Mutiple01
tidyHeatmap
## -- Attaching packages ------------------------------------------------------------------------------------------- tidyverse 1.3.0 --## v ggplot2 3.2.1 v purrr 0.3.3
## v tibble 2.1.3 v dplyr 0.8.4
## v tidyr 1.0.2 v stringr 1.4.0
## v readr 1.3.1 v forcats 0.4.0## -- Conflicts ---------------------------------------------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()## Loading required package: ComplexHeatmap## Loading required package: grid## ========================================
## ComplexHeatmap version 2.3.2
## Bioconductor page: http://bioconductor.org/packages/ComplexHeatmap/
## Github page: https://github.com/jokergoo/ComplexHeatmap
## Documentation: http://jokergoo.github.io/ComplexHeatmap-reference
##
## If you use it in published research, please cite:
## Gu, Z. Complex heatmaps reveal patterns and correlations in multidimensional
## genomic data. Bioinformatics 2016.
##
## This message can be suppressed by:
## suppressPackageStartupMessages(library(ComplexHeatmap))
## ========================================##
## Attaching package: 'tidyHeatmap'## The following object is masked from 'package:stats':
##
## heatmap## # A tibble: 504 x 6
## sample symbol `count normalised adjust~ condition type location
## <chr> <fct> <int> <fct> <fct> <chr>
## 1 treated1 Kal1 37 treated single-re~ Secretory
## 2 treated2 Kal1 41 treated paired-end Secretory
## 3 treated3 Kal1 50 treated paired-end Secretory
## 4 untreated1 Kal1 1127 untreated single-re~ Secretory
## 5 untreated2 Kal1 1046 untreated single-re~ Secretory
## 6 untreated3 Kal1 932 untreated paired-end Secretory
## 7 untreated4 Kal1 1018 untreated paired-end Secretory
## 8 treated1 Ant2 2331 treated single-re~ Intracellul~
## 9 treated2 Ant2 2478 treated paired-end Intracellul~
## 10 treated3 Ant2 2575 treated paired-end Intracellul~
## # ... with 494 more rowspasilla %>%
heatmap(
.horizontal = sample,
.vertical = symbol,
.abundance = `count normalised adjusted`,
annotation = c(condition, type),
log_transform = TRUE
)
pasilla %>%
group_by(location) %>%
heatmap(
.horizontal = sample,
.vertical = symbol,
.abundance = `count normalised adjusted`,
annotation = c(condition, type),
log_transform = TRUE
)## Adding missing grouping variables: `location`
gensvm
##
## Attaching package: 'data.table'## The following objects are masked from 'package:dplyr':
##
## between, first, last## The following object is masked from 'package:purrr':
##
## transposesetwd("C:/Users/s-das/Syncplicity/MyProjects_IMP/MY_Papers_V2/TRB 2021/EScotter_BayesianRule/")
it01 <- fread("IT_aadtMaster.csv")## Warning in require_bit64_if_needed(ans): Some columns are type 'integer64'
## but package bit64 is not installed. Those columns will print as strange
## looking floating point data. There is no need to reload the data. Simply
## install.packages('bit64') to obtain the integer64 print method and print the
## data again.## [1] 1024 86mn01 <- mn[, c("FC_RU", "Default_AADT", "HU", "Pop" , "WAC", "RAC", "Agg_Inc", "Agg_Veh", "Empl" )]
mn02= na.omit(mn01)
mn02$FC_RU= as.factor(mn02$FC_RU)
x <- mn02[, -1]
y <- mn02$FC_RU
fit <- gensvm(x, y, kernel='rbf', gamma=10, max.iter=100, verbose=1, random.seed=123)## Starting main loop.
