dsadasdasdasdasdsadasdasdasdasdsadasdasdasdasdata clinic.

admit2;
/* Data Step */
set clinic.admit;
run;
proc print data=clinic.admit2; /* Procudure Step */
run;sadasdasdasdasdsadasdasdasdasdsadasdasdasdasd

proc tabulate data=proc print data=clinic.admit2;proc print data=clinic.admit2;proc

print data=clinic.admit2;clinic.admit;
class sex; /* Row */
var height weight; /* Column */
table sexsadasdasdasdasdsadasdasdasdasd*(height weight),mean; /* Cell value */
run;
proc print data=clinic.admit2;proc print data=clinic.admit2;proc print
data=clinic.admit2;proc print data=clinic.admit2;
proc sadasdasdasdasdsadasdasdasdasdcopy in=clinic out=work; /* Copy
admit dataset from clinic to work directory */
select admit;
run

/* SAS dsadasdasdasdasdsadasdasdasdasdataset has descriptive and data portion */

/* Attribute: Name, type(char-32767 byte, num-8 byte), format(write),
informat(read), label(256 char)*/
1234 as $1234.00 in a report, you can use the DOLLAR8.2
5678 as 5,678.00 in a report, you can use the COMMA8.2
Formats write values out
informats read data values
*-----;

SAS Help: Sample datasets are stored

libname clinic(1-8) 'd:\users\qtr\reports';

proc contents data=mylib._all_ nods;

run;

proc datasets;
contents data=sasuser._all_ nods;
quit;

35

options nonumber nodate;

options date;
options nodate pageno=3;
options pageno=1 pagesize=15;
options pageno=1 linesize=64;
options yearcutoff=1925;

options firstobs=10 obs=15;

proc print data=sasuser.heart;
run;

proc options; /*To list all SAS system options, their settings */
run;

Data error and syntax error

----------
proc print data=clinic.admit; To get column sum
 sum fee;
run;

proc print data=admit label;

var age height weight fee;
label fee='Admission Fee';
run;

proc print data=clinic.admit noobs;

var age height weight fee;
where age>30;
run;

= ^= > < >= <=

eq ne gt lt ge le

where firstname CONTAINS 'Jon';

where firstname ? 'Jon';

proc sort data=clinic.admit out=work.wgtadmit;

by weight age;
run;

proc print data=work.activity;

var age height weight fee;
where age>30;
sum fee;
by actlevel; Sub total
pageby actlevel;
run;

proc print data=clinic.stress double; Double Spacing

var resthr maxhr rechr;
where tolerance='I';
run;

title1 'Heart Rates for Patients with';

title3 'Increased Stress Tolerance Levels';
proc print data=clinic.stress;
var resthr maxhr rechr;
where tolerance='I';
run;

footnote1 'Data from Treadmill Tests';

footnote3 '1st Quarter Admissions';
proc print data=clinic.stress;
var resthr maxhr rechr;
where tolerance='I';
run;

title1; Remove title1

proc print data=clinic.therapy label;

label walkjogrun='Walk/Jog/Run'; Change label
run;

proc print data=clinic.admit;

var actlevel fee;
where actlevel='HIGH';
 format fee dollar4.;
run;

-------

filename tests 'c:\users\tmill.dat'; reference external file

infile tests;

filename exer 'c:\users\exer.dat';

data exercise;
infile exer;
input ID $ 1-4 Age 6-7 ActLevel $ 9-12 Sex $ 14;
run;

Unlike syntax errors, invalid data errors do not cause SAS to stop processing a
program.

