I have an output of apriori function, which mines data and gives set of rules. I want to convert it to data frame for further processing.
The rules object looks like this:
> inspect(output)
lhs rhs support confidence lift
1 {curtosis=(846,1.27e+03]} => {skewness=(-0.254,419]} 0.2611233 0.8044944 2.418776
2 {variance=(892,1.34e+03]} => {notes.class=FALSE} 0.3231218 0.9888393 1.781470
3 {variance=(-0.336,446]} => {notes.class=TRUE} 0.2859227 0.8634361 1.940608
4 {skewness=(837,1.26e+03]} => {notes.class=FALSE} 0.2924872 0.8774617 1.580815
5 {entropy=(-0.155,386],
class=FALSE} => {skewness=(837,1.26e+03]} 0.1597374 0.9521739 2.856522
6 {variance=(-0.336,446],
curtosis=(846,1.27e+03]} => {skewness=(-0.254,419]} 0.1378556 0.8325991 2.503275
We can create rules object using data frame. Data frame looks like this:
> data
variance skewness curtosis entropy notes.class
1 (892,1.34e+03] (837,1.26e+03] (-0.268,424] (386,771] FALSE
2 (892,1.34e+03] (-0.254,419] (424,846] (771,1.16e+03] FALSE
3 (892,1.34e+03] (837,1.26e+03] (-0.268,424] (-0.155,386] FALSE
4 (446,892] (-0.254,419] (846,1.27e+03] (386,771] FALSE
Than we can get output variable using this:
> output <- apriori(data)
There was used arules package. dput(output) gives this:
new("rules"
, lhs = new("itemMatrix"
, data = new("ngCMatrix"
, i = c(8L, 2L, 0L, 5L, 9L, 12L, 0L, 8L, 0L, 3L, 0L, 8L, 8L, 13L, 8L,
10L, 3L, 10L, 8L, 11L, 8L, 13L, 3L, 12L, 2L, 5L, 2L, 6L, 2L,
5L, 2L, 6L, 2L, 10L, 2L, 7L, 2L, 11L, 0L, 3L, 0L, 10L, 0L, 7L,
11L, 13L, 5L, 6L, 6L, 12L, 5L, 10L, 1L, 5L, 4L, 6L, 6L, 13L,
0L, 3L, 8L, 0L, 8L, 13L, 3L, 8L, 13L, 0L, 3L, 13L, 2L, 5L, 6L,
2L, 5L, 12L, 2L, 6L, 12L)
, p = c(0L, 1L, 2L, 3L, 4L, 6L, 8L, 10L, 12L, 14L, 16L, 18L, 20L, 22L,
24L, 26L, 28L, 30L, 32L, 34L, 36L, 38L, 40L, 42L, 44L, 46L, 48L,
50L, 52L, 54L, 56L, 58L, 61L, 64L, 67L, 70L, 73L, 76L, 79L)
, Dim = c(14L, 38L)
, Dimnames = list(NULL, NULL)
, factors = list()
)
, itemInfo = structure(list(labels = structure(c("variance=(-0.336,446]",
"variance=(446,892]", "variance=(892,1.34e+03]", "skewness=(-0.254,419]",
"skewness=(419,837]", "skewness=(837,1.26e+03]", "curtosis=(-0.268,424]",
"curtosis=(424,846]", "curtosis=(846,1.27e+03]", "entropy=(-0.155,386]",
"entropy=(386,771]", "entropy=(771,1.16e+03]", "notes.class=FALSE",
"notes.class=TRUE"), class = "AsIs"), variables = structure(c(5L,
5L, 5L, 4L, 4L, 4L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L), .Label = c("curtosis",
"entropy", "notes.class", "skewness", "variance"), class = "factor"),
levels = structure(c(4L, 8L, 12L, 2L, 6L, 10L, 3L, 7L, 11L,
1L, 5L, 9L, 13L, 14L), .Label = c("(-0.155,386]", "(-0.254,419]",
"(-0.268,424]", "(-0.336,446]", "(386,771]", "(419,837]",
"(424,846]", "(446,892]", "(771,1.16e+03]", "(837,1.26e+03]",
"(846,1.27e+03]", "(892,1.34e+03]", "FALSE", "TRUE"), class = "factor")), .Names = c("labels",
"variables", "levels"), row.names = c(NA, -14L), class = "data.frame")
, itemsetInfo = structure(list(), .Names = character(0), row.names = integer(0), class = "data.frame")
)
, rhs = new("itemMatrix"
, data = new("ngCMatrix"
, i = c(3L, 12L, 13L, 12L, 5L, 3L, 8L, 13L, 0L, 3L, 8L, 3L, 3L, 8L,
6L, 5L, 12L, 12L, 12L, 12L, 12L, 13L, 13L, 13L, 3L, 12L, 5L,
12L, 12L, 13L, 4L, 13L, 3L, 0L, 8L, 12L, 6L, 5L)
, p = 0:38
, Dim = c(14L, 38L)
, Dimnames = list(NULL, NULL)
, factors = list()
)
, itemInfo = structure(list(labels = structure(c("variance=(-0.336,446]",
"variance=(446,892]", "variance=(892,1.34e+03]", "skewness=(-0.254,419]",
"skewness=(419,837]", "skewness=(837,1.26e+03]", "curtosis=(-0.268,424]",
"curtosis=(424,846]", "curtosis=(846,1.27e+03]", "entropy=(-0.155,386]",
"entropy=(386,771]", "entropy=(771,1.16e+03]", "notes.class=FALSE",
"notes.class=TRUE"), class = "AsIs"), variables = structure(c(5L,
5L, 5L, 4L, 4L, 4L, 1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L), .Label = c("curtosis",
"entropy", "notes.class", "skewness", "variance"), class = "factor"),
levels = structure(c(4L, 8L, 12L, 2L, 6L, 10L, 3L, 7L, 11L,
1L, 5L, 9L, 13L, 14L), .Label = c("(-0.155,386]", "(-0.254,419]",
"(-0.268,424]", "(-0.336,446]", "(386,771]", "(419,837]",
"(424,846]", "(446,892]", "(771,1.16e+03]", "(837,1.26e+03]",
"(846,1.27e+03]", "(892,1.34e+03]", "FALSE", "TRUE"), class = "factor")), .Names = c("labels",
