Create recommender.py

recommender.py

@@ -0,0 +1,46 @@
+import pandas as pd
+
+def score_skills(user_skills, skills_df):
+    return int((len(user_skills) / len(skills_df)) * 100)
+
+def classify_field(text, field_labels):
+    # Replace with a transformer model if needed
+    for field in field_labels:
+        if field.lower() in text.lower():
+            return field
+    return "General"
+
+def recommend_countries(user_skills, countries_df):
+    return countries_df[countries_df["Skill"].isin(user_skills)].drop_duplicates()
+
+def recommend_certifications(user_skills, cert_df):
+    return cert_df[cert_df["Skill"].isin(user_skills)].drop_duplicates()
+
+def recommend_education(background, edu_tech_df, edu_non_tech_df):
+    return edu_tech_df if background == "technical" else edu_non_tech_df
+
+def generate_roadmap(cv_data, field, score, country_jobs, certs, scholarships):
+    roadmap = f"""
+    ## 📍 Your Personalized Career Roadmap
+
+    - **Field**: {field}
+    - **Skill Score**: {score}/100
+    - **Years of Experience**: {cv_data['years_experience']}
+    
+    ### 🌍 Country-Based Job Opportunities:
+    {country_jobs.to_markdown(index=False) if not country_jobs.empty else 'No matching jobs found.'}
+    
+    ### 🎓 Recommended Certifications:
+    {certs.to_markdown(index=False) if not certs.empty else 'None found.'}
+    
+    ### 🎓 Suggested Scholarships:
+    {scholarships.to_markdown(index=False) if not scholarships.empty else 'None found.'}
+
+    ### 🧭 Next Steps:
+    - Improve missing skills.
+    - Pursue listed certifications.
+    - Apply to the recommended countries.
+    - Consider higher education if needed.
+
+    """
+    return roadmap