Taking the frequency of three different columns [duplicate] - r

This question already has answers here:
Count number of rows within each group
(17 answers)
Closed 5 years ago.
I have a dataframe like this:
df <- structure(list(col1 = structure(c(1L, 1L, 2L, 3L, 1L, 3L, 1L,
3L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 4L), .Label = c("stock1",
"stock2", "stock3", "stock4"), class = "factor"), col2 = structure(c(4L,
5L, 7L, 6L, 5L, 5L, 5L, 6L, 6L, 8L, 8L, 4L, 3L, 3L, 1L, 2L, 3L
), .Label = c("comapny1", "comapny1+comapny4", "comapny4", "company1",
"company2", "company2+company1", "company3", "company4"), class = "factor"),
col3 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 2L, 2L), .Label = c("predictor1", "predictor2"
), class = "factor")), .Names = c("col1", "col2", "col3"), class = "data.frame", row.names = c(NA,
-17L))
I would like to take the frequency from the three columns.
Expected output
df2 <- structure(list(col1 = structure(c(1L, 1L, 1L, 2L, 4L, 1L, 1L,
3L, 3L, 1L, 2L, 1L), .Label = c("stock1", "stock2", "stock3",
"stock4"), class = "factor"), col2 = structure(c(1L, 2L, 3L,
3L, 3L, 4L, 5L, 5L, 6L, 6L, 7L, 8L), .Label = c("comapany1",
"comapany1+comapany4", "comapany4", "company1", "company2", "company2+company1",
"company3", "company4"), class = "factor"), col3 = structure(c(2L,
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("predictor1",
"predictor2"), class = "factor"), frequency = c(1L, 1L, 1L, 1L,
1L, 2L, 3L, 1L, 2L, 1L, 1L, 2L)), .Names = c("col1", "col2",
"col3", "frequency"), class = "data.frame", row.names = c(NA,
-12L))
How is it possible to make it?


We can use count
library(dplyr)
count(df, col1, col2, col3)
# A tibble: 12 x 4
# col1 col2 col3 n
# <fctr> <fctr> <fctr> <int>
# 1 stock1 comapny1 predictor2 1
# 2 stock1 comapny1+comapny4 predictor2 1
# 3 stock1 comapny4 predictor2 1
# 4 stock1 company1 predictor1 2
# 5 stock1 company2 predictor1 3
# 6 stock1 company2+company1 predictor1 1
# 7 stock1 company4 predictor1 2
# 8 stock2 comapny4 predictor2 1
# 9 stock2 company3 predictor1 1
#10 stock3 company2 predictor1 1
#11 stock3 company2+company1 predictor1 2
#12 stock4 comapny4 predictor2 1
Or with data.table
library(data.table)
setDT(df)[, .N, .(col1, col2, col3)]

Related

Frequency of one dataframe rows from another dataframe

Can someone help me how to count from another dataframe?
df1(out)
structure(list(Item = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), class = "factor", .Label = "0S1576"), LC = structure(c(1L,
1L, 2L, 2L, 2L, 2L, 3L, 3L, 3L), class = "factor", .Label = c("MW92",
"OY01", "RM11")), Fiscal.Month = c("2019-M06", "2019-M07", "2019-M06",
"2019-M07", "2019-M08", "2019-M09", "2019-M06", "2019-M07", "2019-M08"
)), row.names = c(NA, -9L), class = "data.frame")
df2(tempdf)
structure(list(Item = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "0S1576", class = "factor"),
LC = structure(c(1L, 1L, 1L, 1L, 2L, 3L, 4L, 6L, 5L, 1L,
2L, 2L, 3L, 3L), .Label = c("MW92", "OY01", "RM11", "RS11",
"WK14", "WK15"), class = "factor"), Fiscal.Month = structure(c(1L,
2L, 3L, 4L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("2019-M06",
"2019-M07", "2019-M08", "2019-M09"), class = "factor"), fcst = c(22L,
21L, 20L, 19L, 12L, 10L, 10L, 12L, 10L, 12L, 10L, 10L, 10L,
10L)), row.names = c(NA, -14L), class = "data.frame")
I want to count the frequency of Item,LC,Fiscal.month of df1 from df2

