Feng Zhang's Homepage

C++/Qt

// read in file
#include

#include

QFile file(fileName);

if( !file.open(QIODevice::ReadOnly | QIODevice::Text) ) return;

while(!file.atEnd()) { QString line = file.readLine().trimmed(); }

Java

// read in file
File

// convert epoch time to string
System.out.println(new SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new Date(Long.parseLong(epochDateInMilliseconds))));

JSON

# Install Jshon
$ wget http://kmkeen.com/jshon/jshon.tar.gz

$ wget http://www.digip.org/jansson/releases/jansson-2.4.tar.gz

$ install jansson first

$ cd jshon-xx

$ vim Makefile

$ add -I/path/to/jansson/include to CFLAGS

$ add -L/path/to/jansson/lib to LFLAGS

$ make and copy jshon to your bin folder

$ export PATH=$PATH:/path/to/jshon/bin

$ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/path/to/jansson/lib
# examples/document can be found here: http://kmkeen.com/jshon/

# Processing source forge download data (json format)
# url template: http://sourceforge.net/projects/projectName/files/stats/json?start_date=1990-05-01&end_date=2012-12-15
cat jsonFileName | jshon -k # show keys

Latex

% reset the counter of sections
\newcounter

% use csv file as the input of a table
# Click Here to View the Original References
% use Latex to create a simple csv file for test
1 \documentclass{minimal}

2 \begin{filecontents*}{scientists.csv}

3 name,surname,age

4 Albert,Einstein,133

5 Marie,Curie,145

6 Thomas,Edison,165

7 \end{filecontents*}
% Use package csvsimple to show a simple table
1 \documentclass{article}

2 \usepackage{csvsimple}

3 \begin{document}

4 \csvautotabular{scientists.csv}

5 \end{document}

MySQL

# connect to remote mysql server with specified port
$ mysql -h ipOrHostName -P port -u userName -p databaseName

# store query result into file
# - store the file on the server
mysql> SELECT field1,field2 FROM table1 INTO OUTFILE 'some.csv' FIELDS TERMINATED BY ',' ENCLOSED BY '"' LINES TERMINATED BY '\n';
# - store the file on the client
$ mysql -h ipOrHostName -P port -u userName -p databaseName -e "SELECT field1,field2 FROM table1" > some.csv

# Create database, user, and grant user permissions.
$ mysql -u root -p

mysql> CREATE DATABASE mydatabasename;

mysql> CREATE USER myuser IDENTIFIED BY 'mypassword';

mysql> GRANT ALL ON mydatabasename.* TO myuser;

# Let mysql accepts user from any host
mysql> USE mysql;

mysql> SHOW TABLES;

mysql> DESC user;

mysql> SELECT host,user FROM user;

mysql> UPDATE user SET host='%' WHERE user='root' and host='somehost';
mysql> FLUSH PRIVILEGES;

Perl Script

# read in file
open(FILE, "<", $fileName) or die "$!";

while(<FILE>)

{

chomp;

my$line=$_;

}

close(FILE);

R

# read in csv
> inputData=read.csv(fileName, header='T', split=',')

> names(inputData)

# rotate matrix
> t(matrixX)

# write to csv file
> write.csv(tableX, file=c("fileName.csv"), quote=FALSE)

# show number with specified count of digits
> sprintf("%.2f", 0.250199129003)

[1] 0.25

# append lists and name it
> m <- list()

> m1 <- c(1,2,3)

> m[[length(m)+1]] <- m1

> m2 <- c(5,6,7,8,9)

> m[[length(m)+1]] <- m2

> names(m) <- c("m1Name", "m2Name")
# when use the list, e.g., m1 or m2
> m1 <- m[["m1Name"]]

# Useful functions
# Click Here to View the Original References

> length(object) # number of elements or components

> str(object) # structure of an object

> class(object) # class or type of an object

> names(object) # names

> c(object,object,...) # combine objects into a vector

> cbind(object, object, ...) # combine objects as columns

> rbind(object, object, ...) # combine objects as rows

> object # prints the object

> ls() # list current objects

> rm(object) # delete an object

> newobject <- edit(object) # edit copy and save as newobject

> fix(object) # edit in place

# Useful examples
# Click Here to View the Original References

# Improving Speed Performance of Loops
# Click Here to View the Original References

# string substitution (similar to sed)
# Click Here to View the Original References

> a=c("a_b", "c-d")

> gsub("[_-]", "", a)

[1] "ab", "cd"

sed/awk

$ replace string
$ sed s/oldString/newString/g

$ select specified line from file
$ sed -n 'lineNumber,1p' fileName

$ sum the numbers per line of a file
awk '{sum+=$1} END {print sum}' myNumberFile

