Tuesday, Jan 19, 2016
Introduction to
Textbook
- R Programming for Data Science by Roger D. Peng
- These slides come directly from Roger's book and his coursera classes
What is R?
- R is a dialect of the S language
- S was developed by John Chambers and others from Bell Labs as an statistical analysis environment
- The project started in 1976, in Fortran
- In 1988, it was rewritten in C, Version 3
- In 1998, Version 4
- In 1998, R won the Association for Computing Machinery's Software System Award
- Currently, S-PLUS by TIBCO
S Philosophy
- S had its roots in data analysis not a traditional programming language
- Created to make data analysis easier
- A language for interactive data analysis, more command-line oriented
- Also to write long programs
R
- S was only commercially available, as S-PLUS
- R was created in 1991 by Ross Ihaka and Robert Gentleman, Dept. Statistics at the University of Auckland
- First announcement in 1993
Paper in 1996
- Ross Ihaka and Robert Gentleman. R: A language for data analysis and graphics. Journal of Computational and Graphical Statistics, 5(3):299-314, 1996
- 1995, GNU General Public License to make R free SW
- 1996, public mailing lists (R-help and R-devel)
- 1997, R Core group
2000, R 1.0.0 released to the public
R Key Features
- Syntax very similar to S
- Semantics similar to Scheme
- Runs on almost any computer platform and OS
- Has been adapted to run in tablets, phones, PDAs, game consoles
- Frequent releases
- Sophisticated graphics capabilities
- Good for interactive analysis and to develop new tools
- A great community - R-help, R-devel, even StackOverflow
R is Free Software
- The four freedoms of SW
- Freedom to run the program, for any purpose (freedom 0)
- The freedom to study how the program works, and adapt it to your needs (freedom 1)
- The freedom to redistribute copies so you can help your neighbor (freedom 2)
- The freedom to improve the program, and release your improvements to the public, so that the whole community benefits (freedom 3)
R Design
- A main package and many add-on packages
- Available at: Comprehensive R Archive Network (CRAN)
- Two main parts
- Base package
- Required to run R
- Most fundamental functions
- utils, stats, datasets, graphics, grDevices, grid, methods, tools, parallel, compiler, splines, tcltk, stats4
- Recommended packages
- boot, class, cluster, codetools, foreign, KernSmooth, lattice, mgcv, nlme, rpart, survival, MASS, spatial, nnet, Matrix
R Design
- Two main parts (continue…)
- All other packages
- 4000 packages in CRAN
- Packages in the Bioconductor project
- Packages in personal web sites
- Packages in GitHub, BitBucket
There are also LIMITATIONS
- Yes, nothing is perfect
- Based on almost 50 years old technology
- Objects must generally be stored in physical memory
- Functionality is based on consumer demand and "voluntary" user contributions
Resources
Getting Started with R
Assignment
Basic Commands
- The prompt
- ">"
- Comments with:
- "#"
- Not support for multi-line comments
- Obtain the Current Directory
getwd()
## [1] "/home/jagonzalez/SpiderOak Hive/work/Courses/DataScience"
- Set Working Directory
setwd(".")
Basic Commands 2
- Assign a value to a variable
x <- 3
y <- "abc"
Basic Commands 3
- Print the value of the variable
print(x)
## [1] 3
print(y)
## [1] "abc"
- Another way to print the value of a variable
x
## [1] 3
Evaluation
x <- 3
x
## [1] 3
print(x)
## [1] 3
Evaluation
- Index of vectors printed to the left
x <- 1:50
x
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 ## [24] 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 ## [47] 47 48 49 50
- The ":" operator is used to create sequences
Atomic Classes of Objects
- character
- numeric
- integer
- complex
- logical (True/False)
Types
- Most basic type is vector
- Create an empty vector with
- vector()
- A vector can only contain values of the same class
- Lists may contain values of different classes
Numbers
- Usually treated as numeric objects
- As reals or double precision
- To get an integer number, pass it specifically as integer:
- 1L
Inf represents infinity
- 1 / Inf = 0
- Undefined value represented with:
- NaN, Not a Number
- 0 / 0 = NaN
- NaN also represents missing values
Attributes
- R objects can have attributes –Metadata–
- Such as column names
- Metadata examples
- names, dimnames
- dimensions (for matrices, arrays)
- class (as numeric, integer)
- length
- user defined attributes (metadata)
- Attributes are accessed with function:
- attributes()
Vectors
- Use c() to concatenate values to create a vector:
x <- c(1.5, 2.3, 3.7, 4.6)
x <- c("hello", "world")
x <- c(TRUE, TRUE, FALSE)
- Use vector() to initialize a vector
x <- vector("numeric",length = 10)
x
## [1] 0 0 0 0 0 0 0 0 0 0
Implicit Coersion
- Mixing objects of different classes in a vector is not allowed
- When we mix two classes of objects, coersion occurs
- c(3.1416, "pi") ##coerse to character
Explicit Coersion
- Explicit coersion using as.*
x <- 0:10
class(x)
## [1] "integer"
as.numeric(x)
## [1] 0 1 2 3 4 5 6 7 8 9 10
Explicit Coersion
as.logical(x)
## [1] FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
as.character(x)
## [1] "0" "1" "2" "3" "4" "5" "6" "7" "8" "9" "10"
- When R doesn't find a way to coerse:
- Returns NA's
Matrices
- Matrices are vectors with a dimension attribute
a <- matrix(nrow=2, ncol=3)
a
## [,1] [,2] [,3] ## [1,] NA NA NA ## [2,] NA NA NA
Matrices
dim(a)
## [1] 2 3
attributes(a)
## $dim ## [1] 2 3
Creating Matrices
b <- matrix(1:9, nrow=3, ncol=3)
b
## [,1] [,2] [,3] ## [1,] 1 4 7 ## [2,] 2 5 8 ## [3,] 3 6 9
Creating Matrices
c <- 1:9
c
## [1] 1 2 3 4 5 6 7 8 9
dim(c) <- c(3,3)
c
## [,1] [,2] [,3] ## [1,] 1 4 7 ## [2,] 2 5 8 ## [3,] 3 6 9
Matrices with cbind and rbind
- Creating matrices column-wise and row-wise
x <- 1:3
y <- 10:12
cbind(x,y)
## x y ## [1,] 1 10 ## [2,] 2 11 ## [3,] 3 12
rbind(x,y)
## [,1] [,2] [,3] ## x 1 2 3 ## y 10 11 12
Lists
- May contain objects of different classes
- Lists are very powerful when used withthe apply commands
- Created with the list() command
list("a", TRUE, 3.1416, 5)
## [[1]] ## [1] "a" ## ## [[2]] ## [1] TRUE ## ## [[3]] ## [1] 3.1416 ## ## [[4]] ## [1] 5
Lists
- Creating a NULL list
x <- vector("list", length = 3)
x
## [[1]] ## NULL ## ## [[2]] ## NULL ## ## [[3]] ## NULL
Factors
- We use factors to represent categorical data
- Can be ordered or unordered
- We use labels with factors
- Variable with values "Male" and "Female" better than values 1 and 2
- Factors treated specially by modelling functions such as lm() or glm
- Created with factor() function
- Factors may be automatically created as with read.table()
- Levels can be ordered when we create the factor
Factors
x <- factor(c("high", "high", "low", "low", "high", "medium"))
x
## [1] high high low low high medium ## Levels: high low medium
Factors
table(x)
## x ## high low medium ## 3 2 1
x <- factor(c("high", "high", "low", "low", "high", "medium"),
levels = c("low", "medium", "high"))
x
## [1] high high low low high medium ## Levels: low medium high
Missing Values
- Represented with NA or NaN
- is.na() is used to test if an object is NA
- is.nan() is used to test if an object is NaN
- NA values have a class
- Integer NA
- Character NA
- A NaN value is also a NA value but an NA may not be a NaN
Factors
x <- c(1, 8, 3, NA, 4, 2)
x
## [1] 1 8 3 NA 4 2
is.na(x)
## [1] FALSE FALSE FALSE TRUE FALSE FALSE
Data Frames
- We use data frames to store tabular data in R
- Very useful to work in Machine Learning
- The dplyr package works with dataframes to manipulate the data
- A data frame is a kind of list in which each value is a vector
- The lenght of all vectors must be the same
- Usually the length of columns (or lists) is the number of rows
- Elements of the list, or attributes, are columns of the list
Data Frames
- In a training dataset, our dataframe consists of m list attributes of length equal to the number of rows or samples
- The type of each element of the list corresponds to the type of the attribute.
