R and Analytics Basics3

sankara.deva2016@gmail.com

bharat sreeram, Ventech It Solutions.

-----------------------------------------------------------

# Linear REgression Implementation in R
---------------

df = 
read.csv("C:/Users/Hadoop/Desktop/prof.txt")

> df

    a  w   h   c

1  25 80 5.9 120
2  23 55 5.7  90
3  23 89 6.0 130
4  26 80 5.9 120
5  23 55 5.7  90
6  23 69 6.0 130
7  28 81 5.9 120
8  23 55 5.9 190
9  23 81 6.0 130
10 29 87 5.9 120
11 23 55 5.7 190
12 23 89 5.0 130


> 

Y = matrix(df$c, ncol=1)

Xdf = data.frame(beta = 1, a=df$a, w=df$w,
     h=df$h)
X = data.matrix(Xdf)

Xt = t(X)
XtX = Xt %*% X
inv = solve(XtX)
XtY = Xt %*% Y
beta = inv %*% XtY

-----------------------

model = lm(c ~ a + w + h , data=df)
-----------------------

Model testing: [accuracy testing ]

> x
 [1]  10  20  30  40  23  45  67  90 100 150
> y
 [1]  23  45  67  90  50 100 130 190 210 270
> cor(x,y)
[1] 0.9929889
> df = data.frame(x, y)
> lmfit = lm(y ~ x, data=df)

> params = coefficients(lmfit)
> a = params[1]
> b = params[2]

> test = data.frame(y=df$y)
> test$ycap = a + (b*df$x)
> test$dist = ((test$ycap-test$y)*100)/test$y

> test$res = "Fail"
> test$res[test$dist>=-20 & test$dist<=20] = "Pass"
> prop.table(table(test$res))


--------------------------------

non-linear regression implementation:

> dframe = data.frame(x = df$x,
+                    xsq = df$x^2,
+                    xcube = df$x^3,                             y = df$y)
> nlmfit = lm(y ~ x + xsq + xcube, data=dframe)
> p = coefficients(nlmfit)
> b0 = p[1]
> b1 = p[2]
> b2 = p[3]
> b3 = p[4]

> newtest = data.frame(y = dframe$y)
> newtest$ycap = b0 + (b1*dframe$x) +
+                      (b2 * dframe$xsq) +
+                      (b3 * dframe$xcube)

> newtest$dist = ((newtest$ycap-newtest$y)*100)/newtest$y

> newtest$res = "Fail"
> newtest$res[newtest$dist>=-20 & 
          newtest$dist<=20] = "Pass"
> prop.table(table(newtest$res))