- ** * / + -

& |
and or

TestDate='01jan2000'd;
Time='9:25't;
DateTime='18jan2005:9:27:05'dt

data clinic.stress;
input ID 1-4 Name $ 6-25 RestHr 27-29 MaxHR 31-33
RecHR 35-37 TimeMin 39-40 TimeSec 42-43
Tolerance $ 45;
if tolerance='D';
TotalTime=(timemin*60)+timesec;
datalines;
2458 Murray, W 72 185 128 12 38 D
2462 Almers, C 68 171 133 10 5 I
;

---------

Data step: Compilation phase then execution phase

Program data vector, area of memory where SAS builds a data set, one observation
at a time.
Automactic variables are created _n_ and _error_
end of file marker is reached where process ends

put 'MY NOTE: The condition was met.';

code= _n_= _error_=;

put 'MY NOTE: invalid value: ' _all_ ;

if rate>0 then
Interest=amount*(rate/12);
else put 'DATA ERROR ' rate= _n_=;

Missing numeric values are represented by periods, and missing character values are
represented by blanks.

-------------
proc format lib=library;
 value jobfmt
103='manager'
105='text processor'
111='assoc. technical writer'
112='technical writer'
113='senior technical writer';
run;

proc format lib=library;

value $grade
'A'='Good'
'B'-'D'='Fair'
'F'='Poor'
'I','U'='See Instructor';
run;

proc format lib=library;

value agefmt
low-<13='child'
13-<20='teenager'
20-<65='adult'
65-high='senior citizen'
other='unknown';
run;

If applied to a character format, the keyword LOW includes missing character

values.

data perm.empinfo;
infile empdata;
input @9 FirstName $5. @1 LastName $7. +7 JobTitle 3.
@19 Salary comma9.;
format salary comma9.2 jobtitle jobfmt.;
run;

libname library 'c:\sas\formats\lib';

proc format library=library fmtlib; list of all formats in your cataloge
run;

------------

proc report data=flights.europe nowd;

run;

proc report data=flights.europe nowd;

column flight orig dest mail freight revenue;
run;

proc report data=flights.europe nowd;

column flight orig dest mail freight revenue;
where dest in ('LON','PAR');
run;

proc report data=flights.europe nowd;

where dest in ('LON','PAR');
column flight orig dest mail freight revenue;
define revenue/format=dollar15.2;
run;
proc report data=flights.europe nowd;
where dest in ('LON','PAR');
column flight orig dest mail freight revenue;
define revenue / format=dollar15.2;
define flight / width=6;
define orig / width=4 spacing=5;
define dest / width=4 spacing=5;
run;

proc report data=flights.europe nowd;

where dest in ('LON','PAR');
column flight orig dest mail freight revenue;
define revenue / format=dollar15.2;
define flight / width=13'Flight Number';
define orig / width=13 spacing=5 'Flight Origin';
define dest / width=18 spacing=5 'Flight Destination';
run;

proc report data=flights.europe nowd headline headskip;

where dest in ('LON','PAR');
column flight orig dest mail freight revenue;
define revenue / mean format=dollar15.2
'Average/Revenue';
define flight / group 'Flight/Number' width=6 center;
define orig / group width=6 spacing=5 'Flight/Origin'
center;
define dest / group width=11 spacing=5
'Flight/Destination' center;
run;

-----------

proc means data=perm.survey;

run;

proc means data=perm.survey median range;

run;

proc means data=clinic.diabetes min max maxdec=0;

run;

proc means data=clinic.diabetes min max maxdec=0;

var age height weight;
run;

proc means data=clinic.heart maxdec=1;

var arterial heart cardiac urinary;
class survive sex;
run;

proc means data=clinic.diabetes;

var age height weight;
class sex;
output out=work.sum_gender
mean=AvgAge AvgHeight AvgWeight
min=MinAge MinHeight MinWeight;
run;
class will generate single table, but by will generate small tables

proc summary data=clinic.diabetes;

var age height weight;
class sex;
output out=work.sum_gender
mean=AvgAge AvgHeight AvgWeight;
run;

proc freq data=parts.widgets;

run;

proc freq data=finance.loans;

tables rate months;
run;

proc freq data=clinic.diabetes;

tables weight*height; (rows*cloumn)
format weight wtfmt. height htfmt.;
run;

proc freq data=clinic.diabetes;

tables sex*weight / nofreq norow nocol;
format weight wtfmt.;
run;

