| Version: | 1.3-2 |
| Date: | 2022-11-19 |
| Title: | Introduction to Statistical Learning, Second Edition |
| Suggests: | MASS |
| Description: | We provide the collection of data-sets used in the book 'An Introduction to Statistical Learning with Applications in R, Second Edition'. These include many data-sets that we used in the first edition (some with minor changes), and some new datasets. |
| Depends: | R (≥ 3.5.0) |
| License: | GPL-2 |
| LazyLoad: | yes |
| LazyData: | yes |
| URL: | https://www.statlearning.com |
| NeedsCompilation: | no |
| Packaged: | 2022-11-19 20:28:18 UTC; hastie |
| Author: | Gareth James [aut], Daniela Witten [aut], Trevor Hastie [aut, cre], Rob Tibshirani [aut], Balasubramanian Narasimhan [ctb] |
| Maintainer: | Trevor Hastie <hastie@stanford.edu> |
| Repository: | CRAN |
| Date/Publication: | 2022-11-20 00:20:02 UTC |
Auto Data Set
Description
Gas mileage, horsepower, and other information for 392 vehicles.
Usage
Auto
Format
A data frame with 392 observations on the following 9 variables.
mpgmiles per gallon
cylindersNumber of cylinders between 4 and 8
displacementEngine displacement (cu. inches)
horsepowerEngine horsepower
weightVehicle weight (lbs.)
accelerationTime to accelerate from 0 to 60 mph (sec.)
yearModel year (modulo 100)
originOrigin of car (1. American, 2. European, 3. Japanese)
nameVehicle name
Source
This dataset was taken from the StatLib library which is
maintained at Carnegie Mellon University. The dataset was used in the
1983 American Statistical Association Exposition. The original
dataset has 397 observations, of which 5 have missing values for the
variable "horsepower". These rows are removed here. The original
dataset is avaliable as a CSV file in the docs directory, as
well as at https://www.statlearning.com.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
pairs(Auto)
attach(Auto)
hist(mpg)
Bike sharing data
Description
This data set contains the hourly and daily count of rental bikes between years 2011 and 2012 in Capital bikeshare system, along with weather and seasonal information.
Usage
Bikeshare
Format
A data frame with 8645 observations on a number of variables.
seasonSeason of the year, coded as Winter=1, Spring=2, Summer=3, Fall=4.
mnthMonth of the year, coded as a factor.
dayDay of the year, from 1 to 365
hrHour of the day, coded as a factor from 0 to 23.
holidayIs it a holiday? Yes=1, No=0.
weekdayDay of the week, coded from 0 to 6, where Sunday=0, Monday=1, Tuesday=2, etc.
workingdayIs it a work day? Yes=1, No=0.
weathersitWeather, coded as a factor.
tempNormalized temperature in Celsius. The values are derived via (t-t_min)/(t_max-t_min), t_min=-8, t_max=+39.
atempNormalized feeling temperature in Celsius. The values are derived via (t-t_min)/(t_max-t_min), t_min=-16, t_max=+50.
humNormalized humidity. The values are divided to 100 (max).
windspeedNormalized wind speed. The values are divided by 67 (max).
casualNumber of casual bikers.
registeredNumber of registered bikers.
bikersTotal number of bikers.
Source
The UCI Machine Learning Repository https://archive.ics.uci.edu/ml/datasets/bike+sharing+dataset
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2021) An Introduction to Statistical Learning with applications in R, Second Edition, https://www.statlearning.com, Springer-Verlag, New York
Examples
lm(bikers~hr, data=Bikeshare)
Boston Data
Description
A data set containing housing values in 506 suburbs of Boston.
Usage
Boston
Format
A data frame with 506 rows and 13 variables.
crimper capita crime rate by town.
znproportion of residential land zoned for lots over 25,000 sq.ft.
indusproportion of non-retail business acres per town.
chasCharles River dummy variable (= 1 if tract bounds river; 0 otherwise).
noxnitrogen oxides concentration (parts per 10 million).
rmaverage number of rooms per dwelling.
ageproportion of owner-occupied units built prior to 1940.
disweighted mean of distances to five Boston employment centres.
radindex of accessibility to radial highways.
taxfull-value property-tax rate per $10,000.
ptratiopupil-teacher ratio by town.
lstatlower status of the population (percent).
medvmedian value of owner-occupied homes in $1000s.