Data Frames
- Dataframes have column names and row names
- Created with
- read.table()
- read.csv()
- data.frame()
- Can be converted into matrix
- data.matrix()
Data Frames
name <- c("Mary", "Alice", "John", "George", "Joseph")
age <- c(25, 30, 28, 24, 27)
grade <- c("A", "A", "C", "B", "B")
studentGrade <- data.frame(name, age, grade)
studentGrade
## name age grade ## 1 Mary 25 A ## 2 Alice 30 A ## 3 John 28 C ## 4 George 24 B ## 5 Joseph 27 B
Data Frames
nrow(studentGrade)
## [1] 5
ncol(studentGrade)
## [1] 3
Names
- R objects may have names
- Self describing objects
- Writing clear code
sales <- c(20, 17, 19)
names(sales)
## NULL
names(sales) <- c("Computers", "Printers", "Hard Drives")
sales
## Computers Printers Hard Drives ## 20 17 19
Names
- Matrices may have both, column and row names
- dimnames() # both col and row names at the same time
- rownames() # row names separately
- colnames() # col names separately
Giving Names Table
Reading Data
- We can read data in csv format (tabular)
- read.table()
- read.csv()
- To read lines from a textfile
- readLines()
- To read R code files inside an R program (inverse of dump())
- source()
Reading Data
- To read R code files (inverse of dput())
- dget()
- To read in saved workspaces
- load()
- To read R binary objects
- unserialize()
readtable() Arguments
- file
- header
- logical
- sep
- how columns are separated
- colClasses
- character vector
readtable() Arguments
- nrows
- # of rows in the dataset, default is the entire file
- comment.char
- default is "#"
- stringsAsFactors, either TRUE or FALSE
- Should character variables be coded as factors?
readtable() Example
- Example
- dataset <- read.table("mydata.txt")
readcsv()
- Identical to read.table() except that some parameters are initialized to a different value
- sep is set to ","
Remember, R loads all objects into memory, be aware
dump() and dput()
- Store data in textual format but with additional metadata
- class of each attribute
- levels of a factor variable
- The format is not very space efficient
- Text is partially readable
Using dput() and dget()
name <- c("Alex", "Alice", "Mary")
grade <- c("A", "B", "B")
grades <- data.frame(name, grade)
grades
## name grade ## 1 Alex A ## 2 Alice B ## 3 Mary B
dput(grades)
## structure(list(name = structure(1:3, .Label = c("Alex", "Alice",
## "Mary"), class = "factor"), grade = structure(c(1L, 2L, 2L), .Label = c("A",
## "B"), class = "factor")), .Names = c("name", "grade"), row.names = c(NA,
## -3L), class = "data.frame")
Using dput() and dget()
- Saving the output of dput into a file
dput(grades, file = "grades.R")
new_grades <- dget("grades.R")
new_grades
## name grade ## 1 Alex A ## 2 Alice B ## 3 Mary B
dump() and source()
x <- "Alex"
y <- "A"
dump(c("x", "y"), file = "data.R")
rm(x, y)
source("data.R")
str(y)
## chr "A"
x
## [1] "Alex"
Binary Formats
- Data can also be stored in binary format
- As with images
- Numeric data, to avoid losing precision
- Functions to convert into binary format
- save()
- To save individual objects into a file
- save.image()
- To save many objects into a file (i.e. workspace)
- serialize()
- save()
save() and load()
a <- data.frame(x = rnorm(100), y = runif(100))
b <- c(1, 5.1, 2/3)
save(a, b, file = "mydata.rda")
rm("a", "b")
load("mydata.rda")
a
## x y ## 1 0.254091370 0.84216677 ## 2 1.685355723 0.72267534 ## 3 0.631521709 0.56686937 ## 4 -0.689931916 0.12302968 ## 5 -0.905849990 0.25373114 ## 6 -1.239939643 0.43529656 ## 7 -1.453510309 0.89655194 ## 8 -1.486551737 0.50830777 ## 9 0.302163434 0.69846341 ## 10 -0.057888388 0.72385997 ## 11 0.586150948 0.80584521 ## 12 -0.004544574 0.54556273 ## 13 1.006846439 0.28188886 ## 14 2.061480504 0.85075754 ## 15 0.758175948 0.54823279 ## 16 -0.614024422 0.67038907 ## 17 -0.542151968 0.74277669 ## 18 0.758257194 0.18343342 ## 19 0.517718702 0.03569640 ## 20 -0.853922330 0.20787358 ## 21 1.588420211 0.18039228 ## 22 -1.906204414 0.08777102 ## 23 1.375055711 0.33068697 ## 24 0.736541349 0.20272690 ## 25 0.092855055 0.28634010 ## 26 2.317684480 0.25846113 ## 27 -1.244456085 0.69872277 ## 28 0.759373013 0.24168329 ## 29 1.202575005 0.49173601 ## 30 -0.811015694 0.54479527 ## 31 -1.471904042 0.50937673 ## 32 0.813551585 0.68599401 ## 33 1.160714166 0.44138936 ## 34 -1.394768920 0.38973168 ## 35 -0.417419572 0.28452569 ## 36 0.017063471 0.52311345 ## 37 -0.445858240 0.05264593 ## 38 0.825467544 0.90916983 ## 39 -0.122574353 0.04260943 ## 40 1.065511788 0.21696129 ## 41 0.496413460 0.24757980 ## 42 -1.054612481 0.03201525 ## 43 -0.777780891 0.29375021 ## 44 0.117452824 0.95661225 ## 45 1.340426816 0.96162987 ## 46 2.060540387 0.16930863 ## 47 0.518913149 