+
−.. -*- coding: utf-8 -*-
+
−
+
−===
+
− R
+
−===
+
−.. contents::
+
−   :local:
+
−
+
−Inspecting objects
+
−==================
+
−
+
−Info about object dimensions::
+
−
+
−  length(c(1,2,3))
+
−  dim(matrix(1:6, 2, 3))
+
−  ncol(matrix(1:6, 2, 3))
+
−  nrow(matrix(1:6, 2, 3))
+
−
+
−Brief info about any object::
+
−
+
−  typeof(str)
+
−  class(str)
+
−  unclass(str)
+
−  str(c(1, 2))
+
−  str(summary)
+
−
+
−Column names of datasets::
+
−
+
−  names(...)
+
−  names(list(colA=1, colB=2))
+
−
+
−Column/row names of matrixes::
+
−
+
−  colnames(matrix(...))
+
−  rownames(matrix(...))
+
−
+
−List objects in global context: ``ls()``.
+
−
+
−Objext size in memory: ``object.site(1:2)``
+
−
+
−Interactive session
+
−===================
+
−
+
−Controlling output precision::
+
−
+
−  options(digits=3)
+
−
+
−List of all options::
+
−
+
−  str(options())
+
−
+
−Debugging
+
−=========
+
−
+
−To mark function for debugging call::
+
−
+
−  debug(fun, text = "", condition = NULL)
+
−  debugonce(fun, text = "", condition = NULL)
+
−
+
−To return function to normal execution::
+
−
+
−  undebug(fun)
+
−  isdebugged(fun)
+
−
+
−You can under to debug mode in any piece of code by calling ``browser``.
+
−
+
−``traceback`` prints out the function call stack after an error occurs; does
+
−nothing if there's no error.
+
−
+
−``trace`` allows you to insert debugging code into a function a specific places.
+
−
+
−``recover`` allows you to modify the error behavior so that you can browse the
+
−function call stack.
+
−
+
−Profiling
+
−=========
+
−
+
−How long execution of expression takes (in low sec/milisec resolution)::
+
−
+
−  system.time(expr, gcFirst = TRUE)
+
−  unix.time(expr, gcFirst = TRUE)
+
−
+
−``Rprof`` function enable global profiling. ``summaryRprof`` function decrypt
+
−profiling data::
+
−
+
−  Rprof()       ## start profiling
+
−  Rprof(NULL)   ## suspend profiling
+
−  Rprof(append = TRUE)  ## resume profiling
+
−  Rprof(NULL)   ## end profiling
+
−  summaryRprof() ## investigate profiling report
+
−
+
−Generating random numbers
+
−=========================
+
−
+
−For each distribution there are exists corresponding generation function, named
+
−with prefix ``r``::
+
−
+
−  rnorm(n, mean = 0, sd = 1)
+
−  rt(n, df, ncp)
+
−  rbinom(n, size, prob)
+
−  rpois(n, lambda)
+
−  runif(n, min = 0, max = 1)
+
−  rexp
+
−  rchisq
+
−  rgamma
+
−
+
−In order to generate predictable sequences use::
+
−
+
−  set.seed(seed, kind = NULL, normal.kind = NULL)
+
−
+
−Sampling from array::
+
−
+
−  sample(x, size, replace = FALSE, prob = NULL)
+
−  sample.int(n, size = n, replace = FALSE, prob = NULL)
+
−
+
−  sample(1:10, 10)  ## permutation!!
+
−  sample(1:10, 100, replace=TRUE)
+
−
+
−Looping over data
+
−=================
+
−
+
−``lapply`` iterate over data and return list with result of function
+
−application::
+
−
+
−  lapply(1:5, function(x) x^2)
+
−  lapply(matrix(rnorm(20*10),20,10), mean)
+
−
+
−Usually you don't need a list but a vector. ``sapply`` works like ``lapply`` but
+
−also try to convert result to matrix or vector is dimantions and elvement types
+
−permit this::
+
−
+
−  lapply(list(1:5), mean)
+
−  [[1]]
+
−  [1] 3
+
−  sapply(list(1:5), mean)
+
−  [1] 3
+
−
+
−``apply`` works on specific dimension of data so useful to work with matrixes
+
−and data frames::
+
−
+
−  apply(matrix(1:6, 2, 3), 1, min)
+
−  [1] 1 2
+
−
+
−  apply(matrix(1:6, 2, 3), 2, max)
+
−  [1] 2 4 6
+
−
+
−  apply(array(rnorm(2*2*10), c(2, 2, 10)), c(1, 2), mean)
+
−             [,1]       [,2]
+
−  [1,] -0.2733804  0.3154234
+
−  [2,]  0.1830982 -0.5889010
+
−
+
−``colSums``, ``rowSums``, ``colMeans``, ``rowMeans`` is defined as optimized
+
−equivalent for::
+
−
+
−  rowSums = apply(x, 1, sum)
+
−  colSums = apply(x, 2, sum)
+
−  rowMeans = apply(x, 1, mean)
+
−  colMeans = apply(x, 2, mean)
+
−
+
−``split`` partitioning data on factor (analog of SQL ``group by``)::
+
−
+
−  data<-data.frame(rnorm(10),rbinom(10,1,prob=.7))
+
−  sdata<-split(data[,1],data[,2])
+
−  lapply(sdata,mean)
+
−
+
−Exploring data
+
−==============
+
−
+
−Check `Inspecting objects`_ section.
+
−
+
−Investigating unique values::
+
−
+
−  sapply(data, unique)
+
−  sapply(data$col, unique)
+
−  sapply(data[,c("col1","col2")], unique)
+
−  sapply(data[,5:10], unique)
+
−
+
−  table(data$col)
+
−
+
−  tapply(data$what, data$by, unique)
+
−  tapply(data$what, data$by, summary)
+
−  tapply(data$what, data$by, range)
+
−  tapply(data$what, data$by, mean)
+
−  tapply(data$what, data$by, sd)
+
−
+
−Brief info about vectors and matrixes::
+
−
+
−  summary(1:8)
+
−  summary(matrix(1:20, 4, 5))
+
−
+
−Simple plots::
+
−
+
−  i<-1:100
+
−  x<-i/10
+
−  y<-x^2
+
−  plot(x,y)
+
−
+
−  hist(rpois(100,10))
+
−  hist(rpois(100,10),breaks=20)
+
−
+
−Renaming columns
+
−================
+
−::
+
−
+
−  names(d)[names(d)=="beta"] <- "two"
+
−  names(d)[2] <- "two"
+
−
+
−  library(plyr)
+
−  newd <- rename(d, c("beta"="two", "gamma"="three"))
+
−
+
−Removing names for raws and columns
+
−===================================
+
−::
+
−
+
−  rownames(dt) <- NULL
+
−  colnames(dt) <- NULL
+
−
+
−Filtering raws and columns
+
−==========================
+
−::
+
−
+
−  TODO
+
−
+
−Droping raws and columns
+
−========================
+
−
+
−Drop column from data frame by number::
+
−
+
−  dfnew <- df[-1]         # first
+
−  dfnew <- df[-ncol(df)]  # last
+
−  dfnew <- df[-c(1, 3:4, 7)]  # range
+
−
+
−Drop column from data frame by name::
+
−
+
−  newdf <- df[ , !(names(df) %in% c("lat", "long"))]
+
−
+
−  df <- data.frame( a = 1:10, b = 2:11, c = 3:12 )
+
−  df <- subset(df, select = c(a,c))
+
−  df <- subset(df, select = -c(a,c))
+
−