Index

A

act parameter 233

action class 98–99

action parameters

about 19, 23

nested 24–26

removing 92–93

retrieving 92–93

specifying 22–27

action sets (CAS) 5–8, 35–37

actions

addtable 65–66, 68–70, 75–76

amntrain 233

checking return status of 32–35

columninfo 54, 94

correlation 96

crosstab 172–176

datapreprocess 176–181

distinct 163–166

droptable 56

dtreescore 225

dtreetrain 203–205, 219, 223

echo 23–24

exceptions 38–39

executing on CAS tables 11–12

fetch 55, 85, 89, 94, 120

foresttrain 228

freq 166–169

gbtreescore 231

genmod 201–202

getsessopt 57–58

glm 188–190

histogram 153

impute 181–184

loadactionset 36

logistic 212–214

resolving parameter problems 39–41

save 120

setsessopt 46–48, 58, 82–83

summary 55–56, 95–96, 149–152

tableinfo 54, 94

topk 169–171

actionset parameter 19, 23

activation functions 231

active caslib 57–58, 82–83

activeonadd parameter 58

add (+) operator 131

addtable action 65–66, 68–70, 75–76

alpha option 215

amntrain action 233

Anaconda Python distribution 1

& (and) operator 130

arch parameter 233

attribute interface, managing parameters using 105–106

attributes

dtypes 110

iloc 125, 127–128

loc 125, 127–128

message 39

reason 32

response 39

results 39

severity 32

shape 111

size 111

status 32

status_code 32

attributes, setting parameters as 90–92

attribute-style syntax 31

Authinfo file 16

automatic type casting 26

B

Binary data type 57

binary interfaces, REST interfaces vs. 236–238

Bokeh 12

bootstrap parameter 228

bracket notation 90–91

bracketed syntax 31

Bucket technique 179

BY statement 217

by-group processing

about 136–138

concatenating by-groups 139

handling multiple sets of by-groups 143–145

selecting result keys by table names 139–142

selecting specific by-groups 142

C

CAS

action results 28–35

action sets 5–8, 35–37

connecting to 15–17

data management in 49–83

data types 56–57

executing actions on tables 11–12

help for 37

installing 3

loading data into 9–10

running actions 8–9, 17–22

session options 46–48

CAS actions. see actions

CAS interface. see binary interfaces

CAS tables

about 50, 109

data wrangling 134–145

displaying data in 55

dropping 56

fetching data with a sort order 120–122

getting started with 51–58

indexing techniques 125–134

introspection 109–112

iterating 122–124

loading data into 53–54

selecting data 125–134

streaming data from databases into 75–77

uploading data files to 58–61

uploading data from Pandas DataFrames to 62–63

uploading data from URLs to 61–62

using objects like DataFrames 109–120

visibility of 57

CASAction objects 85–93

CASDataMsgHandler class 63

caslibinfo action 57

caslibs

about 50

active 57–58, 82–83

creating 82

dropping 83

getting started with 51–58

managing 82–83

visibility of 57

casout parameter 27

CASResults class 29

CASTable data, creating plots from 116–119

CASTable objects

getting started 93–107

manually creating 98

CASTable parameters

materializing 106–107

setting 99–102

CASTables

action interface 98–99

exporting to other formats 119–120

categorical variables

modeling 207–233

summarizing 162–176

cbar option 215

cflev parameter 222

Char data type 56

chart types 118–119

classes

action 98–99

CASDataMsgHandler 63

CASResults 29

Clipboard 63

collections.OrderedDict 29

CSV 63

DBAPI 63

Excel 63

HTML 63

JSON 63

OrderedDict 94

PandasDataFrame 63

SQLQuery 63, 72

SQLTable 63, 72

Text 63

"client-side view" 100

Clipboard class 63

cloglog link function 208

closing connections 14

collections.OrderedDict class 29

colon 24

columninfo action 54, 94

columns

computer 134–136

iterating through 122–124

selecting by label and position 125–126

columns attribute 110

comb parameter 233

communication, secure 248

computed columns, creating 134–136

computedvarsprogram parameter 100

concat function 32

concat_bygroups method 139, 152

concatenating, by groups 139

conn variable 16

connection attribute 39

connections

to CAS 15–17

closing 14

to existing sessions 247–248

conn.fetch(...) 87

continuous variables

modeling 185–205

summarizing 148–162

Continuum Analytics (website) 1

cooksd option 190

correlation action 96

correlations 161–162

count method 116

covratio option 190

crosstab action 172–176

CSS statistic 149

CSV class 63

Cutpts technique 179

CV statistic 116, 149

D

data

displaying in CAS tables 55

dynamic selection of 129–134

fetching with sort orders 120–122

loading 9–10, 53–54

loading into CAS tables 53–54

managing in CAS 49–83

selecting 125–134

selecting by label and position 127–129

streaming from databases into CAS tables 75–77

uploading from Pandas DataFrames to CAS tables 62–63

uploading from URLs to CAS tables   61–62

data files, uploading to CAS tables 58–61

