaborative, competitive, mission-driven, innovative)"
+    ]
+    
+    answers = {}
+    for question in questions:
+        answers[question] = st.text_input(question)
+
+    if st.button("Submit Answers"):
+        st.session_state.answers = answers
+        st.success("Your answers have been saved!")
+
 # Intelligent Q&A Section
 st.header("Intelligent Q&A")
 question = st.text_input("Ask a career-related question:")
@@ -54,11 +82,18 @@ st.header("Career and Job Recommendations")
 if "profile_data" in st.session_state:
     job_recommendations = []
     for job in ds_jobs["train"]:
-        # Use an empty string if 'job_skills' is None
         job_skills = job.get("job_skills", "") or ""
         if any(skill.lower() in job_skills.lower() for skill in st.session_state.profile_data["tech_skills"].split(",")):
             job_recommendations.append(job.get("job_title_short", "Unknown Job Title"))
 
+    for _, job in ds_custom_jobs.iterrows():
+        job_skills = job.get("skills", "") or ""
+        if any(skill.lower() in job_skills.lower() for skill in st.session_state.profile_data["tech_skills"].split(",")):
+            job_recommendations.append(job.get("job_title", "Unknown Job Title"))
+
+    # Remove duplicates by converting the list to a set and back to a list
+    job_recommendations = list(set(job_recommendations))
+
     if job_recommendations:
         st.subheader("Job Recommendations")
         st.write("Based on your profile, here are some potential job roles:")
@@ -67,15 +102,22 @@ if "profile_data" in st.session_state:
     else:
         st.write("No specific job recommendations found matching your profile.")
 
-
 # Course Suggestions Section
 st.header("Course Suggestions")
 if "profile_data" in st.session_state:
     course_recommendations = [
-        course.get("Title", "Unknown Course Title") for course in ds_courses["train"]
-        if any(interest.lower() in course.get("Title", "").lower() for interest in st.session_state.profile_data["interests"].split(","))
+        course.get("Course Name", "Unknown Course Title") for course in ds_courses["train"]
+        if any(interest.lower() in course.get("Course Name", "").lower() for interest in st.session_state.profile_data["interests"].split(","))
     ]
 
+    course_recommendations.extend([ 
+        row["Course Name"] for _, row in ds_custom_courses.iterrows()
+        if any(interest.lower() in row["Course Name"].lower() for interest in st.session_state.profile_data["interests"].split(","))
+    ])
+
+    # Remove duplicates from course recommendations
+    course_recommendations = list(set(course_recommendations))
+
     if course_recommendations:
         st.subheader("Recommended Courses")
         st.write("Here are some courses related to your interests:")
@@ -89,5 +131,10 @@ st.header("Top Universities")
 st.write("For further education, you can explore the top universities worldwide:")
 st.write(f"[View Top Universities Rankings]({universities_url})")
 
+st.subheader("Custom University Data")
+if not ds_custom_universities.empty:
+    st.write("Here are some recommended universities based on custom data:")
+    st.dataframe(ds_custom_universities.head())
+
 # Conclusion
 st.write("Thank you for using the Career Counseling Application!")