"variables", "levels"), row.names = c(NA, -14L), class = "data.frame")
, itemsetInfo = structure(list(), .Names = character(0), row.names = integer(0), class = "data.frame")
)
, quality = structure(list(support = c(0.261123267687819, 0.323121808898614,
0.285922684172137, 0.292487235594457, 0.159737417943107, 0.137855579868709,
0.137855579868709, 0.142231947483589, 0.142231947483589, 0.110138584974471,
0.110138584974471, 0.12399708242159, 0.153902261123268, 0.107221006564551,
0.13056163384391, 0.13056163384391, 0.150984682713348, 0.139314369073669,
0.100656455142232, 0.107221006564551, 0.154631655725748, 0.165572574762947,
0.112326768781911, 0.105762217359592, 0.12180889861415, 0.181619256017505,
0.181619256017505, 0.102844638949672, 0.105762217359592, 0.12837345003647,
0.12837345003647, 0.137855579868709, 0.137855579868709, 0.137855579868709,
0.137855579868709, 0.13056163384391, 0.13056163384391, 0.13056163384391
), confidence = c(0.804494382022472, 0.988839285714286, 0.863436123348018,
0.87746170678337, 0.952173913043478, 0.832599118942731, 0.832599118942731,
0.859030837004405, 0.898617511520737, 0.853107344632768, 0.915151515151515,
0.80188679245283, 0.972350230414747, 0.885542168674699, 0.864734299516908,
0.913265306122449, 1, 0.974489795918367, 1, 1, 0.990654205607477,
1, 0.980891719745223, 0.873493975903614, 0.814634146341463, 0.943181818181818,
0.950381679389313, 1, 0.92948717948718, 0.931216931216931, 0.897959183673469,
1, 0.969230769230769, 0.895734597156398, 0.832599118942731, 1,
0.864734299516908, 0.93717277486911), lift = c(2.41877587226493,
1.78146998779801, 1.94060807395104, 1.580814717477, 2.85652173913043,
2.50327498261071, 2.56515369004603, 1.93070701234925, 2.71366653809456,
2.56493458221826, 2.81948927477017, 2.41093594836147, 2.92344773223381,
2.72826587247868, 2.58853870008227, 2.73979591836735, 1.80157687253614,
1.75561827884899, 1.80157687253614, 1.80157687253614, 1.78473970550309,
2.24754098360656, 2.20459434060771, 1.96321350977681, 2.44926187419769,
1.69921455023295, 2.85114503816794, 1.80157687253614, 1.67454260588295,
2.09294821753838, 2.68799572230639, 2.24754098360656, 2.91406882591093,
2.70496064471679, 2.56515369004603, 1.80157687253614, 2.58853870008227,
2.81151832460733)), row.names = c(NA, 38L), .Names = c("support",
"confidence", "lift"), class = "data.frame")
, info = structure(list(data = data, ntransactions = 1371L, support = 0.1,
confidence = 0.8), .Names = c("data", "ntransactions", "support",
"confidence"))
)
We can't duplicate your data from your question (oh, you just added your data as I was typing this! Sorry!), so I'll use the example from the arules package:
library('arules');
data("Adult")
## Mine association rules.
rules <- apriori(Adult,
parameter = list(supp = 0.5, conf = 0.9,
target = "rules"))
Then I can duplicate the stuff output from inspect(rules):
> ruledf = data.frame(
lhs = labels(lhs(rules))$elements,
rhs = labels(rhs(rules))$elements,
rules#quality)
> head(ruledf)
lhs rhs support confidence lift
1 {} {capital-gain=None} 0.9173867 0.9173867 1.0000000
2 {} {capital-loss=None} 0.9532779 0.9532779 1.0000000
3 {hours-per-week=Full-time} {capital-gain=None} 0.5435895 0.9290688 1.0127342
4 {hours-per-week=Full-time} {capital-loss=None} 0.5606650 0.9582531 1.0052191
5 {sex=Male} {capital-gain=None} 0.6050735 0.9051455 0.9866565
6 {sex=Male} {capital-loss=None} 0.6331027 0.9470750 0.9934931
and do stuff like order by decreasing lift:
head(ruledf[order(-ruledf$lift),])
The help for the rules class: http://www.rdocumentation.org/packages/arules/functions/rules-class.html will tell you what you can get from your rules object - I just used that information to build a data frame. If its not exactly what you want, then cook one up using your own recipe!
Run apriori in data Adult
rules <- apriori(Adult, parameter = list(supp = 0.5, conf = 0.9, target =
"rules"))
Inspect LHS, RHS, support, confidence and lift
arules::inspect(rules)
Create a dataframe
df = data.frame(
lhs = labels(lhs(rules)),
rhs = labels(rhs(rules)),
rules#quality)
View top 6 lines in new dataframe
head(df)
This does the trick
rules_dataframe <- as(output, 'data.frame')
Related
Here is a geom_tile displaying hours and days of the week, how can it made to display each hour (i.e. 00:00 through to 23:00 on the x axis)?
