************************************************************************

Kooste The Little SAS Bookin (5.painos) koodeista kahden päivän SAS-peruskurssille

Koodeista on jätetty tyhjiksi avainkohtia, joita täytetään harjoituksissa

HUOM! Lisäksi useimmissa esimerkeissä pitää mahdollisesti vaihtaa kansio-
polut oikeiksi.

Delwichen ja Slaughterin koodia muokannut T.Hurme

************************************************************************;

 /*-------------------------------------------------------------------*/ 
 /*       The Little SAS(r) Book: A Primer, Fifth Edition             */
 /*          by Lora D. Delwiche and Susan J. Slaughter               */
 /*       Copyright(c) 2012 by SAS Institute Inc., Cary, NC, USA      */
 /*                   SAS Publications order                          */
 /*                   ISBN 978-1-61290-343-9                          */
 /*-------------------------------------------------------------------*/
 /*                                                                   */
 /* This material is provided "as is" by SAS Institute Inc.  There    */
 /* are no warranties, expressed or implied, as to merchantability or */
 /* fitness for a particular purpose regarding the materials or code  */
 /* contained herein. The Institute is not responsible for errors     */
 /* in this material as it now exists or will exist, nor does the     */
 /* Institute provide technical support for it.                       */
 /*                                                                   */
 /*-------------------------------------------------------------------*/
 /* Date Last Updated: 30SEP2012                                      */
 /*-------------------------------------------------------------------*/
 /* Questions or problem reports concerning this material may be      */
 /* addressed to the author:                                          */
 /*                                                                   */
 /* SAS Institute Inc.                                                */
 /* SAS Press                                                         */
 /* Attn: Lora Delwiche and Susan Slaughter                           */
 /* SAS Campus Drive                                                  */
 /* Cary, NC   27513                                                  */
 /*                                                                   */
 /*                                                                   */
 /* If you prefer, you can send email to:  saspress@sas.com           */
 /* Use this for subject field:                                       */
 /*     Comments for Lora Delwiche and Susan Slaughter                */
 /*                                                                   */
 /*-------------------------------------------------------------------*/


/* Chapter 2 */

/* Section 2.4 */

/* First program */

* Read internal data into SAS data set uspresidents; 
DATA uspresidents;    

* Täydennetään tämän tilalle *;

RUN;


/* Section 2.4 */

/* Second program */

* Read data from external file into SAS data set; 
DATA uspresidents;

* Täydennetään tämän tilalle *;

   INPUT President $ Party $ Number;
RUN;


/* Section 2.5 */

/* Program */

* Create a SAS data set named toads;
* Read the data file ToadJump.dat using list input;
DATA toads;
   INFILE 'c:\MyRawData\ToadJump.dat';

* Täydennetään tämän tilalle *;

RUN;
* Print the data to make sure the file was read correctly;
PROC PRINT DATA = toads;
   TITLE 'SAS Data Set Toads';
RUN;


/* Section 2.6 */

/* Program */

* Create a SAS data set named sales;
* Read the data file OnionRing.dat using column input;
DATA sales;
   INFILE 'c:\MyRawData\OnionRing.dat';

* Täydennetään tämän tilalle *;

RUN;
* Print the data to make sure the file was read correctly;
PROC PRINT DATA = sales;
   TITLE 'SAS Data Set Sales';
RUN;


/* Section 2.7 */

/* Program */

* Create a SAS data set named contest;
* Read the file Pumpkin.dat using formatted input;
DATA contest;
   INFILE 'c:\MyRawData\Pumpkin.dat';

* Täydennetään tämän tilalle *;

RUN;
* Print the data set to make sure the file was read correctly;
PROC PRINT DATA = contest;
   TITLE 'Pumpkin Carving Contest';
RUN;


/* Section 2.14 */

/* First Program */

DATA icecream;
   INFILE 'c:\MyRawData\IceCreamSales.dat' /* Täydennetään tämän tilalle */;
   INPUT Flavor $ 1-9 Location BoxesSold;
RUN;


/* Second Program */

DATA icecream;
   INFILE 'c:\MyRawData\IceCreamSales2.dat' /* Täydennetään tämän tilalle */;
   INPUT Flavor $ 1-9 Location BoxesSold;
RUN;


/* Third Program */

DATA class102;
   INFILE 'c:\MyRawData\AllScores.dat' /* Täydennetään tämän tilalle */
   INPUT Name $ Test1 Test2 Test3 Test4 Test5;
RUN; 