Source
This dataset was obtained from, and is slightly modified from, the Boston dataset that is part of the MASS library. References are available in the MASS library.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
lm(medv ~ crim + rm, data=Boston)
Brain Cancer Data
Description
A data set consisting of survival times for patients diagnosed with brain cancer.
Usage
BrainCancer
Format
A data frame with 88 observations and 8 variables:
sexFactor with levels "Female" and "Male"
diagnosisFactor with levels "Meningioma", "LG glioma", "HG glioma", and "Other".
locLocation factor with levels "Infratentorial" and "Supratentorial".
kiKarnofsky index.
gtvGross tumor volume, in cubic centimeters.
stereoStereotactic method factor with levels "SRS" and "SRT".
statusWhether the patient is still alive at the end of the study: 0=Yes, 1=No.
timeSurvival time, in months.
Source
I. Selingerova, H. Dolezelova, I. Horova, S. Katina, and J. Zelinka. Survival of patients with primary brain tumors: Comparison of two statistical approaches. PLoS One, 11(2):e0148733, 2016. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4749663/
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2021) An Introduction to Statistical Learning with applications in R, Second Edition, https://www.statlearning.com, Springer-Verlag, New York
The Insurance Company (TIC) Benchmark
Description
The data contains 5822 real customer records. Each record
consists of 86 variables, containing sociodemographic data (variables
1-43) and product ownership (variables 44-86). The sociodemographic
data is derived from zip codes. All customers living in areas with the
same zip code have the same sociodemographic attributes. Variable 86
(Purchase) indicates whether the customer purchased a caravan
insurance policy. Further information on the individual variables can
be obtained at http://www.liacs.nl/~putten/library/cc2000/data.html
Usage
Caravan
Format
A data frame with 5822 observations on 86 variables.
Source
The data was originally supplied by Sentient Machine Research and was used in the CoIL Challenge 2000.
References
P. van der Putten and M. van Someren (eds) . CoIL Challenge
2000: The Insurance Company Case. Published by Sentient Machine
Research, Amsterdam. Also a Leiden Institute of Advanced Computer
Science Technical Report 2000-09. June 22, 2000. See
http://www.liacs.nl/~putten/library/cc2000/
P. van der Putten and M. van Someren. A Bias-Variance Analysis of a Real World Learning Problem: The CoIL Challenge 2000. Machine Learning, October 2004, vol. 57, iss. 1-2, pp. 177-195, Kluwer Academic Publishers
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013)
An Introduction to Statistical Learning with applications in R,
https://www.statlearning.com,
Springer-Verlag, New York
Examples
summary(Caravan)
plot(Caravan$Purchase)
Sales of Child Car Seats
Description
A simulated data set containing sales of child car seats at 400 different stores.
Usage
Carseats
Format
A data frame with 400 observations on the following 11 variables.
SalesUnit sales (in thousands) at each location
CompPricePrice charged by competitor at each location
IncomeCommunity income level (in thousands of dollars)
AdvertisingLocal advertising budget for company at each location (in thousands of dollars)
PopulationPopulation size in region (in thousands)
PricePrice company charges for car seats at each site
ShelveLocA factor with levels
Bad,GoodandMediumindicating the quality of the shelving location for the car seats at each siteAgeAverage age of the local population
EducationEducation level at each location
UrbanA factor with levels
NoandYesto indicate whether the store is in an urban or rural locationUSA factor with levels
NoandYesto indicate whether the store is in the US or not
Source
Simulated data
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(Carseats)
lm.fit=lm(Sales~Advertising+Price,data=Carseats)
U.S. News and World Report's College Data
Description
Statistics for a large number of US Colleges from the 1995 issue of US News and World Report.
Usage
College
Format
A data frame with 777 observations on the following 18 variables.
