Function to calculate age from date of birth.

Description

his function calculates age in days, months, or years from a date of birth to another arbitrary date. This returns a numeric vector in the specified units.

Usage

age_calc(dob, enddate = Sys.Date(), units = "months", precise = TRUE)

Arguments

Value

A numeric vector of ages the same length as the dob vector

Author(s)

Jason P. Becker

Source

This function was developed in part from this response on the R-Help mailing list.

See Also

See also difftime which this function uses and mimics some functionality but at higher unit levels.

Examples

a <- as.Date(seq(as.POSIXct('1987-05-29 018:07:00'), len=26, by="21 day"))
b <- as.Date(seq(as.POSIXct('2002-05-29 018:07:00'), len=26, by="21 day"))

age <- age_calc(a, units='years')
age
age <- age_calc(a, units='months')
age
age <- age_calc(a, as.Date('2005-09-01'))
age

A function to replicate the basic plot function for linear models in ggplot2

Description

This uses ggplot2 to replicate the plot functionality for lm in ggplot2 and allow themes.

Usage

## S3 method for class 'lm'
autoplot(object, which = c(1:6), mfrow = c(3, 2), ...)

Arguments

Value

A ggplot2 object that mimics the functionality of a plot of linear model.

References

Modified from: https://librestats.com/2012/06/11/autoplot-graphical-methods-with-ggplot2/

See Also

plot.lm which this function mimics

Examples

# Univariate
a <- runif(1000)
b <- 7 * a + rnorm(1)
mymod <- lm(b~a)
autoplot(mymod)
# Multivariate
data(mpg)
mymod <- lm(cty~displ + cyl + drv, data=mpg)
autoplot(mymod)

Remove Unwanted LaTeX files after building document

Description

Convenience function for cleaning up your directory after running pdflatex

Usage

cleanTex(fn, keepPDF = TRUE, keepRnw = TRUE, keepRproj = TRUE)

Arguments

Value

Nothing. All files except the .tex, .pdf and .Rnw are removed from your directory.

Draw a visual crosstab (mosaic plot) with shading for correlations and labels in each cell.

Description

Improves labeling of mosaic plots over mosaic from the vcd package

Usage

crosstabplot(
  data,
  rowvar,
  colvar,
  varnames,
  title = NULL,
  subtitle = NULL,
  label = FALSE,
  shade = TRUE,
  ...
)

Arguments

Value

A mosaic plot

See Also

mosaic which this function wraps crosstabs which does the data manipulation for the crosstab

Examples

df <- data.frame(cbind(x=seq(1,3,by=1), y=sample(LETTERS[6:8],60,replace=TRUE)),
fac=sample(LETTERS[1:4], 60, replace=TRUE))
varnames<-c('Quality','Grade')
myCT <- crosstabs(df, rowvar = "x",colvar = "fac", varnames = varnames, digits =2)
crosstabplot(df, rowvar = "x",colvar = "fac", varnames = varnames, 
title = 'My Plot', subtitle = 'Foo', label = FALSE, shade = TRUE, digits = 3)

Build a list of crosstabulations from a dataset

Description

Build a list of crosstabulations from a dataset

Usage

crosstabs(data, rowvar, colvar, varnames, digits = 2)

Arguments

Value

a list with crosstab calculations

Examples

df<-data.frame(cbind(x=seq(1,3,by=1), y=sample(LETTERS[6:8],60,replace=TRUE)),
fac=sample(LETTERS[1:4], 60, replace=TRUE))
varnames<-c('Quality','Grade')
myCT <- crosstabs(df, rowvar = "x",colvar = "fac", varnames = varnames, digits =2)

A function to calculate thresholds of cumulative sums in a vector.

