Create jobs_dataset.py

jobs_dataset.py

@@ -0,0 +1,55 @@
+import random
+from typing import List, Dict
+
+def generate_job_database() -> List[Dict]:
+    """Generate a comprehensive database of jobs across various industries."""
+    job_templates = {
+        "Technology": [
+            {"title": "Software Engineer", "desc": "Design, develop, and maintain software applications.", "skills": ["Python", "Java", "JavaScript", "Git", "Agile", "Problem Solving"]},
+            {"title": "Data Scientist", "desc": "Analyze complex data to extract valuable business insights.", "skills": ["Python", "R", "Machine Learning", "SQL", "Statistics", "Pandas"]},
+            {"title": "DevOps Engineer", "desc": "Manage infrastructure, deployment pipelines, and automation.", "skills": ["AWS", "Docker", "Kubernetes", "Linux", "CI/CD", "Terraform"]},
+            {"title": "Frontend Developer", "desc": "Create intuitive user interfaces and engaging web experiences.", "skills": ["JavaScript", "React", "CSS", "HTML", "TypeScript", "UI/UX Principles"]},
+            {"title": "Backend Developer", "desc": "Build robust server-side applications, services, and APIs.", "skills": ["Python", "Node.js", "Django", "PostgreSQL", "REST APIs", "MongoDB"]},
+            {"title": "Machine Learning Engineer", "desc": "Deploy, monitor, and maintain ML models in production environments.", "skills": ["Python", "TensorFlow", "PyTorch", "MLOps", "Docker", "Scikit-learn"]},
+        ],
+        "Healthcare": [
+            {"title": "Registered Nurse", "desc": "Provide compassionate patient care and medical support.", "skills": ["Patient Care", "Medical Knowledge", "CPR", "Communication", "Teamwork"]},
+            {"title": "Healthcare Data Analyst", "desc": "Analyze clinical data to improve patient outcomes and operational efficiency.", "skills": ["SQL", "Python", "Tableau", "Healthcare Regulations", "Statistics"]},
+            {"title": "Medical Assistant", "desc": "Support healthcare providers with clinical and administrative tasks.", "skills": ["Patient Communication", "Medical Records", "Scheduling", "Clinical Skills"]},
+        ],
+        "Finance": [
+            {"title": "Financial Analyst", "desc": "Analyze financial data, create financial models, and support investment decisions.", "skills": ["Financial Modeling", "Excel", "Data Analysis", "Valuation", "Market Research"]},
+            {"title": "Accountant", "desc": "Manage financial records, prepare tax documents, and ensure compliance.", "skills": ["Accounting", "QuickBooks", "Tax Law", "Financial Reporting", "Auditing"]},
+            {"title": "Fintech Software Engineer", "desc": "Develop software for financial services, focusing on security and scalability.", "skills": ["Python", "Java", "SQL", "Cybersecurity", "Blockchain"]},
+        ],
+        "Marketing": [
+            {"title": "Digital Marketing Manager", "desc": "Develop and execute comprehensive digital marketing strategies.", "skills": ["Digital Marketing", "SEO", "Social Media", "Google Analytics", "Content Strategy"]},
+            {"title": "Content Creator", "desc": "Produce engaging and brand-aligned content for various platforms.", "skills": ["Content Creation", "SEO", "Social Media", "Writing", "Video Editing"]},
+            {"title": "Marketing Data Analyst", "desc": "Analyze marketing campaign performance and customer behavior data.", "skills": ["SQL", "Google Analytics", "Data Visualization", "A/B Testing", "Excel"]},
+        ]
+    }
+    experience_levels = ["Entry-level", "Mid-level", "Senior", "Lead/Principal"]
+    salary_ranges = {
+        "Entry-level": ["$45k-$65k", "$50k-$70k"], "Mid-level": ["$70k-$95k", "$75k-$100k"],
+        "Senior": ["$100k-$130k", "$115k-$145k"], "Lead/Principal": ["$140k-$170k", "$150k-$180k"]
+    }
+    jobs = []
+    job_id = 1
+    for _ in range(150): # Generate a larger database
+        for category, templates in job_templates.items():
+            template = random.choice(templates)
+            exp_level = random.choice(experience_levels)
+            title = f"{exp_level} {template['title']}" if exp_level != "Entry-level" else template['title']
+            job = {
+                "id": job_id, "title": title, "description": template["desc"], "requirements": list(set(template["skills"])),
+                "experience_level": exp_level, "salary_range": random.choice(salary_ranges[exp_level]), "category": category,
+                "location": random.choice(["Remote", "New York, NY", "San Francisco, CA", "Chicago, IL", "Austin, TX"]),
+            }
+            jobs.append(job)
+            job_id += 1
+    return jobs
+
+# --- Important Line ---
+# We run the function once and store the result in a variable.
+# This variable is what we will import into our main app.
+JOBS_DATABASE = generate_job_database()