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([FREQUENCIES procedure])

AT_SETUP([FREQUENCIES string variable])
AT_DATA([frequencies.sps],
  [DATA LIST FREE/
   name  (A8) value * quantity .
BEGIN DATA.
foo 1 5
bar 2 6
baz 1 9
quux 3 1
bar 1 2
baz 4 3
baz 1 4
baz 1 1
foo 6 0
quux 5 8
END DATA.
EXECUTE.

FREQUENCIES /VAR = name/ORDER=ANALYSIS.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: name
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,bar,2,20.0%,20.0%,20.0%
,baz,4,40.0%,40.0%,60.0%
,foo,2,20.0%,20.0%,80.0%
,quux,2,20.0%,20.0%,100.0%
Total,,10,100.0%,,
])
AT_CLEANUP

AT_SETUP([FREQUENCIES with SPLIT FILE - LAYERED])
AT_DATA([frequencies.sps], [dnl
DATA LIST LIST NOTABLE/name (A8) value quantity.
BEGIN DATA.
foo 1 5
bar 2 6
baz 1 9
quux 3 1
bar 1 2
baz 4 3
baz 1 4
baz 1 1
foo 6 0
quux 5 8
END DATA.
EXECUTE.

SORT CASES BY name.
SPLIT FILE BY name.
FREQUENCIES /VARIABLES=value quantity /FORMAT NOTABLE.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: Statistics
name,,,value,quantity
bar,N,Valid,2,2
,,Missing,0,0
,Mean,,1.50,4.00
,Std Dev,,.71,2.83
,Minimum,,1.00,2.00
,Maximum,,2.00,6.00
baz,N,Valid,4,4
,,Missing,0,0
,Mean,,1.75,4.25
,Std Dev,,1.50,3.40
,Minimum,,1.00,1.00
,Maximum,,4.00,9.00
foo,N,Valid,2,2
,,Missing,0,0
,Mean,,3.50,2.50
,Std Dev,,3.54,3.54
,Minimum,,1.00,.00
,Maximum,,6.00,5.00
quux,N,Valid,2,2
,,Missing,0,0
,Mean,,4.00,4.50
,Std Dev,,1.41,4.95
,Minimum,,3.00,1.00
,Maximum,,5.00,8.00
])
AT_CLEANUP

AT_SETUP([FREQUENCIES with SPLIT FILE - SEPARATE])
AT_DATA([frequencies.sps], [dnl
DATA LIST LIST NOTABLE/name (A8) value quantity.
BEGIN DATA.
foo 1 5
bar 2 6
baz 1 9
quux 3 1
bar 1 2
baz 4 3
baz 1 4
baz 1 1
foo 6 0
quux 5 8
END DATA.
EXECUTE.

SORT CASES BY name.
SPLIT FILE SEPARATE BY name.
FREQUENCIES /VARIABLES=value quantity /FORMAT NOTABLE.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: Split Values
Variable,Value
name,bar

Table: Statistics
,,value,quantity
N,Valid,2,2
,Missing,0,0
Mean,,1.50,4.00
Std Dev,,.71,2.83
Minimum,,1.00,2.00
Maximum,,2.00,6.00

Table: Split Values
Variable,Value
name,baz

Table: Statistics
,,value,quantity
N,Valid,4,4
,Missing,0,0
Mean,,1.75,4.25
Std Dev,,1.50,3.40
Minimum,,1.00,1.00
Maximum,,4.00,9.00

Table: Split Values
Variable,Value
name,foo

Table: Statistics
,,value,quantity
N,Valid,2,2
,Missing,0,0
Mean,,3.50,2.50
Std Dev,,3.54,3.54
Minimum,,1.00,.00
Maximum,,6.00,5.00

Table: Split Values
Variable,Value
name,quux

Table: Statistics
,,value,quantity
N,Valid,2,2
,Missing,0,0
Mean,,4.00,4.50
Std Dev,,1.41,4.95
Minimum,,3.00,1.00
Maximum,,5.00,8.00
])
AT_CLEANUP

AT_SETUP([FREQUENCIES with SPLIT FILE - LAYERED - unsorted data])
AT_DATA([frequencies.sps], [dnl
DATA LIST LIST NOTABLE/name (A8) value quantity.
BEGIN DATA.
foo 1 5
bar 2 6
baz 1 9
quux 3 1
baz 4 3
bar 1 2
baz 1 1
foo 6 0
baz 1 4
quux 5 8
END DATA.
EXECUTE.

