mydata<-read.csv("E:\\Yogesh BGLR Data Science Videos\\Aug'19\\50_Startups.CSV")
View(mydata)
attach(mydata)
mydata <- mydata[, c("Marketing.Spend", "Profit")]
mydata
## Marketing.Spend Profit
## 1 471784.10 192261.83
## 2 443898.53 191792.06
## 3 407934.54 191050.39
## 4 383199.62 182901.99
## 5 366168.42 166187.94
## 6 362861.36 156991.12
## 7 127716.82 156122.51
## 8 323876.68 155752.60
## 9 311613.29 152211.77
## 10 304981.62 149759.96
## 11 229160.95 146121.95
## 12 249744.55 144259.40
## 13 249839.44 141585.52
## 14 252664.93 134307.35
## 15 256512.92 132602.65
## 16 261776.23 129917.04
## 17 264346.06 126992.93
## 18 282574.31 125370.37
## 19 294919.57 124266.90
## 20 0.00 122776.86
## 21 298664.47 118474.03
## 22 299737.29 111313.02
## 23 303319.26 110352.25
## 24 304768.73 108733.99
## 25 140574.81 108552.04
## 26 137962.62 107404.34
## 27 134050.07 105733.54
## 28 353183.81 105008.31
## 29 118148.20 103282.38
## 30 107138.38 101004.64
## 31 91131.24 99937.59
## 32 88218.23 97483.56
## 33 46085.25 97427.84
## 34 214634.81 96778.92
## 35 210797.67 96712.80
## 36 205517.64 96479.51
## 37 201126.82 90708.19
## 38 197029.42 89949.14
## 39 185265.10 81229.06
## 40 174999.30 81005.76
## 41 172795.67 78239.91
## 42 164470.71 77798.83
## 43 148001.11 71498.49
## 44 35534.17 69758.98
## 45 28334.72 65200.33
## 46 1903.93 64926.08
## 47 297114.46 49490.75
## 48 0.00 42559.73
## 49 0.00 35673.41
## 50 45173.06 14681.40
mean(Profit)
## [1] 112012.6
dim(mydata)
## [1] 50 2
summary(mydata)
## Marketing.Spend Profit
## Min. : 0 Min. : 14681
## 1st Qu.:129300 1st Qu.: 90139
## Median :212716 Median :107978
## Mean :211025 Mean :112013
## 3rd Qu.:299469 3rd Qu.:139766
## Max. :471784 Max. :192262
qqnorm(Profit)
windows()
plot(Profit ~ Marketing.Spend)
cor(mydata)
## Marketing.Spend Profit
## Marketing.Spend 1.0000000 0.7477657
## Profit 0.7477657 1.0000000
m1 <- lm(Profit ~ Marketing.Spend)
summary(m1)
##
## Call:
## lm(formula = Profit ~ Marketing.Spend)
##
## Residuals:
## Min 1Q Median 3Q Max
## -83739 -18802 4925 15879 64642
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.000e+04 7.685e+03 7.808 4.29e-10 ***
## Marketing.Spend 2.465e-01 3.159e-02 7.803 4.38e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 27040 on 48 degrees of freedom
## Multiple R-squared: 0.5592, Adjusted R-squared: 0.55
## F-statistic: 60.88 on 1 and 48 DF, p-value: 4.381e-10
pv <- predict(m1,mydata)
class(pv)
## [1] "numeric"
Pv <- as.data.frame(pv)
pv
## 1 2 3 4 5 6 7
## 176279.11 169406.45 160542.80 154446.65 150249.15 149434.09 91480.54
## 8 9 10 11 12 13 14
## 139825.96 136803.53 135169.09 116482.39 121555.41 121578.79 122275.16
## 15 16 17 18 19 20 21
## 123223.53 124520.73 125154.08 129646.61 132689.21 60003.55 133612.17
## 22 23 24 25 26 27 28
## 133876.58 134759.39 135116.63 94649.51 94005.71 93041.43 147048.97
## 29 30 31 32 33 34 35
## 89122.27 86408.80 82463.69 81745.75 71361.69 112902.29 111956.59
## 36 37 38 39 40 41 42
## 110655.28 109573.12 108563.27 105663.85 103133.75 102590.64 100538.88
## 43 44 45 46 47 48 49
## 96479.79 68761.27 66986.90 60472.79 133230.16 60003.55 60003.55
## 50
## 71136.87
Finalreport <- cbind(mydata,pv)
Finalreport
## Marketing.Spend Profit pv
## 1 471784.10 192261.83 176279.11
## 2 443898.53 191792.06 169406.45
## 3 407934.54 191050.39 160542.80
## 4 383199.62 182901.99 154446.65
## 5 366168.42 166187.94 150249.15
## 6 362861.36 156991.12 149434.09
## 7 127716.82 156122.51 91480.54
## 8 323876.68 155752.60 139825.96
## 9 311613.29 152211.77 136803.53
## 10 304981.62 149759.96 135169.09
## 11 229160.95 146121.95 116482.39
## 12 249744.55 144259.40 121555.41
## 13 249839.44 141585.52 121578.79
## 14 252664.93 134307.35 122275.16
## 15 256512.92 132602.65 123223.53
## 16 261776.23 129917.04 124520.73
## 17 264346.06 126992.93 125154.08
## 18 282574.31 125370.37 129646.61
## 19 294919.57 124266.90 132689.21
## 20 0.00 122776.86 60003.55
## 21 298664.47 118474.03 133612.17
## 22 299737.29 111313.02 133876.58
## 23 303319.26 110352.25 134759.39
## 24 304768.73 108733.99 135116.63
## 25 140574.81 108552.04 94649.51
## 26 137962.62 107404.34 94005.71
## 27 134050.07 105733.54 93041.43
## 28 353183.81 105008.31 147048.97
## 29 118148.20 103282.38 89122.27
## 30 107138.38 101004.64 86408.80
## 31 91131.24 99937.59 82463.69
## 32 88218.23 97483.56 81745.75
## 33 46085.25 97427.84 71361.69
## 34 214634.81 96778.92 112902.29
## 35 210797.67 96712.80 111956.59
## 36 205517.64 96479.51 110655.28
## 37 201126.82 90708.19 109573.12
## 38 197029.42 89949.14 108563.27
## 39 185265.10 81229.06 105663.85
## 40 174999.30 81005.76 103133.75
## 41 172795.67 78239.91 102590.64
## 42 164470.71 77798.83 100538.88
## 43 148001.11 71498.49 96479.79
## 44 35534.17 69758.98 68761.27
## 45 28334.72 65200.33 66986.90
## 46 1903.93 64926.08 60472.79
## 47 297114.46 49490.75 133230.16
## 48 0.00 42559.73 60003.55
## 49 0.00 35673.41 60003.55
## 50 45173.06 14681.40 71136.87
View(Finalreport)
write.csv(Finalreport, "Simple Linear Regression.CSV")