Description

This function tells us how far we have to go before reaching a cutoff in a variable by sorting the vector, then finding how far to go. Note that the cutoff is expressed in percentage terms (fixed cumulative sum)

Usage

cutoff(x, cutoff, na.rm = TRUE)

Arguments

Details

Calculates the distance through a numeric vector before a certain proportion of the sum is reached by sorting the vector and calculating the cumulative proportion of each element

Value

An integer for the minimum number of elements necessary to reach cutoff

Author(s)

Jared E. Knowles

Examples

# for vector
a <- rnorm(100, mean=6, sd=1)
cutoff(a, .7) #return minimum number of elements to account 70 percent of total

Remove commas from numeric fields and return them as numerics

Description

A shortcut function to strip commas out of numeric fields imported from other software and convert them into numeric vectors that can be operated on. This assumes decimal point as opposed to decimal comma notation.

Usage

decomma(x)

Arguments

Details

This function assumes decimal point notation for numbers. For more information, see https://en.wikipedia.org/wiki/Decimal_mark#Countries_using_Arabic_numerals_with_decimal_point.

Value

A numeric

Author(s)

Jared E. Knowles

Examples

input <- c("10,243", "11,212", "7,011", "5443", "500")
output <- decomma(input)
is.numeric(output)

Convert a factor to a character string safely

Description

This is a shortcut function to convert a factor to a character variable without having to type as.character()

Usage

defac(x)

Arguments

Value

A character

Author(s)

Jared E. Knowles

See Also

factor, levels to understand the R implementation of factors.

Examples

a <- as.factor(LETTERS)
summary(a)
b <- defac(a)
class(b)

Evaluation of educational policy tools

Description

Make common tasks for educational evaluation easier to do!

Details

his package has a number of useful shortcuts for common tasks. It includes some themes for ggplot2 plots, processing arbitrary text files of data, calculating student characteristics, and finding thresholds within vectors. Future development work will include methods for tuning and evaluating early warning system models.

Note

This package is still in beta and function names may change in the next release.

Author(s)

Jared E. Knowles

Examples

gender<-c("M","M","M","F","F","F")
statamode(gender)
statamode(gender[1:5])

missing_data<-c(NA,NA,NA)
max_mis(missing_data)

makenum(gender)
gender <- factor(gender)
defac(gender)

Generate prediction intervals for model functions

Description

Generate prediction intervals from R models following Gelman and Hill

Usage

gelmansim(mod, newdata, n.sims, na.omit = TRUE)

Arguments

Details

Currently gelmansim does not work for lm objects because of the way sim in the arm package handles variable names for these objects. It is recommended users use glm in these cases.

Value

A dataframe with newdata and prediction intervals

References

Modified from Gelman and Hill 2006. Data Analysis Using Regression and Multilevel/Hierarchical Models. Cambridge University Press.

Examples

 #Examples of "sim" 
set.seed (1)
J <- 15
n <- J*(J+1)/2
group <- rep (1:J, 1:J)
mu.a <- 5
sigma.a <- 2
a <- rnorm (J, mu.a, sigma.a)
b <- -3
x <- rnorm (n, 2, 1)
sigma.y <- 6
y <- rnorm (n, a[group] + b*x, sigma.y)
u <- runif (J, 0, 3)
y123.dat <- cbind (y, x, group)
# Linear regression 
x1 <- y123.dat[,2]
y1 <- y123.dat[,1]
M1 <- glm (y1 ~ x1)

cases <- data.frame(x1 = seq(-2, 2, by=0.1))
sim.results <- gelmansim(M1, newdata=cases, n.sims=200, na.omit=TRUE)
## Not run: 

dat <- as.data.frame(y123.dat)
M2 <- glm (y1 ~ x1 + group, data=dat)

cases <- expand.grid(x1 = seq(-2, 2, by=0.1), 
                     group=seq(1, 14, by=2))

sim.results <- gelmansim(M2, newdata=cases, n.sims=200, na.omit=TRUE)
 

## End(Not run)

A function to check if a set of variables form a unique ID in a dataframe.

Description

When passed a set of variable names and a dataframe, this function returns a check TRUE/FALSE whether or not the variables together uniquely identify a row in the dataframe.