0.71126686 ## 48 0.636198729 0.91583976 ## 49 -1.373450609 0.95807571 ## 50 -0.419674635 0.48744647 ## 51 -0.229509086 0.27195293 ## 52 1.557246651 0.68286209 ## 53 1.637436946 0.80601817 ## 54 1.034943938 0.40256151 ## 55 1.580530921 0.43586289 ## 56 1.367273792 0.33130847 ## 57 1.679581049 0.07526132 ## 58 1.075735015 0.02504518 ## 59 1.526304176 0.94177891 ## 60 -0.222324468 0.10439616 ## 61 1.208890811 0.14919900 ## 62 -1.372540896 0.65216228 ## 63 -2.318095318 0.20067534 ## 64 -0.229669692 0.05948637 ## 65 -1.761672309 0.24258475 ## 66 1.436401133 0.87682350 ## 67 0.170324528 0.56137201 ## 68 -0.854233755 0.80918467 ## 69 -0.808413242 0.42584163 ## 70 -1.655440173 0.12804505 ## 71 0.624910836 0.51197904 ## 72 0.326590185 0.35214156 ## 73 0.965835266 0.61629880 ## 74 -0.010644915 0.64745422 ## 75 1.032710788 0.88966153 ## 76 0.821263335 0.13839951 ## 77 1.276315771 0.83818156 ## 78 1.195252971 0.88496060 ## 79 -0.433852654 0.75666248 ## 80 -1.310870763 0.95594798 ## 81 0.447981574 0.72950209 ## 82 -0.607596677 0.80751797 ## 83 0.911798498 0.37177908 ## 84 -0.473920791 0.67891397 ## 85 0.513886051 0.55113423 ## 86 0.080864830 0.74919069 ## 87 0.012497953 0.12207326 ## 88 0.413608303 0.52204736 ## 89 -1.323652309 0.09107455 ## 90 1.789839979 0.22026572 ## 91 -0.209705943 0.90524248 ## 92 -0.522625753 0.87982012 ## 93 -0.433262232 0.73033484 ## 94 -0.032084161 0.51334311 ## 95 0.709014456 0.27710272 ## 96 -0.579694218 0.93869966 ## 97 1.075352091 0.45721181 ## 98 -0.090156882 0.99455063 ## 99 -1.057881089 0.66551360 ## 100 0.202982256 0.25610662
save() and load()
save.image(file = "mydata.RData")
rm("a", "b")
load("mydata.RData")
a
## x y ## 1 0.254091370 0.84216677 ## 2 1.685355723 0.72267534 ## 3 0.631521709 0.56686937 ## 4 -0.689931916 0.12302968 ## 5 -0.905849990 0.25373114 ## 6 -1.239939643 0.43529656 ## 7 -1.453510309 0.89655194 ## 8 -1.486551737 0.50830777 ## 9 0.302163434 0.69846341 ## 10 -0.057888388 0.72385997 ## 11 0.586150948 0.80584521 ## 12 -0.004544574 0.54556273 ## 13 1.006846439 0.28188886 ## 14 2.061480504 0.85075754 ## 15 0.758175948 0.54823279 ## 16 -0.614024422 0.67038907 ## 17 -0.542151968 0.74277669 ## 18 0.758257194 0.18343342 ## 19 0.517718702 0.03569640 ## 20 -0.853922330 0.20787358 ## 21 1.588420211 0.18039228 ## 22 -1.906204414 0.08777102 ## 23 1.375055711 0.33068697 ## 24 0.736541349 0.20272690 ## 25 0.092855055 0.28634010 ## 26 2.317684480 0.25846113 ## 27 -1.244456085 0.69872277 ## 28 0.759373013 0.24168329 ## 29 1.202575005 0.49173601 ## 30 -0.811015694 0.54479527 ## 31 -1.471904042 0.50937673 ## 32 0.813551585 0.68599401 ## 33 1.160714166 0.44138936 ## 34 -1.394768920 0.38973168 ## 35 -0.417419572 0.28452569 ## 36 0.017063471 0.52311345 ## 37 -0.445858240 0.05264593 ## 38 0.825467544 0.90916983 ## 39 -0.122574353 0.04260943 ## 40 1.065511788 0.21696129 ## 41 0.496413460 0.24757980 ## 42 -1.054612481 0.03201525 ## 43 -0.777780891 0.29375021 ## 44 0.117452824 0.95661225 ## 45 1.340426816 0.96162987 ## 46 2.060540387 0.16930863 ## 47 0.518913149 0.71126686 ## 48 0.636198729 0.91583976 ## 49 -1.373450609 0.95807571 ## 50 -0.419674635 0.48744647 ## 51 -0.229509086 0.27195293 ## 52 1.557246651 0.68286209 ## 53 1.637436946 0.80601817 ## 54 1.034943938 0.40256151 ## 55 1.580530921 0.43586289 ## 56 1.367273792 0.33130847 ## 57 1.679581049 0.07526132 ## 58 1.075735015 0.02504518 ## 59 1.526304176 0.94177891 ## 60 -0.222324468 0.10439616 ## 61 1.208890811 0.14919900 ## 62 -1.372540896 0.65216228 ## 63 -2.318095318 0.20067534 ## 64 -0.229669692 0.05948637 ## 65 -1.761672309 0.24258475 ## 66 1.436401133 0.87682350 ## 67 0.170324528 0.56137201 ## 68 -0.854233755 0.80918467 ## 69 -0.808413242 0.42584163 ## 70 -1.655440173 0.12804505 ## 71 0.624910836 0.51197904 ## 72 0.326590185 0.35214156 ## 73 0.965835266 0.61629880 ## 74 -0.010644915 0.64745422 ## 75 1.032710788 0.88966153 ## 76 0.821263335 0.13839951 ## 77 1.276315771 0.83818156 ## 78 1.195252971 0.88496060 ## 79 -0.433852654 0.75666248 ## 80 -1.310870763 0.95594798 ## 81 0.447981574 0.72950209 ## 82 -0.607596677 0.80751797 ## 83 0.911798498 0.37177908 ## 84 -0.473920791 0.67891397 ## 85 0.513886051 0.55113423 ## 86 0.080864830 0.74919069 ## 87 0.012497953 0.12207326 ## 88 0.413608303 0.52204736 ## 89 -1.323652309 0.09107455 ## 90 1.789839979 0.22026572 ## 91 -0.209705943 0.90524248 ## 92 -0.522625753 0.87982012 ## 93 -0.433262232 0.73033484 ## 94 -0.032084161 0.51334311 ## 95 0.709014456 0.27710272 ## 96 -0.579694218 0.93869966 ## 97 1.075352091 0.45721181 ## 98 -0.090156882 0.99455063 ## 99 -1.057881089 0.66551360 ## 100 0.202982256 0.25610662
serialize()
- We use serialize to convert individual objects into binary format