-----------

ODS: Output Delivery System

ods html body='c:\mydata.html';
proc print data=sasuser.mydata;
run;
ods html close;

ods listing close; dont want to produce listing output

ods html file='HTML-file-pathname';

ods pdf file='PDF-file-pathname';
proc print data=sasuser.admit;
run;
ods _all_ close;
ods listing;

ods listing close;

ods html body='f:\admit.html';
proc print data=clinic.admit label;
var sex age height weight actlevel;
label actlevel='Activity Level';
run;
ods html close;
ods listing;

ods listing close;

ods html body='c:\records\data.html'
contents='c:\records\toc.html'
frame='c:\records\frame.html';
proc print data=clinic.admit label;
var id sex age height weight actlevel;
label actlevel='Activity Level';
run;
proc print data=clinic.stress2;
var id resthr maxhr rechr;
run;
ods html close;
ods listing;

----------------

data clinic.stress;
infile tests;
input ID $ 1-4 Name $ 6-25 RestHR 27-29 MaxHR 31-33
RecHR 35-37 TimeMin 39-40 TimeSec 42-43
Tolerance $ 45;
TotalTime=(timemin*60)+timesec;
retain SumSec 5400;
sumsec+totaltime;
run;

data clinic.stress;
infile tests;
input ID $ 1-4 Name $ 6-25 RestHR 27-29 MaxHR 31-33
RecHR 35-37 TimeMin 39-40 TimeSec 42-43
Tolerance $ 45;
TotalTime=(timemin*60)+timesec;
retain SumSec 5400;
sumsec+totaltime;
if totaltime>800 then TestLength='Long';
run;

In SAS, any numeric value other than 0 or missing is true, and a value of 0 or
missing is false.

if totaltime>800 then TestLength='Long';

else if 750<=totaltime<=800 then TestLength='Normal';
else if totaltime<750 then TestLength='Short';

data clinic.stress;
infile tests;
input ID $ 1-4 Name $ 6-25 RestHR 27-29 MaxHR 31-33
RecHR 35-37 TimeMin 39-40 TimeSec 42-43
Tolerance $ 45;
TotalTime=(timemin*60)+timesec;
retain SumSec 5400;
sumsec+totaltime;
length TestLength $ 6;
if totaltime>800 then testlength='Long';
else if 750<=totaltime<=800 then testlength='Normal';
else if totaltime<750 then TestLength='Short';
run;

if resthr<70 then delete;

data clinic.stress(drop=timemin timesec);

data clinic.stress(keep=timemin timesec);

format sumsec comma6.;

data emps(keep=salary group);

 set sasuser.payrollmaster;
length Group $ 20;
select(jobcode);
when ("FA1") group="Flight Attendant I";
when ("FA2") group="Flight Attendant II";
when ("FA3") group="Flight Attendant III";
otherwise group="Other";
end;
run;

if totaltime>800 then
do;
testlength='Long';
message='Run blood panel';
end;
else if 750<=totaltime<=800 then testlength='Normal';
else if totaltime<750 then TestLength='Short';
run;

data payroll;
set salaries;
select(payclass);
when ('monthly') amt=salary;
when ('hourly')
do;
amt=hrlywage*min(hrs,40);
if hrs>40 then put 'CHECK TIMECARD';
end;
otherwise put 'PROBLEM OBSERVATION';
end;
run;

