Update app.py

app.py

@@ -1,6 +1,8 @@
 import streamlit as st
 from datasets import load_dataset
+import pandas as pd
 from transformers import pipeline
+import time
 
 # Constants
 universities_url = "https://www.4icu.org/top-universities-world/"
@@ -10,9 +12,12 @@ 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
@@ -34,55 +39,105 @@ soft_skills = st.sidebar.text_area("Soft Skills (e.g., Communication, Teamwork)"
 
 # Save profile data for session-based recommendations
 if st.sidebar.button("Save Profile"):
-    st.session_state.profile_data = {
-        "educational_background": educational_background,
-        "interests": interests,
-        "tech_skills": tech_skills,
-        "soft_skills": soft_skills
-    }
-    st.sidebar.success("Profile saved successfully!")
+    with st.spinner('Saving your profile...'):
+        time.sleep(2)  # Simulate processing time
+        st.session_state.profile_data = {
+            "educational_background": educational_background,
+            "interests": interests,
+            "tech_skills": tech_skills,
+            "soft_skills": soft_skills
+        }
+        st.sidebar.success("Profile saved successfully!")
 
 # Intelligent Q&A Section
 st.header("Intelligent Q&A")
 question = st.text_input("Ask a career-related question:")
 if question:
-    answer = qa_pipeline(question)[0]["generated_text"]
-    st.write("Answer:", answer)
+    with st.spinner('Processing your question...'):
+        answer = qa_pipeline(question)[0]["generated_text"]
+        time.sleep(2)  # Simulate processing time
+        st.write("Answer:", answer)
 
 # Career and Job Recommendations Section
-st.header("Career and Job Recommendations")
+st.header("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"))
-
-    if job_recommendations:
-        st.subheader("Job Recommendations")
-        st.write("Based on your profile, here are some potential job roles:")
-        for job in job_recommendations[:5]:  # Limit to top 5 job recommendations
-            st.write("- ", job)
-    else:
-        st.write("No specific job recommendations found matching your profile.")
-
+    with st.spinner('Generating job recommendations...'):
+        time.sleep(2)  # Simulate processing time
+        job_recommendations = []
+
+        # Find jobs from ds_jobs
+        for job in ds_jobs["train"]:
+            job_title = job.get("job_title_short", "Unknown Job Title")
+            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_title)
+
+        # Find jobs from ds_custom_jobs
+        for _, job in ds_custom_jobs.iterrows():
+            job_title = job.get("job_title", "Unknown Job Title")
+            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_title)
+
+        # Remove duplicates and keep the unique job titles
+        job_recommendations = list(set(job_recommendations))
+
+        if job_recommendations:
+            st.subheader("Based on your profile, here are some potential job roles:")
+            for job in job_recommendations[:5]:  # Limit to top 5 job recommendations
+                st.write("- ", job)
+        else:
+            st.write("No specific job recommendations found matching your profile. Here are some general recommendations:")
+            for job in ["Data Analyst", "Software Engineer", "Project Manager", "Research Scientist", "Business Analyst"][:5]:
+                st.write("- ", job)
 
 # Course Suggestions Section
-st.header("Course Suggestions")
+st.header("Recommended Courses")
 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(","))
-    ]
-
-    if course_recommendations:
-        st.subheader("Recommended Courses")
-        st.write("Here are some courses related to your interests:")
-        for course in course_recommendations[:5]:  # Limit to top 5 course recommendations
-            st.write("- ", course)
-    else:
-        st.write("No specific courses found matching your interests.")
+    with st.spinner('Finding courses related to your profile...'):
+        time.sleep(2)  # Simulate processing time
+        course_recommendations = []
+
+        # Find relevant courses in ds_courses
+        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.append({
+                    "name": course.get("Course Name", "Unknown Course Title"),
+                    "url": course.get("Links", "#")
+                })
+
+        # Find relevant courses in ds_custom_courses
+        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(",")):
+                course_recommendations.append({
+                    "name": row["Course Name"],
+                    "url": row.get("Links", "#")
+                })
+
+        # Remove duplicates from course recommendations by converting to a set of tuples and back to a list
+        course_recommendations = list({(course["name"], course["url"]) for course in course_recommendations})
+
+        # If there are fewer than 5 exact matches, add nearly related courses
+        if len(course_recommendations) < 5:
+            for course in ds_courses["train"]:
+                if len(course_recommendations) >= 5:
+                    break
+                if any(skill.lower() in course.get("Course Name", "").lower() for skill in st.session_state.profile_data["tech_skills"].split(",")):
+                    course_recommendations.append((course.get("Course Name", "Unknown Course Title"), course.get("Links", "#")))
+
+            for _, row in ds_custom_courses.iterrows():
+                if len(course_recommendations) >= 5:
+                    break
+                if any(skill.lower() in row["Course Name"].lower() for skill in st.session_state.profile_data["tech_skills"].split(",")):
+                    course_recommendations.append((row["Course Name"], row.get("Links", "#")))
+
+            # Remove duplicates again after adding nearly related courses
+            course_recommendations = list({(name, url) for name, url in course_recommendations})
+
+        if course_recommendations:
+            st.write("Here are the top 5 courses related to your interests:")
+            for course in course_recommendations[:5]:  # Limit to top 5 course recommendations
+                st.write(f"- [{course[0]}]({course[1]})")
 
 # University Recommendations Section
 st.header("Top Universities")
@@ -91,3 +146,7 @@ st.write(f"[View Top Universities Rankings]({universities_url})")
 
 # Conclusion
 st.write("Thank you for using the Career Counseling Application!")
+'''
+
+with open('app.py', 'w') as f:
+    f.write(code)