## Dataset:
## n = 973
## m = 476
## K = 3
## Parameters:
## kappa = 0.000000
## p = 1.000000
## lambda = 0.0000000100000000
## epsilon = 1e-006
##
## iter = 0, L = 0.5576051664406462, Lbar = 6.8766950311224893, reldiff = 11.3325525748235220
##
## Optimization finished, iter = 100, loss = 0.0029159207482829, reldiff = 0.0036775211440595
## Number of support vectors: 694
## Training time: 10.521264## Length Class Mode
## call 8 -none- call
## p 1 -none- numeric
## lambda 1 -none- numeric
## kappa 1 -none- numeric
## epsilon 1 -none- numeric
## weights 1 -none- character
## kernel 1 -none- character
## gamma 1 -none- numeric
## coef 1 -none- numeric
## degree 1 -none- numeric
## kernel.eigen.cutoff 1 -none- numeric
## verbose 1 -none- numeric
## random.seed 1 -none- numeric
## max.iter 1 -none- numeric
## n.objects 1 -none- numeric
## n.features 1 -none- numeric
## n.classes 1 -none- numeric
## classes 3 -none- character
## V 954 -none- numeric
## n.iter 1 -none- numeric
## n.support 1 -none- numeric
## training.time 1 -none- numeric## Data:
## n.objects: 973
## n.features: 8
## n.classes: 3
## classes: 6R 7R 7U
## Parameters:
## p: 1
## lambda: 1e-08
## kappa: 0
## epsilon: 1e-06
## weights: unit
## max.iter: 100
## random.seed: 123
## kernel: rbf
## kernel.eigen.cutoff: 1e-08
## gamma: 10
## Results:
## time: 10.52126
## n.iter: 100
## n.support: 694
Random Forest
##
## randomForestSRC 2.9.3
##
## Type rfsrc.news() to see new features, changes, and bug fixes.
## ##
## Attaching package: 'randomForestSRC'## The following object is masked from 'package:purrr':
##
## partialsetwd("C:/Users/s-das/Syncplicity/MyProjects_IMP/MY_Papers_V2/TRB 2021/EScotter_BayesianRule/")
it01 <- fread("IT_aadtMaster.csv")## Warning in require_bit64_if_needed(ans): Some columns are type 'integer64'
## but package bit64 is not installed. Those columns will print as strange
## looking floating point data. There is no need to reload the data. Simply
## install.packages('bit64') to obtain the integer64 print method and print the
## data again.## [1] 5334 86mn01 <- mn[, c("FC_RU", "Default_AADT", "HU", "Pop" , "WAC", "RAC", "Agg_Inc", "Agg_Veh", "Empl" )]
mn02= na.omit(mn01)
mn02$FC_RU= as.factor(mn02$FC_RU)
o1 <- rfsrc(FC_RU ~ ., data = mn02, nsplit = 10)
print(o1)## Sample size: 4881
## Frequency of class labels: 698, 1626, 2557
## Number of trees: 1000
## Forest terminal node size: 1
## Average no. of terminal nodes: 94.025
## No. of variables tried at each split: 3
## Total no. of variables: 8
## Resampling used to grow trees: swor
## Resample size used to grow trees: 3085
## Analysis: RF-C
## Family: class
## Splitting rule: gini *random*
## Number of random split points: 10
## Normalized brier score: 0.75
## AUC: 100
## Error rate: 0, 0.01, 0, 0
##
## Confusion matrix:
##
## predicted
## observed 6R 7R 7U class.error
## 6R 694 0 4 0.0057
## 7R 0 1626 0 0.0000
## 7U 0 0 2557 0.0000
##
## Overall error rate: 0.08%## [1] "Default_AADT" "HU" "Pop" "WAC" "RAC"
## [6] "Agg_Inc" "Agg_Veh" "Empl"
## no importance found: calculating it now ...
## done
##
|
| | 0%
|
|= | 1%
|
|= | 2%
|
|== | 3%
|
|=== | 4%
|
|==== | 5%
|
|==== | 6%
|
|===== | 7%
|
|====== | 8%
|
|====== | 9%
|
|======= | 10%
|
|======== | 11%
|
|======== | 12%
|
|========= | 13%
|
|========== | 14%
|
|========== | 15%
|
|=========== | 16%
|
|============ | 17%
|
|============= | 18%
|
|============= | 19%
|
|============== | 20%
|
|=============== | 21%
|
|=============== | 22%
|
|================ | 23%
|
|================= | 24%
|
|================== | 25%
|
|================== | 26%
|
|=================== | 27%
|
|==================== | 28%
|
|==================== | 29%
|
|===================== | 30%
|
|====================== | 31%
|
|====================== | 32%
|
|======================= | 33%
|
|======================== | 34%
|
|======================== | 35%
|
|========================= | 36%
|
|========================== | 37%
|
|=========================== | 38%
|
|=========================== | 39%
|
|============================ | 40%
|
|============================= | 41%
|
|============================= | 42%
|
|============================== | 43%
|
|=============================== | 44%
|
|================================ | 45%
|
|================================ | 46%
|
|================================= | 47%
|
|================================== | 48%
|
|================================== | 49%
|
|=================================== | 50%
|
|==================================== | 51%
|
|==================================== | 52%
|
|===================================== | 53%
|
|====================================== | 54%
|
|====================================== | 55%
|
|======================================= | 56%
|
|======================================== | 57%
|
|========================================= | 58%
|
|========================================= | 59%
|
|========================================== | 60%
|
|=========================================== | 61%
|
|=========================================== | 62%
|
|============================================ | 63%
|
|============================================= | 64%
|
|============================================== | 65%
|
|============================================== | 66%
|
|=============================================== | 67%
|
|================================================ | 68%
|
|================================================ | 69%
|
|================================================= | 70%
|
|================================================== | 71%
|
|================================================== | 72%