--------------

data lab23.drug1h;
setresearch.cltrials;
run;

data lab23.drug1h(drop=placebo uric);

set research.cltrials(drop=triglyc);
if sex='M' then delete;
if placebo='YES';
TestDate='22MAY1999'd;
retain Days 30;
days+1;
length Retest $ 5;
if cholesterol>190 then retest='YES';
else if 150<=cholesterol<=190 then retest='CHECK';
else if cholesterol<150 then retest='NO';
label retest='Perform Cholesterol Test 2?';
format enddate mmddyy10.;
run;

data lab23.drug1h(drop=placebo);
set research.cltrials(drop=triglycerides uricacid);
if placebo='YES';
run;

data work.addtoend(drop=timemin timesec);

 set clinic.stress2(keep=timemin timesec)end=last;
TotalMin+timemin;
TotalSec+timesec;
TotalTime=totalmin*60+timesec;
if last;
run;

--------------

One-to-one reading : Creates observations that contain all of the variables from
each contributing data set.
Data clinic.one2one;
set clinic.patients;
if age<60;
set clinic.measure;
run;

Concatenating : Appends the observations from one data set to another.

data clinic.concat;
set clinic.therapy1999 clinic.therapy2000;
run;

Interleaving : Intersperses observations from two or more data sets, based on one
or more common variables.
data clinic.interlv;
set clinic.therapy1999 clinic.therapy2000;
by month;
run;

Match-merging : Matches observations from two or more data sets into a single
observation in a new data set according to the values of a common variable.
data clinic.merged;
merge clinic.demog clinic.visit;
by id;
run;

data clinic.merged;
merge clinic.demog(rename=(date=BirthDate))
clinic.visit(rename=(date=VisitDate));
by id;
run;
proc print data=clinic.merged;
run;

data clinic.merged;
merge clinic.demog(in=indemog
rename=(date=BirthDate))
clinic.visit(in=invisit
rename=(date=VisitDate));
by id;
if indemog=1 and invisit=1;
run;

merge clinic.demog(in=indemog
rename=(date=BirthDate))
clinic.visit(drop=weight in=invisit
rename=(date=VisitDate));

----------
mean(of x1-x3)

The INPUT function converts character data values to numeric values.

The PUT function converts numeric data values to character values.

Test=input(saletest,comma9.);

INPUT(source,informat)
PUT(source,format)

data hrd.newtemp;
set hrd.temp;
Assignment=put(site,2.)||'/'||dept;
run;

January 1, 1960

proc print data=hrd.temp;

format startdate enddate date9.;
run;

date=mdy(mon,day,yr);
now=today();
now=date();
curtime=time();
day=day(date);
quarter=qtr(date);
wkday=weekday(date);
month=month(date);
yr=year(date);

x=intck('day',d1,d2);
x=intck('week',d1,d2);
x=intck('month',d1,d2);
x=intck('qtr',d1,d2);
x=intck('year',d1, d2);

x=intnx('interval',start- from,increment);

x=datdif('date1',date2, ACT/ACT);
x=yrdif('date1',date2, ACT/ACT);

Years=intck('year',hired,today());
TargetYear=intnx('year','05feb94'd,3);

MonthX=intnx('month','01jan95'd,5,'b');

DATDIF(start_date,end_date,basis)
YRDIF(start_date,end_date,basis)

Years=intck('year',hired,today());
TargetYear=intnx('year','05feb94'd,3);

MonthX=intnx('month','01jan95'd,5,'b');

SCAN(argument,n,delimiters)
LastName=scan(name,1)
SUBSTR(argument,position,<n>)
substr(middlename,1,1)

MiddleInitial=substr(middlename,1,1); Give value

substr(region,1,3)='NNW'; Set value

data hrd.newtemp(drop=address city state zip);

set hrd.temp;
NewAddress=trim(address)||', '||trim(city)||', '||zip;
run;

data hrd.newtemp(drop=address city state zip);

set hrd.temp;
NewAddress=catx(', ',address,city,zip);
run;

data hrd.datapool;
set hrd.temp;
if index(job,'word processing') > 0; search word processing in column job
run;

index(upcase(job),'WORD PROCESSING')
index(lowcase(job),'word processing')

data hrd.datapool;
set hrd.temp;
if find(job,'word processing','t') > 0;
run;

upcase(job)
lowcase(title)
Contact=propcase(contact)

name=tranwrd(name,'Monroe','Manson') replace Monroe with Manson

INT(argument) interger part is returned

ROUND(argument,round-off-unit)

