To read in excel files
library ( gdata )
# Note the forward slash on windows
# Set the working directory
setwd(“C:/Documents and Settings/csnyder/Desktop/My Dropbox/Projects/NEC/Data/”)
# Check it
(WD <- getwd())
#mdat <- read . xls ( “C:/Documents and Settings/csnyder/Desktop/My Dropbox/Projects/NEC/Data/yourfile.xls”)
# mdat <- read . xls ( “yourfile.xls”)
# Attach it if you wish
attach(mdat)

Set some identifiers
# mdat <- “my_data_frame” # If not already labeled appropriately
# miv <- “my_independent_variable” # This is the focus of your study
# This (below) does not work!
miv <- names(Term)

# What are the continuous variables?
# Create a subset dataframe with only these variables and the independent variable
mdat_continV <- subset ( mdat [ , c ( "Term" , "BWt" , "EGA" , "AgeatOp" , "AgeFirstFed" , "DaysatDx" , "LOS" , "Apgar1" , 'Apgar5' )])
View ( mdat_continV )

# Only the complete cases (no NA’s anywhere) – may skip this
# mdat_continV <-mdat_continV[complete.cases(mdat_continV),]

Create some functions – T-test
# Create a ttest function:
library ( plyr )
tt <- function ( x ) t . test ( x ~ Term , data = mdat_continV)
# One test is easy – supply the parameter to the function: tt(mdat$EGA)
# Use the colwise function in plyr
# colwise(function)(dataframe[c("col1", "col2")])
# Now, get the col names, skipping the first 2:
# names(mdat_continV)[-(1:3)]
colwise ( tt )( mdat_continV [ names ( mdat_continV )[-( 1 : 3 )]])
# The ‘code’ to read these results is
# 1 – t value
# 2 – degrees of freedom
# 3 – p value
# 4 – 95% confidence interval
# 5 – sample means compared (grp 0 and grp 1)
# 6 – ?
# 7 – 2-sided or 1-sided T test
# 9 – dependent variable by independent variable

# Here is another method to do apply t.test to several columns (cols 8 and 9 are the EGA and Bwt:
sapply(mdat[,8:9], FUN=tt) # returns a matrix
# The same function with this nomenclature can be used:
sapply(mdat[c("BWt", "EGA")], FUN=tt) # returns a matrix

Create some functions – Cross-tab and chi squared

# Function for chisq test:
csq_test <- function (x){
mresult <- xtabs(~Term+x, data = mdat, sparse = FALSE, exclude = c(NA, NaN), drop.unused.levels = FALSE)
print(mresult)
summary(mresult)
}
csq_test(Survived)

Create some graphics – Plot one continuous variable against another

# Define the plotting function
library (plyr)
Library(ggplot2)
# Form is: my_plot_fxn <- function(.col) ggplot(my_df) +
# geom_point(aes_string(x=”column_name_of_independ_variable”, y=.col))
plotone <- function ( .col ) ggplot ( mdat ) +
geom_point ( aes_string ( x = “DaysatDx” , y = .col ))
# Call the function with a list of the names of the
# columns you want
l.ply ( names ( mdat )[ c ( 8:9 , 11 )] , plotone , .print = T )

Create some graphics – Make a series of boxplots

library ( reshape2 )
graphcls <- function (mdat_continV) {
mdat_continV.m <- melt (mdat_continV , id.vars = “Term” )
ggplot (mdat_continV.m , aes ( x = factor ( Term ) , y = value , colour = variable )) +
geom_boxplot () +
ylab ( “Total Differences” )
}
# call the function with col 1 (term=your independent factor variable) and whatever col you need
# ignore the NAs by taking only the subset without them:
# mmdd <- subset(mdat_continV, subset= (Term <5 & DaysatDx < 90))
graphcls ( mdat_continV [ c ( 1 , 3 )])
graphcls ( mdat_continV [ c ( 1 , 7 )])
graphcls ( mdat_continV [ c ( 1 , 6 )])

Create some graphics – Make a series of boxplots (alternative)

library ( ggplot2 )
# This plot will work, but the NA’s are unsightly
# qplot ( factor ( Term ) , EGA , data = mdat , geom = “boxplot” )
# Eliminate the NA’s
# qplot ( factor ( Term ) , EGA , data = subset ( mdat , ! is.na ( EGA )) , geom = “boxplot” )
# Better: Same Plot but more fine control; colour outliers and label the axis
p <- ggplot ( subset ( mdat , ! is na ( EGA )) , aes ( factor ( Term ) , BWt ))
p + geom_boxplot ( outlie .colour = “red” , outlier.size = 3 ) + xlab ( “Term” )
# It is possible to create a plot inside a function, and simply call the function with the appropriate variable. Here “Term” is the
# independent binary variable
# Remove any NA’s in the independent variable:
mdat <- subset ( mdat , ! is.na ( Term )
mplot <- function ( x ) {
qplot ( factor ( Term ) , x , data = mdat , geom = “boxplot” )
}
mplot ( mdat$LOS )

Cleaning up imported data

# Any empty rows after the import?
# What are they? (in form c(empty_row_start:empty_row_end)
# Delete empty rows at the end
mdat <- mdat [- c( 492:495 ) , ]

# What are the column names?
names ( mdat )
# What are the column names, skipping the first 3 columns?
names ( yourdf )[-( 1:3 )]