Shell Script

$ convert date to epoch (assume current date is: 2012-11-29 17:58:20)
$ date +%s

$ 1354229900

$ date +%s -d "September 18, 2012"

$ 1347940800
$ convert epoch to date
$ date +"%Y-%m-%d %H:%M:%S" -d @1354229900

$ 2012-11-29 17:58:20

$ CPIO usage
$ 1. Backup(copy-out mode)
$ find someDir | cpio -ov > someDir.cpio
$ 2. Restore(copy-in mode)
$ cpio -idv < someDir.cpio
$ 3. Restore files matching some pattern(copy-in mode)
$ cpio -idv "*fileNamePattern*"< someDir.cpio
$ 4. List files(output format like ls)
$ cpio -it < someDir.cpio

$ cpio -it "*fileNamePattern*"< someDir.cpio
$ 5. List files(output format like ls -l)
$ cpio -itv < someDir.cpio

$ cpio -itv "*fileNamePattern*"< someDir.cpio

$ loop
$ for (( c=1; c<=5; c++ ))

$ do

$ echo "Welcome $c times"

$ done

# loop on each element of an array
# Click Here to View the Original References

$ array=( one two three )

$ printf "%s\n" "${array[@]}"

$ for i in "${arrayName[@]}"

$ do

$ echo i

$ done

$ generate random number
$ echo $(( ( $RANDOM % MaximumNumberToGenerate ) + 1 ))

$ list unique lines of a file (i.e., remove duplicated lines)
$ uniq fileName

$ read a file line by line (white space will be considered as a NEWLINE)
$ for line in $(< fileName)

$ do

$ echo $line

$ done
$ read a file line by line with white space(not efficiency)
$ FILENAME=$1

$ nbLines=`wc -l < $FILENAME`

$ count=0

$ while [ $count -lt $nbLines ]

$ do

$ let count++

$ line=`head -n $count $FILENAME | tail -1`

$ echo "$count: $line"

$ done

$ compare decimal number
$ if [ $var -lt 1000 ]; then

$ echo "$var is < 1000."

$ fi

$ find specified file type or multiple file types
$ find someDir -type f -name '*.cpp'

$ find someDir -type f -name '*.cpp' -o -name '*.h'

$ find someDir -type f -name '*.cpp' -o -name '*.h' -o -name '*.java'

$ Processing CSV file
$ cut -d , -f 1,2,3 csvFile

$ paste -d , <(cut -d , -f 1 csvFile1) <(cut -d , -f 2,5 csvFile2) > mergedCSVFile

$ sort -t , -k 2,2n -k 1,1n csvFile > csvFile_sortedByField2ThenField1

# Repeat a string N times
$ yes $string | head -n N

# Given a pair of , count unique values per key
$ cut keyValuePairFileName -d , -f 1 | sort | uniq | sed 's/$.*$/echo "\1,`grep "^\1," keyValuePairFileName \| wc -l`"/g' | sh

# Execute commands line by line
$ OLDIFS=$IFS

$ IFS=$(echo -en '\n\b')

$ for line in $lines

$ do

$ execute command based on $line here

$ done

# Find the timestamp of first and last commit from CVS log file
$ dateList=`grep ^date cvsLogFileName | sed 's/date:\s\+$[^;]\+$;.*/\1/g' | xargs -L1 -I {} date +%s -d "{}" | sort -n | uniq`

$ firstDate=`echo "$dateList" | head -n 1`

$ lastDate=`echo "$dateList" | tail -n 1`

Understand CLI

$ add files to database and analyze
$ und add @fileList database.udb

$ und analyze database.udb
$ export metrics
$ und metrics database.udb
$ export dependencies (file level)
$ und export -dependencies file matrix dependencyMatrix.csv database.udb
$ export dependencies (class level)
$ und export -dependencies class matrix dependencyMatrix.csv database.udb

vim

"my setting
set tabstop=4

set sw=4

set sts=4

set number

set smarttab

set smartindent

:colorscheme relaxedgreen

# install colorscheme
$ download it from here.

$ mkdir -p ~/.vim/colors (if not exist)

$ copy relaxedgreen.vim to ~/.vim/colors

Mathematic Methods

Evaluate the likeliness of an event to occur
Odds Ratio

Evaluate the duration and degree of some events. Model stochastic time-dependent phenomena.
Hazard rate analysis

Choosing a statistical test
http://www.graphpad.com/support/faqid/1790

Effect Size: mapping Cohen's d and Cliff's delta
http://www.uccs.edu/lbecker/effect-size.html