SPLIT FILE BY name.
FREQUENCIES /VARIABLES=value quantity /FORMAT NOTABLE.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
"frequencies.sps:17: warning: FREQUENCIES: When SPLIT FILE is in effect, the input data must be sorted by the split variables (for example, using SORT CASES), but multiple runs of cases with the same split values were found separated by cases with different values.  Each run will be analyzed separately.  The duplicate split values are: name = baz     "

"frequencies.sps:17: warning: FREQUENCIES: When SPLIT FILE is in effect, the input data must be sorted by the split variables (for example, using SORT CASES), but multiple runs of cases with the same split values were found separated by cases with different values.  Each run will be analyzed separately.  The duplicate split values are: name = bar     "

"frequencies.sps:17: warning: FREQUENCIES: When SPLIT FILE is in effect, the input data must be sorted by the split variables (for example, using SORT CASES), but multiple runs of cases with the same split values were found separated by cases with different values.  Each run will be analyzed separately.  The duplicate split values are: name = baz     "

"frequencies.sps:17: warning: FREQUENCIES: When SPLIT FILE is in effect, the input data must be sorted by the split variables (for example, using SORT CASES), but multiple runs of cases with the same split values were found separated by cases with different values.  Each run will be analyzed separately.  The duplicate split values are: name = foo     "

"frequencies.sps:17: warning: FREQUENCIES: When SPLIT FILE is in effect, the input data must be sorted by the split variables (for example, using SORT CASES), but multiple runs of cases with the same split values were found separated by cases with different values.  Each run will be analyzed separately.  The duplicate split values are: name = baz     "

Table: Statistics
name,,,value,quantity
foo,N,Valid,1,1
,,Missing,0,0
,Mean,,1.00,5.00
,Std Dev,,NaN,NaN
,Minimum,,1.00,5.00
,Maximum,,1.00,5.00
bar,N,Valid,1,1
,,Missing,0,0
,Mean,,2.00,6.00
,Std Dev,,NaN,NaN
,Minimum,,2.00,6.00
,Maximum,,2.00,6.00
baz,N,Valid,1,1
,,Missing,0,0
,Mean,,1.00,9.00
,Std Dev,,NaN,NaN
,Minimum,,1.00,9.00
,Maximum,,1.00,9.00
quux,N,Valid,1,1
,,Missing,0,0
,Mean,,3.00,1.00
,Std Dev,,NaN,NaN
,Minimum,,3.00,1.00
,Maximum,,3.00,1.00
baz,N,Valid,1,1
,,Missing,0,0
,Mean,,4.00,3.00
,Std Dev,,NaN,NaN
,Minimum,,4.00,3.00
,Maximum,,4.00,3.00
bar,N,Valid,1,1
,,Missing,0,0
,Mean,,1.00,2.00
,Std Dev,,NaN,NaN
,Minimum,,1.00,2.00
,Maximum,,1.00,2.00
baz,N,Valid,1,1
,,Missing,0,0
,Mean,,1.00,1.00
,Std Dev,,NaN,NaN
,Minimum,,1.00,1.00
,Maximum,,1.00,1.00
foo,N,Valid,1,1
,,Missing,0,0
,Mean,,6.00,.00
,Std Dev,,NaN,NaN
,Minimum,,6.00,.00
,Maximum,,6.00,.00
baz,N,Valid,1,1
,,Missing,0,0
,Mean,,1.00,4.00
,Std Dev,,NaN,NaN
,Minimum,,1.00,4.00
,Maximum,,1.00,4.00
quux,N,Valid,1,1
,,Missing,0,0
,Mean,,5.00,8.00
,Std Dev,,NaN,NaN
,Minimum,,5.00,8.00
,Maximum,,5.00,8.00

frequencies.sps:17: warning: FREQUENCIES: Suppressed 1 additional warning about duplicate split values.
])
AT_CLEANUP

