Convert all Perl build tools to Python and remove Perl build dependency.
[pspp] / tests / language / stats / examine.at
index 0d9e781488af06158b686cf3fbb1b040f03325b6..bea69dd354d06303f7a71c2f25cbf0f001bb4580 100644 (file)
@@ -115,9 +115,9 @@ Breaking Strain,Mean,,3.54,.32
 ,Kurtosis,,-.36,.92
 
 Table: Case Processing Summary
-,,Cases,,,,,
+,Manufacturer,Cases,,,,,
 ,,Valid,,Missing,,Total,
-,Manufacturer,N,Percent,N,Percent,N,Percent
+,,N,Percent,N,Percent,N,Percent
 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%
@@ -451,9 +451,9 @@ Table: Case Processing Summary
 x,6,85.7%,1,14.3%,7,100.0%
 
 Table: Case Processing Summary
-,,Cases,,,,,
+,y,Cases,,,,,
 ,,Valid,,Missing,,Total,
-,y,N,Percent,N,Percent,N,Percent
+,,N,Percent,N,Percent,N,Percent
 x,1.00,4,100.0%,0,.0%,4,100.0%
 ,2.00,2,66.7%,1,33.3%,3,100.0%
 ])
@@ -678,11 +678,10 @@ 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; $i++) { print "AB04\n" };
-])
-AT_CHECK([$PERL make-big-input.pl > large.txt])
+AT_CHECK([$PYTHON3 -c '
+for i in range(100000): print("AB12")
+for i in range(100000): print("AB04")
+' > large.txt])
 AT_DATA([examine.sps], [dnl
 DATA LIST FILE='large.txt' /S 1-2 (A) X 3 .
 
@@ -694,10 +693,7 @@ EXAMINE /A BY X.
 ])
 AT_CHECK([pspp -o pspp.csv examine.sps])
 dnl Ignore output -- this is just a no-crash check.
-AT_DATA([more-big-input.pl],
-  [for ($i=0; $i<25000; $i++) { print "AB04\nAB12\n" };
-])
-AT_CHECK([$PERL more-big-input.pl >> large.txt])
+AT_CHECK([$PYTHON3 -c 'for i in range(25000): print("AB04\nAB12")' >> large.txt])
 AT_CHECK([pspp -o pspp.csv examine.sps])
 dnl Ignore output -- this is just a no-crash check.
 AT_CLEANUP
@@ -726,6 +722,7 @@ begin data.
 300 threehundred
 end data.
 
+set small=0.
 examine x
        /statistics = extreme
        /id = y
@@ -852,17 +849,15 @@ x,F8.0
 g,F8.0
 
 Table: Case Processing Summary
-,,Cases,,,,,
+,g,Cases,,,,,
 ,,Valid,,Missing,,Total,
-,g,N,Percent,N,Percent,N,Percent
+,,N,Percent,N,Percent,N,Percent
 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.
+Footnote: a. User-missing value.
 
 Table: Extreme Values
 ,g,,,Case Number,Value
@@ -916,9 +911,7 @@ x,.,Highest,1,31,4004
 ,,,3,25,701
 ,,,4,26,801
 ,,,5,27,901
-
-Footnotes:
-a,User-missing value.
+Footnote: a. User-missing value.
 ]])
 
 AT_CLEANUP
@@ -1171,52 +1164,53 @@ 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
+
+AT_CHECK([pspp -O format=csv repairs.sps], [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%
+Mean time between failures (months) ,30,100.0%,0,.0%,30,100.0%
 
 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,
+Mean time between failures (months) ,Mean,,8.78,1.10
+,95% Confidence Interval for Mean,Lower Bound,6.53,
+,,Upper Bound,11.04,
+,5% Trimmed Mean,,8.20,
+,Median,,8.29,
+,Variance,,36.34,
+,Std. Deviation,,6.03,
 ,Minimum,,1.63,
 ,Maximum,,26.47,
 ,Range,,24.84,
-,Interquartile Range,,5.83,
-,Skewness,,1.85,.58
-,Kurtosis,,4.49,1.12
+,Interquartile Range,,6.03,
+,Skewness,,1.65,.43
+,Kurtosis,,3.41,.83
 
 Table: Case Processing Summary
 ,Cases,,,,,
 ,Valid,,Missing,,Total,
 ,N,Percent,N,Percent,N,Percent
-mtbf_ln,15,100.0%,0,.0%,15,100.0%
+mtbf_ln,30,100.0%,0,.0%,30,100.0%
 
 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,
+mtbf_ln,Mean,,1.95,.13
+,95% Confidence Interval for Mean,Lower Bound,1.69,
+,,Upper Bound,2.22,
+,5% Trimmed Mean,,1.96,
+,Median,,2.11,
+,Variance,,.49,
+,Std. Deviation,,.70,
 ,Minimum,,.49,
 ,Maximum,,3.28,
 ,Range,,2.79,
-,Interquartile Range,,.92,
-,Skewness,,-.16,.58
-,Kurtosis,,-.09,1.12
+,Interquartile Range,,.88,
+,Skewness,,-.37,.43
+,Kurtosis,,.01,.83
 ])
+
 AT_CLEANUP
 
 dnl This is an example from doc/tutorial.texi
@@ -1310,15 +1304,15 @@ examine x  by g
 
 AT_CHECK([pspp -O format=csv shapiro-wilk.sps], [0],[dnl
 Table: Case Processing Summary
-,,Cases,,,,,
+,g,Cases,,,,,
 ,,Valid,,Missing,,Total,
-,g,N,Percent,N,Percent,N,Percent
+,,N,Percent,N,Percent,N,Percent
 x,1.00,10,100.0%,0,.0%,10,100.0%
 ,2.00,10,100.0%,0,.0%,10,100.0%
 
 Table: Tests of Normality
-,,Shapiro-Wilk,,
-,g,Statistic,df,Sig.
+,g,Shapiro-Wilk,,
+,,Statistic,df,Sig.
 x,1.00,.984,10,.983
 ,2.00,.882,10,.136
 ])