library(tidyverse)
df %>%
ggplot(aes(hour, day, fill = value)) +
geom_tile(colour = "ivory")
Currently it displays every fifth hour:
I have tried a bunch of different things, and would prefer a 'best practice' way (i.e. without manually generating labels), but in case labels are needed, here's one way to produce them hour_labs <- 0:23 %>% { ifelse(nchar(.) == 1, paste0("0", .), .) } %>% paste0(., ":00")
Data for reproducible example
df <- structure(list(day = structure(c(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, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L,
5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L), .Label = c("Sunday",
"Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"
), class = c("ordered", "factor")), hour = c(0L, 2L, 3L, 5L,
6L, 7L, 8L, 10L, 11L, 12L, 13L, 18L, 21L, 22L, 23L, 0L, 1L, 2L,
3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 20L, 21L, 22L,
23L, 0L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L,
20L, 21L, 22L, 23L, 0L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L,
11L, 13L, 14L, 20L, 21L, 22L, 23L, 0L, 1L, 2L, 3L, 4L, 5L, 6L,
7L, 8L, 9L, 10L, 11L, 12L, 13L, 15L, 20L, 21L, 22L, 23L, 0L,
1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 11L, 13L, 14L, 15L, 16L,
19L, 21L, 0L, 1L, 2L, 3L, 7L, 8L, 10L, 13L, 14L, 22L, 23L), value = c(1L,
1L, 1L, 2L, 1L, 3L, 1L, 1L, 2L, 1L, 3L, 1L, 2L, 13L, 13L, 24L,
39L, 21L, 17L, 25L, 22L, 27L, 28L, 19L, 6L, 2L, 2L, 1L, 2L, 2L,
7L, 23L, 38L, 18L, 26L, 21L, 20L, 31L, 40L, 35L, 22L, 5L, 3L,
2L, 7L, 4L, 3L, 3L, 3L, 17L, 13L, 23L, 24L, 19L, 31L, 13L, 35L,
50L, 22L, 13L, 7L, 2L, 1L, 1L, 1L, 1L, 3L, 14L, 17L, 33L, 32L,
32L, 25L, 29L, 27L, 38L, 26L, 11L, 8L, 4L, 5L, 5L, 3L, 1L, 1L,
3L, 14L, 21L, 24L, 22L, 25L, 26L, 23L, 58L, 36L, 26L, 6L, 3L,
1L, 5L, 3L, 1L, 1L, 3L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L,
1L, 1L)), row.names = c(NA, -116L), groups = structure(list(day = structure(1:7, .Label = c("Sunday",
"Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"
), class = c("ordered", "factor")), .rows = structure(list(1:15,
16:33, 34:51, 52:69, 70:88, 89:105, 106:116), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr"))), row.names = c(NA, 7L), class = c("tbl_df", "tbl",
"data.frame"), .drop = TRUE), class = c("grouped_df", "tbl_df",
"tbl", "data.frame"))
Here's one way using sprintf to construct labels.
library(dplyr)
library(ggplot2)
df %>%
mutate(lab = sprintf('%02d:00', hour)) %>%
ggplot() + aes(lab, day, fill = value) +
geom_tile(colour = "ivory") +
theme(axis.text.x = element_text(angle = 90, hjust = 1))
To complete the missing times apart from #Eric Watt's suggestion we can also use complete.
df %>%
mutate(lab = sprintf('%02d:00', hour)) %>%
tidyr::complete(lab = sprintf('%02d:00', 0:23)) %>%
ggplot() + aes(lab, day, fill = value) +
geom_tile(colour = "ivory") +
theme(axis.text.x = element_text(angle = 90, hjust = 1))
I would suggest making sure your data type is correctly representing your data. If your hour column is representing time in hours, then it should be a time based structure. For example:
df$hour <- as.POSIXct(as.character(df$hour), format = "%H", tz = "UTC")
Then you can tell ggplot that the x axis is a datetime variable using scale_x_datetime.
ggplot(df, aes(hour, day, fill = value)) +
geom_tile(colour = "ivory") +
scale_x_datetime(labels = date_format("%H:%M")) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
If you want a break for every hour, you can input that as breaks:
ggplot(df, aes(hour, day, fill = value)) +
geom_tile(colour = "ivory") +
scale_x_datetime(breaks = as.POSIXct(as.character(0:23), format = "%H", tz = "UTC"),
labels = date_format("%H:%M")) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
You can also use the scales package which has handy formatting options such as date_breaks:
library(scales)
ggplot(df, aes(hour, day, fill = value)) +
geom_tile(colour = "ivory") +
scale_x_datetime(breaks = date_breaks("1 hour"),
labels = date_format("%H:%M")) +
theme(axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5))
Using arules, I have got two itemsets, and I want to do subtraction between the two different itemsets when having same items.
> inspect(fsets_model_test)
items support count
[1] {SURFSKINTEMP=6,MODIS_LST=1} 0.01235235 663
[2] {TOTCO=13,MODIS_LST=1} 0.01373104 737
[3] {TOTCO=6,MODIS_LST=1} 0.01393598 748
[4] {TOTO3=15,MODIS_LST=1} 0.01265045 679
[5] {TOTH2OVAP=6,MODIS_LST=1} 0.01548236 831
[6] {TOTH2OVAP=1,MODIS_LST=1} 0.01565004 840
> inspect(fsets_nonsesmic_test)
items support count
[1] {TOTCO=6,MODIS_LST=1} 0.02192761 10013
[2] {TOTCO=13,MODIS_LST=1} 0.02261524 10327
[3] {TOTO3=15,MODIS_LST=1} 0.02432556 11108
[4] {SURFAIRTEMP=3,TOTH2OVAP=1,MODIS_LST=1} 0.01772735 8095
[5] {TOTH2OVAP=1,MODIS_LST=1} 0.02873605 13122
[6] {SURFAIRTEMP=3,TOTH2OVAP=1} 0.01856828 8479
you can see that itemsets fsets_model_test and itemsets fsets_nonsesmic_test have same items {TOTO3=15,MODIS_LST=1}
What I want to do is subtract support between two itemsets, in above case is
0.02432556 - 0.01265045 = 0.01167511, and then get a new itemsets.