MiddleInitial=substr(scan(name,3),1,1);
Years=intck('year','15jun1999'd,today());

--------------

data finance.earnings;
Amount=1000;
Rate=.075/12;
do month=1 to 12;
Earned+(amount+earned)*(rate);
end;
run;

data work.earn (drop=counter);

Value=2000;
do counter=1 to 20;
Interest=value*.075;
value+interest;
Year+1;
end;
run;
data work.earn;
Value=2000;
do Year=1 to 20;
Interest=value*.075;
value+interest;
output; explicit output
end;
run;

DO index-variable=5 to 1 by -1;
SAS statements
END;

data work.earn;
do year=1 to 20;
Capital+2000;
do month=1 to 12;
Interest=capital*(.075/12);
capital+interest;
end;
end;
run;

data work.invest;
do until(Capital>=50000);
capital+2000;
capital+capital*.10;
Year+1;
end;
run;

data work.invest;
do while(Capital>=50000);
capital+2000;
capital+capital*.10;
Year+1;
end;
run;

data work.subset;
do sample=10 to 5000 by 10;
set factory.widgets point=sample;
output;
end;
stop;
run;

-------------

A SAS array is a temporary grouping of SAS variables under a single name. An array
exists only for the duration of the DATA step.

data work.report(drop=i);
set master.temps;
array wkday{7} mon tue wed thr fri sat sun;
do i=1 to 7;
wkday{i}=5*(wkday{i}-32)/9;
end;
run;

array sales{4} qtr1 qtr2 qtr3 qtr4;

array sales{4} qtr1-qtr4;
array sales{96:99} totals96-totals99;

Amount Rate Term → _NUMERIC_

array sales{*} _numeric_;

FrstName LastName Address → →→ → _CHARACTER_

array sales{*} _character_

data work.report(drop=i);
set master.temps;
array wkday{7} mon tue wed thr fri sat sun;
do i=1 to 7;
if wkday{i}>95 then output;
end;
run;

data work.weights(drop=i);
set master.class;
array wt{6} w1-w6;
do i=1 to 6;
wt{i}=wt{i}*2.2;
end;
run;

data work.new(drop=i);
set master.synyms;
array term{9} also1-also9;
do i=1 to 9;
if term{i} ne ' ' then output;
end;
run;

data hrd.convert;
set hrd.fitclass;
array wt{*} weight1-weight6;
do i=1 to dim(wt);
wt{i}=wt{i}*2.2046;
end;
run;

array firstname{5} $ 24; /* Creating array */

data hrd.diff;
set hrd.convert;
array wt{6} weight1-weight6;
array WgtDiff{5};
do i=1 to 5;
wgtdiff{i}=wt{i+1}-wt{i};
end;
run;

array goal{4} g1 g2 g3 g4 (9000 9300 9600 9900); Assigining values to macro

array col{3} $ color1-color3 ('red','green','blue');

 array Var{4} (1 2 3 4);

data finance.report;
set finance.qsales;
array sale{4} sales1-sales4;
array Goal{4} (9000 9300 9600 9900);
array Achieved{4};
do i=1 to 4;
achieved{i}=100*sale{i}/goal{i};
end;
run;

data finance.report;
set finance.qsales;
array sale{4} sales1-sales4;
array goal{4} _temporary_ (9000 9300 9600 9900);
array Achieved{4};
do i=1 to 4;
achieved{i}=100*sale{i}/goal{i};
end;
run;

array new{3,4} x1-x12; 2-D Array

new{2,3}=0;

data finance.quarters(drop=i j);

set finance.monthly;
array m{4,3} month1-month12;
array Qtr{4};
do i=1 to 4;
qtr{i}=0;
do j=1 to 3;
qtr{i}+m{i,j};
end;
end;
run;

data work.rotate(drop=qtr1-qtr4); Rotating the dataset

set finance.funddrive;
array contrib{4} qtr1-qtr4;
do Qtr=1 to 4;
Amount=contrib{qtr};
output;
end;
run;