data message handlers

Excel 69–71

HTML 64–69

PandasDataFrame 71–72

using 63–77

using with databases 72–77

writing your own 77–82

data transformers, adding 79–82

data types 56–57

data visualization 12–14

data wrangling

about 134

by-group processing 136–145

creating computed columns 134–136

databases

streaming data into CAS tables from 75–77

using data message handlers with 72–77

DataFrame method 137

DataFrames 30–32, 109–120

datapreprocess action 176–181

Date data type 57

Datetime data type 57

DATETIME format 68

date/time properties 133

DBAPI class 63

decision trees 217–226

DecQuad data type 56

DecSext data type 56

del_param(s) method 104, 152

describe method 97, 112–113

describe_option function 41–45

descriptive statistics 148–153

dffits option 190

dict constructor 24, 27

dictionary conversion 27

difchisq option 215

difdev option 215

dimension reduction 176–184

distinct action 163–166

distribution parameter 231

divide (/) operator 131

dot syntax 31

dot-separated notation 89

Double data type 56

droptable action 56

dtreescore action 225

dtreetrain action 203–205, 219, 223

dtypes attribute 110

dynamic data selection 129–134

E

echo action 23–24

equal-distance binning 153

equality (==) operator 131

error handling 37–38

errorFunc parameter 233

Excel class 63

Excel data message handler 69–71

exceptions 38–39

executing actions on CAS tables 11–12

export methods 119–120

exporting CASTables to other formats 119–120

F

fetch action 55, 85, 89, 94, 120

fetching data with sort orders 120–122

forests 226–233

foresttrain action 228

freq action 166–169

FREQ procedure 173–176

functions

activation 231

cloglog link 208

concat 32

describe_option 41–45

getnext 245

get_option 41–45

gridplot 158

link 198

log link 198

logit link 208

negative cloglog link 208

option_content 41–45

probit link 208, 212–213

reset_option 41–45

set_option 41–45

str2cas_datetime utility 80

str2cas_time utility 80

utility 25

vl utility 25

G

gbtreescore action 231

generalized linear models 197–202

genmod action 201–202

get_dtype_counts method 111

get_group method 142

getnext function 245

get_option function 41–45

get_param(s) method 88, 92–93

getrow method 77–78, 81–82

getsessopt action 57–58

GitHub 2

glm action 188–190

gradient boosting 226–233

greater than (>) operator 131

greater than or equal to (>=) operator 131

gridplot function 158

groupby method 142

groupby parameter 105, 138

H

h option 190, 214

has_param(s) method 93

head method 111–112, 121–122

help

for CAS 37

displaying 19

histogram action 153

histograms 153–159

HTML class 63

HTML data message handler 64–69

I

iloc attribute 125, 127–128

importing SWAT 5–8

impute action 181–184

includeBias parameter 233

indexing techniques 125–134

inequality (!=) operator 131

info method 97, 111

__init__constructor 77, 81–82

installing

CAS 3

Python 1

SAS SWAT 2–3

Int32 data type 56

Int64 data type 56

integers 26

invoke method 243–247

IPython 15–17, 20, 85–87

iterating, through columns and rows 122–124

iterrows method 124

ix accessor 128–129

J

JSON class 63

Jupyter notebook 2

K

**kwargs argument 22

L

label

selecting columns by 125–126

selecting data by 127–129

lasso parameter 231

lcl option 190, 214

lclm option 190, 214

leafsize parameter 222

less than (<) operator 131

less than or equal to (<=) operator 131

likedist option 190

linear regressions 186–197, 197–205

link function 198

loadactionset action 36

loading data 9–10

loadtable action 59, 67

loc attribute 125, 127–128

log link function 198

logistic action 212–214

logistic regression 207–217

logit link function 208

Lua programming language 24

M

m parameter 228, 231

Matplotib 12–13, 117

Max statistic 116, 149, 183

maxbranch parameter 222

maxlevel parameter 222

MEAN technique 116, 183

MEDIAN technique 183

message attribute 39

method interface, managing parameters using 102–104

methodcontinuous option 183

methodnominal option 183

methods

concat_bygroups 139, 152

count 116

DataFrame 137

del_param(s) 104, 152

describe 97, 112–113

export 119–120

get_dtype_counts 111

get_group 142

get_param(s) 88, 92–93

getrow 77–78, 81–82

groupby 142

has_param(s) 93

head 111–112, 121–122

info 97, 111

invoke 243–247

iterrows 124

plot 12–13, 117

probt 116

set_params 88

sort_values 121

stack 150

string 132–133

tail 111–112, 121–122

time-related 134

upload 53, 58–59, 61–62

MIDRANGE technique 183

Min statistic 149, 183

MODE technique 183

modeling

categorical variables 207–233

continuous variables 185–205

modulo (%) operator 131

multiply (*) operator 131

N

N statistic 149

negative cloglog link function 208

nested parameters 24–26, 89–90

Netrc file 16

neural networks 226–233

NMiss statistic 116, 149