How to implement this in arules, thanks
following are the example itemsets
one itemsets
fsets_model_test <- new("itemsets"
, items = new("itemMatrix"
, data = new("ngCMatrix"
, i = c(5L, 121L, 74L, 121L, 67L, 121L, 59L, 121L, 33L, 121L, 28L,
121L)
, p = c(0L, 2L, 4L, 6L, 8L, 10L, 12L)
, Dim = c(125L, 6L)
, Dimnames = list(NULL, NULL)
, factors = list()
)
, itemInfo = structure(list(labels = c("SURFSKINTEMP=1", "SURFSKINTEMP=2",
"SURFSKINTEMP=3", "SURFSKINTEMP=4", "SURFSKINTEMP=5", "SURFSKINTEMP=6",
"SURFSKINTEMP=7", "SURFSKINTEMP=8", "SURFSKINTEMP=9", "SURFSKINTEMP=10",
"SURFSKINTEMP=11", "SURFSKINTEMP=12", "SURFSKINTEMP=13", "SURFSKINTEMP=14",
"SURFSKINTEMP=15", "SURFSKINTEMP=16", "SURFAIRTEMP=1", "SURFAIRTEMP=2",
"SURFAIRTEMP=3", "SURFAIRTEMP=4", "SURFAIRTEMP=5", "SURFAIRTEMP=6",
"SURFAIRTEMP=7", "SURFAIRTEMP=8", "SURFAIRTEMP=9", "SURFAIRTEMP=10",
"SURFAIRTEMP=11", "SURFAIRTEMP=12", "TOTH2OVAP=1", "TOTH2OVAP=2",
"TOTH2OVAP=3", "TOTH2OVAP=4", "TOTH2OVAP=5", "TOTH2OVAP=6", "TOTH2OVAP=7",
"TOTH2OVAP=8", "TOTH2OVAP=9", "TOTH2OVAP=10", "TOTH2OVAP=11",
"TOTH2OVAP=12", "TOTH2OVAP=13", "TOTH2OVAP=14", "TOTH2OVAP=15",
"TOTH2OVAP=16", "TOTH2OVAP=17", "TOTO3=1", "TOTO3=2", "TOTO3=3",
"TOTO3=4", "TOTO3=5", "TOTO3=6", "TOTO3=7", "TOTO3=8", "TOTO3=9",
"TOTO3=10", "TOTO3=11", "TOTO3=12", "TOTO3=13", "TOTO3=14", "TOTO3=15",
"TOTO3=16", "TOTO3=17", "TOTCO=1", "TOTCO=2", "TOTCO=3", "TOTCO=4",
"TOTCO=5", "TOTCO=6", "TOTCO=7", "TOTCO=8", "TOTCO=9", "TOTCO=10",
"TOTCO=11", "TOTCO=12", "TOTCO=13", "TOTCO=14", "TOTCO=15", "TOTCH4=1",
"TOTCH4=2", "TOTCH4=3", "TOTCH4=4", "TOTCH4=5", "TOTCH4=6", "TOTCH4=7",
"TOTCH4=8", "TOTCH4=9", "TOTCH4=10", "TOTCH4=11", "TOTCH4=12",
"TOTCH4=13", "TOTCH4=14", "OLR_ARIS=1", "OLR_ARIS=2", "OLR_ARIS=3",
"OLR_ARIS=4", "OLR_ARIS=5", "OLR_ARIS=6", "OLR_ARIS=7", "OLR_ARIS=8",
"OLR_ARIS=9", "OLR_ARIS=10", "CLROLR_ARIS=1", "CLROLR_ARIS=2",
"CLROLR_ARIS=3", "CLROLR_ARIS=4", "CLROLR_ARIS=5", "CLROLR_ARIS=6",
"CLROLR_ARIS=7", "CLROLR_ARIS=8", "CLROLR_ARIS=9", "CLROLR_ARIS=10",
"OLR_NOAA=1", "OLR_NOAA=2", "OLR_NOAA=3", "OLR_NOAA=4", "OLR_NOAA=5",
"OLR_NOAA=6", "OLR_NOAA=7", "OLR_NOAA=8", "OLR_NOAA=9", "OLR_NOAA=10",
"MODIS_LST=1", "MODIS_LST=2", "MODIS_LST=3", "MODIS_LST=4"),
variables = structure(c(6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 10L, 10L, 10L, 10L, 10L, 10L, 10L,
10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 2L, 2L, 2L,
2L), .Label = c("CLROLR_ARIS", "MODIS_LST", "OLR_ARIS", "OLR_NOAA",
"SURFAIRTEMP", "SURFSKINTEMP", "TOTCH4", "TOTCO", "TOTH2OVAP",
"TOTO3"), class = "factor"), levels = structure(c(1L, 10L,
11L, 12L, 13L, 14L, 15L, 16L, 17L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 2L, 3L, 4L,
1L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 2L, 3L, 4L, 5L,
6L, 7L, 8L, 9L, 1L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 1L, 10L, 11L, 12L, 13L, 14L,
15L, 16L, 17L, 2L, 3L, 4L, 5L, 6L, 7L, 1L, 10L, 11L, 12L,
13L, 14L, 15L, 16L, 17L, 2L, 3L, 4L, 5L, 6L, 1L, 10L, 11L,
12L, 13L, 14L, 15L, 16L, 17L, 2L, 1L, 10L, 11L, 12L, 13L,
14L, 15L, 16L, 17L, 2L, 1L, 10L, 11L, 12L, 13L, 14L, 15L,
16L, 17L, 2L, 1L, 10L, 11L, 12L), .Label = c("1", "10", "11",
"12", "13", "14", "15", "16", "17", "2", "3", "4", "5", "6",
"7", "8", "9"), class = "factor")), .Names = c("labels",
"variables", "levels"), row.names = c(NA, -125L), class = "data.frame")
, itemsetInfo = structure(list(), .Names = character(0), row.names = integer(0), class = "data.frame")
)
, tidLists = NULL
, quality = structure(list(support = c(0.0123523493684093, 0.0137310429630734,
0.0139359839028207, 0.0126504452807691, 0.0154823564481872, 0.0156500353988896
), count = c(663, 737, 748, 679, 831, 840)), .Names = c("support",
"count"), row.names = c(NA, 6L), class = "data.frame")
, info = structure(list(data = model_data_tr, ntransactions = 53674L,
support = 0.01), .Names = c("data", "ntransactions", "support"
))
)
another itemsets is:
fsets_nonsesmic_test <- new("itemsets"
, items = new("itemMatrix"
, data = new("ngCMatrix"
, i = c(67L, 121L, 74L, 121L, 59L, 121L, 18L, 28L, 121L, 28L, 121L,
18L, 28L)
, p = c(0L, 2L, 4L, 6L, 9L, 11L, 13L)
, Dim = c(125L, 6L)
