+dnl PSPP - a program for statistical analysis.
+dnl Copyright (C) 2017 Free Software Foundation, Inc.
+dnl
+dnl This program is free software: you can redistribute it and/or modify
+dnl it under the terms of the GNU General Public License as published by
+dnl the Free Software Foundation, either version 3 of the License, or
+dnl (at your option) any later version.
+dnl
+dnl This program is distributed in the hope that it will be useful,
+dnl but WITHOUT ANY WARRANTY; without even the implied warranty of
+dnl MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+dnl GNU General Public License for more details.
+dnl
+dnl You should have received a copy of the GNU General Public License
+dnl along with this program. If not, see <http://www.gnu.org/licenses/>.
+dnl
AT_BANNER([EXAMINE])
AT_SETUP([EXAMINE])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [
DATA LIST LIST /QUALITY * W * BRAND * .
BEGIN DATA
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-Breaking Strain,24.00,100%,.00,0%,24.00,100%
+Breaking Strain,24.00,100.0%,.00,.0%,24.00,100.0%
Table: Extreme Values
,,,Case Number,Value
,,Cases,,,,,
,,Valid,,Missing,,Total,
,Manufacturer,N,Percent,N,Percent,N,Percent
-Breaking Strain,Aspeger,8.00,100%,.00,0%,8.00,100%
-,Bloggs,8.00,100%,.00,0%,8.00,100%
-,Charlies,8.00,100%,.00,0%,8.00,100%
+Breaking Strain,Aspeger,8.00,100.0%,.00,.0%,8.00,100.0%
+,Bloggs,8.00,100.0%,.00,.0%,8.00,100.0%
+,Charlies,8.00,100.0%,.00,.0%,8.00,100.0%
Table: Extreme Values
,Manufacturer,,,Case Number,Value
AT_CLEANUP
AT_SETUP([EXAMINE -- extremes])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
data list free /V1 W
begin data.
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-V1,23.00,100%,.00,0%,23.00,100%
+V1,23.00,100.0%,.00,.0%,23.00,100.0%
Table: Extreme Values
,,,Case Number,Value
AT_SETUP([EXAMINE -- extremes with fractional weights])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([extreme.sps], [dnl
set format=F20.3.
data list notable list /w * x *.
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-x,19.430,100%,.000,0%,19.430,100%
+x,19.430,100.0%,.000,.0%,19.430,100.0%
Table: Extreme Values
,,,Case Number,Value
dnl In particular test that it behaves properly when there are only
dnl a few cases.
AT_SETUP([EXAMINE -- percentiles])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
DATA LIST LIST /X *.
BEGIN DATA.
EXAMINE /x
/PERCENTILES=AEMPIRICAL.
])
-AT_CHECK([pspp -o pspp.csv examine.sps])
+AT_CHECK([pspp -o pspp.csv -o pspp.txt examine.sps])
AT_CHECK([cat pspp.csv], [0], [dnl
Table: Reading free-form data from INLINE.
Variable,Format
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-X,3,100%,0,0%,3,100%
+X,3,100.0%,0,.0%,3,100.0%
Table: Percentiles
,,Percentiles,,,,,,
,,5,10,25,50,75,90,95
-X,HAverage,.40,.80,2.00,5.00,8.00,8.00,8.00
+X,Weighted Average,.40,.80,2.00,5.00,8.00,8.00,8.00
,Tukey's Hinges,,,3.50,5.00,6.50,,
Table: Case Processing Summary
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-X,3,100%,0,0%,3,100%
+X,3,100.0%,0,.0%,3,100.0%
Table: Percentiles
,,Percentiles,,,,,,
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-X,3,100%,0,0%,3,100%
+X,3,100.0%,0,.0%,3,100.0%
Table: Percentiles
,,Percentiles,,,,,,
,,5,10,25,50,75,90,95
-X,Rounded,.00,.00,2.00,5.00,5.00,8.00,8.00
+X,Weighted Average,.00,.00,2.00,5.00,5.00,8.00,8.00
,Tukey's Hinges,,,3.50,5.00,6.50,,
Table: Case Processing Summary
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-X,3,100%,0,0%,3,100%
+X,3,100.0%,0,.0%,3,100.0%
Table: Percentiles
,,Percentiles,,,,,,
,,5,10,25,50,75,90,95
-X,Empirical,2.00,2.00,2.00,5.00,8.00,8.00,8.00
+X,Weighted Average,2.00,2.00,2.00,5.00,8.00,8.00,8.00
,Tukey's Hinges,,,3.50,5.00,6.50,,
Table: Case Processing Summary
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-X,3,100%,0,0%,3,100%
+X,3,100.0%,0,.0%,3,100.0%
Table: Percentiles
,,Percentiles,,,,,,
,,5,10,25,50,75,90,95
-X,Empirical with averaging,2.00,2.00,2.00,5.00,8.00,8.00,8.00
+X,Weighted Average,2.00,2.00,2.00,5.00,8.00,8.00,8.00
,Tukey's Hinges,,,3.50,5.00,6.50,,
])
AT_CLEANUP
AT_SETUP([EXAMINE -- missing values])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
DATA LIST LIST /x * y *.
