R/data.R

#' Prices of 50,000 round cut diamonds
#'
#' A dataset containing the prices and other attributes of almost 54,000
#'  diamonds. The variables are as follows:
#'
#' @format A data frame with 53940 rows and 10 variables:
#' \describe{
#'   \item{price}{price in US dollars (\$326--\$18,823)}
#'   \item{carat}{weight of the diamond (0.2--5.01)}
#'   \item{cut}{quality of the cut (Fair, Good, Very Good, Premium, Ideal)}
#'   \item{color}{diamond colour, from J (worst) to D (best)}
#'   \item{clarity}{a measurement of how clear the diamond is (I1 (worst), SI1,
#'     SI2, VS1, VS2, VVS1, VVS2, IF (best))}
#'   \item{x}{length in mm (0--10.74)}
#'   \item{y}{width in mm (0--58.9)}
#'   \item{z}{depth in mm (0--31.8)}
#'   \item{depth}{total depth percentage = z / mean(x, y) = 2 * z / (x + y) (43--79)}
#'   \item{table}{width of top of diamond relative to widest point (43--95)}
#' }
"diamonds"


#' US economic time series
#'
#' This dataset was produced from US economic time series data available from
#' \url{http://research.stlouisfed.org/fred2}. \code{economics} is in "wide"
#' format, \code{economics_long} is in "long" format.
#'
#' @format A data frame with 478 rows and 6 variables
#' \describe{
#'   \item{date}{Month of data collection}
#'   \item{psavert}{personal savings rate,
#'     \url{http://research.stlouisfed.org/fred2/series/PSAVERT/}}
#'   \item{pce}{personal consumption expenditures, in billions of dollars,
#'     \url{http://research.stlouisfed.org/fred2/series/PCE}}
#'   \item{unemploy}{number of unemployed in thousands,
#'     \url{http://research.stlouisfed.org/fred2/series/UNEMPLOY}}
#'   \item{uempmed}{median duration of unemployment, in weeks,
#'     \url{http://research.stlouisfed.org/fred2/series/UEMPMED}}
#'   \item{pop}{total population, in thousands,
#'     \url{http://research.stlouisfed.org/fred2/series/POP}}
#' }
#'
"economics"

#' @rdname economics
"economics_long"

#' Midwest demographics
#'
#' Demographic information of midwest counties
#'
#' @format A data frame with 437 rows and 28 variables
#' \describe{
#'  \item{PID}{}
#'  \item{county}{}
#'  \item{state}{}
#'  \item{area}{}
#'  \item{poptotal}{Total population}
#'  \item{popdensity}{Population density}
#'  \item{popwhite}{Number of whites.}
#'  \item{popblack}{Number of blacks.}
#'  \item{popamerindian}{Number of American Indians.}
#'  \item{popasian}{Number of Asians.}
#'  \item{popother}{Number of other races.}
#'  \item{percwhite}{Percent white.}
#'  \item{percblack}{Percent black.}
#'  \item{percamerindan}{Percent American Indian.}
#'  \item{percasian}{Percent Asian.}
#'  \item{percother}{Percent other races.}
#'  \item{popadults}{Number of adults.}
#'  \item{perchsd}{}
#'  \item{percollege}{Percent college educated.}
#'  \item{percprof}{Percent profession.}
#'  \item{poppovertyknown}{}
#'  \item{percpovertyknown}{}
#'  \item{percbelowpoverty}{}
#'  \item{percchildbelowpovert}{}
#'  \item{percadultpoverty}{}
#'  \item{percelderlypoverty}{}
#'  \item{inmetro}{In a metro area.}
#'  \item{category}{}
#' }
#'
"midwest"