, Dimnames = list(NULL, NULL)
, factors = list()
)
, itemInfo = structure(list(labels = c("SURFSKINTEMP=1", "SURFSKINTEMP=2",
"SURFSKINTEMP=3", "SURFSKINTEMP=4", "SURFSKINTEMP=5", "SURFSKINTEMP=6",
"SURFSKINTEMP=7", "SURFSKINTEMP=8", "SURFSKINTEMP=9", "SURFSKINTEMP=10",
"SURFSKINTEMP=11", "SURFSKINTEMP=12", "SURFSKINTEMP=13", "SURFSKINTEMP=14",
"SURFSKINTEMP=15", "SURFSKINTEMP=16", "SURFAIRTEMP=1", "SURFAIRTEMP=2",
"SURFAIRTEMP=3", "SURFAIRTEMP=4", "SURFAIRTEMP=5", "SURFAIRTEMP=6",
"SURFAIRTEMP=7", "SURFAIRTEMP=8", "SURFAIRTEMP=9", "SURFAIRTEMP=10",
"SURFAIRTEMP=11", "SURFAIRTEMP=12", "TOTH2OVAP=1", "TOTH2OVAP=2",
"TOTH2OVAP=3", "TOTH2OVAP=4", "TOTH2OVAP=5", "TOTH2OVAP=6", "TOTH2OVAP=7",
"TOTH2OVAP=8", "TOTH2OVAP=9", "TOTH2OVAP=10", "TOTH2OVAP=11",
"TOTH2OVAP=12", "TOTH2OVAP=13", "TOTH2OVAP=14", "TOTH2OVAP=15",
"TOTH2OVAP=16", "TOTH2OVAP=17", "TOTO3=1", "TOTO3=2", "TOTO3=3",
"TOTO3=4", "TOTO3=5", "TOTO3=6", "TOTO3=7", "TOTO3=8", "TOTO3=9",
"TOTO3=10", "TOTO3=11", "TOTO3=12", "TOTO3=13", "TOTO3=14", "TOTO3=15",
"TOTO3=16", "TOTO3=17", "TOTCO=1", "TOTCO=2", "TOTCO=3", "TOTCO=4",
"TOTCO=5", "TOTCO=6", "TOTCO=7", "TOTCO=8", "TOTCO=9", "TOTCO=10",
"TOTCO=11", "TOTCO=12", "TOTCO=13", "TOTCO=14", "TOTCO=15", "TOTCH4=1",
"TOTCH4=2", "TOTCH4=3", "TOTCH4=4", "TOTCH4=5", "TOTCH4=6", "TOTCH4=7",
"TOTCH4=8", "TOTCH4=9", "TOTCH4=10", "TOTCH4=11", "TOTCH4=12",
"TOTCH4=13", "TOTCH4=14", "OLR_ARIS=1", "OLR_ARIS=2", "OLR_ARIS=3",
"OLR_ARIS=4", "OLR_ARIS=5", "OLR_ARIS=6", "OLR_ARIS=7", "OLR_ARIS=8",
"OLR_ARIS=9", "OLR_ARIS=10", "CLROLR_ARIS=1", "CLROLR_ARIS=2",
"CLROLR_ARIS=3", "CLROLR_ARIS=4", "CLROLR_ARIS=5", "CLROLR_ARIS=6",
"CLROLR_ARIS=7", "CLROLR_ARIS=8", "CLROLR_ARIS=9", "CLROLR_ARIS=10",
"OLR_NOAA=1", "OLR_NOAA=2", "OLR_NOAA=3", "OLR_NOAA=4", "OLR_NOAA=5",
"OLR_NOAA=6", "OLR_NOAA=7", "OLR_NOAA=8", "OLR_NOAA=9", "OLR_NOAA=10",
"MODIS_LST=1", "MODIS_LST=2", "MODIS_LST=3", "MODIS_LST=4"),
variables = structure(c(6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L,
6L, 6L, 6L, 6L, 6L, 6L, 6L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 5L, 5L, 5L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 9L, 9L, 9L, 10L, 10L, 10L, 10L, 10L, 10L, 10L,
10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 8L, 8L,
8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 7L, 7L,
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 2L, 2L, 2L,
2L), .Label = c("CLROLR_ARIS", "MODIS_LST", "OLR_ARIS", "OLR_NOAA",
"SURFAIRTEMP", "SURFSKINTEMP", "TOTCH4", "TOTCO", "TOTH2OVAP",
"TOTO3"), class = "factor"), levels = structure(c(1L, 10L,
11L, 12L, 13L, 14L, 15L, 16L, 17L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 2L, 3L, 4L,
1L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 2L, 3L, 4L, 5L,
6L, 7L, 8L, 9L, 1L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L,
2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 1L, 10L, 11L, 12L, 13L, 14L,
15L, 16L, 17L, 2L, 3L, 4L, 5L, 6L, 7L, 1L, 10L, 11L, 12L,
13L, 14L, 15L, 16L, 17L, 2L, 3L, 4L, 5L, 6L, 1L, 10L, 11L,
12L, 13L, 14L, 15L, 16L, 17L, 2L, 1L, 10L, 11L, 12L, 13L,
14L, 15L, 16L, 17L, 2L, 1L, 10L, 11L, 12L, 13L, 14L, 15L,
16L, 17L, 2L, 1L, 10L, 11L, 12L), .Label = c("1", "10", "11",
"12", "13", "14", "15", "16", "17", "2", "3", "4", "5", "6",
"7", "8", "9"), class = "factor")), .Names = c("labels",
"variables", "levels"), row.names = c(NA, -125L), class = "data.frame")
, itemsetInfo = structure(list(), .Names = character(0), row.names = integer(0), class = "data.frame")
)
, tidLists = NULL
, quality = structure(list(support = c(0.0219276058330541, 0.0226152387334415,
0.024325561329628, 0.0177273513650827, 0.0287360475123675, 0.0185682782241552
), count = c(10013, 10327, 11108, 8095, 13122, 8479)), .Names = c("support",
"count"), row.names = c(NA, 6L), class = "data.frame")
, info = structure(list(data = nonsesmic_data_tr, ntransactions = 456639L,
support = 0.01), .Names = c("data", "ntransactions", "support"
))
)
If the two sets come from transaction data that are compatible (see ? itemCoding) then you can use match to find matching itemsets in the two sets. After that, it should be easy to subtract the support.
