R Markdown

#Linear Regression:

# Linear regression analysis is used to predict the value of a variable based on 
# the value of another variable. The variable you want to predict is called the 
# dependent variable. The variable you are using to predict the other variable's
# value is called the independent variable.

data <- data.frame(
  Years_Exp = c(1.1, 1.3, 1.5, 2.0, 2.2, 2.9, 3.0, 3.2, 3.2, 3.7),
  Salary = c(39343.00, 46205.00, 37731.00, 43525.00,
             39891.00, 56642.00, 60150.00, 54445.00, 64445.00, 57189.00)
)


plot(data$Years_Exp, data$Salary,
     xlab = "Years Experienced",
     ylab = "Salary",
     main = "Scatter Plot of Years Experienced vs Salary")

library(caTools)
## Warning: package 'caTools' was built under R version 4.3.3
split = sample.split(data$Salary, SplitRatio = 0.7)
trainingset = subset(data, split == TRUE)
testset = subset(data, split == FALSE)


lm.r= lm(formula = Salary ~ Years_Exp,
         data = trainingset)

summary(lm.r)
## 
## Call:
## lm(formula = Salary ~ Years_Exp, data = trainingset)
## 
## Residuals:
##     2     3     4     6     7     8    10 
##  4889 -5153 -3282  2775  5499 -1775 -2953 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)   
## (Intercept)    31118       5576   5.581  0.00255 **
## Years_Exp       7844       2102   3.733  0.01353 * 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 4713 on 5 degrees of freedom
## Multiple R-squared:  0.7359, Adjusted R-squared:  0.6831 
## F-statistic: 13.93 on 1 and 5 DF,  p-value: 0.01353
new_data <- data.frame(Years_Exp = c(4.0, 4.5, 5.0))

predicted_salaries <- predict(lm.r, newdata = new_data)
print(predicted_salaries)
##        1        2        3 
## 62495.65 66417.88 70340.12
# Logistic Regression:

# Logistic regression estimates the probability of an event occurring, such as 
# voted or didn't vote, based on a given data set of independent variables

library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
summary(mtcars)
##       mpg             cyl             disp             hp       
##  Min.   :10.40   Min.   :4.000   Min.   : 71.1   Min.   : 52.0  
##  1st Qu.:15.43   1st Qu.:4.000   1st Qu.:120.8   1st Qu.: 96.5  
##  Median :19.20   Median :6.000   Median :196.3   Median :123.0  
##  Mean   :20.09   Mean   :6.188   Mean   :230.7   Mean   :146.7  
##  3rd Qu.:22.80   3rd Qu.:8.000   3rd Qu.:326.0   3rd Qu.:180.0  
##  Max.   :33.90   Max.   :8.000   Max.   :472.0   Max.   :335.0  
##       drat             wt             qsec             vs        
##  Min.   :2.760   Min.   :1.513   Min.   :14.50   Min.   :0.0000  
##  1st Qu.:3.080   1st Qu.:2.581   1st Qu.:16.89   1st Qu.:0.0000  
##  Median :3.695   Median :3.325   Median :17.71   Median :0.0000  
##  Mean   :3.597   Mean   :3.217   Mean   :17.85   Mean   :0.4375  
##  3rd Qu.:3.920   3rd Qu.:3.610   3rd Qu.:18.90   3rd Qu.:1.0000  
##  Max.   :4.930   Max.   :5.424   Max.   :22.90   Max.   :1.0000  
##        am              gear            carb      
##  Min.   :0.0000   Min.   :3.000   Min.   :1.000  
##  1st Qu.:0.0000   1st Qu.:3.000   1st Qu.:2.000  
##  Median :0.0000   Median :4.000   Median :2.000  
##  Mean   :0.4062   Mean   :3.688   Mean   :2.812  
##  3rd Qu.:1.0000   3rd Qu.:4.000   3rd Qu.:4.000  
##  Max.   :1.0000   Max.   :5.000   Max.   :8.000
library(caTools)


split <- sample.split(mtcars, SplitRatio = 0.8)
split
##  [1]  TRUE  TRUE  TRUE FALSE FALSE  TRUE  TRUE  TRUE FALSE  TRUE  TRUE
train_reg <- subset(mtcars, split == "TRUE")
test_reg <- subset(mtcars, split == "FALSE")

logistic_model <- glm(vs ~ wt + disp,
                      data = train_reg,
                      family = "binomial")
logistic_model
## 
## Call:  glm(formula = vs ~ wt + disp, family = "binomial", data = train_reg)
## 
## Coefficients:
## (Intercept)           wt         disp  
##     2.03395      2.54026     -0.05441  
## 
## Degrees of Freedom: 22 Total (i.e. Null);  20 Residual
## Null Deviance:       31.49 
## Residual Deviance: 12.69     AIC: 18.69
summary(logistic_model)
## 
## Call:
## glm(formula = vs ~ wt + disp, family = "binomial", data = train_reg)
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)  
## (Intercept)  2.03395    3.02219   0.673   0.5009  
## wt           2.54026    2.10430   1.207   0.2274  
## disp        -0.05441    0.02883  -1.887   0.0591 .
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 31.492  on 22  degrees of freedom
## Residual deviance: 12.692  on 20  degrees of freedom
## AIC: 18.692
## 
## Number of Fisher Scoring iterations: 7
predict_reg <- predict(logistic_model,
                       test_reg, type = "response")
predict_reg
##      Hornet 4 Drive   Hornet Sportabout            Merc 230  Cadillac Fleetwood 
##        2.108528e-02        1.482411e-04        9.148477e-01        3.319776e-05 
## Lincoln Continental      Toyota Corolla           Fiat X1-9       Porsche 914-2 
##        9.922485e-05        9.440919e-01        9.340524e-01        7.158836e-01 
##       Maserati Bora 
##        5.087486e-03