python spark dataframe

1# import pyspark class Row from module sql
2from pyspark.sql import *
3
4# Create Example Data - Departments and Employees
5
6# Create the Departments
7department1 = Row(id='123456', name='Computer Science')
8department2 = Row(id='789012', name='Mechanical Engineering')
9department3 = Row(id='345678', name='Theater and Drama')
10department4 = Row(id='901234', name='Indoor Recreation')
11
12# Create the Employees
13Employee = Row("firstName", "lastName", "email", "salary")
14employee1 = Employee('michael', 'armbrust', 'no-reply@berkeley.edu', 100000)
15employee2 = Employee('xiangrui', 'meng', 'no-reply@stanford.edu', 120000)
16employee3 = Employee('matei', None, 'no-reply@waterloo.edu', 140000)
17employee4 = Employee(None, 'wendell', 'no-reply@berkeley.edu', 160000)
18employee5 = Employee('michael', 'jackson', 'no-reply@neverla.nd', 80000)
19
20# Create the DepartmentWithEmployees instances from Departments and Employees
21departmentWithEmployees1 = Row(department=department1, employees=[employee1, employee2])
22departmentWithEmployees2 = Row(department=department2, employees=[employee3, employee4])
23departmentWithEmployees3 = Row(department=department3, employees=[employee5, employee4])
24departmentWithEmployees4 = Row(department=department4, employees=[employee2, employee3])
25
26print(department1)
27print(employee2)
28print(departmentWithEmployees1.employees[0].email)
29