I'll start with my goal which is to generate graphs for each of my variables (magnitude [mag], duration [dura] and distance [dist] but with distinct error bars for train and test. :
Almost finished graph
I have a data-frame that looks like this: (screenshot + dput below). It shows the responses (magnitude, distance, duration) during train and test of various biological strains along with their standard error (SEM). For example, the duration response at train is in column "train_avg_dura" and at test is "test_avg_dura". The standard error for each of these is in the columns train_duraSEM and test_duraSEM
df_group_sum.wide (data-frame)
dput data:
df_group_sum.wide <-
structure(list(strain = structure(1:8, .Label = c("N2", "acy-1(LOF)",
"acy-1(GOF)", "pde-4", "unc-43", "crh-1", "glr-1", "avr-14"), class = "factor"),
test_avg_dist = c(0.23102447163515, 0.198503787878788, 0.23892936802974,
0.247270588235294, 0.148316666666667, 0.195762711864407,
0.204740740740741, 0.238755154639175), test_avg_dura = c(1.04759733036707,
1.15537878787879, 0.914684014869888, 1.12286274509804, 0.828916666666667,
0.785491525423729, 0.788407407407407, 1.02309278350515),
test_avg_mag = c(0.112163461525871, 0.113447031611172, 0.15930172539742,
0.105397926645665, 0.0370000063024116, 0.0823626968797451,
0.0441620688813484, 0.135786546158742), test_distSEM = c(0.00460504533342531,
0.0050568065734325, 0.00945562739572128, 0.00524044558789062,
0.00882224860763199, 0.00983820301449839, 0.0162322856355826,
0.00738407922404085), test_duraSEM = c(0.0187491841242793,
0.0287113186085301, 0.0283764910080623, 0.0215386973519077,
0.0471018319675206, 0.0341593217329755, 0.0564553992545153,
0.0271939362203803), test_magSEM = c(0.00335619679815181,
0.00443251320170775, 0.00919066553588191, 0.00432150262248429,
0.00400887448034098, 0.00664866437888279, 0.00575860867691942,
0.00524462205156711), train_avg_dist = c(0.337652222222222,
0.294218518518519, 0.338651851851852, 0.311313725490196,
0.254675, 0.2737, 0.390688888888889, 0.314817948717949),
train_avg_dura = c(1.3543, 1.429, 1.19151851851852, 1.37256862745098,
1.236, 1.06376666666667, 1.41396296296296, 1.31512820512821
), train_avg_mag = c(0.1930557426236, 0.19297076970836, 0.212916856705011,
0.127417008935649, 0.0841239843171108, 0.117210954090848,
0.115413610503398, 0.179227387006556)), class = "data.frame", .Names = c("strain",
"test_avg_dist", "test_avg_dura", "test_avg_mag", "test_distSEM",
"test_duraSEM", "test_magSEM", "train_avg_dist", "train_avg_dura",
"train_avg_mag"), row.names = c(NA, -8L))
The problem I am having is how to add error bars using SEM since I need them to be merged into one variable as opposed to two when I map the variable to geom_bar. I think this is a melt issue but I can't figure it out.
Update:
The melted data-frame I used to plot the graph is as follows:
structure(list(strain = structure(c(1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L), .Label = c("N2", "acy-1(LOF)",
"acy-1(GOF)", "pde-4", "unc-43", "crh-1", "glr-1", "avr-14"), class = "factor"),
variable = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L,
5L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 7L,
7L, 7L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L,
9L, 9L, 9L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 10L, 11L,
11L, 11L, 11L, 11L, 11L, 11L, 11L, 12L, 12L, 12L, 12L, 12L,
12L, 12L, 12L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 13L, 14L,
14L, 14L, 14L, 14L, 14L, 14L, 14L, 15L, 15L, 15L, 15L, 15L,
15L, 15L, 15L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 17L,
17L, 17L, 17L, 17L, 17L, 17L, 17L, 18L, 18L, 18L, 18L, 18L,
18L, 18L, 18L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 19L, 20L,
20L, 20L, 20L, 20L, 20L, 20L, 20L), .Label = c("test_avg_dist",
"test_avg_dura", "test_avg_mag", "test_avg_prob", "test_avg_spd",
"test_distSEM", "test_duraSEM", "test_magSEM", "test_probSEM",
"test_spdSEM", "train_avg_dist", "train_avg_dura", "train_avg_mag",
"train_avg_prob", "train_avg_spd", "train_distSEM", "train_duraSEM",
"train_magSEM", "train_probSEM", "train_spdSEM"), class = "factor"),
value = c(0.23102447163515, 0.198503787878788, 0.23892936802974,
0.247270588235294, 0.148316666666667, 0.195762711864407,
0.204740740740741, 0.238755154639175, 1.04759733036707, 1.15537878787879,
0.914684014869888, 1.12286274509804, 0.828916666666667, 0.785491525423729,
0.788407407407407, 1.02309278350515, 0.112163461525871, 0.113447031611172,
0.15930172539742, 0.105397926645665, 0.0370000063024116,
0.0823626968797451, 0.0441620688813484, 0.135786546158742,
0.457040018571118, 0.563727434411572, 0.624264612406578,
0.392625726149316, 0.219488346025285, 0.355836464305103,
0.158243463050796, 0.549997886634136, 0.218104671667048,
0.175578055416405, 0.256197987699313, 0.218534931269605,
0.181253278716812, 0.235434749265196, 0.236043513165036,
0.229165553562148, 0.00460504533342531, 0.0050568065734325,
0.00945562739572128, 0.00524044558789062, 0.00882224860763199,