- raw vector in hexadecimal format
- Perfectly represent an R object in an exportable format
- Without losing precision or any metadata
- Good for data exchange
- If only storing objects, better use save()
serialize()
x <- list("A", "B", "C")
y <- list(1, 2, 3)
serialize(x, NULL)
## [1] 58 0a 00 00 00 02 00 03 02 02 00 02 03 00 00 00 00 13 00 00 00 03 00 ## [24] 00 00 10 00 00 00 01 00 04 00 09 00 00 00 01 41 00 00 00 10 00 00 00 ## [47] 01 00 04 00 09 00 00 00 01 42 00 00 00 10 00 00 00 01 00 04 00 09 00 ## [70] 00 00 01 43
serialize(y, NULL)
## [1] 58 0a 00 00 00 02 00 03 02 02 00 02 03 00 00 00 00 13 00 00 00 03 00 ## [24] 00 00 0e 00 00 00 01 3f f0 00 00 00 00 00 00 00 00 00 0e 00 00 00 01 ## [47] 40 00 00 00 00 00 00 00 00 00 00 0e 00 00 00 01 40 08 00 00 00 00 00 ## [70] 00
Connections
- file
- opens a file connection
- gzfile
- opens a file connection to a file compressed with gzip
- bzfile
- opens a file connection to a file compressed with bzip2
- url
- opens a connection to a webpage
file() Attributes
- description
- Name of the file
- open
- Code of the mode used to open the file
- "r", read only mode
- "w", writing (initializes a new file)
- "a", append
- "rb", "wb", "ab", for binary modes in Windows
- Code of the mode used to open the file
- We might not need to deal with the connection if we use a function such as read.table()
- data <- read.csv("mydata.csv")
Reading from a Connection
getwd()
## [1] "/home/jagonzalez/SpiderOak Hive/work/Courses/DataScience"
con <- file("genes-leukemia.csv")
open(con, "r")
data <- read.csv(con)
close(con)
data
## SNUM CLASS BM_PB TB_if_ALL FAB_if_AML Year Gender pct_Blasts ## 1 s1 ALL BM B-cell ? 1996 M ? ## 2 s2 ALL BM T-cell ? ? M ? ## 3 s3 ALL BM T-cell ? ? M ? ## 4 s4 ALL BM B-cell ? ? ? ? ## 5 s5 ALL BM B-cell ? ? ? ? ## 6 s6 ALL BM T-cell ? ? M ? ## 7 s7 ALL BM B-cell ? 1983 F ? ## 8 s8 ALL BM B-cell ? ? F ? ## 9 s9 ALL BM T-cell ? ? M ? ## 10 s10 ALL BM T-cell ? 1987 M ? ## 11 s11 ALL BM T-cell ? 1985 M ? ## 12 s12 ALL BM B-cell ? 1985 F ? ## 13 s13 ALL BM B-cell ? 1988 F ? ## 14 s14 ALL BM T-cell ? 1987 M ? ## 15 s15 ALL BM B-cell ? 1989 F ? ## 16 s16 ALL BM B-cell ? 1990 M ? ## 17 s17 ALL BM B-cell ? 1990 M ? ## 18 s18 ALL BM B-cell ? ? F ? ## 19 s19 ALL BM B-cell ? ? ? ? ## 20 s20 ALL BM B-cell ? ? ? ? ## 21 s21 ALL BM B-cell ? 1984 M ? ## 22 s22 ALL BM B-cell ? 1988 M ? ## 23 s23 ALL BM T-cell ? 1991 M ? ## 24 s24 ALL BM B-cell ? 1981 M ? ## 25 s25 ALL BM B-cell ? 1982 M ? ## 26 s26 ALL BM B-cell ? ? F ? ## 27 s27 ALL BM B-cell ? ? F ? ## 28 s28 AML BM ? M2 ? ? 79 ## 29 s29 AML BM ? M2 ? ? 34 ## 30 s30 AML BM ? M5 ? ? 93 ## 31 s31 AML BM ? M4 ? ? 77 ## 32 s32 AML BM ? M1 ? ? 86 ## 33 s33 AML BM ? M2 ? ? 70 ## 34 s34 AML BM ? M2 ? ? 77 ## 35 s35 AML BM ? M1 ? ? 67 ## 36 s36 AML BM ? M5 ? ? 76 ## 37 s37 AML BM ? M2 ? ? 44 ## 38 s38 AML BM ? M1 ? ? 80 ## 39 s39 ALL BM B-cell ? ? F ? ## 40 s40 ALL BM B-cell ? 1980 F ? ## 41 s41 ALL BM B-cell ? ? F ? ## 42 s42 ALL BM B-cell ? ? F ? ## 43 s43 ALL BM B-cell ? ? F ? ## 44 s44 ALL BM B-cell ? 1998 F ? ## 45 s45 ALL BM B-cell ? 1998 M ? ## 46 s46 ALL BM B-cell ? 1999 F ? ## 47 s47 ALL BM B-cell ? 1986 M ? ## 48 s48 ALL BM B-cell ? 1992 F ? ## 49 s49 ALL BM B-cell ? ? M ? ## 50 s50 AML BM ? M4 ? ? 93 ## 51 s51 AML BM ? M2 ? ? 57 ## 52 s52 AML PB ? M4 ? ? 86 ## 53 s53 AML BM ? M2 ? ? 76 ## 54 s54 AML BM ? M4 ? F ? ## 55 s55 ALL BM B-cell ? ? F ? ## 56 s56 ALL BM B-cell ? ? F ? ## 57 s57 AML BM ? M2 ? F ? ## 58 s58 AML BM ? M2 ? ? ? ## 59 s59 ALL BM B-cell ? ? F ? ## 60 s60 AML BM ? M2 ? M ? ## 61 s61 AML BM ? M1 ? ? ? ## 62 s62 AML PB ? ? ? M ? ## 63 s63 AML PB ? ? ? F ? ## 64 s64 AML PB ? ? ? M ? ## 65 s65 AML BM ? ? ? M ? ## 66 s66 AML BM ? ? ? M ? ## 67 s67 ALL PB T-cell ? 1997 M ? ## 68 s68 ALL PB B-cell ? 1998 M ? ## 69 s69 ALL PB B-cell ? 1998 M ? ## 70 s70 ALL PB B-cell ? 1998 F ? ## 71 s71 ALL PB B-cell ? 1998 ? ? ## 72 s72 ALL PB B-cell ? 1998 ? ? ## Treatment_Response PS Source D49950 D63880 J03473 J05243 L13278 ## 1 ? 1.00 DFCI 75 556 2018 610 193 ## 2 ? 0.41 DFCI 129 476 650 927 31 ## 3 ? 0.87 DFCI 44 498 573 1697 198 ## 4 ? 0.91 DFCI 218 1211 2291 425 91 ## 5 ? 0.89 DFCI 110 820 2796 529 194 ## 6 ? 0.76 DFCI 33 485 405 1682 96 ## 7 ? 0.78 DFCI 115 734 1829 386 178 ## 8 ? 0.77 DFCI 32 223 2497 629 112 ## 9 ? 0.89 DFCI 20 686 1204 2760 198 ## 10 ? 0.56 DFCI 54 721 324 1722 20 ## 11 ? 0.74 DFCI 38 551 264 1587 36 ## 12 ? 0.20 DFCI 20 198 472 169 20 ## 13 ? 1.00 DFCI 103 550 1591 719 170 ## 14 ? 0.73 DFCI 72 694 999 859 188 ## 15 ? 0.98 DFCI 158 1287 2352 661 217 ## 16 ? 0.95 DFCI 28 475 2576 1034 240 ## 17 ? 0.49 DFCI 117 883 1875 447 254 ## 18 ? 