ntree parameter 228, 231

nTries parameter 233

O

oob parameter 229

option_content function 41–45

options

alpha 215

cbar 215

cooksd 190

covratio 190

dffits 190

difchisq 215

difdev 215

h 190, 214

lcl 190, 214

lclm 190, 214

likedist 190

methodcontinuous 183

methodnominal 183

pred 190, 214

press 190

reschi 215

resdev 215

resid 190

reslik 215

resraw 214

reswork 215

rstudent 190

stats 115–116

stdi 190

stdp 190

stdr 190

stdreschi 215

stdxbeta 214

student 190

ucl 190, 214

uclm 190, 214

xbeta 214

| (or) operator 130

OrderedDict class 94

ordinary linear regressions, extensions of 197–205

out variable 28–29

P

Pandas DataFrame 9, 12, 62–63

PandasDataFrame class 63

PandasDataFrame data message handler 71–72

parameters

act 233

action 19, 22–27, 92–93

actionset 19, 23

activeonadd 58

arch 233

bootstrap 228

casout 27

CASTable 99–102, 106–107

cflev 222

comb 233

computedvarsprogram 100

distribution 231

errorFunc 233

groupby 105, 138

includeBias 233

lasso 231

leafsize 222

m 228, 231

managing using attribute interface 105–106

managing using method interface 102–104

maxbranch 222

maxlevel 222

nested 24–26, 89–90

ntree 228, 231

nTries 233

oob 229

pop 91

prune=True|False 222

responsefunc= 239–243

resultfunc= 239–243

ridge 231

scalar 27

seed 228, 231

setting as attributes 90–92

sortby 91, 120

subsamplerate 231

targetAct 233

targetComb 233

varimp=True|False 222

verbose 19, 23

vote='majority' 228

vote='prob' 228

percentiles 159–161

periods (.) 90

pip tool 2

platform 2

plot method 12–13, 117

plots, creating from CASTable data 116–119

pop parameter 91

position

selecting columns by 125–126

selecting data by 127–129

power (**) operator 25–26, 66, 131

pred option 190, 214

press option 190

probit link function 208, 212–213

probt method 116

ProbT statistic 149

prune=True|False parameter 222

Python 1

Q

Quantile technique 179

R

RANDOM technique 183

reason attribute 32

regression trees 202–205

regressions

linear 186–197

linear, extensions of ordinary 197–205

logistic 207–217

reschi option 215

resdev option 215

reset_option function 41–45

resid option 190

reslik option 215

resolving CAS action parameter problems 39–41

response attribute 39

responsefunc= parameter 239–243

resraw option 214

REST interface 63, 236–238

result keys, selecting by table name 139–142

result processing workflows 238–247

resultfunc= parameter 239–243

results attribute 39

reswork option 215

return status, checking of CAS actions 32–35

ridge parameter 231

rows, iterating through 122–124

rstudent option 190

running CAS actions 8–9, 17–22

S

SAS SWAT, installing 2–3

save action 120

scalar parameter 27

secure communication 248

seed parameter 228, 231

SELECT statement 74

set_option function 41–45

set_params method 88

setsessopt action 46–48, 58, 82–83

severity attribute 32

shape attribute 111

size attribute 111

sort orders, fetching data with 120–122

sortby parameter 91, 120

sort_values method 121

Spyder IDE 2

SQLite database 75

SQLQuery class 63, 72

SQLTable class 63, 72

stack method 150

statistics, descriptive 148–153

stats option 115–116

status attribute 32

status_code attribute 32

Std statistic 116, 149

StdErr statistic 116, 149

stdi option 190

stdp option 190

stdr option 190

stdreschi option 215

stdxbeta option 214

str2cas_datetime utility function 80

str2cas_time utility function 80

streaming data from databases into CAS tables 75–77

string methods 132–133

strings 26

student option 190

subsamplerate parameter 231

subtract (-) operator 131

Sum statistic 116, 149

summarizing

categorical variables 162–176

continuous variables 148–162

summary action 55–56, 95–96, 149–152

SWAT

importing 5–8

options 41–45

swat.options object 44–45

syntax 24

T

table name, selecting result keys by 139–142

tableinfo action 54, 94

tables. see CAS tables

tail method 111–112, 121–122

targetAct parameter 233

targetComb parameter 233

test connection 3

Text class 63

Time data type 57

time-related methods 134

topk action 169–171

transforming variables 176–184

TValue statistic 116, 149

U

ucl option 190, 214

uclm option 190, 214

upload method 53, 58–59, 61–62

URLs, uploading data to CAS tables from 61–62

USS statistic 116, 149

utility function 25

V

VALUE technique 183

Var statistic 116, 149

Varbinary data type 57

Varchar data type 57

variable binning 177–181

variable imputation 181–184

variables

about 79

categorical 162–176, 207–233

continuous 148–162, 185–205

transforming 176–184

varimp=True|False parameter 222

verbose parameter 19, 23

versions, Python 1

visibility, of caslib and CAS tables 57

vl utility function 25

vote='majority' parameter 228

vote='prob' parameter 228

W

WHERE clause 74

X

xbeta option 214