sai sairamdgr8

## Sai-Working-with-window-functions-on-Dataframes-using-PySpark-series.py
# Databricks notebook source

# Write a  pyspark code  to identify 𝒕𝒉𝒆 𝑯𝒊𝒈𝒉𝒆𝒔𝒕 & 𝑳𝒐𝒘𝒆𝒔𝒕 𝑺𝒂𝒍𝒂𝒓𝒊𝒆𝒅 𝑬𝒎𝒑𝒍𝒐𝒚𝒆𝒆 𝒊𝒏 𝒆𝒂𝒄𝒉 𝑫𝒆𝒑𝒂𝒓𝒕𝒎𝒆𝒏𝒕.


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

from pyspark.sql import SparkSession
from pyspark.sql.functions import min,max,col,rank,desc
from  pyspark.sql.window import Window

## Sai-Working-with-Lead-Lag-functions-on-Dataframes-using-PySpark-series.py
# COMMAND ----------

from pyspark.sql import SparkSession
from pyspark.sql.functions import lead,lag,round
from  pyspark.sql.functions import col
from pyspark.sql.window import Window
from pyspark.sql.types import *

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

## Sai-Working-with-Complex-JSON-data-structure-using-PySpark-series-4 raw dataset
[{
	"name": "John Doe",
	"age": 30,
	"email": "john@example.com",
	"address": {
		"street": "123 Main Street",
		"city": "New York",
		"zipcode": "10001"
	},
	"phones": [{

## Sai-Working-with-Complex-JSON-data-structure-using-PySpark-series-3 raw dataset
{ "data": [
{
"MainId": 1111,
"firstName": "bunny",
"lastName": "dgr8",
"categories": [
{
"CategoryID": 1,
"CategoryName": "Example"
}

## word-count-in-multiple-ways-in-python.py
# Databricks notebook source
s="sai is a good boy sai is working in SG sai is a DE guy he has a pet called rocky he is having two laptops."

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

words_split=s.split(" ")
print(words_split)
letters_split=[]
letters_split[:]=s[:]
print(letters_split)

## Sai_Joining_two_tables_Vetrically_when_no_common_column_is_invovled.py
# Databricks notebook source
from pyspark.sql import SparkSession
from pyspark.sql.functions import *
from pyspark.sql.types import *
from pyspark.sql import Window

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

spark=SparkSession.builder.appName("Joining two tables Vetrically when no common column is invovled").getOrCreate()

## a-after-b-true-or-false-check-in-given-string-using-python.py
s=input(str())

def a_b_occurence_check(s):
    s1=[]
    s1[:]=s
    #s1
    s1_a=[]
    for i in range(0,len(s1)):
        if s1[i]=='a':
            s1_a.append(i)

## Working_with_Json_data_using_pyspark_series-2.py
# Databricks notebook source
## input
"""
{"id":"1","Name":"Sai"Ram","City":"Hyderabad"}
{"id":"2","Name":"Avi"nash","City":"Bihar"}
{"id":"3","Name":"Di"nesh","City":"Kurool"}
{"id":"4","Name":"Pramod"Kumar","City":"Mathura"}

#### output
{"id":"1","Name":"SaiRam","City":"Hyderabad"}

## Sai-working-calculating-the-salary-credit-of-an-each-employee-with-their-attendance-using-Pyspark.py
from pyspark.sql import SparkSession
from pyspark.sql.types import *
from pyspark.sql.functions import *
from pyspark.sql.window import *

spark=SparkSession.builder.appName("Sai-working-calculating-the-salary-credit-of-an-each-employee-with-their-attendance-using-Pyspark").getOrCreate()

Users = [("James","","Smith","36636","M",30000,{"22/06/2022":"leave","23/06/2022":"present"}),
    ("Michael","Rose","","40288","M",3000,{"22/06/2022":"present","23/06/2022":"leave"}),
    ("Robert","","Williams","42114","M",40000,{"22/06/2022":"present","23/06/2022":"present"}),

## Sai-Working-find the biggest consecitve series from binary code -using-python.py
print("Input the binary code of 1's and 0's")
s=input(str())
print("Please press 1 or 0 to get their biggest series")
choose=input(str())
list_s=[]
list_1=[]
list_2=[]
for i_1 in s:
    list_s.append(i_1)
list_s_index=[]
	# Databricks notebook source

	# Write a pyspark code to identify 𝒕𝒉𝒆 𝑯𝒊𝒈𝒉𝒆𝒔𝒕 & 𝑳𝒐𝒘𝒆𝒔𝒕 𝑺𝒂𝒍𝒂𝒓𝒊𝒆𝒅 𝑬𝒎𝒑𝒍𝒐𝒚𝒆𝒆 𝒊𝒏 𝒆𝒂𝒄𝒉 𝑫𝒆𝒑𝒂𝒓𝒕𝒎𝒆𝒏𝒕.


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

	from pyspark.sql import SparkSession
	from pyspark.sql.functions import min,max,col,rank,desc
	from pyspark.sql.window import Window
	# COMMAND ----------

	from pyspark.sql import SparkSession
	from pyspark.sql.functions import lead,lag,round
	from pyspark.sql.functions import col
	from pyspark.sql.window import Window
	from pyspark.sql.types import *

	# COMMAND ----------
	[{
	"name": "John Doe",
	"age": 30,
	"email": "john@example.com",
	"address": {
	"street": "123 Main Street",
	"city": "New York",
	"zipcode": "10001"
	},
	"phones": [{
	{ "data": [
	{
	"MainId": 1111,
	"firstName": "bunny",
	"lastName": "dgr8",
	"categories": [
	{
	"CategoryID": 1,
	"CategoryName": "Example"
	}
	# Databricks notebook source
	s="sai is a good boy sai is working in SG sai is a DE guy he has a pet called rocky he is having two laptops."

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

	words_split=s.split(" ")
	print(words_split)
	letters_split=[]
	letters_split[:]=s[:]
	print(letters_split)
	# Databricks notebook source
	from pyspark.sql import SparkSession
	from pyspark.sql.functions import *
	from pyspark.sql.types import *
	from pyspark.sql import Window

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

	spark=SparkSession.builder.appName("Joining two tables Vetrically when no common column is invovled").getOrCreate()
	s=input(str())

	def a_b_occurence_check(s):
	s1=[]
	s1[:]=s
	#s1
	s1_a=[]
	for i in range(0,len(s1)):
	if s1[i]=='a':
	s1_a.append(i)
	# Databricks notebook source
	## input
	"""
	{"id":"1","Name":"Sai"Ram","City":"Hyderabad"}
	{"id":"2","Name":"Avi"nash","City":"Bihar"}
	{"id":"3","Name":"Di"nesh","City":"Kurool"}
	{"id":"4","Name":"Pramod"Kumar","City":"Mathura"}

	#### output
	{"id":"1","Name":"SaiRam","City":"Hyderabad"}
	print("Input the binary code of 1's and 0's")
	s=input(str())
	print("Please press 1 or 0 to get their biggest series")
	choose=input(str())
	list_s=[]
	list_1=[]
	list_2=[]
	for i_1 in s:
	list_s.append(i_1)
	list_s_index=[]