0.59 DFCI 99 1281 2150 252 32 ## 19 ? 0.80 DFCI 101 256 1338 1041 200 ## 20 ? 0.90 DFCI 22 568 4443 1717 338 ## 21 ? 0.76 DFCI 48 454 1040 604 119 ## 22 ? 0.37 DFCI 74 43 1191 304 20 ## 23 ? 0.77 DFCI 43 613 579 397 85 ## 24 ? 0.92 DFCI 168 298 2741 642 191 ## 25 ? 0.43 DFCI 20 231 569 295 20 ## 26 ? 0.89 DFCI 117 306 2088 1122 20 ## 27 ? 0.82 DFCI 20 433 1702 209 79 ## 28 Failure 0.44 CALGB 297 279 841 102 20 ## 29 Failure 0.74 CALGB 190 277 500 237 20 ## 30 Failure 0.80 CALGB 326 136 426 238 20 ## 31 Failure 0.61 CALGB 197 321 871 57 60 ## 32 Failure 0.47 CALGB 259 283 671 628 34 ## 33 Failure 0.89 CALGB 100 151 109 20 20 ## 34 Success 0.64 CALGB 355 226 803 206 20 ## 35 Success 0.21 CALGB 295 20 430 20 20 ## 36 Success 0.94 CALGB 283 410 603 20 22 ## 37 Success 0.95 CALGB 311 185 404 87 20 ## 38 Success 0.73 CALGB 70 118 355 71 20 ## 39 ? 0.78 DFCI 214 166 1001 786 67 ## 40 ? 0.68 DFCI 234 20 872 994 216 ## 41 ? 0.99 DFCI 20 867 2158 615 118 ## 42 ? 0.42 DFCI 35 376 844 233 100 ## 43 ? 0.66 DFCI 43 586 942 853 84 ## 44 ? 0.97 DFCI 97 560 2090 773 20 ## 45 ? 0.88 DFCI 142 462 1588 382 86 ## 46 ? 0.84 DFCI 80 368 561 443 69 ## 47 ? 0.81 DFCI 191 741 926 510 176 ## 48 ? 0.94 DFCI 51 579 1924 598 461 ## 49 ? 0.84 DFCI 128 391 2186 861 119 ## 50 Failure 0.97 CALGB 346 164 675 135 38 ## 51 Failure 1.00 CALGB 211 209 506 48 20 ## 52 Success 0.61 CALGB 109 131 488 294 20 ## 53 Success 0.89 CALGB 106 94 449 109 20 ## 54 ? 0.23 St-Jude 204 335 1061 352 76 ## 55 ? 0.73 St-Jude 74 449 1490 421 20 ## 56 ? 0.84 St-Jude 20 494 1593 1359 33 ## 57 ? 0.22 St-Jude 96 326 569 21 20 ## 58 ? 0.74 St-Jude 151 238 658 151 64 ## 59 ? 0.68 St-Jude 205 691 724 739 144 ## 60 ? 0.06 St-Jude 183 428 575 336 20 ## 61 ? 0.40 St-Jude 175 95 795 288 20 ## 62 ? 0.58 CCG 333 333 560 282 113 ## 63 ? 0.69 CCG 250 318 776 20 87 ## 64 ? 0.52 CCG 455 325 534 195 113 ## 65 ? 0.60 CCG 218 156 409 220 20 ## 66 ? 0.27 CCG 65 349 828 230 67 ## 67 ? 0.15 DFCI 53 72 540 519 20 ## 68 ? 0.80 DFCI 145 734 3090 1226 179 ## 69 ? 0.85 DFCI 84 545 2412 765 91 ## 70 ? 0.73 DFCI 20 440 1146 344 117 ## 71 ? 0.30 DFCI 105 113 704 1164 25 ## 72 ? 0.77 DFCI 146 78 1231 894 20 ## L47738 M21551_rna1 M55150 M62762 M81933 M91432 S50223 U12471_cds1 ## 1 571 178 654 835 20 767 268 160 ## 2 2893 336 1283 3072 20 814 346 134 ## 3 2723 345 1286 609 124 1547 804 167 ## 4 731 374 915 935 167 831 452 104 ## 5 649 321 732 1665 114 1423 476 145 ## 6 1858 44 691 499 56 430 256 81 ## 7 280 359 853 764 203 764 208 122 ## 8 1716 364 1238 1323 20 752 310 335 ## 9 2388 333 822 1741 124 1777 640 131 ## 10 913 271 885 1188 89 426 152 264 ## 11 2147 267 680 1870 46 472 441 195 ## 12 140 20 412 1030 44 76 90 104 ## 13 556 268 548 1482 192 920 545 150 ## 14 1483 20 1157 892 77 606 570 135 ## 15 1505 64 387 1306 96 1417 571 128 ## 16 904 160 707 593 120 869 235 182 ## 17 643 363 1822 2376 98 2031 352 227 ## 18 669 333 738 542 89 954 20 157 ## 19 1137 279 907 809 82 532 84 290 ## 20 3810 117 860 2475 120 3192 867 70 ## 21 1631 152 92 1514 161 896 323 39 ## 22 857 265 686 1977 111 70 241 126 ## 23 813 20 803 672 22 321 493 74 ## 24 899 392 803 1235 20 992 502 205 ## 25 223 305 842 933 113 363 301 144 ## 26 759 330 514 1114 52 636 101 98 ## 27 899 64 561 20 20 419 20 143 ## 28 449 456 1929 2702 313 323 107 238 ## 29 65 259 1647 1736 243 125 150 217 ## 30 172 487 2112 3553 229 158 20 213 ## 31 239 554 1555 3255 132 295 31 283 ## 32 683 462 1514 4249 230 368 210 264 ## 33 153 672 2693 1871 282 110 20 304 ## 34 20 405 1811 3236 179 263 56 293 ## 35 218 327 1406 1125 214 226 168 322 ## 36 20 485 1707 4647 179 87 20 337 ## 37 20 415 2072 3808 330 183 20 417 ## 38 201 582 1753 3594 407 111 62 271 ## 39 837 20 627 1738 94 335 43 20 ## 40 180 363 503 708 27 382 373 411 ## 41 770 20 181 1188 173 707 167 154 ## 42 273 199 1565 2274 371 553 127 649 ## 43 439 69 1165 951 355 562 274 20 ## 44 579 38 441 1393 314 575 216 183 ## 45 444 165 309 1062 445 747 236 278 ## 46 570 20 385 586 222 392 177 160 ## 47 575 235 767 1828 224 638 239 75 ## 48 603 302 927 1946 143 1340 776 194 ## 49 763 404 894 417 20 799 20 86 ## 50 578 342 1895 3427 274 225 48 175 ## 51 446 339 1339 2120 20 126 20 434 ## 52 455 354 801 3266 62 163 20 198 ## 53 118 308 1534 3457 206 135 45 334 ## 54 269 319 1811 2860 216 413 26 238 ## 55 287 194 781 1170 224 339 20 107 ## 56 1009 46 669 1246 296 496 56 239 ## 57 21 253 1147 1662 20 196 20 192 ## 58 37 646 1656 1489 20 129 20 71 ## 59 310 20 261 1769 195 155 106 66 ## 60 471 20 880 1933 275 412 20 176 ## 61 218 361 1263 2600 71 422 20 132 ## 62 393 345 1295 4346 20 384 20 155 ## 63 233 93 1476 4514 20 462 20 256 ## 64 309 534 3220 2803 20 273 20 143 ## 65 