# Tests for a bug where pspp would crash if two FREQUENCIES commands
# existed in a input file.
AT_SETUP([FREQUENCIES two runs crash])
AT_DATA([frequencies.sps],
  [data list free /v1 v2.
begin data.
0 1
2 3
4 5
3 4
end data.

frequencies v1 v2/statistics=none/ORDER=VARIABLE.
frequencies v1 v2/statistics=none.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: v1
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,.00,1,25.0%,25.0%,25.0%
,2.00,1,25.0%,25.0%,50.0%
,3.00,1,25.0%,25.0%,75.0%
,4.00,1,25.0%,25.0%,100.0%
Total,,4,100.0%,,

Table: v2
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,1,25.0%,25.0%,25.0%
,3.00,1,25.0%,25.0%,50.0%
,4.00,1,25.0%,25.0%,75.0%
,5.00,1,25.0%,25.0%,100.0%
Total,,4,100.0%,,

Table: v1
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,.00,1,25.0%,25.0%,25.0%
,2.00,1,25.0%,25.0%,50.0%
,3.00,1,25.0%,25.0%,75.0%
,4.00,1,25.0%,25.0%,100.0%
Total,,4,100.0%,,

Table: v2
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,1,25.0%,25.0%,25.0%
,3.00,1,25.0%,25.0%,50.0%
,4.00,1,25.0%,25.0%,75.0%
,5.00,1,25.0%,25.0%,100.0%
Total,,4,100.0%,,
])
AT_CLEANUP

# Test that the LIMIT specification works.
AT_SETUP([FREQUENCIES with LIMIT])
AT_DATA([frequencies.sps],
  [data list free /v1 v2.
begin data.
0 1
2 5
4 3
3 5
end data.

frequencies v1 v2/statistics=none/FORMAT=LIMIT(3).
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: v2
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,1,25.0%,25.0%,25.0%
,3.00,1,25.0%,25.0%,50.0%
,5.00,2,50.0%,50.0%,100.0%
Total,,4,100.0%,,
])
AT_CLEANUP

# Tests for a bug where PSPP would crash when a FREQUENCIES command
# was used with the HTML output driver.
AT_SETUP([FREQUENCIES HTML output crash])
AT_DATA([frequencies.sps],
  [data list free /v1 v2.
begin data.
0 1
2 3
4 5
3 4
end data.

list.

frequencies v1/statistics=none.
])
AT_CHECK([pspp -o - -O format=csv -o pspp.html frequencies.sps], [0],
  [Table: Data List
v1,v2
.00,1.00
2.00,3.00
4.00,5.00
3.00,4.00

Table: v1
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,.00,1,25.0%,25.0%,25.0%
,2.00,1,25.0%,25.0%,50.0%
,3.00,1,25.0%,25.0%,75.0%
,4.00,1,25.0%,25.0%,100.0%
Total,,4,100.0%,,
])
AT_CHECK([test -s pspp.html])
AT_CLEANUP

# Tests for a bug which crashed PSPP when a piechart with too many
# segments was requested.
AT_SETUP([FREQUENCIES pie chart crash])
AT_DATA([frequencies.sps],
  [data list list /x * w *.
begin data.
1  4
34 10
-9 15
232 6
11  4
134 1
9  5
32 16
-2 6
2  16
20  6
end data.

weight by w.

frequencies /x /format=notable /statistics=none
	/piechart.
])
# Cannot use the CSV driver for this because it does not output charts
# at all.
AT_CHECK([pspp frequencies.sps], [0], [dnl
Reading free-form data from INLINE.
+--------+------+
|Variable|Format|
+--------+------+
|x       |F8.0  |
|w       |F8.0  |
+--------+------+
])
AT_CLEANUP

dnl Check that histogram subcommand runs wihout crashing
AT_SETUP([FREQUENCIES histogram crash])
AT_DATA([frequencies.sps],
  [data list notable list /x * w *.
begin data.
1  4
34 10
-9 15
232 6
11  4
134 1
9  5
32 16
-2 6
2  16
20  6
end data.

