groupBy()

from pyspark.sql import SparkSession

spark = SparkSession.builder.appName('aggs').getOrCreate()

df = spark.read.csv('sales_info.csv', inferSchema = True, header = True)

df.printSchema()

df.show()

df.groupby("Company")

df.groupby("Company").mean().show()

df.groupby("Company").sum().show(
 
)

Aggregation

# general method do aggregation
df.agg({'Sales':'sum'}).show()
df.agg({'Sales':'max'}).show()  # notion line

# we could set the group by and then use aggregate
group_data = df.groupBy("Company")
group_data.agg({'Sales':'max'}).show() # the same effect with the notion line

Aggregation Function

from pyspark.sql.functions import countDistinct, avg, stddev
# aggregate function to select
df.select(countDistinct('Sales'))
df.select(countDistinct('Sales'),alias('Count of Distinct Sales'))

# how to format the result
from pyspark.sql.functions import format_number
# add alias
sales_std = df.select(
 
stddev('Sales').alias('std'))
# format the number
sales_std.select(format_number('std',2)).show()

# how to sort the result
# sort things by sales

df.orderBy("Sales").show()
df.orderBy(df['Sales'].desc()).show() # descending order