Usage

isid(data, vars, verbose = FALSE)

Arguments

Value

TRUE or FALSE. TRUE indicates the variables uniquely identify the rows. FALSE indicates they do not.

Author(s)

Jared E. Knowles

Examples

data(stuatt)
isid(stuatt, vars = c("sid"))
isid(stuatt, vars = c("sid", "school_year"))
isid(stuatt, vars = c("sid", "school_year"), verbose = TRUE)

Create a lag

Description

Lag variables by an arbitrary number of periods even if the data is grouped

Usage

lag_data(df, group, time, periods, values)

Arguments

Value

A dataframe with a newly created variable lagged

Examples

test_data <- expand.grid(id = sample(letters, 10), 
                        time = 1:10)
test_data$value1 <- rnorm(100)
test_data$value2 <- runif(100)
test_data$value3 <- rpois(100, 4)
group <- "id"
time <- "time"
values <- c("value1", "value2")
vars <- c(group, time, values)
periods <- 2
newdat <- lag_data(test_data, group="id", time="time", 
                 values=c("value1", "value2"), periods=3)

Function to add leading zeroes to maintain fixed width.

Description

This function ensures that fixed width data is the right length by padding zeroes to the front of values. This is a common problem with fixed width data after importing into R as non-character type.

Usage

leading_zero(x, digits = 2)

Arguments

Details

If x contains negative values then the width specified by digits will include one space taken up for the negative sign. The function does not trim values that are longer than digits, so the vector produced will not have a uniform width if nchar(x) > d

Value

A character vector of length digits

Author(s)

Jason P. Becker

Jared E. Knowles

Examples

a <- seq(1,10)
a <- leading_zero(a, digits = 3)
a

a function to convert numeric factors into numeric class objects

Description

This function allows you to convert directly from a numeric factor to the numeric class in R and strip away the underlying level index of a factor. This makes it safer to convert from factors to numeric characters directly without accidentally misassigning numbers.

Usage

makenum(x)

Arguments

Details

This function should only be used on factors where all levels are valid numbers that can be coerced into a numeric class.

Value

A numeric

Note

This will force all levels to be converted to characters and then to numeric objects. Leading zeroes will be stripped off and commas will cause errors.

Author(s)

Jared E. Knowles

See Also

character

Examples

a <- ordered(c(1, 3, '09', 7, 5))
b <- makenum(a)
class(b)
b
a

A function to safely take the maximum of a vector that could include only NAs.

Description

When computing the maximum on arbitrary subsets of data, some of which may only have missing values, it may be necessary to take the maximum of a vector of NAs. This replaces the behavior that returns Inf or-Inf and replaces it with simply returning an NA.

Usage

max_mis(x)

Arguments

Details

This function only returns valid results for vectors with a mix of NA and numeric values.

Value

A vector with the maximum value or with an NA of the proper type

Author(s)

Jared E. Knowles

See Also

See also max which this function wraps.

Examples

max(c(7,NA,3,2,0),na.rm=TRUE)
max_mis(c(7,NA,3,2,0))
max(c(NA,NA,NA,NA),na.rm=TRUE)
max_mis(c(NA,NA,NA,NA))

A dataframe of aggregate test scores for schools in a Midwest state.

Description

This data comes from publicly available aggregated test scores of a large midwestern state. Each row represents scores for school A in grade X and then scores in school A and grade X+1. Additionally, some regression diagnostics and results from a predictive model of test scores in grade X+1 are included.

Usage

midsch

Format

A data frame with 19985 observations on the following 16 variables.

district_id

a numeric vector

school_id

a numeric vector

subject

a factor with levels math read representing the subject of the test scores in the row

grade

a numeric vector

n1

a numeric vector for the count of students in the school and grade in t

ss1

a numeric vector for the scale score in t

n2

a numeric vector for the count of students in the school and grade in t+1

ss2

a numeric vector for the mean scale score in t+1

predicted

a numeric vector of the predicted ss2 for this observation

residuals

a numeric vector of residuals from the predicted ss2

resid_z

a numeric vector of standardized residuals

resid_t

a numeric vector of studentized residuals

cooks

a numeric vector of cooks D for the residuals

test_year

a numeric vector representing the year the test was taken

tprob

a numeric vector representing the probability of a residual appearing

flagged_t95

a numeric vector

Details

These data were fit with a statistical model by a large newspaper to investigate unusual gains in test scores. Fifty separate models were fit representing all unique combinations of grade,year, and subject

Examples

data(midsch)
head(midsch)

Function to calculate the number of times a student has changed schools.