weight by w.

frequencies /x
	    /format=notable
	    /statistics=none
	    /histogram=minimum(0) maximum(50) percent(5) normal.
])
# Cannot use the CSV driver for this because it does not output charts
# at all.
AT_CHECK([pspp -O format=pdf frequencies.sps], [0], [ignore], [ignore])
AT_CLEANUP

# Tests for a bug which crashed PSPP when the median and a histogram
# were both requested.
AT_SETUP([FREQUENCIES median with histogram crash])
AT_DATA([frequencies.sps], [dnl
data list list notable /x.
begin data.
1
end data.

frequencies /x /histogram /STATISTICS=median.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [ignore])
dnl Ignore output - No crash test.
AT_CLEANUP

# Tests for a bug which caused FREQUENCIES following TEMPORARY to
# crash (bug #11492).
AT_SETUP([FREQUENCIES crash after TEMPORARY])
AT_DATA([frequencies.sps],
  [DATA LIST LIST /SEX (A1) X *.
BEGIN DATA.
M 31
F 21
M 41
F 31
M 13
F 12
M 14
F 13
END DATA.


TEMPORARY
SELECT IF SEX EQ 'F'
FREQUENCIES /X .

FINISH
])
AT_CHECK([pspp -o pspp.csv -o pspp.txt frequencies.sps])
AT_CHECK([cat pspp.csv], [0], [dnl
Table: Reading free-form data from INLINE.
Variable,Format
SEX,A1
X,F8.0

Table: Statistics
,,X
N,Valid,4
,Missing,0
Mean,,19.25
Std Dev,,8.81
Minimum,,12.00
Maximum,,31.00

Table: X
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,12.00,1,25.0%,25.0%,25.0%
,13.00,1,25.0%,25.0%,50.0%
,21.00,1,25.0%,25.0%,75.0%
,31.00,1,25.0%,25.0%,100.0%
Total,,4,100.0%,,
])
AT_CLEANUP

m4_define([FREQUENCIES_NTILES_OUTPUT], [dnl
Table: Statistics
,,x,y
N,Valid,5,5
,Missing,0,0
Mean,,3.00,30.00
Std Dev,,1.58,15.81
Minimum,,1.00,10.00
Maximum,,5.00,50.00
Percentiles,0,1.00,10.00
,25,2.00,20.00
,33,2.33,23.33
,50,3.00,30.00
,67,3.67,36.67
,75,4.00,40.00
,100,5.00,50.00
])
AT_SETUP([FREQUENCIES basic percentiles])
AT_DATA([frequencies.sps],
  [DATA LIST LIST notable /x y.
BEGIN DATA.
1 10
2 20
3 30
4 40
5 50
END DATA.

FREQUENCIES
	VAR=x y
	/FORMAT=NOTABLE
	/PERCENTILES = 0 25 33.333 50 66.666 75 100.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0],
  [FREQUENCIES_NTILES_OUTPUT])
AT_CLEANUP

AT_SETUP([FREQUENCIES basic n-tiles])
AT_DATA([frequencies.sps],
  [DATA LIST LIST notable /x y.
BEGIN DATA.
1 10
2 20
3 30
4 40
5 50
END DATA.

FREQUENCIES
	VAR=x y
	/FORMAT=NOTABLE
	/NTILES = 3
	/NTILES = 4.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0],
  [FREQUENCIES_NTILES_OUTPUT])
AT_CLEANUP

AT_SETUP([FREQUENCIES compatibility percentiles])
AT_DATA([frequencies.sps],
  [DATA LIST LIST notable /X * .
BEGIN DATA.
1
2
3
4
5
END DATA.