0.00983820301449839, 0.0162322856355826, 0.00738407922404085,
0.0187491841242793, 0.0287113186085301, 0.0283764910080623,
0.0215386973519077, 0.0471018319675206, 0.0341593217329755,
0.0564553992545153, 0.0271939362203803, 0.00335619679815181,
0.00443251320170775, 0.00919066553588191, 0.00432150262248429,
0.00400887448034098, 0.00664866437888279, 0.00575860867691942,
0.00524462205156711, 0.00460504533342531, 0.0050568065734325,
0.00945562739572128, 0.00524044558789062, 0.00882224860763199,
0.00983820301449839, 0.0162322856355826, 0.00738407922404085,
0.00148090077905166, 0.00224725406956702, 0.00293788372166611,
0.00142518092482957, 0.00475313026432338, 0.00259537819051875,
0.00439432015310276, 0.00179190641262238, 0.337652222222222,
0.294218518518519, 0.338651851851852, 0.311313725490196,
0.254675, 0.2737, 0.390688888888889, 0.314817948717949, 1.3543,
1.429, 1.19151851851852, 1.37256862745098, 1.236, 1.06376666666667,
1.41396296296296, 1.31512820512821, 0.1930557426236, 0.19297076970836,
0.212916856705011, 0.127417008935649, 0.0841239843171108,
0.117210954090848, 0.115413610503398, 0.179227387006556,
0.525206741295172, 0.606796097537911, 0.592920766963248,
0.383218177729097, 0.294853306191478, 0.37983654970313, 0.244065736387288,
0.529995494304863, 0.245519078777542, 0.204069564920836,
0.279438682643543, 0.223741850875084, 0.203505986396722,
0.244494243449087, 0.263225928969608, 0.235094347033923,
0.00509151719343593, 0.00741331297357774, 0.0110354960774679,
0.0058641318136066, 0.0114389388703232, 0.0108143010933781,
0.0182904578688527, 0.00913426247712326, 0.0167858570502119,
0.0279705569908445, 0.030133138276768, 0.0219057666071679,
0.0479637760140276, 0.0332974908188985, 0.0605392786801207,
0.0323033076008837, 0.00498395111761598, 0.0081988397756359,
0.0107052683837969, 0.00442352355941589, 0.00723029142814287,
0.00764631328347674, 0.00980735575566329, 0.00789476278044047,
0.00509151719343593, 0.00741331297357774, 0.0110354960774679,
0.0058641318136066, 0.0114389388703232, 0.0108143010933781,
0.0182904578688527, 0.00913426247712326, 0.00139403793044242,
0.00220415921330836, 0.00299625483623813, 0.00144528089431754,
0.00441088530148196, 0.00248394605240026, 0.00319027562414684,
0.00174638373495128)), row.names = c(NA, -160L), .Names = c("strain",
"variable", "value"), class = "data.frame")
The code I used to plot this (after removing SEM rows) is as follows:
(abs_bar_mag <-
df_group_sum.long %>%
filter(grepl("mag", variable)) %>%
ggplot(aes(x = strain,
y = value,
fill = variable))+
scale_fill_manual(values=c("lightseagreen", "indianred1"))+
geom_bar(stat="identity", position = "dodge") +
#geom_errorbar(aes(ymin=value-1, ymax=value+1), width=.1, position = position_dodge(width=0.9)) +
theme(panel.background = element_blank()) +
theme(text = element_text(size = 20),
axis.line = element_line(colour = "black")) +
ggtitle("") +
theme(plot.title = element_text(size = 30, hjust = 0.5, face = "bold"),
axis.text = element_text(size = 70),
strip.text = element_text(size = 40),
axis.text.x = element_text(angle = 65, hjust = 1, size = 40),
axis.title.y = (element_text(size = 65)))
+
labs(colour = "",
y = "Magnitude",
x = "") +
scale_colour_manual(values = rev())
)
I appreciate any pointers or solutions you may have!
Thanks,
Aram
The issue here is that the avg columns and the SEM (standard error) columns need to stay together. This requires to reshape two value columns simultaneously. See section 3.a of Efficient reshaping using data.tables for more details.
Therefore, we start with the data in wide format (df_group_sum.wide). To be in line with the code provided by the OP, only magnitudes are plotted.
library(data.table)
library(ggplot2)
molten <- melt(
data.table(df_group_sum.wide), id.vars = "strain",
measure.vars = patterns("avg_mag$", "magSEM$"),
value.name = c("avg", "SEM"))[
, variable := forcats::lvls_revalue(variable, c("test_mag", "train_mag"))][]
molten
strain variable avg SEM
1: N2 test_mag 0.11216346 0.003356197
2: acy-1(LOF) test_mag 0.11344703 0.004432513
3: acy-1(GOF) test_mag 0.15930173 0.009190666
4: pde-4 test_mag 0.10539793 0.004321503
5: unc-43 test_mag 0.03700001 0.004008874
6: crh-1 test_mag 0.08236270 0.006648664
7: glr-1 test_mag 0.04416207 0.005758609
8: avr-14 test_mag 0.13578655 0.005244622
9: N2 train_mag 0.19305574 NA
10: acy-1(LOF) train_mag 0.19297077 NA
11: acy-1(GOF) train_mag 0.21291686 NA
12: pde-4 train_mag 0.12741701 NA
13: unc-43 train_mag 0.08412398 NA
14: crh-1 train_mag 0.11721095 NA
15: glr-1 train_mag 0.11541361 NA
16: avr-14 train_mag 0.17922739 NA
ggplot(molten,
aes(strain, avg, ymin = avg - SEM, ymax = avg + SEM, fill = variable)) +
geom_col(position = "dodge") +
geom_errorbar(width=.1, position = position_dodge(width=0.9)) +
scale_fill_manual(values=c("lightseagreen", "indianred1")) +
theme_bw() +
labs(fill = "", y = "Magnitude", x = "")
The OP also has provided a data.frame in long format df_group_sum.long which does contain more data than df_group_sum.wide. These should be plotted as well, now.