Description

This function calculates the number of times a student has changed schools, including accounting for gaps in enrollment data. It returns a data.table with the student ID and the number of student moves.

Usage

moves_calc(
  df,
  enrollby,
  exitby,
  gap = 14,
  sid = "sid",
  schid = "schid",
  enroll_date = "enroll_date",
  exit_date = "exit_date"
)

Arguments

Details

enrollby and exitby are specified automatically if not defined. They are assigned to the default dates of -09-15 and -06-01 of the min and max year respectively.

Value

a data.frame

Author(s)

Jason P. Becker

Examples

## Not run: 
df <- data.frame(sid = c(rep(1,3), rep(2,4), 3, rep(4,2)), 
                 schid = c(1, 2, 2, 2, 3, 1, 1, 1, 3, 1),
                 enroll_date = as.Date(c('2004-08-26',
                                         '2004-10-01',
                                         '2005-05-01',
                                         '2004-09-01',
                                         '2004-11-03',
                                         '2005-01-11',
                                         '2005-04-02',
                                         '2004-09-26',
                                         '2004-09-01',
                                         '2005-02-02'), 
                                       format='%Y-%m-%d'),
                 exit_date = as.Date(c('2004-08-26',
                                       '2005-04-10',
                                       '2005-06-15',
                                       '2004-11-02',
                                       '2005-01-10',
                                       '2005-03-01',
                                       '2005-06-15',
                                       '2005-05-30',
                                       NA,
                                       '2005-06-15'), 
                                     format='%Y-%m-%d'))
moves <- moves_calc(df)
moves
moves <- moves_calc(df, enrollby='2004-10-15', gap=22)
moves
moves <- moves_calc(df, enrollby='2004-10-15', exitby='2005-05-29')
moves

## End(Not run)

Find the nth maximum value

Description

Find the nth maximum value

Usage

nth_max(x, n = 1)

Arguments

Value

the value of the nth most maximum value in a vector

Note

If n is smaller/larger than 0/length(unique(x)) the error ‘index outside bounds’ is thrown.

Examples

x <- c(1:20, 20:1)
nth_max(x, n = 1) #20
nth_max(x, n = 2) #19

Creates a proficiency polygon in ggplot2 for showing assessment categories

Description

Creates a proficiency polygon in ggplot2 for showing assessment categories

Usage

profpoly(data)

Arguments

Value

a ggplot2 object that can be printed or saved

See Also

geom_polygon which this function wraps

Examples

grades<-c(3,4,5,6,7,8)
g <- length(grades)
LOSS <- rep(200, g)
HOSS <- rep(650, g)
basic <- c(320,350,370,390,420,440)
minimal <- basic-30
prof <- c(380,410,430,450,480,500)
adv <- c(480,510,530,550,580,600)
z <- profpoly.data(grades, LOSS, minimal, basic, proficient = prof, 
                  advanced = adv, HOSS)
profpoly(z)

Creates a data frame suitable for building custom polygon layers in ggplot2 objects

Description

Creates a data frame suitable for building custom polygon layers in ggplot2 objects

Usage

profpoly.data(grades, LOSS, minimal, basic, proficient, advanced, HOSS)

Arguments

Value

a dataframe for adding a polygon to layers in other ggplot2 plots

See Also

geom_polygon which this function assists

Examples

grades<-c(3,4,5,6,7,8)
g<-length(grades)
LOSS<-rep(200,6)
HOSS<-rep(650,6)
basic<-c(320,350,370,390,420,440)
minimal<-basic-30
prof<-c(380,410,430,450,480,500)
adv<-c(480,510,530,550,580,600)

z<-profpoly.data(grades,LOSS,minimal,basic,
               proficient = prof,advanced = adv, HOSS)
z

A function to replace an arbitrary character like a "*" in redacted data with an NA in R

Description

Redacted education data files often have a "*" character. When importing into R this is a problem, which this function solves in a simple step by replacing "*" with NA, and then converting the vector to numeric.