FREQUENCIES
	VAR=x
	/ALGORITHM=COMPATIBLE
	/PERCENTILES = 0 25 50 75 100.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: Statistics
,,X
N,Valid,5
,Missing,0
Mean,,3.00
Std Dev,,1.58
Minimum,,1.00
Maximum,,5.00
Percentiles,0,1.00
,25,1.50
,50,3.00
,75,4.50
,100,5.00

Table: X
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,1,20.0%,20.0%,20.0%
,2.00,1,20.0%,20.0%,40.0%
,3.00,1,20.0%,20.0%,60.0%
,4.00,1,20.0%,20.0%,80.0%
,5.00,1,20.0%,20.0%,100.0%
Total,,5,100.0%,,
])
AT_CLEANUP

AT_SETUP([FREQUENCIES enhanced percentiles])
AT_DATA([frequencies.sps],
  [DATA LIST LIST notable /X * .
BEGIN DATA.
1
2
3
4
5
END DATA.

FREQUENCIES
	VAR=x
	/PERCENTILES = 0 25 50 75 100.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: Statistics
,,X
N,Valid,5
,Missing,0
Mean,,3.00
Std Dev,,1.58
Minimum,,1.00
Maximum,,5.00
Percentiles,0,1.00
,25,2.00
,50,3.00
,75,4.00
,100,5.00

Table: X
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,1,20.0%,20.0%,20.0%
,2.00,1,20.0%,20.0%,40.0%
,3.00,1,20.0%,20.0%,60.0%
,4.00,1,20.0%,20.0%,80.0%
,5.00,1,20.0%,20.0%,100.0%
Total,,5,100.0%,,
])
AT_CLEANUP

AT_SETUP([FREQUENCIES enhanced percentiles, weighted])
AT_DATA([frequencies.sps],
  [DATA LIST LIST notable /X * F *.
BEGIN DATA.
1 2
2 2
3 2
4 1
4 1
5 1
5 1
END DATA.

WEIGHT BY f.

FREQUENCIES
	VAR=x
	/PERCENTILES = 0 25 50 75 100.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: Statistics
,,X
N,Valid,10.00
,Missing,.00
Mean,,3.00
Std Dev,,1.49
Minimum,,1.00
Maximum,,5.00
Percentiles,0,1.00
,25,2.00
,50,3.00
,75,4.00
,100,5.00

Table: X
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,2.00,20.0%,20.0%,20.0%
,2.00,2.00,20.0%,20.0%,40.0%
,3.00,2.00,20.0%,20.0%,60.0%
,4.00,2.00,20.0%,20.0%,80.0%
,5.00,2.00,20.0%,20.0%,100.0%
Total,,10.00,100.0%,,
])
AT_CLEANUP

AT_SETUP([FREQUENCIES enhanced percentiles, weighted (2)])
AT_DATA([frequencies.sps],
  [DATA LIST LIST notable /X * F *.
BEGIN DATA.
1 1
3 2
4 1
5 1
5 1
END DATA.

WEIGHT BY f.

FREQUENCIES
	VAR=x
	/PERCENTILES = 0 25 50 75 100.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: Statistics
,,X
N,Valid,6.00
,Missing,.00
Mean,,3.50
Std Dev,,1.52
Minimum,,1.00
Maximum,,5.00
Percentiles,0,1.00
,25,3.00
,50,3.50
,75,4.75
,100,5.00

Table: X
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,1.00,16.7%,16.7%,16.7%
,3.00,2.00,33.3%,33.3%,50.0%
,4.00,1.00,16.7%,16.7%,66.7%
,5.00,2.00,33.3%,33.3%,100.0%
Total,,6.00,100.0%,,
])
AT_CLEANUP

dnl Data for this test case from Fabio Bordignon <bordignon@demos.it>.
AT_SETUP([FREQUENCIES enhanced percentiles, weighted (3)])
AT_DATA([frequencies.sps],
  [DATA LIST LIST notable /X * F *.
BEGIN DATA.
1 7
2 16
3 12
4 5
END DATA.

WEIGHT BY f.