-------------

SAS provides three primary input styles—column input, formatted input, and list
input.

input Item $ 1-13 IDnum $ 15-19 InStock 21-22

BackOrd 24-25;

The @n moves the input pointer to a specific column number.

The +n moves the input pointer forward to a column number that is relative to the
current position
input @1 LastName $7.

input LastName $7. @9 FirstName $5.

input @9 FirstName $5. @1 LastName $7. @15 JobTitle 3.

input LastName $7. +1 FirstName $5. +5 Salary comma9.

input LastName $7. +1 FirstName $5. +5 Salary comma9. @15 JobTitle 3.;

You can use the notation +(-n) to move the +n pointer control backward.

input @9 FirstName $5.;

input @9 FirstName $5. @1 LastName $7. +7 JobTitle 3.; read with length 3

input @9 FirstName $5. @1 LastName $7. +7 JobTitle 3; assign length of 3

data perm.empinfo;
infile empdata;
input @9 FirstName $5. @1 LastName $7. +7 JobTitle 3.
@19 Salary comma9.;
run;

Two common record formats are fixed-length records and variable-length records.
input Dept $ 1-11 @13 Receipts comma8.;
infile receipts pad;
The PAD option pads each record with blanks so that all data lines have the same
length.

---------------

data perm.survey;
infile credit;
input Gender $ Age Bankcard FreqBank Deptcard
FreqDept;
run;

data perm.survey;
infile credit dlm=',';
input Gender $ Age Bankcard FreqBank
Deptcard FreqDept;
run;

data survey.phone;
infile survey;
input IDnum $ Ques1-Ques5;
run;

data survey.stores;
infile stordata;
input Age (Store1-Store3) ($); Range of character variable
run;

data test.scores;
infile group3;
input Age (Score1-Score4) (6.);
run;
data perm.survey;
infile credit missover; Missing at the end
input Gender $ Age Bankcard FreqBank
Deptcard FreqDept;
run;

data perm.survey;
infile credit dsd;
input Gender $ Age Bankcard FreqBank
Deptcard FreqDept;
run;

data perm.growth;
infile citydata;
length City $ 12; Specify length
input city $ Pop70 Pop80;
run;

The ampersand (&) modifier is used to read character values that contain embedded
blanks.
The colon (:) modifier is used to read nonstandard data values and character values
that are longer than eight characters, but which contain no embedded blanks.

input Rank City &; 2 consec blanks

The colon (:) indicates that values are read until a blank (or other delimiter)
is encountered, and then an informat is applied

data perm.cityrank;
infile topten;
input Rank City & $12.
Pop86 : comma.;

data _null_; free format

set perm.finance;
file 'c:\data\findat';
put ssn name salary date : date9.;
run;

data _null_;
set perm.finance;
file 'c:\data\findat2' dlm=',';
put ssn name salary date : date9.;
run;

data _null_
set perm.finance;
file 'c:\data\findat2' dlm=',';
put ssn name salary : comma6. date date9.;
run;

data _null_;
set perm.finance;
file 'c:\data\findat2' dsd; value containing commas
put ssn name salary : comma. date : date9.;
run;

data work.finance2;
infile findat2 dsd;
 length SSN $ 11 Name $ 9;
input ssn name Salary : comma. Date date9.;
run;

data _null_;
set work.totals;
file totaldat;
put 'Sales for salesrep ' salesrep
'totaled ' sales : dollar9.;
run;

--------------------

A SAS date value is the number of days from January 1, 1960, to the given date.