Usage

remove_char(x, char)

Arguments

Value

Returns a vector of the same length as the input vector that is numeric with NAs in place of the character.

Note

Future versions could be modified to accommodate other indicators of redacted data.

Author(s)

Jared E. Knowles

Examples

a <- c(1, 5, 3, 6, "*", 2, 5, "*", "*")
b <- remove_char(a, "*")
as.numeric(b)

Function to calculate whether a student has repeated a grade.

Description

This function calculates whether or not a student has repeated a grade. It returns a data.frame with the student ID and a character vector with Y representing they repeated the grade and N that they had not.

Usage

retained_calc(df, sid = "sid", grade = "grade", grade_val = 9)

Arguments

Value

a data.frame

Author(s)

Jason P. Becker

Examples

x <- data.frame(sid = c(101, 101, 102, 103, 103, 103, 104),
               grade = c(9, 10, 9, 9, 9, 10, 10))
retained_calc(x)

A function to mimic the mode function in Stata.

Description

This function mimics the functionality of the mode function in Stata. It does this by calculating the modal category of a vector and replacing tied categories with a "."to represent a single mode does not exist.

Usage

statamode(x, method = c("last", "stata", "sample"))

Arguments

Details

Specifying method="stata" will result in ties for the mode being replaced with a "." character. Specifying "sample" will result in the function randomly sampling among the tied values and picking a single value. Finally, specifying "last" will result in the function picking the value that appears last in the original x vector. The default behavior is stata.

Value

The modal value of a vector if a unique mode exists, else output determined by method

Author(s)

Jared E. Knowles

See Also

table which this function uses

Examples

a <- c(month.name, month.name)
statamode(a, method="stata") # returns "." to show no unique mode; useful for ddply
statamode(a ,method="sample") # randomly pick one
a <- c(LETTERS, "A" , "A")
statamode(a)

Student Attributes from the Strategic Data Project Toolkit

Description

A synthetic dataset of student attributes from the Strategic Data Project which includes records with errors to practice data cleaning and implementing business rules for consistency in data.

Usage

stuatt

Format

A data frame with 87534 observations on the following 9 variables.

sid

a numeric vector of the unique student ID

school_year

a numeric vector of the school year

male

a numeric vector indicating 1 = male

race_ethnicity

a factor with levels A B H M/O W

birth_date

a numeric vector of the student birthdate

first_9th_school_year_reported

a numeric vector of the first year a student is reported in 9th grade

hs_diploma

a numeric vector

hs_diploma_type

a factor with levels Alternative Diploma College Prep Diploma Standard Diploma

hs_diploma_date

a factor with levels 12/2/2008 12/21/2008 4/14/2008 4/18/2008 ...

Details

This is the non-clean version of the data to allow for implementing business rules to clean data.

Source

Available from the Strategic Data Project online at https://sdp.cepr.harvard.edu/toolkit-effective-data-use

References

Visit the Strategic Data Project online at: https://sdp.cepr.harvard.edu/

Examples

data(stuatt)
head(stuatt)

A synthetic data set of K-12 student attributes.

Description

A small dataset of synthetic data on K-12 students with 2700 observations. 1200 individual students are represented, nested within 4 districts and 2 schools.

Usage

stulevel

Format

A data frame with 2700 observations on the following 32 variables.