You can count using table and merge df1 with df2 by using factor and you need interaction as you use more than one column to merge.
table(factor(interaction(df2[c("Item","LC","Fiscal.Month")]), levels=interaction(df1)))
#0S1576.MW92.2019-M06 0S1576.MW92.2019-M07 0S1576.OY01.2019-M06
# 2 1 3
#0S1576.OY01.2019-M07 0S1576.OY01.2019-M08 0S1576.OY01.2019-M09
# 0 0 0
#0S1576.RM11.2019-M06 0S1576.RM11.2019-M07 0S1576.RM11.2019-M08
# 3 0 0
Or a speed improved version using match and tabulate:
(df1$freq <- tabulate(match(interaction(df2[c("Item","LC","Fiscal.Month")]), interaction(df1)), nrow(df1)))
#[1] 2 1 3 0 0 0 3 0 0
Or sometimes even faster using fastmatch:
library(fastmatch)
df1$freq <- tabulate(fmatch(interaction(df2[c("Item","LC","Fiscal.Month")]), interaction(df1)), nrow(df1))

Add a column by counting words for each row in R code

I have a data frame of 2511 rows and 6 columns with candy and color items. Please see the first 15 rows as below:
structure(list(x = 1:15, iteml = structure(c(2L, 1L, 1L, 1L,
5L, 4L, 4L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("{dulce1_rojo",
"{dulce2_verde", "{dulce7_plata", "{miel21_amarillo", "{miel30_azul"
), class = "factor"), item2 = structure(c(4L, 2L, 2L, 2L, 1L,
5L, 5L, 4L, 3L, 3L, 4L, 1L, 4L, 4L, 1L), .Label = c("chocolate2l_amarillo",
"dulce2_verde", "dulce7_plata", "miel21_amarillo", "miel30_azul"
), class = "factor"), item3 = structure(c(1L, 1L, 3L, 3L, 2L,
2L, 1L, 2L, 2L, 3L, 2L, 2L, 2L, 1L, 2L), .Label = c("chocolate2l_amarillo",
"chocolate30_azul", "miel21_amarillo"), class = "factor"), item4 = structure(c(2L,
2L, 2L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("chocolate2l_amarillo",
"chocolate32_violeta", "cookie30_azul"), class = "factor"), item5 = structure(c(2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("cookie2l_amarillo}",
"cookie32_violeta}"), class = "factor"), item6 = structure(c(4L,
6L, 1L, 3L, 6L, 1L, 2L, 4L, 6L, 2L, 5L, 6L, 1L, 2L, 4L), .Label = c(">{chocolate2l_amarillo}",
">{chocolate30_azul}", ">{chocolate32_violeta}", ">{dulce1_rojo}",
">{dulce7_plata}", ">{miel21_amarillo}"), class = "factor")), class = "data.frame", row.names = c(NA,
-15L))
I don`t know how can I count in new columns only the kind of candy that each row has. This first line as an expected ouput of the resulting data frame:
x iteml item2 item3 item4 item5 item6 dulce miel chocolate cookie
1 1 {dulce2_verde miel21_amarillo chocolate2l_amarillo chocolate32_violeta cookie32_violeta} >{dulce1_rojo} 2 1 2 1
I'm stuck and I'd appreciate a little help.