FREQUENCIES
	VAR=x
	/PERCENTILES = 0 25 50 75 100.
])
AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: Statistics
,,X
N,Valid,40.00
,Missing,.00
Mean,,2.38
Std Dev,,.93
Minimum,,1.00
Maximum,,4.00
Percentiles,0,1.00
,25,2.00
,50,2.00
,75,3.00
,100,4.00

Table: X
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,7.00,17.5%,17.5%,17.5%
,2.00,16.00,40.0%,40.0%,57.5%
,3.00,12.00,30.0%,30.0%,87.5%
,4.00,5.00,12.5%,12.5%,100.0%
Total,,40.00,100.0%,,
])
AT_CLEANUP

AT_SETUP([FREQUENCIES enhanced percentiles, weighted, missing values])
AT_DATA([frequencies.sps],
  [DATA LIST LIST notable /X * F *.
BEGIN DATA.
1 1
3 2
4 1
5 1
5 1
99 4
END DATA.

MISSING VALUE x (99.0) .
WEIGHT BY f.

FREQUENCIES
	VAR=x
	/PERCENTILES = 0 25 50 75 100.
])

AT_CHECK([pspp -O format=csv frequencies.sps], [0], [dnl
Table: Statistics
,,X
N,Valid,6.00
,Missing,4.00
Mean,,3.50
Std Dev,,1.52
Minimum,,1.00
Maximum,,5.00
Percentiles,0,1.00
,25,3.00
,50,3.50
,75,4.75
,100,5.00

Table: X
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,1.00,10.0%,16.7%,16.7%
,3.00,2.00,20.0%,33.3%,50.0%
,4.00,1.00,10.0%,16.7%,66.7%
,5.00,2.00,20.0%,33.3%,100.0%
Missing,99.00,4.00,40.0%,,
Total,,10.00,100.0%,,
])
AT_CLEANUP

AT_SETUP([FREQUENCIES dichotomous histogram])
AT_DATA([frequencies.sps], [dnl
data list notable list /d4 *.
begin data.
0
0
0
1
0
0
0
0
1
0
0
0
0
0
1
2
0
end data.

FREQUENCIES
	/VARIABLES = d4
	/FORMAT=AVALUE TABLE
	/HISTOGRAM=NORMAL
	.
])

AT_CHECK([pspp frequencies.sps], [0],  [ignore])
AT_CLEANUP


AT_SETUP([FREQUENCIES median])
AT_DATA([median.sps], [dnl
data list notable list /x *.
begin data.
1
2
3000000
end data.

FREQUENCIES
	/VARIABLES = x
	/STATISTICS = MEDIAN
	.
])

AT_CHECK([pspp median.sps -O format=csv], [0], [dnl
Table: Statistics
,,x
N,Valid,3
,Missing,0
Median,,2.00

Table: x
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,1,33.3%,33.3%,33.3%
,2.00,1,33.3%,33.3%,66.7%
,3000000,1,33.3%,33.3%,100.0%
Total,,3,100.0%,,
])
AT_CLEANUP

AT_SETUP([FREQUENCIES variance])
AT_DATA([variance.sps], [dnl
data list notable list /forename (A12) height.
begin data.
Ahmed 188
bertram 167
Catherine 134
David 109
end data.

FREQUENCIES
   /VARIABLES = height
   /STATISTICS = VARIANCE.
])

AT_CHECK([pspp variance.sps -O format=csv], [0], [dnl
Table: Statistics
,,height
N,Valid,4
,Missing,0
Variance,,1223.00

Table: height
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,109.00,1,25.0%,25.0%,25.0%
,134.00,1,25.0%,25.0%,50.0%
,167.00,1,25.0%,25.0%,75.0%
,188.00,1,25.0%,25.0%,100.0%
Total,,4,100.0%,,
])
AT_CLEANUP

AT_SETUP([FREQUENCIES default statistics])
AT_DATA([median.sps], [dnl
data list notable list /x *.
begin data.
10
20
3000000
end data.

FREQUENCIES
	/VARIABLES = x
	/STATISTICS
	.