#' Fuel economy data from 1999 and 2008 for 38 popular models of car
#'
#' This dataset contains a subset of the fuel economy data that the EPA makes
#' available on \url{http://fueleconomy.gov}. It contains only models which
#' had a new release every year between 1999 and 2008 - this was used as a
#' proxy for the popularity of the car.
#'
#' @format A data frame with 234 rows and 11 variables
#' \describe{
#'   \item{manufacturer}{}
#'   \item{model}{model name}
#'   \item{displ}{engine displacement, in litres}
#'   \item{year}{year of manufacture}
#'   \item{cyl}{number of cylinders}
#'   \item{trans}{type of transmission}
#'   \item{drv}{f = front-wheel drive, r = rear wheel drive, 4 = 4wd}
#'   \item{cty}{city miles per gallon}
#'   \item{hwy}{highway miles per gallon}
#'   \item{fl}{fuel type}
#'   \item{class}{"type" of car}
#' }
"mpg"

#' An updated and expanded version of the mammals sleep dataset
#'
#' This is an updated and expanded version of the mammals sleep dataset.
#' Updated sleep times and weights were taken from V. M. Savage and G. B.
#' West. A quantitative, theoretical framework for understanding mammalian
#' sleep. Proceedings of the National Academy of Sciences, 104 (3):1051-1056,
#' 2007.
#'
#' Additional variables order, conservation status and vore were added from
#' wikipedia.
#'
#' @format A data frame with 83 rows and 11 variables
#' \describe{
#'   \item{name}{common name}
#'   \item{genus}{}
#'   \item{vore}{carnivore, omnivore or herbivore?}
#'   \item{order}{}
#'   \item{conservation}{the conservation status of the animal}
#'   \item{sleep_total}{total amount of sleep, in hours}
#'   \item{sleep_rem}{rem sleep, in hours}
#'   \item{sleep_cycle}{length of sleep cycle, in hours}
#'   \item{awake}{amount of time spent awake, in hours}
#'   \item{brainwt}{brain weight in kilograms}
#'   \item{bodywt}{body weight in kilograms}
#' }
"msleep"

#' Terms of 11 presidents from Eisenhower to Obama
#'
#' The names of each president, the start and end date of their term, and
#' their party of 11 US presidents from Eisenhower to Obama.
#'
#' @format A data frame with 11 rows and 4 variables
"presidential"

#' Vector field of seal movements
#'
#' This vector field was produced from the data described in Brillinger, D.R.,
#' Preisler, H.K., Ager, A.A. and Kie, J.G. "An exploratory data analysis
#' (EDA) of the paths of moving animals". J. Statistical Planning and
#' Inference 122 (2004), 43-63, using the methods of Brillinger, D.R.,
#' "Learning a potential function from a trajectory", Signal Processing
#' Letters. December (2007).
#'
#' @format A data frame with 1155 rows and 4 variables
#' @references \url{http://www.stat.berkeley.edu/~brill/Papers/jspifinal.pdf}
"seals"

#' 2d density estimate of Old Faithful data
#'
#' A 2d density estimate of the waiting and eruptions variables data
#' \link{faithful}.
#'
#' @format A data frame with 5,625 observations and 3 variables.
"faithfuld"

#' \code{colors()} in Luv space
#'
#' All built-in \code{\link{colors}()} translated into Luv colour space.
#'
#' @format A data frame with 657 observations and 4 variables:
#' \describe{
#' \item{L,u,v}{Position in Luv colour space}
#' \item{col}{Colour name}
#' }
"luv_colours"

#' Housing sales in TX
#'
#' Information about the housing market in Texas provided by the TAMU
#' real estate center, \url{http://recenter.tamu.edu/}.
#'
#' @format A data frame with 8602 observations and 9 variables:
#' \describe{
#' \item{city}{Name of MLS area}
#' \item{year,month,date}{Date}
#' \item{sales}{Number of sales}
#' \item{volume}{Total value of sales}
#' \item{median}{Median sale price}
#' \item{listings}{Total active listings}
#' \item{inventory}{"Months inventory": amount of time it would take to sell
#'   all current listings at current pace of sales.}
#' }
"txhousing"