BEGIN DATA.
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-x,6,85.7143%,1,14.2857%,7,100%
+x,6,85.7%,1,14.3%,7,100.0%
Table: Case Processing Summary
,,Cases,,,,,
,,Valid,,Missing,,Total,
,y,N,Percent,N,Percent,N,Percent
-x,1.00,4,100%,0,0%,4,100%
-,2.00,2,66.6667%,1,33.3333%,3,100%
+x,1.00,4,100.0%,0,.0%,4,100.0%
+,2.00,2,66.7%,1,33.3%,3,100.0%
])
AT_CLEANUP
AT_SETUP([EXAMINE -- user missing values])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine-m.sps], [dnl
DATA LIST notable LIST /x * y *.
BEGIN DATA.
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-x,1,33.3333%,2,66.6667%,3,100%
-y,2,66.6667%,1,33.3333%,3,100%
+x,1,33.3%,2,66.7%,3,100.0%
+y,2,66.7%,1,33.3%,3,100.0%
])
AT_CLEANUP
AT_SETUP([EXAMINE -- missing values and percentiles])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
DATA LIST LIST /X *.
BEGIN DATA.
dnl Tests the trimmed mean calculation in the case
dnl where the data is weighted towards the centre.
AT_SETUP([EXAMINE -- trimmed mean])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
DATA LIST LIST /X * C *.
BEGIN DATA.
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-X,52.00,100%,.00,0%,52.00,100%
+X,52.00,100.0%,.00,.0%,52.00,100.0%
Table: Descriptives
,,,Statistic,Std. Error
AT_CLEANUP
AT_SETUP([EXAMINE -- crash bug])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
data list list /a * x * y *.
begin data.
dnl Test that two consecutive EXAMINE commands don't crash PSPP.
AT_SETUP([EXAMINE -- consecutive runs don't crash])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
data list list /y * z *.
begin data.
dnl Test that /DESCRIPTIVES does not crash in presence of missing values.
AT_SETUP([EXAMINE -- missing values don't crash])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
data list list /x * y *.
begin data.
dnl Test that having only a single case doesn't crash.
AT_SETUP([EXAMINE -- single case doesn't crash])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
DATA LIST LIST /quality * .
BEGIN DATA
dnl Test that all-missing data doesn't crash.
AT_SETUP([EXAMINE -- all-missing data doesn't crash])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine.sps], [dnl
DATA LIST LIST /x *.
BEGIN DATA.
.
END DATA.
-EXAMINE /x PLOT=HISTOGRAM.
+EXAMINE /x
+ PLOT=HISTOGRAM BOXPLOT NPPLOT SPREADLEVEL(1) ALL
+ /ID=x
+ /STATISTICS = DESCRIPTIVES EXTREME (5) ALL
+ /PERCENTILE=AEMPIRICAL
+ .
])
AT_CHECK([pspp -o pspp.csv examine.sps], [0], [ignore])
dnl Ignore output -- this is just a no-crash check.
dnl Test that big input doesn't crash (bug 11307).
AT_SETUP([EXAMINE -- big input doesn't crash])
+AT_KEYWORDS([categorical categoricals slow])
AT_DATA([examine.sps], [dnl
INPUT PROGRAM.
LOOP #I=1 TO 50000.
dnl Another test that big input doesn't crash.
dnl The actual bug that this checks for has been lost.
AT_SETUP([EXAMINE -- big input doesn't crash 2])
+AT_KEYWORDS([categorical categoricals slow])
AT_DATA([make-big-input.pl],
[for ($i=0; $i<100000; $i++) { print "AB12\n" };
for ($i=0; $i<100000; $i++) { print "AB04\n" };
dnl Test that the ID command works with non-numberic variables
AT_SETUP([EXAMINE -- non-numeric ID])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine-id.sps], [dnl
data list notable list /x * y (a12).