/* Fourth Program */

DATA homeaddress;
   INFILE 'c:\MyRawData\Address.dat' /* Täydennetään tämän tilalle */
   INPUT Name $ 1-15 Number 16-19 Street $ 22-37;
RUN;


/* Section 2.18 */

/* First Program */

DATA /* Täydennetään tämän tilalle */
   Miles = 26.22;
   Kilometers = 1.61 * Miles;
RUN;
PROC PRINT DATA = /* Täydennetään tämän tilalle */;
RUN;

/* Second Program */
DATA /* Täydennetään tämän tilalle */; 
   Miles = 26.22;
   Kilometers = 1.61 * Miles;
RUN;
PROC PRINT DATA = /* Täydennetään tämän tilalle */;
RUN;


/* Section 2.19 */

/* First Program */

/* Täydennetään tämän tilalle */
DATA /* Täydennetään tämän tilalle */;
   INFILE 'c:\MyRawData\Mag.dat';
   INPUT ScientificName $ 1-14 CommonName $ 16-32 MaximumHeight
      AgeBloom Type $ Color $;
RUN;

/* Second Program */

PROC PRINT DATA = /* Täydennetään tämän tilalle */;
   TITLE 'Magnolias';
RUN;




/* Chapter 3 */

/* Section 3.1 */
/* Program */

* Modify homegarden data set with assignment statements;
DATA homegarden;
   INFILE 'c:\MyRawData\Garden.dat';
   INPUT Name $ 1-7 Tomato Zucchini Peas Grapes;

   /* Täydennetään tämän tilalle */

RUN;
PROC PRINT DATA = homegarden;
   TITLE 'Home Gardening Survey';
RUN;


/* Section 3.2 */
/* Program */

DATA contest;
   INFILE 'c:\MyRawData\Pumpkin.dat';
   INPUT Name $16. Age 3. +1 Type $1. +1 Date MMDDYY10.
         (Scr1 Scr2 Scr3 Scr4 Scr5) (4.1);

   /* Täydennetään tämän tilalle */

RUN;
PROC PRINT DATA = contest;
   TITLE 'Pumpkin Carving Contest';
RUN;


/* Section 3.5 */
/* Program */

DATA oldcars;
   INFILE 'c:\MyRawData\Auction.dat';
   INPUT Make $ 1-13 Model $ 15-29 YearMade Seats MillionsPaid;

   /* Täydennetään tämän tilalle */

RUN;
PROC PRINT DATA = oldcars;
   TITLE 'Cars Sold at Auction';
RUN;


/* Section 3.6 */
/* Program */

* Group observations by cost;
DATA homeimprovements;
   INFILE 'c:\MyRawData\Home.dat';
   INPUT Owner $ 1-7 Description $ 9-33 Cost;

   /* Täydennetään tämän tilalle */

RUN;
PROC PRINT DATA = homeimprovements;
   TITLE 'Home Improvement Cost Groups';
RUN;


/* Section 3.7 */
/* Program */

* Choose only comedies;
DATA comedy;
   INFILE 'c:\MyRawData\Shakespeare.dat';
   INPUT Title $ 1-26 Year Type $;

   /* Täydennetään tämän tilalle */

RUN;
PROC PRINT DATA = comedy;
   TITLE 'Shakespearean Comedies';
RUN;


/* Section 3.8 */
/* Program */

DATA librarycards;
   INFILE 'c:\MyRawData\Library.dat' TRUNCOVER;

   /* Täydennetään tämän tilalle */

RUN;
PROC PRINT DATA = librarycards;

   /* Täydennetään tämän tilalle */

   TITLE 'SAS Dates without and with Formats';
RUN;



/* Chapter 4 */


/* Section 4.2 */
/* First Program */

DATA 'c:\MySASLib\style';
   INFILE 'c:\MyRawData\Artists.dat';
   INPUT Name $ 1-21 Genre $ 23-40 Origin $ 42;
RUN;

/* Second Program */

PROC PRINT DATA = 'c:\MySASLib\style';
 
   /* Täydennetään tämän tilalle */

   TITLE 'Major Impressionist Painters';
   FOOTNOTE 'F = France N = Netherlands U = US';
RUN;