# What if the column names need to be changed? This changes the name of col 2
colnames ( yourdf )[2] <- “newname”

# How many different values are in the rows of a specific column?
table ( mdat$YearDx )
# or, another way:
xtabs (~ YearDx , data = mdat )

# To do a more extensive cross-tabulation:
xtabs (~ YearDx + EGA + Survived , data = mdat )

# How many NA values are there in each column?
library ( plyr )
nmissing <- function ( x ) sum ( is.na ( x ))
table ( colwise ( nmissing )( mdat ))
# How do we deal with the NA values?
# Format is newdf <- olddf[complete.cases(olddf[, c("col_name1", "col_name2")]),]
# for NAs in a single column: newdf<-olddf[complete.cases(olddf[,"co_name1"]),]
mdat1 <- mdat [ complete.cases ( mdat [ , c( "Term" , "BWt" , "EGA" )]) , ]

# Bad data – we find there is an “F” instead of a “0″ for gender:
mdat $ Sex [ mdat $ Sex == "F" ] <- 0

# Ignore the rows with NA for Term:
mdat <- subset ( mdat , ! is.na ( Term ))

Reviewing summary variables

# To find the mean of the numerical columns, grouped by whether or not they are M/F or another binary variable
ddply ( mdat , .(Term) , colwise ( mean))
# Suppose you want to test various numerical (continuous) columns of data based on whether or not the baby is Term (0,1):
# This can be done with plyr, using colwise:
# Now, apply it to many columns with the colwise function
colwise ( tt )( mdat [ c ( "BWt" , "EGA" )])
# This is the best way to do it
sapply ( mdat [ , 8 : 9 ] , FUN = summary ) # returns a matrix

# What was the mean birthweight for term vs non term babies?
ddply ( mdat , “Term” , function ( mdat ) mean ( mdat$BWt , na.rm = T ))
# What were the number of survivors for term vs non term babies?
ddply ( mdat , “Term” , function ( mdat ) sum ( mdat$Survived , na.rm = T ))

library ( reshape2 )
# This will make 3 columns – the name of the two identifiers (Term and EGA), and the measured result (EGA)
melt ( mdat , “Term” , c ( “EGA” ) , na . rm = T )

# How many term infants versus non term?
myx <- arrange ( count ( mdat , “Term” ) , desc ( freq ))
myx

# What is the mean and sd for various values with term or non term infants?
aggregate ( EGA ~ Term , data = mdat , FUN = function ( x ) c ( M = mean ( x ) , SD = sd ( x )))

General

# What example data is available?
data ()

# Eliminate any rows with missing or NA data in the col of choice:
mdat2<-mdat[complete.cases(mdat1[,"BreastFed"]),]
View(mdat2)

This post is password protected. To view it please enter your password below:

Password:

Bret Victor – Inventing on Principle from CUSEC on Vimeo.

Here is an easy way to concatenate multiple word (or other format) files into another format – in this case, text.

1. cd to the directory containing the files

2. Run the following from the command line:

textutil -cat txt -title "Several Files" -output merged.txt *.doc

1. This uses textutil to bring together (cat) all *.doc files in the directory (folder) and output them as merged.text in the same directory

2. Link to textutil

Demographics

There were 213 visits, of which 110 were new patient visits. The patients were primarily loco-regional, with a few exceptions:

Pectus Referral Map

A ‘live’ version of this map can be seen at this link.

Overview

The mean age for new patients was 13.1 years; 13.4 for PC (Pectus Carinatum) and 12.8 for PE (Pectus Excavatum).

The overall M:F ratio was 87:23 (3.7:1). For PC the gender ratio was 2.4:1, and for PE 8:1.

Mean BMI overall was 18.8.

62 patients were classified as a PC variant, and 36 as PE.

Mean age at onset/recognition of the deformity was 9.5 years for PC and 1.7 years for PE (overall mean was 6.6 years).

FH was positive in 9/62 PC patients and 15/36 PE patients.

Haller index for the PE patients was a mean of 3.6, and the CI (Corrective Index) was 27.4.

1
2
3
4
5
6

//assign the file contents to the array myJsonInput
$myJsonInput = file_get_contents("/Path/test.json");
//Use json_decode to "Take a JSON encoded string and convert it into a PHP variable"
$json_arr=json_decode($myJsonInput,true);
//Create an empty array, $myLinks, to put the links in (in this example of pinboard bookmarks)
$mylinks = array();

The test.json file is of the form:

1

{"data":[{"description": "blah blah", "href":"http://google.com", "tags":"Search, News"},{"description": "more blah", "href":"http://nyt.com", "tags":"News"}]}

1
2
3
4
5
6
7
8
9
10

//Now, loop through the array to extract k:v pairs:
//Note that "data" is the name of the container in the json file
//The variable $link is basically a row of data
foreach ($json_arr['data'] as $link) 
{
	//Create an associative array ('hash', 'dictionay') pairing the description with the hyperlink in this case
    $mylinks[$link['description']] = $link['href'];
    //Put the results in a table:
    echo '<tr><td>', '<a href="', $link['href'], '">',$link['description'], '</a>', '</td><td>', $link['tags'],'</td></tr><p>';
}

Links
json_decode

Powered by Twitter Tools