spark dataframe example

Example 1: create spark dataframe in python

spark.createDataFrame(["10","11","13"], "string").toDF("age")

Example 2: create spark dataframe from pandas

import numpy as np
import pandas as pd

# Enable Arrow-based columnar data transfers
spark.conf.set("spark.sql.execution.arrow.enabled", "true")

# Generate a pandas DataFrame
pdf = pd.DataFrame(np.random.rand(100, 3))

# Create a Spark DataFrame from a pandas DataFrame using Arrow
df = spark.createDataFrame(pdf)

Example 3: python spark dataframe

# import pyspark class Row from module sql
from pyspark.sql import *

# Create Example Data - Departments and Employees

# Create the Departments
department1 = Row(id='123456', name='Computer Science')
department2 = Row(id='789012', name='Mechanical Engineering')
department3 = Row(id='345678', name='Theater and Drama')
department4 = Row(id='901234', name='Indoor Recreation')

# Create the Employees
Employee = Row("firstName", "lastName", "email", "salary")
employee1 = Employee('michael', 'armbrust', '[email protected]', 100000)
employee2 = Employee('xiangrui', 'meng', '[email protected]', 120000)
employee3 = Employee('matei', None, '[email protected]', 140000)
employee4 = Employee(None, 'wendell', '[email protected]', 160000)
employee5 = Employee('michael', 'jackson', '[email protected]', 80000)

# Create the DepartmentWithEmployees instances from Departments and Employees
departmentWithEmployees1 = Row(department=department1, employees=[employee1, employee2])
departmentWithEmployees2 = Row(department=department2, employees=[employee3, employee4])
departmentWithEmployees3 = Row(department=department3, employees=[employee5, employee4])
departmentWithEmployees4 = Row(department=department4, employees=[employee2, employee3])

print(department1)
print(employee2)
print(departmentWithEmployees1.employees[0].email)