you can use apply function to apply grepl function by row for the initial data frame. Then you use sapply to iterate through four ingridients you indicated. Then use cbind to concatentate the initial data frame and the data frame with ingedients into one. Please see the code below:
# initialize data frame
df <- structure(list(x = 1:15, iteml = structure(c(2L, 1L, 1L, 1L,
5L, 4L, 4L, 3L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), .Label = c("{dulce1_rojo",
"{dulce2_verde", "{dulce7_plata", "{miel21_amarillo", "{miel30_azul"
), class = "factor"), item2 = structure(c(4L, 2L, 2L, 2L, 1L,
5L, 5L, 4L, 3L, 3L, 4L, 1L, 4L, 4L, 1L), .Label = c("chocolate2l_amarillo",
"dulce2_verde", "dulce7_plata", "miel21_amarillo", "miel30_azul"
), class = "factor"), item3 = structure(c(1L, 1L, 3L, 3L, 2L,
2L, 1L, 2L, 2L, 3L, 2L, 2L, 2L, 1L, 2L), .Label = c("chocolate2l_amarillo",
"chocolate30_azul", "miel21_amarillo"), class = "factor"), item4 = structure(c(2L,
2L, 2L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("chocolate2l_amarillo",
"chocolate32_violeta", "cookie30_azul"), class = "factor"), item5 = structure(c(2L,
2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("cookie2l_amarillo}",
"cookie32_violeta}"), class = "factor"), item6 = structure(c(4L,
6L, 1L, 3L, 6L, 1L, 2L, 4L, 6L, 2L, 5L, 6L, 1L, 2L, 4L), .Label = c(">{chocolate2l_amarillo}",
">{chocolate30_azul}", ">{chocolate32_violeta}", ">{dulce1_rojo}",
">{dulce7_plata}", ">{miel21_amarillo}"), class = "factor")), class = "data.frame", row.names = c(NA,
-15L))
# counting ingridients
ingridients <- c("dulce", "miel", "chocolate", "cookie")
x <- sapply(ingridients, function(y) apply(df, 1, function(x) sum(grepl(y, x))))
df_res <- cbind(df, x)
head(df_res)
Output:
x iteml item2 item3 item4 item5 item6 dulce miel chocolate cookie
1 1 {dulce2_verde miel21_amarillo chocolate2l_amarillo chocolate32_violeta cookie32_violeta} >{dulce1_rojo} 2 1 2 1
2 2 {dulce1_rojo dulce2_verde chocolate2l_amarillo chocolate32_violeta cookie32_violeta} >{miel21_amarillo} 2 1 2 1
3 3 {dulce1_rojo dulce2_verde miel21_amarillo chocolate32_violeta cookie32_violeta} >{chocolate2l_amarillo} 2 1 2 1
4 4 {dulce1_rojo dulce2_verde miel21_amarillo chocolate2l_amarillo cookie32_violeta} >{chocolate32_violeta} 2 1 2 1
5 5 {miel30_azul chocolate2l_amarillo chocolate30_azul cookie30_azul cookie2l_amarillo} >{miel21_amarillo} 0 2 2 2
6 6 {miel21_amarillo miel30_azul chocolate30_azul cookie30_azul cookie2l_amarillo} >{chocolate2l_amarillo} 0 2 2 2

plot count of discrete data by date

I am new to ggplot2 and trying to plot a continuous histogram showing the evolution of reviews by date and rating.
My data set look like this:
date rating reviews
1 2017-11-24 1 some text here
2 2017-11-24 1 some text here
3 2017-12-02 5 some text here
4 2017-11-24 3 some text here
5 2017-11-24 3 some text here
6 2017-11-24 4 some text here
What I want to get is something like this:
for rating == 1
date count
1 2017-11-24 2
2 2017-11-25 7
.
.
.
and so on for rating == 2 and 3
I've tried
ggplot(aes(x = date, y = rating), data = df) + geom_line()
but it gives me only rating on the y axis and not counts:

You can use dplyr to get the desired dataset and pass that into ggplot();
library(dplyr)
library(ggplot2)
sample_data %>% group_by(rating,date) %>% summarise(n=n()) %>%
ggplot(aes(x=date, y=n, group=rating, color=as.factor(rating))) +
geom_line(size=1.5) + geom_point()
Data:
sample_data <- structure(list(id = c(1L, 2L, 2L, 3L, 4L, 5L, 5L, 6L, 6L, 1L,
2L, 3L, 3L, 4L, 5L, 6L, 1L, 2L, 2L, 2L, 3L, 4L, 5L, 6L), date = structure(c(1L,
1L, 3L, 7L, 1L, 1L, 1L, 1L, 5L, 2L, 3L, 8L, 8L, 3L, 4L, 5L, 5L,
6L, 6L, 6L, 9L, 6L, 6L, 6L), .Label = c("2017-11-24", "2017-11-25",
"2017-11-26", "2017-11-27", "2017-11-28", "2017-11-29", "2017-12-02",
"2017-12-04", "2017-12-08"), class = "factor"), rating = c(1L,
1L, 1L, 5L, 3L, 3L, 3L, 4L, 4L, 1L, 1L, 5L, 5L, 3L, 3L, 4L, 1L,
1L, 1L, 1L, 5L, 3L, 3L, 4L), reviews = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L), .Label = "review", class = "factor")), .Names = c("id",
"date", "rating", "reviews"), row.names = c(NA, 24L), class = "data.frame")

Just using some dummy data:
library(tidyverse)
set.seed(999)
df <- data.frame(date = sample(seq(as.Date('2017/01/01'), as.Date('2017/04/01'), by="day"), 2000, replace = T),
rating = sample(1:5,2000,replace = T))
df$rating <- as.factor(df$rating)
df %>%
group_by(date,rating) %>%
summarise(n = length(rating)) %>%
ggplot(aes(date,n, color = rating)) +
geom_line() +
geom_point()

Summarise/reshape data in R

For an example dataframe:
df <- structure(list(id = 1:18, region = structure(c(1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("a",
"b"), class = "factor"), age.cat = structure(c(1L, 1L, 2L, 2L,
2L, 3L, 3L, 4L, 1L, 1L, 1L, 1L, 2L, 2L, 3L, 4L, 4L, 4L), .Label = c("0-18",
"19-35", "36-50", "50+"), class = "factor")), .Names = c("id",
"region", "age.cat"), class = "data.frame", row.names = c(NA,
-18L))
I want to reshape the data, as detailed below:
region 0-18 19-35 36-50 50+
a 2 3 2 1
b 4 2 1 3
Do I simply aggregate or reshape the data? Any help would be much appreciated.

You can do it just using table:
table(df$region, df$age.cat)
0-18 19-35 36-50 50+
a 2 3 2 1
b 4 2 1 3

Using reshape2:
install.packages('reshape2')
library(reshape2)
df1 <- melt(df, measure.vars = 'age.cat')
df1 <- dcast(df1, region ~ value)