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-x,14,100%,0,0%,14,100%
+x,14,100.0%,0,.0%,14,100.0%
Table: Extreme Values
,,,y,Value
x,Highest,1,threehundred,300.00
-,,2,thirty ,30.00
-,,3,twelve ,12.00
-,,4,eleven ,11.00
-,,5,ten ,10.00
-,Lowest,1,one ,1.00
-,,2,two ,2.00
-,,3,three ,3.00
-,,4,four ,4.00
-,,5,five ,5.00
+,,2,thirty,30.00
+,,3,twelve,12.00
+,,4,eleven,11.00
+,,5,ten,10.00
+,Lowest,1,one,1.00
+,,2,two,2.00
+,,3,three,3.00
+,,4,four,4.00
+,,5,five,5.00
])
AT_CLEANUP
dnl Test for a crash which happened on cleanup from a bad input syntax
AT_SETUP([EXAMINE -- Bad Input])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine-bad.sps], [dnl
data list list /h * g *.
dnl Check the MISSING=REPORT option
AT_SETUP([EXAMINE -- MISSING=REPORT])
-
+AT_KEYWORDS([categorical categoricals])
AT_DATA([examine-report.sps], [dnl
set format = F22.0.
])
-AT_CHECK([pspp -O format=csv examine-report.sps], [0], [dnl
-Table: Reading free-form data from INLINE.
+AT_CHECK([pspp -o pspp.csv -o pspp.txt examine-report.sps])
+AT_CHECK([cat pspp.csv], [0],
+ [[Table: Reading free-form data from INLINE.
Variable,Format
x,F8.0
g,F8.0
,,Cases,,,,,
,,Valid,,Missing,,Total,
,g,N,Percent,N,Percent,N,Percent
-x,. (missing),4,100%,0,0%,4,100%
-,1,9,100%,0,0%,9,100%
-,2,9,100%,0,0%,9,100%
-,9 (missing),4,100%,0,0%,4,100%
-,99 (missing),5,100%,0,0%,5,100%
+x,.,4,100.0%,0,.0%,4,100.0%
+,1,9,100.0%,0,.0%,9,100.0%
+,2,9,100.0%,0,.0%,9,100.0%
+,9[a],4,100.0%,0,.0%,4,100.0%
+,99[a],5,100.0%,0,.0%,5,100.0%
+
+Footnotes:
+a,User-missing value.
Table: Extreme Values
,g,,,Case Number,Value
-x,. (missing),Highest,1,31,4004
+x,.,Highest,1,31,4004
,,,2,30,3003
,,,3,29,2002
,,,4,28,1001
,,,3,12,30
,,,4,13,40
,,,5,14,50
-,9 (missing),Highest,1,22,401
+,9[a],Highest,1,22,401
,,,2,21,301
,,,3,20,201
,,,4,19,101
,,,3,21,301
,,,4,22,401
,,,5,22,401
-,99 (missing),Highest,1,27,901
+,99[a],Highest,1,27,901
,,,2,26,801
,,,3,25,701
,,,4,24,601
,,,3,25,701
,,,4,26,801
,,,5,27,901
-])
+Footnotes:
+a,User-missing value.
+]])
AT_CLEANUP
dnl dataset and comparing with "real" results kindly
dnl provided by Olaf Nöhring
AT_SETUP([EXAMINE -- sample unweighted])
+AT_KEYWORDS([categorical categoricals])
AT_DATA([sample.sps], [dnl
set format = F22.4.
,Cases,,,,,
,Valid,,Missing,,Total,
,N,Percent,N,Percent,N,Percent
-X,100,100%,0,0%,100,100%
+X,100,100.0%,0,.0%,100,100.0%
Table: Descriptives
,,,Statistic,Std. Error
])
AT_CLEANUP
+
+
+
+dnl Test for a crash which happened on bad input syntax
+AT_SETUP([EXAMINE -- Empty Parentheses])
+AT_KEYWORDS([categorical categoricals])
+
+AT_DATA([examine-empty-parens.sps], [dnl
+DATA LIST notable LIST /X *
+BEGIN DATA.
+2
+3
+END DATA.
+
+
+EXAMINE
+ x
+ /PLOT = SPREADLEVEL()
+ .
+])
+
+AT_CHECK([pspp -o pspp.csv examine-empty-parens.sps], [1], [ignore])
+
+AT_CLEANUP
+
+
+
+
+dnl Test for another crash which happened on bad input syntax
+AT_SETUP([EXAMINE -- Bad variable])
+AT_KEYWORDS([categorical categoricals])
+
+AT_DATA([examine-bad-variable.sps], [dnl
+data list list /h * g *.
+begin data.
+3 1
+4 1
+5 2
+end data.
+
+EXAMINE
+ /VARIABLES/ h
+ BY g
+ .
+])
+
+AT_CHECK([pspp -o pspp.csv examine-bad-variable.sps], [1], [ignore])
+
+AT_CLEANUP
+
+
+
+dnl Test for yet another crash. This time for extremes vs. missing weight values.\0
+AT_SETUP([EXAMINE -- Extremes vs. Missing Weights])
+AT_KEYWORDS([categorical categoricals])
+
+AT_DATA([examine-missing-weights.sps], [dnl
+data list notable list /h * g *.
+begin data.
+3 1
+4 .