#' Housing sales in TX
#'
#' Information about the housing market in Texas provided by the TAMU
#' real estate center, \url{http://recenter.tamu.edu/}.
#'
#' @format A data frame with 8602 observations and 9 variables:
#' \describe{
#' \item{city}{Name of MLS area}
#' \item{year,month,date}{Date}
#' \item{sales}{Number of sales}
#' \item{volume}{Total value of sales}
#' \item{median}{Median sale price}
#' \item{listings}{Total active listings}
#' \item{inventory}{"Months inventory": amount of time it would take to sell
#'   all current listings at current pace of sales.}
#' }
"txhousing"

#' metabolite data in Sudeepa's analysis
#'
#'
#' @format A data frame with 870 observations and 61 variables:
#' \describe{
#' \item{subject       }{ chr  "SSRI007" "SSRI007" "SSRI007" "SSRI051"...}
#' \item{time          }{ chr  "Baseline" "week4" "week8" "Baseline" ...}
#' \item{Gender        }{ Factor w/ 2 levels "F","M": 1 1 1 2 2 2 1 1 1 1 ...}
#' \item{RMC           }{ Factor w/ 2 levels "No","Yes": NA NA NA 2 2 2 2 2 2 1 ...}
#' \item{Age           }{ num  54.3 54.3 54.3 37.3 37.3 ...}
#' \item{HAMD_baseline }{ int  33 33 33 17 17 17 16 16 16 31 ...}
#' \item{HAMD_week8    }{ int  12 12 12 1 1 1 4 4 4 24 ...}
#' \item{CYS           }{ num  0.1725 -0.0803 -0.7347 0.1095 0.3133 ...}
#' \item{MET           }{ num  0.0157 0.7803 0.6911 -0.3285 0.4899 ...}
#' \item{G             }{ num  1.716 1.51 2.176 0.788 -1.544 ...}
#' \item{GR            }{ num  -0.533 -1.087 -1.73 -0.412 0.851 ...}
#' \item{HX            }{ num  0.887 2.66 3.028 1.809 1.26 ...}
#' \item{PXAN          }{ num  0.677 0.806 1.132 -0.407 -2.032 ...}
#' \item{URIC          }{ num  0.747 0.746 0.849 0.845 0.788 ...}
#' \item{XAN           }{ num  0.323 1.779 1.867 1.413 0.743 ...}
#' \item{XANTH         }{ num  0.125 0.836 0.187 -0.205 0.321 ...}
#' \item{G_by_GR       }{ num  1.761 1.651 2.407 0.837 -1.646 ...}
#' \item{XAN_by_G      }{ num  -1.652 -0.988 -1.641 -0.365 1.81 ...}
#' \item{GR_by_XANTH   }{ num  -0.278 -1.1097 -0.6436 0.0731 -0.115 ...}
#' \item{XAN_by_XANTH  }{ num  0.0426 0.0271 0.6512 0.8096 0.0465 ...}
#' \item{PXAN_by_XANTH }{ num  0.414 -0.038 0.697 -0.121 -1.706 ...}
#' \item{PXAN_by_XAN   }{ num  0.4575 -0.0783 0.1726 -0.9918 -2.1363 ...}
#' \item{URIC_by_XAN   }{ num  -0.00292 -1.40964 -1.45208 -1.01537 -0.39179 ...}
#' \item{HX_by_XAN     }{ num  0.712 1.701 2.021 1.048 0.859 ...}
#' \item{ATOCO         }{ num  1.584 0.861 0.463 -0.89 -0.403 ...}
#' \item{DTOCO         }{ num  0.7451 0.1183 -0.0741 -0.148 0.1376 ...}