20 308 610 2631 20 179 20 280 ## 66 408 254 749 960 165 362 20 163 ## 67 908 222 654 2601 70 140 31 134 ## 68 1235 140 859 1618 20 1385 439 216 ## 69 1284 351 623 1760 182 1012 607 120 ## 70 853 30 360 1025 301 334 106 185 ## 71 1213 263 310 1494 170 146 20 134 ## 72 586 339 665 2122 174 235 163 115 ## U32944 U35451 U50136_rna1 U53468 U72342 U82759 X15949 X52142 ## 1 3349 408 1124 141 978 393 277 107 ## 2 1002 633 1062 84 324 118 104 20 ## 3 2089 912 1398 98 855 667 91 20 ## 4 1625 304 942 20 369 410 403 190 ## 5 3502 398 928 238 653 119 416 361 ## 6 316 506 842 32 449 147 46 26 ## 7 1530 357 1066 20 638 735 267 191 ## 8 1042 134 1668 71 361 248 314 179 ## 9 2286 982 966 90 576 258 210 240 ## 10 934 613 1175 62 99 409 97 96 ## 11 282 745 626 54 686 306 27 69 ## 12 277 20 747 63 20 20 20 20 ## 13 2069 810 706 112 1354 87 588 269 ## 14 1613 404 864 20 901 188 307 159 ## 15 2952 547 515 62 905 99 747 499 ## 16 3110 72 825 108 909 67 393 260 ## 17 2591 665 1837 20 1024 20 822 214 ## 18 820 726 883 20 171 102 515 20 ## 19 1116 95 1309 191 493 432 339 184 ## 20 5908 767 817 167 1224 359 748 326 ## 21 1143 600 383 162 353 149 201 122 ## 22 108 247 825 82 128 160 48 20 ## 23 146 442 731 20 136 366 20 142 ## 24 2457 621 899 196 740 770 598 277 ## 25 1081 116 1171 58 20 267 163 20 ## 26 1480 96 805 55 295 59 169 105 ## 27 1283 291 1286 143 220 20 104 109 ## 28 384 209 1641 20 32 822 64 20 ## 29 179 29 2545 31 173 1137 35 20 ## 30 651 160 3818 21 118 1050 20 20 ## 31 469 223 2943 52 20 1157 23 20 ## 32 328 293 2535 24 249 1083 59 20 ## 33 133 73 1373 29 380 1099 33 20 ## 34 427 208 2402 20 20 652 35 20 ## 35 288 57 2137 20 117 262 79 20 ## 36 295 214 3965 20 259 618 71 20 ## 37 224 149 2539 20 20 805 20 20 ## 38 230 195 2286 36 20 673 64 20 ## 39 306 181 1122 20 20 67 171 20 ## 40 759 269 1016 29 749 68 275 81 ## 41 1657 417 428 122 479 198 198 331 ## 42 727 136 64 110 217 472 113 20 ## 43 1802 108 646 20 341 242 233 122 ## 44 2345 552 188 20 320 54 68 378 ## 45 1407 27 470 132 78 46 205 218 ## 46 798 284 591 51 372 103 49 83 ## 47 2582 42 1141 155 590 176 264 113 ## 48 3482 48 769 106 1892 353 778 213 ## 49 1146 189 1390 20 66 20 141 297 ## 50 185 82 2442 20 20 1375 202 41 ## 51 249 160 2335 20 34 677 20 201 ## 52 882 70 541 20 222 218 27 20 ## 53 177 76 3568 79 439 300 20 20 ## 54 2110 333 1083 20 494 280 194 430 ## 55 1145 289 861 20 282 20 82 327 ## 56 1148 136 973 20 224 20 206 203 ## 57 807 186 721 20 86 110 184 20 ## 58 534 71 2392 20 20 340 182 20 ## 59 734 94 571 20 167 20 216 55 ## 60 1235 290 723 20 307 139 228 109 ## 61 773 95 1023 58 20 407 112 101 ## 62 919 236 1030 20 597 653 298 20 ## 63 1425 312 2502 64 304 359 313 20 ## 64 393 384 3190 21 1076 1116 260 20 ## 65 501 20 2349 117 20 386 152 26 ## 66 993 115 775 20 106 217 67 20 ## 67 59 243 993 175 331 96 58 20 ## 68 3869 523 1049 335 1083 386 469 352 ## 69 1569 146 1496 271 659 349 379 161 ## 70 1072 252 682 27 85 51 75 86 ## 71 227 239 931 78 168 20 75 31 ## 72 325 358 1029 97 510 157 20 62 ## X56411_rna1 X63469 X74262 X76061 X76648 X95735 Y08612 Y12670 D38073 ## 1 178 460 1372 210 1361 298 517 600 994 ## 2 183 151 1184 216 237 307 351 337 539 ## 3 166 230 2221 250 1240 309 214 574 1441 ## 4 131 314 1051 139 992 693 432 716 680 ## 5 141 632 1370 270 1233 713 596 524 950 ## 6 151 181 1306 67 401 247 220 270 1258 ## 7 245 213 1339 193 821 52 196 463 509 ## 8 77 227 655 167 1012 20 436 689 331 ## 9 205 362 3593 152 929 20 513 262 1974 ## 10 119 47 1058 20 330 492 114 167 664 ## 11 107 225 953 71 512 20 492 174 884 ## 12 20 43 209 38 90 408 119 258 314 ## 13 153 495 1624 418 827 724 393 201 1991 ## 14 206 442 2050 449 679 360 416 180 1062 ## 15 56 522 1995 335 1426 938 651 625 1030 ## 16 225 467 1625 253 1578 848 278 330 675 ## 17 234 485 3139 413 660 926 623 784 1731 ## 18 255 472 882 121 541 390 198 314 762 ## 19 82 156 1459 211 1225 615 251 146 800 ## 20 308 629 4253 166 3081 827 847 636 1158 ## 21 183 256 768 266 1620 68 689 371 1185 ## 22 39 104 176 20 532 122 290 180 141 ## 23 113 172 862 20 303 20 199 780 767 ## 24 232 494 1409 364 1463 222 569 655 1145 ## 25 95 162 489 35 416 700 292 402 521 ## 26 297 348 716 97 1134 433 424 190 700 ## 27 291 217 500 92 477 20 517 273 456 ## 28 20 28 596 75 214 2224 292 733 832 ## 29 20 178 309 20 514 3348 151 1296 294 ## 30 84 20 313 29 147 6218 173 647 148 ## 31 20 115 275 20 159 1548 119 1085 309 ## 32 127 136 311 165 165 3297 185 1467 259 ## 33 47 63 20 20 307 3482 172 1513 256 ## 34 121 181 279 34 110 2947 200 1807 238 ## 35 33 74 336 40 209 1050 86 1038 382 ## 36 20 202 194 58 358 4863 209 1051 245 ## 37 81 20 130 20 254 2612 253 1064 267 ## 38 94 20 51 20 550 1671 199 2538 