SAS | Migrate from SAS to Python

Inhaltsverzeichnis

Introduction

Cookbook

proc freq

proc freq data=mydata;
    tables myvar / nocol nopercent nocum;
run;
mydata.myvar.value_counts().sort_index()

sort by frequency

proc freq order=freq data=mydata;
	tables myvar / nocol nopercent nocum;
run;
mydata.myvar.value_counts()

with missing

proc freq order=freq data=mydata;
    tables myvar / nocol nopercent nocum missing;
run;
mydata.myvar.value_counts(dropna=False)

proc means

proc means data=mydata n mean std min max p25 median p75;
    var myvar;
run;
mydata.myvar.describe()

more percentiles

proc means data=mydata n mean std min max p1 p5 p10 p25 median p75 p90 p95 p99;
	var myvar;
run;
mydata.myvar.describe(percentiles=[.01, .05, .1, .25, .5, .75, .9, .95, .99])

data step

concatenate datasets

data concatenated;
    set mydata1 mydata2;
run;
concatenated = pandas.concat([mydata1, mydata2])

proc contents

proc contents data=mydata;
run;
mydata.info()

save output

proc contents noprint data=mydata out=contents;
run;
contents = mydata.info()  # check this is right

Misc

number of rows in a datastep

* Try this for size: http://www2.sas.com/proceedings/sugi26/p095-26.pdf;
len(mydata)