/* Section 4.3 */
/* Program */

DATA marine;
   INFILE 'c:\MyRawData\Lengths.dat';
   INPUT Name $ Family $ Length @@;
RUN;
* Sort the data;

   /* Täydennetään tämän tilalle */

PROC PRINT DATA = seasort;
   TITLE 'Whales and Sharks';
RUN;


/* Section 4.5 */
/* Program */

DATA sales;    
   INFILE 'c:\MyRawData\CandySales.dat'; 
   INPUT Name $ 1-11 Class @15 DateReturned MMDDYY10. CandyType $ Quantity;
   Profit = Quantity * 1.25;
PROC SORT DATA = sales;
   BY Class;

   /* Täydennetään tämän tilalle */


/* Section 4.6 */
/* Program */

DATA sales;
   INFILE 'c:\MyRawData\CandySales.dat';
   INPUT Name $ 1-11 Class @15 DateReturned MMDDYY10. CandyType $ Quantity;
   Profit = Quantity * 1.25;
PROC PRINT DATA = sales;
   VAR Name DateReturned CandyType Profit;

   /* Täydennetään tämän tilalle */

   TITLE 'Candy Sale Data Using Formats';
RUN;


/* Section 4.8 */
/* Program */

DATA carsurvey;
   INFILE 'c:\MyRawData\Cars.dat';
   INPUT Age Sex Income Color $;
RUN;

/* Täydennetään tämän tilalle */


* Print data using user-defined and standard (DOLLAR8.) formats;
PROC PRINT DATA = carsurvey;

   /* Täydennetään tämän tilalle */

   TITLE 'Survey Results Printed with User-Defined Formats';
RUN;


/* Section 4.10 */
/* Program */

DATA sales;
   INFILE 'c:\MyRawData\Flowers.dat';
   INPUT CustID $ @9 SaleDate MMDDYY10. Petunia SnapDragon Marigold;
   Month = MONTH(SaleDate);
PROC SORT DATA = sales;
   BY Month; 
* Calculate means by Month for flower sales;

/* Täydennetään tämän tilalle */


/* Section 4.11 */
/* Program */

DATA sales;
   INFILE 'c:\MyRawData\Flowers.dat';
   INPUT CustID $ @9 SaleDate MMDDYY10. Petunia SnapDragon Marigold;
PROC SORT DATA = sales;
   BY CustID;
* Calculate means by CustomerID, output sum and mean to new data set;
PROC MEANS NOPRINT DATA = sales;
   BY CustID;
   VAR Petunia SnapDragon Marigold;

/* Täydennetään tämän tilalle */

PROC PRINT DATA = totals;
   TITLE 'Sum of Flower Data over Customer ID';
   FORMAT MeanP MeanSD MeanM 3.;
RUN;


/* Section 4.12 */
/* Program */

DATA orders;
   INFILE 'c:\MyRawData\Coffee.dat';
   INPUT Coffee $ Window $ @@;
* Print tables for Window and Window by Coffee;

/* Täydennetään tämän tilalle */



/* Chapter 5 */

/* Section 5.6 */
/* Program */

* Create an RTF file;

/* Täydennetään tämän tilalle */

DATA marine;
   INFILE 'c:\MyRawData\Lengths8.dat';
   INPUT Name $ Family $ Length @@;
RUN;
PROC MEANS DATA = marine MEAN MIN MAX;
   CLASS Family;
   TITLE 'Whales and Sharks';
RUN;
PROC PRINT DATA = marine;
RUN;
* Close the RTF file;
/* Täydennetään tämän tilalle */



/* Chapter 6 */

/* Section 6.1 */

/* First Program */
* Create permanent SAS data set trains; 
DATA 'c:\MySASLib\trains';    
   INFILE 'c:\MyRawData\Train.dat';    
   INPUT Time TIME5. Cars People; 
RUN;
	
/* Second Program */
* Read the SAS data set trains with a SET statement;

/* Täydennetään tämän tilalle */

   PeoplePerCar = People / Cars;
RUN;
PROC PRINT DATA = averagetrain;
   TITLE 'Average Number of People per Train Car';
   FORMAT Time TIME5.;
RUN;


/* Section 6.2 */
	
/* Program */	
DATA southentrance;
   INFILE 'c:\MyRawData\South.dat';
   INPUT Entrance $ PassNumber PartySize Age;
PROC PRINT DATA = southentrance;
   TITLE 'South Entrance Data';
RUN;
DATA northentrance;
   INFILE 'c:\MyRawData\North.dat';
   INPUT Entrance $ PassNumber PartySize Age Lot;
PROC PRINT DATA = northentrance;
   TITLE 'North Entrance Data';
RUN; 