342 ## 39 427 321 176 77 637 178 333 465 335 ## 40 20 225 490 199 860 105 338 639 472 ## 41 100 184 1258 133 668 252 428 203 929 ## 42 116 157 678 98 539 92 471 450 543 ## 43 74 115 699 225 629 20 252 389 737 ## 44 77 287 1236 84 800 20 346 244 898 ## 45 131 228 555 60 679 20 264 466 889 ## 46 80 194 384 64 457 28 283 180 674 ## 47 113 380 1903 56 546 399 157 342 853 ## 48 188 449 2123 437 1627 805 648 535 1587 ## 49 243 172 424 122 464 20 498 396 733 ## 50 20 20 148 20 176 5814 166 729 212 ## 51 30 20 148 30 168 2335 112 683 108 ## 52 20 65 401 35 495 2007 109 442 232 ## 53 161 112 162 125 108 3870 284 4460 288 ## 54 60 258 784 20 310 4403 157 458 740 ## 55 54 269 723 24 431 878 177 244 506 ## 56 139 221 834 54 502 162 337 244 746 ## 57 147 64 330 31 222 2287 165 318 654 ## 58 284 86 105 20 287 2871 173 333 327 ## 59 236 30 818 127 754 373 132 101 963 ## 60 296 104 919 168 769 2122 57 391 325 ## 61 179 58 301 82 23 3186 307 485 225 ## 62 206 217 748 139 1047 7133 187 676 379 ## 63 117 544 810 139 1018 5949 233 656 646 ## 64 257 130 544 485 249 4174 216 1152 609 ## 65 20 105 215 20 43 2194 185 323 423 ## 66 20 217 1082 108 228 543 115 410 825 ## 67 156 208 581 20 79 2451 223 501 156 ## 68 107 400 1700 312 1690 1931 517 648 688 ## 69 152 599 808 457 1211 395 596 391 706 ## 70 69 213 490 37 533 43 349 86 519 ## 71 232 232 149 396 471 509 353 396 144 ## 72 234 262 583 113 986 417 502 754 347 ## AF012024_s D26156_s M84371_rna1_s M31211_s U09087_s U26266_s L49229_f ## 1 257 1595 2911 601 358 289 337 ## 2 46 822 575 435 82 288 131 ## 3 139 1452 905 547 263 447 529 ## 4 168 654 2038 472 218 424 422 ## 5 94 1011 1871 661 186 364 354 ## 6 197 1584 634 337 209 320 327 ## 7 188 578 2364 309 144 381 354 ## 8 61 1024 1409 263 167 53 232 ## 9 269 1297 644 978 385 869 568 ## 10 99 971 358 752 146 403 20 ## 11 132 1913 500 897 89 526 20 ## 12 54 329 1119 334 37 60 20 ## 13 89 1593 1473 668 283 673 207 ## 14 199 1011 408 265 179 308 290 ## 15 147 1763 2239 898 314 929 513 ## 16 182 2065 1981 666 106 698 190 ## 17 358 1778 409 374 335 1060 214 ## 18 20 764 1046 516 119 358 20 ## 19 65 1448 3210 473 91 310 45 ## 20 128 2191 4072 1487 268 1047 312 ## 21 123 768 1069 688 20 20 37 ## 22 20 1323 1878 143 30 20 184 ## 23 98 1992 685 376 334 395 93 ## 24 93 1210 1967 531 204 651 424 ## 25 153 738 2537 481 81 166 77 ## 26 121 2143 3495 647 109 190 20 ## 27 90 1245 1768 145 139 201 170 ## 28 43 893 443 300 91 151 20 ## 29 50 624 225 237 58 66 20 ## 30 20 388 251 100 20 20 60 ## 31 45 432 595 192 61 20 56 ## 32 68 706 863 339 50 192 88 ## 33 20 736 678 59 20 20 20 ## 34 28 302 469 153 34 282 20 ## 35 50 201 548 20 48 43 38 ## 36 29 667 763 88 74 64 20 ## 37 98 697 466 139 52 20 93 ## 38 41 721 838 75 33 20 20 ## 39 111 4048 1477 475 94 306 181 ## 40 20 879 2758 251 20 136 178 ## 41 173 1147 1681 616 114 457 64 ## 42 109 1140 721 362 135 138 123 ## 43 134 605 2047 329 26 20 48 ## 44 91 1749 2305 710 200 750 69 ## 45 65 795 1995 467 32 348 72 ## 46 99 521 1787 475 77 488 158 ## 47 69 466 779 493 100 632 109 ## 48 204 1355 2338 951 192 703 20 ## 49 125 1816 2363 356 213 20 20 ## 50 20 802 676 70 45 20 48 ## 51 90 667 502 64 50 20 52 ## 52 36 20 291 248 20 376 25 ## 53 31 1024 530 158 20 119 39 ## 54 169 640 517 575 185 56 213 ## 55 102 911 3739 439 20 644 54 ## 56 136 1521 2721 190 131 432 33 ## 57 66 534 463 21 20 131 20 ## 58 188 534 126 173 20 114 20 ## 59 20 950 2213 592 33 338 40 ## 60 20 371 655 137 82 201 93 ## 61 54 1092 429 201 58 99 60 ## 62 141 349 535 94 71 326 20 ## 63 140 832 996 74 76 63 20 ## 64 70 818 1157 51 119 162 20 ## 65 70 440 383 198 20 367 20 ## 66 65 625 512 226 49 378 20 ## 67 73 1295 658 200 20 234 69 ## 68 202 1131 643 580 255 755 443 ## 69 227 1187 2362 573 208 476 258 ## 70 77 693 1955 348 43 100 89 ## 71 81 1313 1399 218 110 388 81 ## 72 38 2352 1667 493 53 82 22 ## M31523 M28170 U29175 ## 1 1320 397 1582 ## 2 898 20 624 ## 3 597 183 753 ## 4 1644 363 743 ## 5 1322 251 626 ## 6 787 74 1157 ## 7 946 280 552 ## 8 1917 235 572 ## 9 1440 24 1776 ## 10 442 20 756 ## 11 617 20 1972 ## 12 474 84 219 ## 13 1969 87 1322 ## 14 686 155 732 ## 15 2572 371 1636 ## 16 1439 360 2076 ## 17 989 20 917 ## 18 1186 195 453 ## 19 1224 285 1660 ## 20 4555 470 2174 ## 21 2707 514 3707 ## 22 274 95 295 ## 23 590 53 1377 ## 24 1823 418 1456 ## 25 553 391 404 ## 26 1909 495 1982 ## 27 1076 219 949 ## 28 353 20 429 ## 29 279 35 314 ## 30 250 20 208 ## 31 381 20 385 ## 32 671 20 688 ## 33 200 20 248 ## 34 299 20 454 ## 35 389 67 391 ## 36 126 20 412 ## 37 190 20 393 ## 38 275 20 286 ## 39 1484 67 2112 ## 40 606 437 1323 ## 41 1479 84 1033 ## 42 1751 20 826 ## 43 2148 420 937 ## 44 1955 180 1691 ## 45 1275 32 479 ## 46 980 313 438 ## 47 1052 20 613 ## 48 2428 275 1475 ## 49 1467 457 1353 ## 50 197 110 190 ## 51 110 44 382 ## 52 139 20 250 ## 53 388 20 367 ## 54 282 20 578 ## 55 821 184 751 ## 56 1297 620 1127 ## 57 196 20 398 ## 58 268 20 151 ## 59 1087 231 846 ## 60 461 20 486 ## 61 446 20 485 ## 62 328 132 625 ## 63 253 20 745 ## 64 450 113 878 ## 65 375 20 588 ## 66 528 20 669 ## 67 929 20 1661 ## 68 3923 67 1088 ## 69 1794 155 1187 ## 70 1277 266 1002 ## 71 828 142 1504 ## 72 1361 119 1926
Reading Lines of a Text File
