In [9]:

    

load('/home/duyetdev/Downloads/Mumbai2013.RData')
write.csv(Mumbai2013, 'mumbai2013.csv')


    

In [13]:

    

Mumbai2013 <- read.csv('./mumbai2013.csv')


    

In [14]:

    

# Xem 6 dòng đầu
head(Mumbai2013)


    

    






X
Time
Temperature

	
1                  
2013-01-01 00:10:00
75.2               
	
2                  
2013-01-01 00:40:00
75.2               
	
3                  
2013-01-01 01:10:00
75.2               
	
4                  
2013-01-01 01:40:00
73.4               
	
5                  
2013-01-01 02:10:00
73.4               
	
6                  
2013-01-01 02:30:00
71.0               

In [15]:

    

# Xem 10 dòng cuối
tail(Mumbai2013, n = 10)


    

    






X
Time
Temperature

	
18319
18319              
2013-12-31 20:10:00
77.0               
	
18320
18320              
2013-12-31 20:30:00
76.0               
	
18321
18321              
2013-12-31 20:40:00
77.0               
	
18322
18322              
2013-12-31 21:10:00
77.0               
	
18323
18323              
2013-12-31 21:40:00
77.0               
	
18324
18324              
2013-12-31 22:10:00
75.2               
	
18325
18325              
2013-12-31 22:40:00
75.2               
	
18326
18326              
2013-12-31 23:10:00
75.2               
	
18327
18327              
2013-12-31 23:30:00
72.0               
	
18328
18328              
2013-12-31 23:40:00
75.2               

In [16]:

    

# Cấu trúc (struct), mô tả dataframe
str(Mumbai2013)


    

    




'data.frame':	18328 obs. of  3 variables:
 $ X          : int  1 2 3 4 5 6 7 8 9 10 ...
 $ Time       : Factor w/ 18328 levels "2013-01-01 00:10:00",..: 1 2 3 4 5 6 7 8 9 10 ...
 $ Temperature: num  75.2 75.2 75.2 73.4 73.4 71 73.4 73.4 75.2 73.4 ...

In [17]:

    

# Chiều 
dim(Mumbai2013)


    

    






	
18328
	
3

In [18]:

    

# Danh sách các cột
names(Mumbai2013)


    

    






	
'X'
	
'Time'
	
'Temperature'

In [19]:

    

# Class name
class(Mumbai2013)


    

    





'data.frame'

In [20]:

    

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

In [21]:

    

# Summary dataframe
summary(Mumbai2013)


    

    






       X                          Time        Temperature    
 Min.   :    1   2013-01-01 00:10:00:    1   Min.   : 53.00  
 1st Qu.: 4583   2013-01-01 00:40:00:    1   1st Qu.: 78.80  
 Median : 9164   2013-01-01 01:10:00:    1   Median : 82.40  
 Mean   : 9164   2013-01-01 01:40:00:    1   Mean   : 81.79  
 3rd Qu.:13746   2013-01-01 02:10:00:    1   3rd Qu.: 86.00  
 Max.   :18328   2013-01-01 02:30:00:    1   Max.   :102.20  
                 (Other)            :18322                   

In [22]:

    

glimpse(Mumbai2013)


    

    




Observations: 18,328
Variables: 3
$ X           <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, ...
$ Time        <fctr> 2013-01-01 00:10:00, 2013-01-01 00:40:00, 2013-01-01 0...
$ Temperature <dbl> 75.2, 75.2, 75.2, 73.4, 73.4, 71.0, 73.4, 73.4, 75.2, 7...

In [ ]:

    




    

In [ ]:

    




    

In [ ]: