R Notebook

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.

plot(cars)

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.

summary(titanic_data)

  PassengerId       Survived          Pclass     
 Min.   :  1.0   Min.   :0.0000   Min.   :1.000  
 1st Qu.:223.5   1st Qu.:0.0000   1st Qu.:2.000  
 Median :446.0   Median :0.0000   Median :3.000  
 Mean   :446.0   Mean   :0.3838   Mean   :2.309  
 3rd Qu.:668.5   3rd Qu.:1.0000   3rd Qu.:3.000  
 Max.   :891.0   Max.   :1.0000   Max.   :3.000  
                                                 
     Name               Sex           
 Length:891         Length:891        
 Class :character   Class :character  
 Mode  :character   Mode  :character  
                                      
                                      
                                      
                                      
      Age            SibSp           Parch       
 Min.   : 0.42   Min.   :0.000   Min.   :0.0000  
 1st Qu.:20.12   1st Qu.:0.000   1st Qu.:0.0000  
 Median :28.00   Median :0.000   Median :0.0000  
 Mean   :29.70   Mean   :0.523   Mean   :0.3816  
 3rd Qu.:38.00   3rd Qu.:1.000   3rd Qu.:0.0000  
 Max.   :80.00   Max.   :8.000   Max.   :6.0000  
 NA's   :177                                     
    Ticket               Fare       
 Length:891         Min.   :  0.00  
 Class :character   1st Qu.:  7.91  
 Mode  :character   Median : 14.45  
                    Mean   : 32.20  
                    3rd Qu.: 31.00  
                    Max.   :512.33  
                                    
    Cabin             Embarked        
 Length:891         Length:891        
 Class :character   Class :character  
 Mode  :character   Mode  :character  
                                      
                                      
                                      
                                      

str(titanic_data)

tibble [891 x 12] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ PassengerId: num [1:891] 1 2 3 4 5 6 7 8 9 10 ...
 $ Survived   : num [1:891] 0 1 1 1 0 0 0 0 1 1 ...
 $ Pclass     : num [1:891] 3 1 3 1 3 3 1 3 3 2 ...
 $ Name       : chr [1:891] "Braund, Mr. Owen Harris" "Cumings, Mrs. John Bradley (Florence Briggs Thayer)" "Heikkinen, Miss. Laina" "Futrelle, Mrs. Jacques Heath (Lily May Peel)" ...
 $ Sex        : chr [1:891] "male" "female" "female" "female" ...
 $ Age        : num [1:891] 22 38 26 35 35 NA 54 2 27 14 ...
 $ SibSp      : num [1:891] 1 1 0 1 0 0 0 3 0 1 ...
 $ Parch      : num [1:891] 0 0 0 0 0 0 0 1 2 0 ...
 $ Ticket     : chr [1:891] "A/5 21171" "PC 17599" "STON/O2. 3101282" "113803" ...
 $ Fare       : num [1:891] 7.25 71.28 7.92 53.1 8.05 ...
 $ Cabin      : chr [1:891] NA "C85" NA "C123" ...
 $ Embarked   : chr [1:891] "S" "C" "S" "S" ...
 - attr(*, "spec")=
  .. cols(
  ..   PassengerId = col_double(),
  ..   Survived = col_double(),
  ..   Pclass = col_double(),
  ..   Name = col_character(),
  ..   Sex = col_character(),
  ..   Age = col_double(),
  ..   SibSp = col_double(),
  ..   Parch = col_double(),
  ..   Ticket = col_character(),
  ..   Fare = col_double(),
  ..   Cabin = col_character(),
  ..   Embarked = col_character()
  .. )

select a column

head(titanic_data$PassengerId,5)

[1] 1 2 3 4 5

tail(titanic_data)

select a single row

titanic_data[1,]

titanic_data[1:10,]

titanic_data[3,4]

titanic_data$Name[1:5]

[1] "Braund, Mr. Owen Harris"                            
[2] "Cumings, Mrs. John Bradley (Florence Briggs Thayer)"
[3] "Heikkinen, Miss. Laina"                             
[4] "Futrelle, Mrs. Jacques Heath (Lily May Peel)"       
[5] "Allen, Mr. William Henry"                           

table command tablulates one variable vs other variable

get the no. of people who survived and no of people who does not survived

table(titanic_data$Survived)

  0   1 
549 342 

percentage of people servived and died

t<-table(titanic_data$Survived)
prop.table(t)

        0         1 
0.6161616 0.3838384 

t<-table(titanic_data$Sex,titanic_data$Survived)
prop.table(t,margin=1)

        
                 0         1
  female 0.2579618 0.7420382
  male   0.8110919 0.1889081

prop.table(t,margin=2)

        
                 0         1
  female 0.1475410 0.6812865
  male   0.8524590 0.3187135

Data manipulation using dplyr

titanic_data %>% group_by(Pclass) %>% summarise(mean_Price = mean(Fare))

`summarise()` ungrouping output (override with `.groups` argument)

titanic_data %>% select(Name,Age) %>% arrange(desc(Age)) %>% head(10)

titanic_data %>% group_by(Sex,Pclass) %>%
  summarise(count = n_distinct(Name))

`summarise()` regrouping output by 'Sex' (override with `.groups` argument)

titanic_data %>% group_by(Sex,Pclass) %>%
  summarise(count = n_distinct(Name)) %>% 
  mutate(count_2 = count/2)

`summarise()` regrouping output by 'Sex' (override with `.groups` argument)

titanic_data %>% group_by(Sex,Pclass) %>%
  summarise(count = n_distinct(Name)) %>% 
  spread(Sex,count)

`summarise()` regrouping output by 'Sex' (override with `.groups` argument)