+5 1
+2 1
+end data.
+
+WEIGHT BY g.
+
+EXAMINE h
+ /STATISTICS extreme(3)
+ .
+])
+
+AT_CHECK([pspp -O format=csv examine-missing-weights.sps], [0], [dnl
+"examine-missing-weights.sps:13: warning: EXAMINE: At least one case in the data file had a weight value that was user-missing, system-missing, zero, or negative. These case(s) were ignored."
+
+Table: Case Processing Summary
+,Cases,,,,,
+,Valid,,Missing,,Total,
+,N,Percent,N,Percent,N,Percent
+h,3.00,100.0%,.00,.0%,3.00,100.0%
+
+Table: Extreme Values
+,,,Case Number,Value
+h,Highest,1,3,5.00
+,,2,2,4.00
+,,3,1,3.00
+,Lowest,1,4,2.00
+,,2,1,3.00
+,,3,2,4.00
+])
+
+AT_CLEANUP
+
+dnl This is an example from doc/tutorial.texi
+dnl So if the results of this have to be changed in any way,
+dnl make sure to update that file.
+AT_SETUP([EXAMINE tutorial example 1])
+cp $top_srcdir/examples/repairs.sav .
+AT_DATA([repairs.sps], [dnl
+GET FILE='repairs.sav'.
+EXAMINE mtbf /STATISTICS=DESCRIPTIVES.
+COMPUTE mtbf_ln = LN (mtbf).
+EXAMINE mtbf_ln /STATISTICS=DESCRIPTIVES.
+])
+AT_CHECK([pspp -o pspp.csv -o pspp.txt repairs.sps])
+AT_CHECK([cat pspp.csv], [0], [dnl
+Table: Case Processing Summary
+,Cases,,,,,
+,Valid,,Missing,,Total,
+,N,Percent,N,Percent,N,Percent
+Mean time between failures (months) ,15,100.0%,0,.0%,15,100.0%
+
+Table: Descriptives
+,,,Statistic,Std. Error
+Mean time between failures (months) ,Mean,,8.32,1.62
+,95% Confidence Interval for Mean,Lower Bound,4.85,
+,,Upper Bound,11.79,
+,5% Trimmed Mean,,7.69,
+,Median,,8.12,
+,Variance,,39.21,
+,Std. Deviation,,6.26,
+,Minimum,,1.63,
+,Maximum,,26.47,
+,Range,,24.84,
+,Interquartile Range,,5.83,
+,Skewness,,1.85,.58
+,Kurtosis,,4.49,1.12
+
+Table: Case Processing Summary
+,Cases,,,,,
+,Valid,,Missing,,Total,
+,N,Percent,N,Percent,N,Percent
+mtbf_ln,15,100.0%,0,.0%,15,100.0%
+
+Table: Descriptives
+,,,Statistic,Std. Error
+mtbf_ln,Mean,,1.88,.19
+,95% Confidence Interval for Mean,Lower Bound,1.47,
+,,Upper Bound,2.29,
+,5% Trimmed Mean,,1.88,
+,Median,,2.09,
+,Variance,,.54,
+,Std. Deviation,,.74,
+,Minimum,,.49,
+,Maximum,,3.28,
+,Range,,2.79,
+,Interquartile Range,,.92,
+,Skewness,,-.16,.58
+,Kurtosis,,-.09,1.12
+])
+AT_CLEANUP
+
+dnl This is an example from doc/tutorial.texi
+dnl So if the results of this have to be changed in any way,
+dnl make sure to update that file.
+AT_SETUP([EXAMINE tutorial example 2])
+cp $top_srcdir/examples/physiology.sav .
+AT_DATA([examine.sps], [dnl
+GET FILE='physiology.sav'.
+EXAMINE height, weight /STATISTICS=EXTREME(3).
+])
+AT_CHECK([pspp -o pspp.csv -o pspp.txt examine.sps])
+AT_CHECK([cat pspp.csv], [0], [dnl
+Table: Case Processing Summary
+,Cases,,,,,
+,Valid,,Missing,,Total,
+,N,Percent,N,Percent,N,Percent
+Height in millimeters ,40,100.0%,0,.0%,40,100.0%
+Weight in kilograms ,40,100.0%,0,.0%,40,100.0%
+
+Table: Extreme Values
+,,,Case Number,Value
+Height in millimeters ,Highest,1,14,1903
+,,2,15,1884
+,,3,12,1802
+,Lowest,1,30,179
+,,2,31,1598
+,,3,28,1601
+Weight in kilograms ,Highest,1,13,92.1
+,,2,5,92.1
+,,3,17,91.7
+,Lowest,1,38,-55.6
+,,2,39,54.5
+,,3,33,55.4
+])
+AT_CLEANUP
+
projects / pspp / blobdiff