Explain the sample and sampleBy functions in PySpark in Databricks

sample() and sampleBy() PySpark.py

# Databricks notebook source
# Importing packages
import pyspark
from pyspark.sql import SparkSession, Row
from pyspark.sql.types import MapType, StringType
from pyspark.sql.functions import col
from pyspark.sql.types import StructType,StructField, StringType        

# COMMAND ----------

# Implementing the sample() function and sampleBy() function in Databricks in PySpark 

spark = SparkSession.builder \
    .master("local[1]") \
    .appName("sample() and sampleBy() PySpark") \
    .getOrCreate()

dataframe = spark.range(100)
print(dataframe.sample(0.06).collect())

# Using sample() function
print(dataframe.sample(0.1,123).collect())

print(dataframe.sample(0.1,123).collect())

print(dataframe.sample(0.1,456).collect())

# Using the withReplacement(May contain duplicates)
## With Duplicates
print(dataframe.sample(True,0.3,123).collect()) 

## Without Duplicates
print(dataframe.sample(0.3,123).collect())

# Using sampleBy() function
dataframe2 = dataframe.select((dataframe.id % 3).alias("key"))

print(dataframe2.sampleBy("key", {0: 0.1, 1: 0.2},0).collect())