File_Meta_Data

Basic Correlation Matrix

correlation_function <- function(MainDirectory,FileName,DataSet)

{

fullPath <- paste(MainDirectory,FileName,sep="\\")
file.create(fullPath, showWarnings = TRUE)


sink(file =fullPath, append = TRUE, type = c("output", "message"),
     split = FALSE)

cor(hrData)
cat("Spearman Correlation Matrix : \n")
cor(DataSet, method="spearman")
cat("Kendall Correlation Matrix : \n")
cor(DataSet, method="kendall")
sink()

}

How to Get Rid of Duplicate Data in SQL

WITH population_table AS (
SELECT
        Person_id
        , income
        , zipcode
        , age
        , gender
        , ROW_NUMBER()OVER(PARTITION BY person_id,
        income,zipcode,age,gender ORDER BY person_id ) as row_counter 
FROM    dbo.people_table

SELECT    person_id 
FROM      population_table  
WHERE     row_counter > 1

How to Handle Missing Data with SQL

Select 
        Person_ID,
        ISNULL(AGE,
        (
          Select                
                      avg(AGE) 
           from       People_Table
           Where      subq1.zipcode = mainT1.zipcode
        ) as Age
        ISNULL(Income,
        (
          Select       avg(Income) 
          from         People_Table as subq2
          Where        subq2.zipcode = mainT1.zipcode
        ) as Income
        Zipcode
From    People_Table as mainT1

R Progamming Normalization

normalize <- function(x) {
    return ((x - min(x)) / (max(x) - min(x)))
  }

Python Normalization

Python(This can also depend on whether you are using Numpy, Pandas, etc)

x= [1,23,50,30,60]
normalized = (x-min(x))/(max(x)-min(x))