CREATE TABLE feedback_vnr(comments STRING);

load data LOCAL INPATH '/home/cloudera/Desktop/file.txt' INTO TABLE feedback_vnr;


select * from feedback_vnr;

select split(comments,' ') FROM feedback_vnr;
select explode(split(comments,' ')) FROM feedback_vnr
select word,count(*) from (select explode(split(comments,' ')) as word from feedback_vnr)  tmp GROUP BY word;

Most occurred first character in the word of a file

lines  = LOAD '/user/cloudera/my-friends' AS (line: chararray); 
tokens = FOREACH lines GENERATE flatten(TOKENIZE(line)) As token:chararray;
letters = FOREACH tokens  GENERATE SUBSTRING(token,0,1) As letter:chararray;
lettergrp = GROUP letters by letter; 
countletter  = FOREACH  lettergrp  GENERATE group,COUNT(letters);
OrderCnt = ORDER countletter BY $1 DESC; 
result = LIMIT OrderCnt 1;
STORE result into '/user/cloudera/dummy5556777777';

shiny new

library(shiny)
ui <- fluidPage(
   titlePanel("TABLE"),
    sidebarLayout(
      sidebarPanel(
        sliderInput("num", "integer", 1, 20, 1,
                    step = 1, animate =
                      animationOptions(interval=400, loop=TRUE))),
      mainPanel(
        tableOutput("prod")
      )) )
 
server <- function(input, output) {
    output$prod <- renderPrint({ x<-input$num
    for(i in 1:10){
      a=x*i
      cat(x,"x",i,"=",a,"<br>")
       }})}

shinyApp(ui = ui, server = server)

table shiny

library(shiny)
fluidPage(
  titlePanel("Manish"),
  sidebarLayout(
    sidebarPanel(
      sliderInput("num", "integer", 1, 20, 1,
         step = 1, animate =
 animationOptions(interval=400, loop=TRUE))),
    mainPanel(
      tableOutput("prod")
    ) ))
______________________________________________
function(input, output) {
  output$prod = renderPrint({ x=input$num
  for(i in 1:10){
    a=x*i
    cat(x,"x",i,"=",a,"<br>") } }) }

Shiny Code

library(shiny)
ui<-fluidPage(
  sidebarPanel(
    sliderInput("num","integer",1,200,5,step=1,animate = animationOptions(interval = 1000,loop = TRUE))),
  radioButtons("radio",label = h1("Choose one"),choices = list("Table"=1,"Even/Odd"=2,"Fact"=3),selected = 1),
  hr(),
  mainPanel(
    tableOutput("abc")
  )
)


server<-function(input,output)
{
 
    output$abc<-renderPrint({
      r<-input$radio
      x<-input$num
      if(r==1){
        for(i in 1:10)
        {
          cat(x,"X",i,"=",x*i,"<br>")
        }
      }else if(r==2)
      {
        if(x%%2==0)
        {
          print("Even")
        }else{
          print("Odd")
        }
      }
      else{
        print(factorial(x))
      }
    })
   
}   
   
shinyApp(ui=ui,server=server)

R Softwares

R      - https://cran.r-project.org/bin/windows/base/
RStudio   - https://www.rstudio.com/products/rstudio/download/

OCR -AI -ML

https://digi.bib.uni-mannheim.de/tesseract/tesseract-ocr-setup-3.05.02-20180621.exe
________________________________________________________________________
create path variable:
TESSDATA_PREFIX=C:\Program Files (x86)\Tesseract-OCR


_______________________________________________________________________
import os
import tempfile
import subprocess
import pytesseract
pytesseract.pytesseract.tesseract_cmd = 'C:/Program Files (x86)/Tesseract-OCR/tesseract'
def ocr(path):
    temp = tempfile.NamedTemporaryFile(delete=False)

    process = subprocess.Popen(['tesseract', path, temp.name], stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
    process.communicate()

    with open(temp.name + '.txt', 'r') as handle:
        contents = handle.read()

    os.remove(temp.name + '.txt')

    #os.remove(temp.name)
    

    return contents


str = ocr(r'C:\Users\Freeware Sys\Downloads\alpha.jpg')
print(str)

MR - Classification

word_list = ['Emma','Woodhouse','father','Taylor','Miss','been','she','her']
    #i'm using this example text in place of the file you are using
text = 'This is an example text. It will contain words you are looking for, like Emma, Emma, Emma, Woodhouse, Woodhouse, Father, Father, Taylor,Miss,been,she,her,her,her. I made them repeat to show that the code works.'
text = text.replace(',',' ') #these statements remove irrelevant punctuation
text = text.replace('.','')
text = text.lower() #this makes all the words lowercase, so that capitalization wont affect the frequency measurement
for repeatedword in word_list:
        counter = 0 #counter starts at 0
        for word in text.split():
            if repeatedword.lower() == word:
                counter = counter + 1 #add 1 every time there is a match in the list
        print(repeatedword,':', counter) #prints the word from 'word_list' and its frequency