#' \item{GTOCO.A       }{ num  0.775 -0.164 -0.223 -0.261 0.346 ...}
#' \item{3OHKY         }{ num  -0.1324 0.1354 -0.1722 0.0701 0.0748 ...}
#' \item{3OHKY.b       }{ num  0.1677 0.0301 1.5402 0.2047 -0.3073 ...}
#' \item{5HIAA         }{ num  0.402 0.137 1.161 -0.586 -0.316 ...}
#' \item{5HT           }{ num  -0.515 -0.444 -0.407 1.004 -1.052 ...}
#' \item{5HTP          }{ num  1.323 1.399 1.851 -0.483 -1.794 ...}
#' \item{I3AA          }{ num  -0.128 -0.254 0.347 -1.211 -0.207 ...}
#' \item{KYN           }{ num  0.0761 0.3037 0.5247 0.2234 -0.0779 ...}
#' \item{TRP           }{ num  -0.2272 -0.253 -0.3045 0.1017 0.0854 ...}
#' \item{I3AA_by_TRP   }{ num  -0.0253 -0.1406 0.4871 -1.263 -0.2468 ...}
#' \item{5HTP_by_TRP   }{ num  1.333 1.411 1.865 -0.488 -1.788 ...}
#' \item{KYN_by_TRP    }{ num  0.236 0.475 0.726 0.143 -0.136 ...}
#' \item{KYN_by_3OHKY  }{ num  0.223 0.118 0.677 0.121 -0.158 ...}
#' \item{KYN_by_3OHKY.b}{ num  -0.1528 0.0278 -1.4376 -0.1617 0.2921 ...}
#' \item{5HIAA_by_TRP  }{ num  0.467 0.241 1.183 -0.573 -0.323 ...}
#' \item{5HIAA_by_5HTP }{ num  -1.249 -1.373 -1.64 0.376 1.736 ...}
#' \item{5HT_by_5HTP   }{ num  1.408 1.435 1.805 -0.944 -0.986 ...}
#' \item{5HIAA_by_5HT  }{ num  0.601 0.459 0.711 -1.117 0.91 ...}
#' \item{4HPAC         }{ num  -1.22262 -0.04903 1.62482 -0.7352 0.00609 ...}
#' \item{4HPLA         }{ num  -1.104 -0.88 0.184 -0.517 0.11 ...}
#' \item{HGA           }{ num  -0.027 0.6542 0.4525 0.0959 0.1155 ...}
#' \item{HVA           }{ num  0.353 0.319 1.578 -0.926 -0.188 ...}
#' \item{MHPG          }{ num  1.664 1.258 0.302 0.951 0.163 ...}
#' \item{TYR           }{ num  0.243 1.022 0.768 -0.283 0.372 ...}
#' \item{VMA           }{ num  -0.61 -0.228 -1.349 -0.15 0.264 ...}
#' \item{HVA_by_TYR    }{ num  0.222 -0.153 1.134 -0.738 -0.339 ...}
#' \item{HGA_by_TYR    }{ num  -0.10805 0.37705 0.24108 0.19747 0.00464 ...}
#' \item{4HPAC_by_TYR  }{ num  -1.34 -0.566 1.23 -0.589 -0.182 ...}
#' \item{MHPG_by_TYR   }{ num  1.154 0.327 -0.261 0.934 -0.113 ...}
#' \item{VMA_by_TYR    }{ num  -0.7055 -0.5839 -1.6397 -0.0558 0.142 ...}
#' \item{4HBAC         }{ num  0.195 1.182 0.182 0.419 -1.569 ...}
#' \item{AMTRP         }{ num  0.6728 -0.6783 0.7083 -0.0306 0.6328 ...}
#' \item{I3PA          }{ num  -0.5847 -0.7796 0.1097 -0.3721 0.0578 ...}
#' \item{SA            }{ num  0.4771 0.0348 3.332 -0.7776 -1.0345 ...}
#' \item{THEOPHYLINE   }{ num  0.509 0.752 1.145 -0.379 -1.639 ...}
#' }
"mtbl"
ShouyeLiu/metaboliteUtility documentation built on May 6, 2019, 9:07 a.m.