Merge / match two variables with one group of variables from another dataframe

I have two data.frames df.1 and df.2 that I would merge or otherwise select data from to create a new data.frame. df.1 contains information about each individual (ID), sampling event (Event), Site and sample number (Sample). The tricky part for me is that Site and the corresponding Sample for each ID-Event pairing is different. For example, F3-3 has Site "plum" for Sample "1" and M6-3 has Site "pear" for Sample "1".
df.2 has Sample1 and Sample2 which corresponds to the Sample information in df.1 by way of the ID-Event pairing.
I'd like to match/merge the information between these two data.frames. Essentially, get the "word" from Site in df.1 that matches the Sample number. An example (df.3) is below.
Each ID-Event pairing will only have one Site and corresponding Sample (e.g. "Apple" will correspond to "1" not to "1" and "4"). I know I could use merge if I was only matching, for example, Sample1 or Sample2 I am not sure how to do this with both to populate Site1 and Site2 with the correctly matched word.
df.1 <- structure(list(ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("F1",
"F3", "M6"), class = "factor"), Sex = structure(c(1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L), .Label = c("F", "M"), class = "factor"), Event = c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L,
4L, 4L, 4L, 4L), Site = structure(c(1L, 3L, 9L, 7L, 8L, 10L,
2L, 6L, 4L, 5L, 1L, 9L, 7L, 8L, 10L, 5L, 10L, 2L, 6L, 4L, 5L,
1L, 9L, 2L, 6L, 4L, 5L, 1L, 8L, 3L, 10L, 4L, 2L, 6L, 4L, 5L,
1L), .Label = c("Apple", "Banana", "Grape", "Guava", "Kiwi",
"Mango", "Orange", "Peach", "Pear", "Plum"), class = "factor"),
Sample = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 1L, 2L,
3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L, 6L, 1L, 2L, 3L, 4L, 5L,
6L, 7L, 8L, 9L, 10L, 1L, 2L, 3L, 4L, 5L)), .Names = c("ID",
"Sex", "Event", "Site", "Sample"), class = "data.frame", row.names = c(NA,
-37L))
#
df.2 <- structure(list(Sample1 = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L), Sample2 = c(2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
3L, 4L, 5L), V1 = c(0.12, 0.497, 0.715, 0, 0.001, 0, 0.829, 0,
0, 0.001, 0, 0.829), V2 = c(0.107, 0.273, 0.595, 0, 0.004, 0,
0.547, 0.001, 0.001, 0.107, 0.273, 0.595), ID = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("F1",
"M6"), class = "factor"), Sex = structure(c(1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("F", "M"), class = "factor"),
Event = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 3L, 3L, 3L)), .Names = c("Sample1",
"Sample2", "V1", "V2", "ID", "Sex", "Event"), class = "data.frame", row.names = c(NA,
-12L))
#
df.3 <- structure(list(Sample1 = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L), Sample2 = c(2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
3L, 4L, 5L), V1 = c(0.12, 0.497, 0.715, 0, 0.001, 0, 0.829, 0,
0, 0.001, 0, 0.829), V2 = c(0.107, 0.273, 0.595, 0, 0.004, 0,
0.547, 0.001, 0.001, 0.107, 0.273, 0.595), Site1 = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("Apple",
"Banana"), class = "factor"), Site2 = structure(c(2L, 8L, 6L,
7L, 9L, 1L, 5L, 3L, 4L, 5L, 3L, 4L), .Label = c("Banana", "Grape",
"Guava", "Kiwi", "Mango", "Orange", "Peach", "Pear", "Plum"), class = "factor"),
ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L), .Label = c("F1", "M6"), class = "factor"), Sex = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("F",
"M"), class = "factor"), Event = c(1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 3L, 3L, 3L)), .Names = c("Sample1", "Sample2",
"V1", "V2", "Site1", "Site2", "ID", "Sex", "Event"), class = "data.frame", row.names = c(NA, -12L))

Two merges should do it:
first <- merge(df.2, unique(df.1[,3:5]), by.x=c("Sample1","Event"), by.y=c("Sample","Event"), all.x=TRUE)
second <- merge(first, unique(df.1[,3:5]),by.x=c("Sample2","Event"), by.y=c("Sample","Event"), all.x=TRUE)
print(second)
Sample2 Event Sample1 V1 V2 ID Sex Site.x Site.y
1 10 1 1 0.000 0.001 F1 F Apple Kiwi
2 2 1 1 0.120 0.107 F1 F Apple Grape
3 3 1 1 0.497 0.273 F1 F Apple Pear
4 3 3 2 0.001 0.107 M6 M Banana Mango
5 4 1 1 0.715 0.595 F1 F Apple Orange
6 4 3 2 0.000 0.273 M6 M Banana Guava
7 5 1 1 0.000 0.000 F1 F Apple Peach
8 5 3 2 0.829 0.595 M6 M Banana Kiwi
9 6 1 1 0.001 0.004 F1 F Apple Plum
10 7 1 1 0.000 0.000 F1 F Apple Banana
11 8 1 1 0.829 0.547 F1 F Apple Mango
12 9 1 1 0.000 0.001 F1 F Apple Guava

Resources