Scribd
Upload
9 views

SQL & Python Interview Q&A

Uploaded by

David Mramba
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
9 views

SQL & Python Interview Q&A

Uploaded by

David Mramba
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

SQL & Python Interview Q&A

1. Find the employee(s) with the second highest salary in the company

SQL: SELECT employee_id, salary


FROM employees
WHERE salary = (SELECT DISTINCT salary
FROM employees
ORDER BY salary DESC
LIMIT 1 OFFSET 1)

Pandas: second_highest_salary = employees['salary'].nlargest(2).iloc[-1]


second_highest_salary_employees = employees[employees['salary'] ==
second_highest_salary]

2. Find employees who earn more than the average salary of their department

SQL: SELECT employee_id, department_id, salary


FROM employees e
WHERE salary > (SELECT AVG(salary)
FROM employees
WHERE department_id = e.department_id)

Pandas: avg_salary_by_dept =
employees.groupby('department_id')['salary'].transform('mean')
higher_than_avg = employees[employees['salary'] > avg_salary_by_dept]

3. Identify the employees who have the longest tenure in each department

SQL: SELECT department_id, employee_id, hire_date


FROM employees e
WHERE hire_date = (SELECT MIN(hire_date)
FROM employees
WHERE department_id = e.department_id)

Pandas: longest_tenure =
employees.loc[employees.groupby('department_id')['hire_date'].idxmin()]

4. Determine the top N percent of employees based on salary

SQL: WITH ranked_employees AS (


SELECT employee_id, salary,
PERCENT_RANK() OVER (ORDER BY salary DESC) AS percentile
FROM employees
)
SELECT employee_id, salary
FROM ranked_employees
WHERE percentile <= 0.1 -- Adjust this value for top N percent

Pandas: top_n_percent = 0.1


salary_threshold = employees['salary'].quantile(1 - top_n_percent)
top_employees = employees[employees['salary'] >= salary_threshold]

5. Find employees who joined after a specific date

SQL: SELECT employee_id, hire_date


FROM employees
WHERE hire_date > '2020-01-01'

Pandas: recent_hires = employees[employees['hire_date'] > '2020-01-01']

6. Find the employee with the highest salary in each department


SQL: SELECT department_id, employee_id, salary
FROM employees e
WHERE salary = (SELECT MAX(salary)
FROM employees
WHERE department_id = e.department_id)

Pandas: highest_salary_per_dept =
employees.loc[employees.groupby('department_id')['salary'].idxmax()]

7. Find the average salary of employees by department

SQL: SELECT department_id, AVG(salary) AS avg_salary


FROM employees
GROUP BY department_id

Pandas: avg_salary_by_dept =
employees.groupby('department_id')['salary'].mean()

8. Find the total number of employees in each department

SQL: SELECT department_id, COUNT(*) AS total_employees


FROM employees
GROUP BY department_id

Pandas: total_employees_per_dept = employees.groupby('department_id').size()

9. Find employees whose salary is greater than the average salary

SQL: SELECT employee_id, salary


FROM employees
WHERE salary > (SELECT AVG(salary) FROM employees)
Pandas: avg_salary = employees['salary'].mean()
higher_than_avg = employees[employees['salary'] > avg_salary]

10.List employees who have been with the company for more than 5 years

SQL: SELECT employee_id, hire_date


FROM employees
WHERE hire_date <= CURRENT_DATE - INTERVAL '5 years'

Pandas: employees_5_years_plus = employees[employees['hire_date'] <=


pd.to_datetime('today') - pd.DateOffset(years=5)]

11.Find employees who have not received a salary increase in the last year

SQL: SELECT employee_id, last_salary_increase_date


FROM employees
WHERE last_salary_increase_date <= CURRENT_DATE - INTERVAL '1 year'

Pandas: one_year_ago = pd.to_datetime('today') - pd.DateOffset(years=1)


no_salary_increase = employees[employees['last_salary_increase_date'] <=
one_year_ago]

12.Count the number of employees who report to each manager

SQL: SELECT manager_id, COUNT(*) AS num_employees


FROM employees
GROUP BY manager_id

Pandas: employees_per_manager = employees.groupby('manager_id').size()

13.Find employees who have been in the company the longest in each
department
SQL: SELECT department_id, employee_id, hire_date
FROM employees e
WHERE hire_date = (SELECT MIN(hire_date)
FROM employees
WHERE department_id = e.department_id)

Pandas: longest_in_company_per_dept =
employees.loc[employees.groupby('department_id')['hire_date'].idxmin()]

14.Find employees whose department has the highest average salary

SQL: SELECT employee_id, department_id, salary


FROM employees e
WHERE department_id = (SELECT department_id
FROM employees
GROUP BY department_id
ORDER BY AVG(salary) DESC
LIMIT 1)

Pandas: dept_avg_salary = employees.groupby('department_id')['salary'].mean()


highest_avg_salary_dept = dept_avg_salary.idxmax()
high_salary_employees = employees[employees['department_id'] ==
highest_avg_salary_dept]

15.Get the number of employees who joined each month

SQL: SELECT EXTRACT(MONTH FROM hire_date) AS hire_month,


COUNT(*) AS num_employees
FROM employees
GROUP BY hire_month

Pandas: employees['hire_month'] = employees['hire_date'].dt.month


employees_per_month = employees.groupby('hire_month').size()
16.Find employees with the highest number of projects assigned

SQL: SELECT employee_id, COUNT(*) AS project_count


FROM employee_projects
GROUP BY employee_id
ORDER BY project_count DESC
LIMIT 1

Pandas: project_count = employee_projects.groupby('employee_id').size()


highest_project_count = project_count.idxmax()
employees_with_highest_projects =
employee_projects[employee_projects['employee_id'] == highest_project_count]

17.Find employees who belong to a specific department and have a salary


above a threshold

SQL: SELECT employee_id, department_id, salary


FROM employees
WHERE department_id = 3 AND salary > 60000

Pandas: specific_dept_salary = employees[(employees['department_id'] == 3) &


(employees['salary'] > 60000)]

18.Find employees who do not belong to any department

SQL: SELECT employee_id


FROM employees
WHERE department_id IS NULL

Pandas: no_dept_employees = employees[employees['department_id'].isna()]


19.Find employees who are younger than 30 years old

SQL: SELECT employee_id, birth_date


FROM employees
WHERE birth_date > CURRENT_DATE - INTERVAL '30 years'

Pandas: young_employees = employees[employees['birth_date'] >


pd.to_datetime('today') - pd.DateOffset(years=30)]

20.Find employees with a salary within a specific range

SQL: SELECT employee_id, salary


FROM employees
WHERE salary BETWEEN 50000 AND 70000

Pandas: salary_range = employees[(employees['salary'] >= 50000) &


(employees['salary'] <= 70000)]

You might also like