Job Market Analytics — Analyzing Data Analyst Job Postings

import pandas as pd

# Sample job data structure
jobs_data = {
    'job_title': ['Data Analyst', 'Business Analyst', 'Data Scientist'],
    'company': ['Flipkart', 'Amazon', 'Swiggy'],
    'location': ['Bangalore', 'Mumbai', 'Pune'],
    'salary_min': [500000, 600000, 800000],
    'salary_max': [800000, 1000000, 1500000],
    'experience': ['2-4 years', '3-5 years', '4-7 years'],
    'skills': ['SQL, Python, Power BI', 'Excel, SQL, Tableau', 'Python, ML, SQL'],
    'posted_date': ['2026-03-01', '2026-03-05', '2026-03-10']
}

df = pd.DataFrame(jobs_data)
print(df.head())

# Extract and count skills
all_skills = df['skills'].str.split(', ').explode()
skill_counts = all_skills.value_counts()

print("Top 10 In-Demand Skills:")
print(skill_counts.head(10))

# Visualize
import matplotlib.pyplot as plt
skill_counts.head(10).plot(kind='barh', color='skyblue')
plt.title('Most Demanded Skills for Data Analysts')
plt.xlabel('Number of Job Postings')
plt.tight_layout()
plt.show()

df['avg_salary'] = (df['salary_min'] + df['salary_max']) / 2

city_salary = df.groupby('location')['avg_salary'].agg(['mean', 'min', 'max', 'count'])
city_salary = city_salary.sort_values('mean', ascending=False)

print(city_salary)

top_companies = df['company'].value_counts().head(15)
print("Companies Hiring Most Data Analysts:")
print(top_companies)