DATA VISUALIZATION PROJECT

library(dplyr)
library(readr)
library(ggplot2)

?mtcars

head(mtcars)

tail(mtcars)

summary(mtcars)

      mpg             cyl             disp             hp             drat      
 Min.   :10.40   Min.   :4.000   Min.   : 71.1   Min.   : 52.0   Min.   :2.760  
 1st Qu.:15.43   1st Qu.:4.000   1st Qu.:120.8   1st Qu.: 96.5   1st Qu.:3.080  
 Median :19.20   Median :6.000   Median :196.3   Median :123.0   Median :3.695  
 Mean   :20.09   Mean   :6.188   Mean   :230.7   Mean   :146.7   Mean   :3.597  
 3rd Qu.:22.80   3rd Qu.:8.000   3rd Qu.:326.0   3rd Qu.:180.0   3rd Qu.:3.920  
 Max.   :33.90   Max.   :8.000   Max.   :472.0   Max.   :335.0   Max.   :4.930  
       wt             qsec             vs               am              gear      
 Min.   :1.513   Min.   :14.50   Min.   :0.0000   Min.   :0.0000   Min.   :3.000  
 1st Qu.:2.581   1st Qu.:16.89   1st Qu.:0.0000   1st Qu.:0.0000   1st Qu.:3.000  
 Median :3.325   Median :17.71   Median :0.0000   Median :0.0000   Median :4.000  
 Mean   :3.217   Mean   :17.85   Mean   :0.4375   Mean   :0.4062   Mean   :3.688  
 3rd Qu.:3.610   3rd Qu.:18.90   3rd Qu.:1.0000   3rd Qu.:1.0000   3rd Qu.:4.000  
 Max.   :5.424   Max.   :22.90   Max.   :1.0000   Max.   :1.0000   Max.   :5.000  
      carb       cylFactor
 Min.   :1.000   4:11     
 1st Qu.:2.000   6: 7     
 Median :2.000   8:14     
 Mean   :2.812            
 3rd Qu.:4.000            
 Max.   :8.000            

mean(mtcars$cyl)

[1] 6.1875

Scatter Plot

# scatter plot shape 1
ggplot(mtcars, aes(x=mpg, y=wt)) + 
  geom_point(shape=1)

# scatter plot shape 19
ggplot(mtcars, aes(x=mpg, y=wt)) + 
  geom_point(shape=19)

# shape identity
ggplot(mtcars,aes(x=mpg, y=wt, shape=cyl)) + 
  geom_point() + 
  scale_shape_identity()

mtcars$cylFactor <- factor(mtcars$cyl)

ggplot(mtcars,aes(x=mpg, y=wt, shape=cylFactor)) + 
  geom_point()

# color parameter
ggplot(mtcars, aes(x=mpg, y=wt)) + 
  geom_point(shape=19, color="blue")

# shape 19
ggplot(mtcars, aes(x=mpg, y=wt, color=cyl)) + 
  geom_point(shape=19)

ggplot(mtcars,aes(x=mpg, y=wt, color=cylFactor)) + 
  geom_point(shape=19)

# rename the legend
ggplot(mtcars, aes(x=mpg, y=wt, color=cylFactor)) + 
  geom_point(shape=19) + 
  labs(color="Cylinders")

# add new labels and title
ggplot(mtcars, aes(x=mpg, y=wt, color=cylFactor)) + 
  geom_point(shape=19) +
  xlab("Miles per Gallon") +
  ylab("Weight") +
  labs(color="Cylinders") +
  ggtitle("Scatterplot")

Line Graph EuStockMarkets Dataset

?EuStockMarkets

EuStockDF <- as.data.frame(EuStockMarkets)

head(EuStockDF)

# DAX stock price
ggplot(EuStockDF, aes(x=c(1:nrow(EuStockDF)), y=DAX)) + 
  geom_line()

# line width
ggplot(EuStockDF, aes(x=c(1:nrow(EuStockDF)), y=DAX)) + 
  geom_line(size=1.5) +
  labs(x="Stocks")

# color
ggplot(EuStockDF,aes(x=c(1:nrow(EuStockDF)), y=DAX)) + 
  geom_line(size=1.5, colour="light blue") + 
  labs(x="Time", y="Stocks")

# plot the 2 stocks
dax_smi_plot <- ggplot() +
  geom_line(data=EuStockDF, aes(x=c(1:nrow(EuStockDF)), y=DAX), size=1.5, colour="light blue") +
  geom_line(data=EuStockDF, aes(x=c(1:nrow(EuStockDF)), y=SMI), size=1.5, colour="red") +
  labs(x="Time", y="Stocks")
print(dax_smi_plot)

# all stocks
all_stocks <- ggplot() +
  geom_line(data = EuStockDF, aes(x=c(1:nrow(EuStockDF)), y=DAX), size=1, colour="light blue") +
  geom_line(data = EuStockDF, aes(x=c(1:nrow(EuStockDF)), y=SMI), size=1, colour="red") + 
  geom_line(data = EuStockDF, aes(x=c(1:nrow(EuStockDF)), y=CAC), size=1, colour="purple") + 
  geom_line(data = EuStockDF, aes(x=c(1:nrow(EuStockDF)), y=FTSE), size=1, colour="green") +
  labs(x="Time", y="Stocks")
print(all_stocks)

# rename the labels
legend_stocks <- all_stocks + 
  xlab("Days") + 
  ylab("Price") + 
  ggtitle("Eu Stocks")
print(legend_stocks)

Linear Regression

ggplot(mtcars, aes(x=mpg, y=wt))  + 
  geom_point(shape=19) +
  geom_smooth(method="lm", se=FALSE, color="red")

#se = TRUE -> confidence interval appear (default = true)

ggplot(mtcars, aes(x=mpg, y=wt, color=cylFactor)) + 
  geom_point(shape=19) +
  geom_smooth(method="lm", se=TRUE, color="red")

# add the labels
ggplot(mtcars, aes(x=mpg, y=wt, color=cylFactor)) + 
  geom_point(shape=19) + 
  geom_smooth(method="lm", se=TRUE, color="red") + 
  xlab("Miles per Gallon") + 
  ylab("Weight") +
  labs(color="Cylinders") +
  ggtitle("Linear Regression")

Gaussian Regression

ggplot(mtcars, aes(x=mpg, y=wt, color=cylFactor)) +
  geom_point(shape=19) + 
  geom_smooth(method="auto", se=TRUE, color="red") +
  xlab("Miles per Gallon") + 
  ylab("Weight") +
  labs(colour="Cylinders") + 
  ggtitle("Gaussian Regression")

End Of Report