|
|=================================================== | 73%
|
|==================================================== | 74%
|
|==================================================== | 75%
|
|===================================================== | 76%
|
|====================================================== | 77%
|
|======================================================= | 78%
|
|======================================================= | 79%
|
|======================================================== | 80%
|
|========================================================= | 81%
|
|========================================================= | 82%
|
|========================================================== | 83%
|
|=========================================================== | 84%
|
|============================================================ | 85%
|
|============================================================ | 86%
|
|============================================================= | 87%
|
|============================================================== | 88%
|
|============================================================== | 89%
|
|=============================================================== | 90%
|
|================================================================ | 91%
|
|================================================================ | 92%
|
|================================================================= | 93%
|
|================================================================== | 94%
|
|================================================================== | 95%
|
|=================================================================== | 96%
|
|==================================================================== | 97%
|
|===================================================================== | 98%
|
|===================================================================== | 99%
|
|======================================================================| 100%
Air Crash
### from https://github.com/philjette/CrashData/blob/master/PlaneCrashes.R
startYear<-1920
library(XML)
library(stringr)
getData <-function(year){
#url
url<-paste("http://www.planecrashinfo.com/", year, "/", year, ".htm", sep="")
# Read and parse HTML file
html.raw <- htmlTreeParse(url,useInternal = TRUE)
html.parse<-unlist(xpathApply(html.raw, '//td', function(x)
xpathSApply(x,".//text()", xmlValue)))
#get rid of field names
html.parse<-html.parse[5:length(html.parse)]
#Get fields into vectors to prepare for data frame
crashDates <- html.parse[seq(1, length(html.parse), 6)]
crashLocation <- html.parse[seq(2, length(html.parse), 6)]
crashOperator <- html.parse[seq(3, length(html.parse), 6)]
crashType <- html.parse[seq(4, length(html.parse), 6)]
crashOutcome <- html.parse[seq(6, length(html.parse), 6)]
#compile into data.frame
data<-data.frame(cbind(crashDates,crashLocation,crashOperator,crashType,crashOutcome))
return(data)
}
#initialize data table
compiledData <-data.frame()
#loop through years and get data
for (i in startYear:2020) {
compiledData <- rbind(compiledData, getData(i))
}
#split the crash outcome into passengers and fatalities
compiledData$crashF <- unlist(str_split(compiledData$crashOutcome, "\\/", n=2))[seq(1, length(compiledData$crashOutcome)*2, 2)]
compiledData$crashP <- unlist(str_split(compiledData$crashOutcome, "\\/", n=2))[seq(2, length(compiledData$crashOutcome)*2, 2)]
compiledData$crashP <- unlist(str_split(compiledData$crashP, "\\(", n=2))[seq(1, length(compiledData$crashP)*2, 2)]
#coerce fields to appropriate data types
compiledData$crashF <-as.numeric(compiledData$crashF)## Warning: NAs introduced by coercion## Warning: NAs introduced by coercioncompiledData$Prop<-round(compiledData$crashF/compiledData$crashP,2)
compiledData$crashDates<-as.Date(compiledData$crashDates,"%d %b %Y")
compiledData$crashYear <- format(compiledData$crashDates, format="%Y")
#Fix certain locations to allow for mapping
compiledData$crashLocation<-str_replace(compiledData$crashLoc, "Near ", "")
compiledData$crashLocation<-str_replace(compiledData$crashLoc, "Off ", "")
dim(compiledData)## [1] 4977 9## crashDates crashLocation crashOperator
## 1 1908-09-17 Fort Myer, Virginia Military - U.S. Army\n
## 2 1909-09-07 Juvisy-sur-Orge, France ?\n
## 3 1912-07-12 Atlantic City, New Jersey Military - U.S. Navy\n
## 4 1913-08-06 Victoria, British Columbia, Canada Private\n
## 5 1913-09-09 Over the North Sea Military - German Navy\n
## 6 1913-10-17 Johannisthal, Germany Military - German Navy\n
## crashType crashOutcome crashF crashP Prop crashYear
## 1 Wright Flyer III 1/2(0) 1 2 0.5 1908
## 2 Wright Byplane 1/1(0) 1 1 1.0 1909
## 3 Dirigible 5/5(0) 5 5 1.0 1912
## 4 Curtiss seaplane 1/1(0) 1 1 1.0 1913
## 5 Zeppelin L-1 (airship) 14/20(0) 14 20 0.7 1913
## 6 Zeppelin L-2 (airship) 30/30(0) 30 30 1.0 1913##
## 1908 1909 1912 1913 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926
## 1 1 1 3 2 5 7 4 9 18 12 13 13 7 11 13
## 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942
## 20 36 39 26 33 28 28 31 41 50 34 56 30 25 27 38
## 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958
## 44 56 74 88 82 77 67 69 75 65 69 61 57 53 66 68
## 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974
## 66 70 60 78 63 55 62 60 58 65 69 73 58 77 64 58
## 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990
## 51 57 63 51 60 45 50 54 48 48 56 50 54 64 83 61
## 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006
## 69 66 56 74 60 68 56 59 62 63 58 55 62 46 45 38
## 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020
## 43 50 46 40 36 26 25 23 18 23 15 16 13 2