con <- file("genes-leukemia.csv")
x <- readLines(con, 2)
x
## [1] "SNUM,CLASS,BM_PB,TB_if_ALL,FAB_if_AML,Year,Gender,pct_Blasts,Treatment_Response,PS,Source,D49950,D63880,J03473,J05243,L13278,L47738,M21551_rna1,M55150,M62762,M81933,M91432,S50223,U12471_cds1,U32944,U35451,U50136_rna1,U53468,U72342,U82759,X15949,X52142,X56411_rna1,X63469,X74262,X76061,X76648,X95735,Y08612,Y12670,D38073,AF012024_s,D26156_s,M84371_rna1_s,M31211_s,U09087_s,U26266_s,L49229_f,M31523,M28170,U29175" ## [2] "s1,ALL,BM,B-cell,?,1996,M,?,?,1,DFCI,75,556,2018,610,193,571,178,654,835,20,767,268,160,3349,408,1124,141,978,393,277,107,178,460,1372,210,1361,298,517,600,994,257,1595,2911,601,358,289,337,1320,397,1582"
close(con)
Reading from a URL Connection
con <- url("http://ccc.inaoep.mx/~jagonzalez/", "r")
x <- readLines(con)
head(x)
## [1] "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Transitional//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd\">" ## [2] "<!--" ## [3] "Design by Free CSS Templates" ## [4] "http://www.freecsstemplates.org" ## [5] "Released for free under a Creative Commons Attribution 2.5 License" ## [6] ""
close(con)
Subsetting R Objects
- There are 3 operators to extract subsets of R objects
- [, returns an object of the same class as the original
- To select multiple elements of an object
- [[, returns elements of a list or data frame
- To extract a single element and the class of the returned object will not necessarily be a list or data frame
- $, returns elements of a list or data frame by name
- Semantics similar to [[
- [, returns an object of the same class as the original
Subsetting a Vector
x <- c("A", "B", "C", "C", "B", "A")
x[1]
## [1] "A"
x[3]
## [1] "C"
x[1:3]
## [1] "A" "B" "C"
Subsetting a Vector
x <- c("A", "B", "C", "C", "B", "A")
x[c(3, 2, 1)]
## [1] "C" "B" "A"
x[x > "A"]
## [1] "B" "C" "C" "B"
Subsetting a Vector
x <- c("A", "B", "C", "C", "B", "A")
u <- x > "A"
u
## [1] FALSE TRUE TRUE TRUE TRUE FALSE
x[u]
## [1] "B" "C" "C" "B"
Subsetting a Matrix
x <- matrix(1:9, 3, 3)
x
## [,1] [,2] [,3] ## [1,] 1 4 7 ## [2,] 2 5 8 ## [3,] 3 6 9
x[2, 1]
## [1] 2
x[1, 2]
## [1] 4
x[1, ]
## [1] 1 4 7
x[, 2]
## [1] 4 5 6
Subsetting a Matrix
x <- matrix(1:9, 3, 3)
x
## [,1] [,2] [,3] ## [1,] 1 4 7 ## [2,] 2 5 8 ## [3,] 3 6 9
x[1, ]
## [1] 1 4 7
x[, 2]
## [1] 4 5 6
Dropping Matrix Dimensions
x <- matrix(1:9, 3, 3)
x
## [,1] [,2] [,3] ## [1,] 1 4 7 ## [2,] 2 5 8 ## [3,] 3 6 9
x[1, 2]
## [1] 4
x[1, 2, drop = FALSE]
## [,1] ## [1,] 4
Dropping Matrix Dimensions
x <- matrix(1:9, 3, 3)
x
## [,1] [,2] [,3] ## [1,] 1 4 7 ## [2,] 2 5 8 ## [3,] 3 6 9
x[1, ]
## [1] 1 4 7
x[1, , drop = FALSE]
## [,1] [,2] [,3] ## [1,] 1 4 7
Subsetting Lists
x <- list(temp = 70:75, hum = 0.55)
x
## $temp ## [1] 70 71 72 73 74 75 ## ## $hum ## [1] 0.55
x[[1]]
## [1] 70 71 72 73 74 75
Subsetting Lists
x <- list(temp = 70:75, hum = 0.55)
x[["temp"]]
## [1] 70 71 72 73 74 75
x$temp
## [1] 70 71 72 73 74 75
Subsetting Nested Elements of a List
x <- list(a = list(1, 2, 3), b = c(11, 12, 13))
## Get the 3rd element of the 1st element
x[[c(1, 3)]]
## [1] 3
## The same as above
x[[1]][[3]]
## [1] 3
## Get the 1st element of the 2nd element
x[[c(2, 1)]]
## [1] 11
Extracting Multiple Elements of a List
x <- list(temp = 70:75, hum = 0.55, wind = "T")
x[c(1, 3)]
## $temp ## [1] 70 71 72 73 74 75 ## ## $wind ## [1] "T"
Partial Matching
x <- list(abcdefghijklmno = 1:10)
x$a
## [1] 1 2 3 4 5 6 7 8 9 10
x[["a"]]
## NULL
x[["a", exact = FALSE]]
## [1] 1 2 3 4 5 6 7 8 9 10
- Partial matching possible with [ and $
Removing NA Values
- NA refers to missing values
x <- c(1, 2, NA, 4, NA, 6)
bad <- is.na(x)
print(bad)
## [1] FALSE FALSE TRUE FALSE TRUE FALSE
x[!bad]
## [1] 1 2 4 6
Removing NA Values
x <- c(1, 2, NA, 4, NA, 6)
y <- c("a", "b", "c", NA, "e", NA)
good <- complete.cases(x, y)
good
## [1] TRUE TRUE FALSE FALSE FALSE FALSE
x[good]
## [1] 1 2
y[good]
## [1] "a" "b"
Assignment
- Install swirl
- install.packages("swirl")
- Load swirl
- library(swirl)
- Execute swirl
- swirl()
- Choose a tutorial and follow it!
- Start with the "R programming" tutorial
- Keep working with advanced tutorials…