X

a numeric vector

school

a numeric vector

stuid

a numeric vector

grade

a numeric vector

schid

a numeric vector

dist

a numeric vector

white

a numeric vector

black

a numeric vector

hisp

a numeric vector

indian

a numeric vector

asian

a numeric vector

econ

a numeric vector

female

a numeric vector

ell

a numeric vector

disab

a numeric vector

sch_fay

a numeric vector

dist_fay

a numeric vector

luck

a numeric vector

ability

a numeric vector

measerr

a numeric vector

teachq

a numeric vector

year

a numeric vector

attday

a numeric vector

schoolscore

a numeric vector

district

a numeric vector

schoolhigh

a numeric vector

schoolavg

a numeric vector

schoollow

a numeric vector

readSS

a numeric vector

mathSS

a numeric vector

proflvl

a factor with levels advanced basic below basic proficient

race

a factor with levels A B H I W

Details

This data is synthetically generated to reflect student test scores and demographic attributes.

Source

The script to generate this synthetic dataset can be found and modified at https://github.com/jknowles/r_tutorial_ed

Examples

data(stulevel)
head(stulevel)

a deprecated ggplot2 theme developed for PDF and PNG for use at the Wisconsin Department of Public Instruction

Description

This is a custom ggplot2 theme developed for the Wisconsin Department of Public Instruction. This function is now deprecated.

Usage

theme_dpi(base_size = 16, base_family = "")

Arguments

Details

All values are optional

Value

A theme object which is a list of attributes applied to a ggplot2 object.

Author(s)

Jared E. Knowles

Source

For more information see https://github.com/hadley/ggplot2/wiki/Themes

See Also

his uses unit from the grid package extensively. See also theme_bw from the ggplot2 package.

a deprecated ggplot2 theme developed for PDF or SVG maps

Description

This is a deprecated ggplot2 theme developed for the Wisconsin Department of Public Instruction for making PDF maps

Usage

theme_dpi_map(base_size = 14, base_family = "")

Arguments

Details

All values are optional

Value

A theme object which is a list of attributes applied to a ggplot2 object.

Author(s)

Jared E. Knowles

Source

For more information see https://github.com/hadley/ggplot2/wiki/Themes

See Also

his uses unit from the grid package extensively. See also theme_bw from the ggplot2 package.

an alternate deprecated ggplot2 theme developed for PDF or SVG maps

Description

This is a deprecated ggplot2 theme developed for the Wisconsin Department of Public Instruction for making PDF maps

Usage

theme_dpi_map2(base_size = 14, base_family = "")

Arguments

Details

All values are optional

Value

A theme object which is a list of attributes applied to a ggplot2 object.

Author(s)

Jared E. Knowles

Source

For more information see https://github.com/hadley/ggplot2/wiki/Themes

See Also

his uses unit from the grid package extensively. See also theme_bw from the ggplot2 package.

an deprecated ggplot2 theme developed for PNG or JPG maps

Description

This is a deprecated ggplot2 theme developed for the Wisconsin Department of Public Instruction for making PNG or JPG maps

Usage

theme_dpi_mapPNG(base_size = 18, base_family = "")

Arguments

Details

All values are optional

Value

A theme object which is a list of attributes applied to a ggplot2 object.

Author(s)

Jared E. Knowles

Source

For more information see https://github.com/hadley/ggplot2/wiki/Themes

See Also

his uses unit from the grid package extensively. See also theme_bw from the ggplot2 package.

A function to return the maximum percentage of the cumulative sum represented by a subset of the vector

Description

Returns the proportion of the cumulative sum represented by the number of elements in the vector a user specifies. This allows the user to identify the maximum proportion of the total that only X number of elements may represent in the vector.

Usage

thresh(x, cutoff, na.rm = TRUE)

Arguments

Details

Calculates the proportion of a numeric vector reached after sorting the vector in ascending order and stopping at the specified count

Value

A numeric proportion

Author(s)

Jared E. Knowles

See Also

cutoff which this function is related to

Examples

# for vector
a <- rnorm(100, mean=6, sd=1)
thresh(a, 8) #return minimum number of elements to account 70 percent of total