* Create a data set, both, combining northentrance and southentrance;
* Create a variable, AmountPaid, based on value of variable Age;

/* Täydennetään tämän tilalle */
   IF Age = . THEN AmountPaid = .;
      ELSE IF Age < 3  THEN AmountPaid = 0;
      ELSE IF Age < 65 THEN AmountPaid = 35;
      ELSE AmountPaid = 27;
RUN;
PROC PRINT DATA = both;
   TITLE 'Both Entrances';
RUN;

/* Section 6.4 */

/* Program */

DATA descriptions;     
   INFILE 'c:\MyRawData\chocolate.dat' TRUNCOVER;    
   INPUT CodeNum $ 1-4 Name $ 6-14 Description $ 15-60; 
RUN;
DATA sales;    
   INFILE 'c:\MyRawData\chocsales.dat';    
   INPUT CodeNum $ 1-4 PiecesSold 6-7; 
PROC SORT DATA = sales;
   BY CodeNum;
RUN;
* Merge data sets by CodeNum;

/* Täydennetään tämän tilalle */

PROC PRINT DATA = chocolates;   
   TITLE "Today's Chocolate Sales"; 
RUN;


/* Section 6.14 */

/* Program */
DATA baseball;
   INFILE 'c:\MyRawData\Transpos.dat';
   INPUT Team $ Player Type $ Entry;
PROC SORT DATA = baseball;
   BY Team Player;
PROC PRINT DATA = baseball;
   TITLE 'Baseball Data After Sorting and Before Transposing';
RUN;
* Transpose data so salary and batavg are variables;

/* Täydennetään tämän tilalle */

PROC PRINT DATA = flipped;
   TITLE 'Baseball Data After Transposing';
RUN;



/* Chapter 8 */


/* Section 8.5 */

DATA wings;
   INFILE 'c:\MyRawData\Birds.dat';
   INPUT Name $12. Type $ Length Wingspan @@;
RUN;
* Plot Wingspan by Length;
PROC FORMAT;
   VALUE $birdtype
      'S' = 'Songbirds'
      'R' = 'Raptors';
RUN;

/* Täydennetään tämän tilalle */

   FORMAT Type $birdtype.;
   TITLE 'Comparison of Wingspan vs. Length';
RUN;


/* Section 8.6 */

DATA electricity;
   INFILE 'c:\MyRawData\Hourly.dat';
   INPUT Time kWh @@;
RUN;
* Plot temperatures by time;

/* Täydennetään tämän tilalle */

   TITLE 'Hourly Use of Electricity';
RUN;


/* Section 8.7 */

DATA Olympic1500;
   INFILE 'C:\MyRawData\Olympic1500.dat';
   INPUT Year Men @@;
RUN;

/* Täydennetään tämän tilalle */

   LABEL Men = 'Time in Seconds';
   TITLE "Olympic Times for Men's 1500 Meter Run";
RUN;



/* Chapter 9 */

/* Section 9.1 */

/* Program */
DATA class;
   INFILE 'c:\MyRawData\Scores.dat';
   INPUT Score @@;
RUN;

/* Täydennetään tämän tilalle */


/* Section 9.2 */

/* Program */
DATA class;
   INFILE 'c:\MyRawData\Scores.dat';
   INPUT Score @@;
RUN;
PROC UNIVARIATE DATA = class;
   VAR Score;
/* Täydennetään tämän tilalle */
   TITLE;
RUN;


/* Section 9.8 */

/* Program */	
DATA class;
   INFILE 'c:\MyRawData\Exercise.dat';
   INPUT Score Television Exercise @@;
RUN;

/* Täydennetään tämän tilalle */

   TITLE 'Correlations for Test Scores';
   TITLE2 'With Hours of Television and Exercise';
RUN;


/* Section 9.9 */

/* Program */
DATA class;
   INFILE 'c:\MyRawData\Exercise.dat';
   INPUT Score Television Exercise @@;
RUN;
PROC CORR DATA = class /* Täydennetään tämän tilalle */;
   VAR Television Exercise;
   WITH Score;
   TITLE 'Correlations for Test Scores';
   TITLE2 'With Hours of Television and Exercise';
RUN;