PrivateA factor with levels
NoandYesindicating private or public universityAppsNumber of applications received
AcceptNumber of applications accepted
EnrollNumber of new students enrolled
Top10percPct. new students from top 10% of H.S. class
Top25percPct. new students from top 25% of H.S. class
F.UndergradNumber of fulltime undergraduates
P.UndergradNumber of parttime undergraduates
OutstateOut-of-state tuition
Room.BoardRoom and board costs
BooksEstimated book costs
PersonalEstimated personal spending
PhDPct. of faculty with Ph.D.'s
TerminalPct. of faculty with terminal degree
S.F.RatioStudent/faculty ratio
perc.alumniPct. alumni who donate
ExpendInstructional expenditure per student
Grad.RateGraduation rate
Source
This dataset was taken from the StatLib library which is maintained at Carnegie Mellon University. The dataset was used in the ASA Statistical Graphics Section's 1995 Data Analysis Exposition.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(College)
lm(Apps~Private+Accept,data=College)
Credit Card Balance Data
Description
A simulated data set containing information on 400 customers.
Usage
Credit
Format
A data frame with 400 observations on a number of variables.
IncomeIncome in $1,000's
LimitCredit limit
RatingCredit rating
CardsNumber of credit cards
AgeAge in years
EducationEducation in years
OwnA factor with levels
NoandYesindicating whether the individual owns a homeStudentA factor with levels
NoandYesindicating whether the individual is a studentMarriedA factor with levels
NoandYesindicating whether the individual is marriedRegionA factor with levels
East,South, andWestindicating the individual's geographical locationBalanceAverage credit card balance in $.
Source
Simulated data. Many thanks to Albert Kim for helpful suggestions, and for supplying a draft of the man documentation page on Oct 19, 2017.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2021) An Introduction to Statistical Learning with applications in R, Second Edition, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(Credit)
lm(Balance ~ Student + Limit, data=Credit)
Credit Card Default Data
Description
A simulated data set containing information on ten thousand customers. The aim here is to predict which customers will default on their credit card debt.
Usage
Default
Format
A data frame with 10000 observations on the following 4 variables.
defaultA factor with levels
NoandYesindicating whether the customer defaulted on their debtstudentA factor with levels
NoandYesindicating whether the customer is a studentbalanceThe average balance that the customer has remaining on their credit card after making their monthly payment
incomeIncome of customer
Source
Simulated data
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(Default)
glm(default~student+balance+income,family="binomial",data=Default)
Fund Manager Data
Description
A simulated data set containing the returns for 2,000 hedge fund managers.
Usage
Fund
Format
A data frame containing the returns of 2,000 hedge fund managers over 50 months.
Source
Simulated data.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2021) An Introduction to Statistical Learning with applications in R, Second Edition, https://www.statlearning.com, Springer-Verlag, New York
Examples
t.test(Fund$Manager1, mu=0)
Baseball Data
Description
Major League Baseball Data from the 1986 and 1987 seasons.
Usage
Hitters
Format
A data frame with 322 observations of major league players on the following 20 variables.
AtBatNumber of times at bat in 1986
HitsNumber of hits in 1986
HmRunNumber of home runs in 1986
RunsNumber of runs in 1986
RBINumber of runs batted in in 1986
WalksNumber of walks in 1986
YearsNumber of years in the major leagues
CAtBatNumber of times at bat during his career
CHitsNumber of hits during his career
CHmRunNumber of home runs during his career
CRunsNumber of runs during his career
CRBINumber of runs batted in during his career
CWalksNumber of walks during his career
LeagueA factor with levels
AandNindicating player's league at the end of 1986DivisionA factor with levels
EandWindicating player's division at the end of 1986PutOutsNumber of put outs in 1986
AssistsNumber of assists in 1986
ErrorsNumber of errors in 1986
Salary1987 annual salary on opening day in thousands of dollars
NewLeagueA factor with levels
AandNindicating player's league at the beginning of 1987
Source
This dataset was taken from the StatLib library which is maintained at Carnegie Mellon University. This is part of the data that was used in the 1988 ASA Graphics Section Poster Session. The salary data were originally from Sports Illustrated, April 20, 1987. The 1986 and career statistics were obtained from The 1987 Baseball Encyclopedia Update published by Collier Books, Macmillan Publishing Company, New York.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(Hitters)
lm(Salary~AtBat+Hits,data=Hitters)
Khan Gene Data
Description
The data consists of a number of tissue samples corresponding to four distinct types of small round blue cell tumors. For each tissue sample, 2308 gene expression measurements are available.
Usage
Khan
Format
The format is a list containing four components: xtrain,
xtest, ytrain, and ytest. xtrain contains
the 2308 gene expression values for 63 subjects and ytrain
records the corresponding tumor type. ytrain and ytest
contain the corresponding testing sample information for a further 20 subjects.
Source
This data were originally reported in:
Khan J, Wei J, Ringner M, Saal L, Ladanyi M, Westermann F, Berthold F, Schwab M, Antonescu C, Peterson C, and Meltzer P. Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nature Medicine, v.7, pp.673-679, 2001.
The data were also used in:
Tibshirani RJ, Hastie T, Narasimhan B, and G. Chu. Diagnosis of Multiple Cancer Types by Shrunken Centroids of Gene Expression. Proceedings of the National Academy of Sciences of the United States of America, v.99(10), pp.6567-6572, May 14, 2002.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
table(Khan$ytrain)
table(Khan$ytest)
NCI 60 Data
Description
NCI microarray data. The data contains expression levels on 6830 genes from 64 cancer cell lines. Cancer type is also recorded.
Usage
NCI60
Format
The format is a list containing two elements: data and
labs.
data is a 64 by 6830 matrix of the expression values while
labs is a vector listing the cancer types for the 64 cell lines.
Source
The data come from Ross et al. (Nat Genet., 2000). More information can be obtained at http://genome-www.stanford.edu/nci60/
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
table(NCI60$labs)
New York Stock Exchange Data
Description
Data consisting of the Dow Jones returns, log trading volume, and log volatility for the New York Stock Exchange over a 20 year period
Usage
Portfolio
Format
A data frame with 6,051 observations and 6 variables:
dateDate
day_of_weekDay of the week
DJ_returnReturn for Dow Jones Industrial Average
log_volumeLog of trading volume
log_volatilityLog of volatility
trainFor the first 4,281 observations, this is set to TRUE
Source
B. LeBaron and A. Weigend (1998), IEEE Transactions on Neural Networks 9(1): 213-220.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2021) An Introduction to Statistical Learning with applications in R, Second Edition, https://www.statlearning.com, Springer-Verlag, New York
Examples
attach(NYSE)
plot(log_volatility)
Orange Juice Data
Description
The data contains 1070 purchases where the customer either purchased Citrus Hill or Minute Maid Orange Juice. A number of characteristics of the customer and product are recorded.
Usage
OJ
Format
A data frame with 1070 observations on the following 18 variables.
PurchaseA factor with levels
CHandMMindicating whether the customer purchased Citrus Hill or Minute Maid Orange JuiceWeekofPurchaseWeek of purchase
StoreIDStore ID
PriceCHPrice charged for CH
PriceMMPrice charged for MM
DiscCHDiscount offered for CH
DiscMMDiscount offered for MM
SpecialCHIndicator of special on CH
SpecialMMIndicator of special on MM
LoyalCHCustomer brand loyalty for CH
SalePriceMMSale price for MM
SalePriceCHSale price for CH
PriceDiffSale price of MM less sale price of CH
Store7A factor with levels
NoandYesindicating whether the sale is at Store 7PctDiscMMPercentage discount for MM
PctDiscCHPercentage discount for CH
ListPriceDiffList price of MM less list price of CH
STOREWhich of 5 possible stores the sale occured at
Source
Stine, Robert A., Foster, Dean P., Waterman, Richard P. Business Analysis Using Regression (1998). Published by Springer.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(OJ)
plot(OJ$Purchase,OJ$PriceCH)
Portfolio Data
Description
A simple simulated data set containing 100 returns for each of two assets, X and Y. The data is used to estimate the optimal fraction to invest in each asset to minimize investment risk of the combined portfolio. One can then use the Bootstrap to estimate the standard error of this estimate.
Usage
Portfolio
Format
A data frame with 100 observations on the following 2 variables.
XReturns for Asset X
YReturns for Asset Y
Source
Simulated data
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(Portfolio)
attach(Portfolio)
plot(X,Y)
Time-to-Publication Data
Description
Publication times for 244 clinical trials funded by the National Heart, Lung, and Blood Institute.
Usage
Publication
Format
A data frame with 244 observations, each representing a clinical trial, and 9 variables:
posresDid the trial produce a positive (significant) result? 1=Yes, 0=No.
multiDid the trial involve multiple centers? 1=Yes, 0=No.
clinendDid the trial focus on a clinical endpoint? 1=Yes, 0=No.
mechFunding mechanism within National Institute of Health: a qualitative variable.
sampsizeSample size for the trial.
budgetBudget of the trial, in millions of dollars.
impactImpact of the trial; this is related to the number of publications.
timeTime to publication, in months.
statusWhether or not the trial was published at
time: 1=Published, 0=Not yet published.
Source
Gordon, Taddei-Peters, Mascette, Antman, Kaufmann, and Lauer. Publication of trials funded by the National Heart, Lung, and Blood Institute. New England Journal of Medicine, 369(20):1926-1934, 2013.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2021) An Introduction to Statistical Learning with applications in R, Second Edition, https://www.statlearning.com, Springer-Verlag, New York
S&P Stock Market Data
Description
Daily percentage returns for the S&P 500 stock index between 2001 and 2005.
Usage
Smarket
Format
A data frame with 1250 observations on the following 9 variables.
YearThe year that the observation was recorded
Lag1Percentage return for previous day
Lag2Percentage return for 2 days previous
Lag3Percentage return for 3 days previous
Lag4Percentage return for 4 days previous
Lag5Percentage return for 5 days previous
VolumeVolume of shares traded (number of daily shares traded in billions)
TodayPercentage return for today
DirectionA factor with levels
DownandUpindicating whether the market had a positive or negative return on a given day
Source
Raw values of the S&P 500 were obtained from Yahoo Finance and then converted to percentages and lagged.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(Smarket)
lm(Today~Lag1+Lag2,data=Smarket)
Mid-Atlantic Wage Data
Description
Wage and other data for a group of 3000 male workers in the Mid-Atlantic region.
Usage
Wage
Format
A data frame with 3000 observations on the following 11 variables.
yearYear that wage information was recorded
ageAge of worker
maritlA factor with levels
1. Never Married2. Married3. Widowed4. Divorcedand5. Separatedindicating marital statusraceA factor with levels
1. White2. Black3. Asianand4. Otherindicating raceeducationA factor with levels
1. < HS Grad2. HS Grad3. Some College4. College Gradand5. Advanced Degreeindicating education levelregionRegion of the country (mid-atlantic only)
jobclassA factor with levels
1. Industrialand2. Informationindicating type of jobhealthA factor with levels
1. <=Goodand2. >=Very Goodindicating health level of workerhealth_insA factor with levels
1. Yesand2. Noindicating whether worker has health insurancelogwageLog of workers wage
wageWorkers raw wage
Source
Data was manually assembled by Steve Miller, of Inquidia Consulting (formerly Open BI). From the March 2011 Supplement to Current Population Survey data.
https://www.re3data.org/repository/r3d100011860
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(Wage)
lm(wage~year+age,data=Wage)
## maybe str(Wage) ; plot(Wage) ...
Weekly S&P Stock Market Data
Description
Weekly percentage returns for the S&P 500 stock index between 1990 and 2010.
Usage
Weekly
Format
A data frame with 1089 observations on the following 9 variables.
YearThe year that the observation was recorded
Lag1Percentage return for previous week
Lag2Percentage return for 2 weeks previous
Lag3Percentage return for 3 weeks previous
Lag4Percentage return for 4 weeks previous
Lag5Percentage return for 5 weeks previous
VolumeVolume of shares traded (average number of daily shares traded in billions)
TodayPercentage return for this week
DirectionA factor with levels
DownandUpindicating whether the market had a positive or negative return on a given week
Source
Raw values of the S&P 500 were obtained from Yahoo Finance and then converted to percentages and lagged.
References
James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013) An Introduction to Statistical Learning with applications in R, https://www.statlearning.com, Springer-Verlag, New York
Examples
summary(Weekly)
lm(Today~Lag1+Lag2,data=Weekly)