Adding an extra column that gives a value for day of the week

July 30, 2022

I would like to add a column to my dataset that assigns to each date a number based on the week it is in

So I would have for day1 day2… etc day7 a value in the column for the days part of that week equal to 1, and for day8, day 9 etc… till day 14 a value equal to 2

what would be the best way to add that column ?

dput(head(sdata0))
structure(list(date = structure(c(18628, 18629, 18630, 18631, 
18632, 18633), class = "Date"), launches = c(-0.423325435196192, 
-0.95406180171082, -0.95406180171082, -0.95406180171082, 0.107410931318437, 
-0.423325435196192), pledged = c(-0.242997575062835, -0.300759417946595, 
-0.300759417946595, -0.300759417946595, 0.120035260531115, -0.103075942164302
), backers = c(-0.124417670254619, -0.269239525943361, -0.269239525943361, 
-0.269239525943361, 0.0620404689446357, -0.0918327527246523), 
    total_goal = c(-0.314834573033319, -0.33600837985916, -0.33600837985916, 
    -0.33600837985916, -0.205436571099805, -0.283073862794557
    ), mean_goal = c(-0.350195946618206, -0.422316295398803, 
    -0.422316295398803, -0.422316295398803, -0.199945219991962, 
    -0.24201542344731), US = c(0.179454667531907, -0.720497098001238, 
    -0.720497098001238, -0.720497098001238, 0.179454667531907, 
    -0.720497098001238), `number of success` = c(0.23782061224498, 
    -0.594551530612449, -0.594551530612449, -0.594551530612449, 
    1.07019275510241, 0.23782061224498), duration_days = c(-0.0399540270332042, 
    -1.6958261375219, -1.6958261375219, -1.6958261375219, 0.0152417099830856, 
    -0.0399540270332042), Twitter = c(-2.35635395414648, -1.37949565613006, 
    -2.47410026685382, -1.21813959797556, -0.995729896195041, 
    -1.226861547065), replies = c(-1.11872430995012, -0.454408610464075, 
    -1.06845177052955, -0.874543404193084, -1.24799655417443, 
    -0.906861465249162), likes = c(-0.812127568832484, -0.63113030668481, 
    -1.40968119485432, -1.1127549475184, -1.2106558412922, -1.22498280135666
    ), retweets = c(-0.606241425199139, -0.766152931679175, -1.64441036779204, 
    -1.39868247694445, -1.31077301003134, -1.3509601949059), 
    group_date = c("01", "01", "01", "01", "01", "01")), row.names = c(NA, 
6L), class = "data.frame")`

>Solution :

You can use the function week from lubridate like this:

library(dplyr)
library(lubridate)
sdata0 %>%
  mutate(week_number = week(ymd(date)))
#>         date   launches    pledged     backers total_goal  mean_goal         US
#> 1 2021-01-01 -0.4233254 -0.2429976 -0.12441767 -0.3148346 -0.3501959  0.1794547
#> 2 2021-01-02 -0.9540618 -0.3007594 -0.26923953 -0.3360084 -0.4223163 -0.7204971
#> 3 2021-01-03 -0.9540618 -0.3007594 -0.26923953 -0.3360084 -0.4223163 -0.7204971
#> 4 2021-01-04 -0.9540618 -0.3007594 -0.26923953 -0.3360084 -0.4223163 -0.7204971
#> 5 2021-01-05  0.1074109  0.1200353  0.06204047 -0.2054366 -0.1999452  0.1794547
#> 6 2021-01-06 -0.4233254 -0.1030759 -0.09183275 -0.2830739 -0.2420154 -0.7204971
#>   number of success duration_days    Twitter    replies      likes   retweets
#> 1         0.2378206   -0.03995403 -2.3563540 -1.1187243 -0.8121276 -0.6062414
#> 2        -0.5945515   -1.69582614 -1.3794957 -0.4544086 -0.6311303 -0.7661529
#> 3        -0.5945515   -1.69582614 -2.4741003 -1.0684518 -1.4096812 -1.6444104
#> 4        -0.5945515   -1.69582614 -1.2181396 -0.8745434 -1.1127549 -1.3986825
#> 5         1.0701928    0.01524171 -0.9957299 -1.2479966 -1.2106558 -1.3107730
#> 6         0.2378206   -0.03995403 -1.2268615 -0.9068615 -1.2249828 -1.3509602
#>   group_date week_number
#> 1         01           1
#> 2         01           1
#> 3         01           1
#> 4         01           1
#> 5         01           1
#> 6         01           1

^{Created on 2022-07-30 by the reprex package (v2.0.1)}