Update app.py

app.py

@@ -1,15 +1,16 @@
 import streamlit as st
 import pandas as pd
 import pdfplumber
-from extractor import (
-    extract_text_from_pdf,
-    extract_entities,
-    extract_experience_years,
-    classify_field
-)
+import spacy
+import requests
+import plotly.express as px
+from datetime import datetime, timedelta
 
-# Set page configuration
-st.set_page_config(page_title="Skill Scoring & Roadmap App", layout="wide")
+# Page config
+st.set_page_config(page_title="Skill Scoring & Career Roadmap App", layout="wide")
+
+# Load spaCy model
+nlp = spacy.load("en_core_web_sm")
 
 # Load datasets
 skills_df = pd.read_csv("data/skills_dataset.csv")
@@ -17,9 +18,22 @@ countries_df = pd.read_csv("data/countries_dataset.csv")
 cert_df = pd.read_csv("data/certifications.csv")
 edu_tech_df = pd.read_csv("data/education_technical.csv")
 edu_non_tech_df = pd.read_csv("data/education_non_technical.csv")
-scholarship_df = pd.read_csv("data/scholarships.csv")
+scholarship_df = pd.read_csv("data/scholarships_dataset.csv")
+
+# Helper functions
+def extract_text_from_pdf(file):
+    with pdfplumber.open(file) as pdf:
+        return "\n".join(page.extract_text() for page in pdf.pages if page.extract_text())
+
+def extract_entities(text):
+    doc = nlp(text)
+    skills = [token.text for token in doc if token.text in skills_df['Skill'].values]
+    technical_skills = {"Python", "Machine Learning", "Cloud Computing", "Cybersecurity", "AI", "DevOps"}
+    background = "technical" if any(s in technical_skills for s in skills) else "non-technical"
+    # Dummy experience extraction (you should improve with NLP)
+    years_exp = 3  # Placeholder, replace with better extraction logic
+    return list(set(skills)), background, years_exp
 
-# Helper function
 def score_skills(user_skills):
     if not skills_df.shape[0]:
         return 0
@@ -39,23 +53,48 @@ def recommend_education(background):
 def recommend_scholarships(field):
     return scholarship_df[scholarship_df["Field"].str.lower() == field.lower()].reset_index(drop=True)
 
-# UI
-st.title("📊 Personalized Skill Scoring & Global Career Roadmap")
-st.markdown("Upload your CV and receive a customized global career path, skill score, job matches, education and scholarship suggestions.")
+def fetch_jobs(skill, country_code="us", max_results=5):
+    app_id = "YOUR_ADZUNA_APP_ID"
+    app_key = "YOUR_ADZUNA_APP_KEY"
+    url = f"https://api.adzuna.com/v1/api/jobs/{country_code}/search/1"
+    params = {
+        "app_id": app_id,
+        "app_key": app_key,
+        "results_per_page": max_results,
+        "what": skill,
+        "content-type": "application/json"
+    }
+    response = requests.get(url, params=params)
+    if response.status_code == 200:
+        return response.json()["results"]
+    else:
+        return []
+
+def create_roadmap_timeline():
+    # Example roadmap with skill cert + scholarships + education timelines
+    now = datetime.now()
+    roadmap = [
+        {"Task": "Complete Python Certification", "Start": now.strftime("%Y-%m-%d"), "Finish": (now + timedelta(days=90)).strftime("%Y-%m-%d")},
+        {"Task": "Apply for Erasmus Scholarship", "Start": (now + timedelta(days=100)).strftime("%Y-%m-%d"), "Finish": (now + timedelta(days=150)).strftime("%Y-%m-%d")},
+        {"Task": "Master's in AI (Online)", "Start": (now + timedelta(days=160)).strftime("%Y-%m-%d"), "Finish": (now + timedelta(days=700)).strftime("%Y-%m-%d")},
+    ]
+    return pd.DataFrame(roadmap)
+
+# Streamlit UI
+st.title("📊 Personalized Skill Scoring & Career Roadmap App")
+st.markdown("Upload your CV and get a detailed career roadmap with live job listings.")
 
-uploaded_file = st.file_uploader("📤 Upload your CV (PDF format)", type=["pdf"])
+uploaded_file = st.file_uploader("📤 Upload your CV (PDF only)", type=["pdf"])
 
 if uploaded_file:
     with st.spinner("Analyzing your CV..."):
         text = extract_text_from_pdf(uploaded_file)
-        skills, background = extract_entities(text, skills_df)
-        years_exp = extract_experience_years(text)
-        field = classify_field(text)
-
+        skills, background, years_exp = extract_entities(text)
         score = score_skills(skills)
         country_info = recommend_countries(skills, years_exp)
         certs = recommend_certifications(skills)
         edu = recommend_education(background)
+        field = background  # Simplified; you should detect actual field from CV
         scholarships = recommend_scholarships(field)
 
     st.subheader("✅ Identified Skills")
@@ -64,34 +103,57 @@ if uploaded_file:
     st.subheader("📈 Skill Score")
     st.metric("Your Skill Score", f"{score}/100")
 
-    st.subheader("🧠 Experience")
-    st.write(f"{years_exp} years of experience detected.")
-
-    st.subheader("📂 Categorized Field")
-    st.write(f"Detected Field: `{field}` | Background: `{background}`")
-
-    st.subheader("🌍 Country Recommendations")
+    st.subheader("🌍 Job Opportunities & Country Recommendations")
     if not country_info.empty:
         st.dataframe(country_info)
     else:
-        st.write("No matching jobs found based on your current skills and experience.")
+        st.write("No country/job recommendations available for your skill set.")
 
-    st.subheader("🎓 Certifications (Free/Paid)")
+    st.subheader("🎓 Recommended Certifications")
     if not certs.empty:
         st.dataframe(certs)
     else:
-        st.write("No certification recommendations found.")
+        st.write("No certification recommendations available.")
 
-    st.subheader("🎓 Higher Education")
+    st.subheader("🎓 Higher Education Opportunities")
     if not edu.empty:
         st.dataframe(edu)
     else:
-        st.write("No higher education recommendations.")
+        st.write("No higher education opportunities available.")
 
     st.subheader("🎓 Scholarship Opportunities")
     if not scholarships.empty:
         st.dataframe(scholarships)
     else:
-        st.write("No matching scholarships found.")
+        st.write("No scholarships available for your field.")
+
+    # Timeline chart for roadmap
+    st.subheader("🛤️ Your Career Roadmap Timeline")
+    timeline_df = create_roadmap_timeline()
+    fig = px.timeline(timeline_df, x_start="Start", x_end="Finish", y="Task", title="Career Roadmap Timeline")
+    fig.update_yaxes(autorange="reversed")
+    st.plotly_chart(fig, use_container_width=True)
+
+    # Show live job listings using first identified skill and first country code (you can improve this logic)
+    if skills and not country_info.empty:
+        st.subheader(f"🔍 Live Job Listings for '{skills[0]}'")
+        country_code_map = {
+            "USA": "us",
+            "Canada": "ca",
+            "UK": "gb",
+            "Germany": "de",
+            "Australia": "au",
+            "India": "in",
+            "Netherlands": "nl"
+        }
+        country_code = country_code_map.get(country_info.iloc[0]["Country"], "us")
+        jobs = fetch_jobs(skills[0], country_code=country_code, max_results=5)
+        if jobs:
+            for job in jobs:
+                st.markdown(f"**[{job['title']}]({job['redirect_url']})** - {job['location']['display_name']}")
+                st.markdown(f"*{job.get('description', '')[:200]}...*")
+                st.markdown("---")
+        else:
+            st.write("No live job listings found.")
 else:
     st.info("Please upload your CV to begin.")