By looking at the variable names
unique(df_group_sum.long$variable)
[1] test_avg_dist test_avg_dura test_avg_mag test_avg_prob test_avg_spd
[6] test_distSEM test_duraSEM test_magSEM test_probSEM test_spdSEM
[11] train_avg_dist train_avg_dura train_avg_mag train_avg_prob train_avg_spd
[16] train_distSEM train_duraSEM train_magSEM train_probSEM train_spdSEM
20 Levels: test_avg_dist test_avg_dura test_avg_mag test_avg_prob ... train_spdSEM
the data.frame seems to contain aggregated data (avg and SEM) of five different variables (dist, dura, mag, prob, spd) of two data sets (train and test). Again, avg and SEM need to stay together on one row for plotting bar charts with error bars.
Unfortunately, the naming scheme is inconsistent. It would have been better if the variables containing standard errors would have been named similar to train_avg_mag, e.g., train_SEM_mag instead of train_magSEM.
So, the first step is to split up the variable names to get the different groups separately:
library(data.table)
DT <- data.table(df_group_sum.long)
DT[, c("dataset", "measure", "variable") :=
DT[, tstrsplit(variable, "_|SEM$")][is.na(V3), `:=`(V3 = V2, V2 = "SEM")]]
DT
strain variable value dataset measure
1: N2 dist 0.231024472 test avg
2: acy-1(LOF) dist 0.198503788 test avg
3: acy-1(GOF) dist 0.238929368 test avg
4: pde-4 dist 0.247270588 test avg
5: unc-43 dist 0.148316667 test avg
---
156: pde-4 spd 0.001445281 train SEM
157: unc-43 spd 0.004410885 train SEM
158: crh-1 spd 0.002483946 train SEM
159: glr-1 spd 0.003190276 train SEM
160: avr-14 spd 0.001746384 train SEM
unique(DT[, variable])
"dist" "dura" "mag" "prob" "spd"
unique(DT[, dataset])
"test" "train"
unique(DT[, measure])
"avg" "SEM"
Now, the abbreviated variable names are replaced by their full names using an update on join:
abbr2full <- data.table(
variable = c("dist", "dura", "mag"),
full = c("Distance", "Duration", "Magnitude")
)
DT[abbr2full, on = "variable", variable := full][]
Finally, a facetted plot of all five variables is created. dcast() is used to reshape the data from long to a wide format where each row has two measures avg and SEM.
library(ggplot2)
ggplot(dcast(DT, ... ~ measure),
aes(strain, avg, ymin = avg - SEM, ymax = avg + SEM, fill = dataset)) +
geom_col(position = "dodge") +
geom_errorbar(width=.1, position = position_dodge(width=0.9)) +
scale_fill_manual(values=c("lightseagreen", "indianred1")) +
theme_bw() +
labs(fill = "", y = "Average", x = "") +
facet_wrap(~ variable, scales = "free_y") +
theme(axis.text.x = element_text(angle = 65, hjust = 1))
How can the analysis of repeated replicated design given on this page ( https://stats.stackexchange.com/questions/115135/repeated-measures-anova-with-replicated-measurements ) be done in R? I can perform ANOVA using aov() but I have some doubts as to the Error term there.
The data is as follows:
mydf = structure(list(User = c(1L, 1L, 1L, 2L, 2L, 2L, 3L, 3L, 3L),
Mode = c(1L, 2L, 3L, 1L, 2L, 3L, 1L, 2L, 3L), Trial1Time = c(20L,
5L, 40L, 10L, 15L, 30L, 13L, 11L, 35L), Trial2Time = c(30L,
7L, 25L, 20L, 17L, 35L, 26L, 11L, 38L)), .Names = c("User",
"Mode", "Trial1Time", "Trial2Time"), class = "data.frame", row.names = c(NA,
-9L))
I can't get why the testing of dataset is not working in R neural networks (nnet package).
I have two datasets with similar structures - for training (trainset, 17 cases) and prediction (testset, 9 cases). Each dataset has columns: Age, Gender, Height, Weight. In the testing dataset the age is unknown (NaN).
The formula for training is obtained successfully below:
library(nnet)
trainednetwork<-nnet(age~gender+emLength+action5cnt,trainset, size=17)
Anyway, if I try to use test dataset for prediction in the next string of the code,
prediction<-predict(trainednetwork,testset)
I get mistake "No component terms, no attribute". Can anyone help?
The data (obtained with dput() function):
testset:
structure(list(
age = c(NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_,
NA_integer_, NA_integer_, NA_integer_, NA_integer_),
gender = structure(
c(2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L),
.Label = c("f", "m"),
class = "factor"),
Height= c(9L, 11L, 9L, 11L, 9L, 11L, 9L, 11L, 9L),
Weight= c(1L, 41L, 2L, 1L, 2L, 29L, 12L, 6L, 12L)),
.Names = c("age", "gender", "Height", "Weight"),
class = "data.frame",
row.names = c(NA, 9L))
trainset:
structure(list(
age = c(43L, 35L, 22L, 28L, 20L, 47L, 41L, 23L,
42L, 27L, 22L, 60L, 62L, 47L, 42L, 26L, 54L),
gender = structure(
c(2L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L),
.Label = c("f", "m"),
class = "factor"),
Height= c(7L, 9L, 11L, 11L, 11L, 9L, 11L, 9L, 23L, 9L,
9L, 9L, 10L, 7L, 7L, 11L, 7L),
Weight= c(2L, 2L, 9L, 9L, 28L, 8L, 6L, 3L, 1L, 2L, 40L,
1L, 9L, 1L, 7L, 4L, 35L)),
.Names = c("age", "gender", "Height", "Weight"),
class = "data.frame",
row.names = c(NA, 17L))
I think in the R neuralnet package the command to use for prediction is "compute", not predict, which is very confusing. A