FREQUENCIES
	/VARIABLES = x
	/STATISTICS = DEFAULT
	.
])

AT_CHECK([pspp median.sps -o pspp.csv -o pspp.txt])
AT_CHECK([cat pspp.csv], [0], [dnl
Table: Statistics
,,x
N,Valid,3
,Missing,0
Mean,,1000010
Std Dev,,1732042
Minimum,,10.00
Maximum,,3000000

Table: x
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,10.00,1,33.3%,33.3%,33.3%
,20.00,1,33.3%,33.3%,66.7%
,3000000,1,33.3%,33.3%,100.0%
Total,,3,100.0%,,

Table: Statistics
,,x
N,Valid,3
,Missing,0
Mean,,1000010
Std Dev,,1732042
Minimum,,10.00
Maximum,,3000000

Table: x
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,10.00,1,33.3%,33.3%,33.3%
,20.00,1,33.3%,33.3%,66.7%
,3000000,1,33.3%,33.3%,100.0%
Total,,3,100.0%,,
])
AT_CLEANUP



AT_SETUP([FREQUENCIES no valid data])
AT_DATA([empty.sps], [dnl
data list notable list /x *.
begin data.
.
.
.
end data.

FREQUENCIES
	/VARIABLES = x
	/STATISTICS = ALL
	.
])

AT_CHECK([pspp empty.sps -O format=csv], [0],  [dnl
Table: Statistics
,,x
N,Valid,0
,Missing,3
Mean,,.  @&t@
S.E. Mean,,.  @&t@
Median,,.  @&t@
Mode,,.  @&t@
Std Dev,,.  @&t@
Variance,,.  @&t@
Kurtosis,,.  @&t@
S.E. Kurt,,.  @&t@
Skewness,,.  @&t@
S.E. Skew,,.  @&t@
Range,,.  @&t@
Minimum,,.  @&t@
Maximum,,.  @&t@
Sum,,.  @&t@

Table: x
,,Frequency,Percent
Missing,.  ,3,100.0%
Total,,3,.0%
])

AT_CLEANUP


AT_SETUP([FREQUENCIES histogram no valid cases])
AT_DATA([empty.sps], [dnl
data list notable list /x w *.
begin data.
1 .
2 .
3 .
end data.

weight by w.

FREQUENCIES
	/VARIABLES = x
	/histogram
	.
])

AT_CHECK([pspp empty.sps -O format=csv], [0],  [ignore])

AT_CLEANUP

AT_SETUP([FREQUENCIES percentiles + histogram bug#48128])
AT_DATA([bug.sps], [dnl
SET FORMAT=F8.0.

INPUT PROGRAM.
	LOOP I=1 TO 10.
		COMPUTE SCORE=EXP(NORMAL(1)).
		END CASE.
	END LOOP.
	END FILE.
END INPUT PROGRAM.

FREQUENCIES VARIABLES=SCORE
/FORMAT=NOTABLE
/STATISTICS=ALL
/PERCENTILES=1 10 20 30 40 50 60 70 80 90 99
/HISTOGRAM.

])

AT_CHECK([pspp bug.sps], [0],  [ignore])

AT_CLEANUP


AT_SETUP([FREQUENCIES vs. missing weights])
AT_DATA([warn.sps], [dnl
data list notable list /x w .
begin data.
1 1
2 1
1 1
3 1
3 .
4 .
end data.

weight by w.

frequencies /variables=x.
])

AT_CHECK([pspp warn.sps -O format=csv], [0],  [dnl
"warn.sps:13: warning: FREQUENCIES: 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: Statistics
,,x
N,Valid,4.00
,Missing,.00
Mean,,1.75
Std Dev,,.96
Minimum,,1.00
Maximum,,4.00

Table: x
,,Frequency,Percent,Valid Percent,Cumulative Percent
Valid,1.00,2.00,50.0%,50.0%,50.0%
,2.00,1.00,25.0%,25.0%,75.0%
,3.00,1.00,25.0%,25.0%,100.0%
,4.00,.00,.0%,.0%,100.0%
Total,,4.00,100.0%,,
])

AT_CLEANUP