pintos-os.org Git - pspp/blob - tests/language/stats/descriptives.at

   1 AT_BANNER([DESCRIPTIVES procedure])
   2
   3 AT_SETUP([DESCRIPTIVES basics])
   4 AT_DATA([descriptives.sps],
   5   [title 'Test DESCRIPTIVES procedure'.
   6
   7 data list / V0 to V16 1-17.
   8 begin data.
   9 12128989012389023
  10 34128080123890128
  11 56127781237893217
  12 78127378123793112
  13 90913781237892318
  14 37978547878935789
  15 52878237892378279
  16 12377912789378932
  17 26787654347894348
  18 29137178947891888
  19 end data.
  20
  21 descript all/stat=all/format=serial.
  22 ])
  23 AT_CHECK([pspp -O format=csv descriptives.sps], [0],
  24   [Title: Test DESCRIPTIVES procedure
  25
  26 Table: Reading 1 record from INLINE.
  27 Variable,Record,Columns,Format
  28 V0,1,1-  1,F1.0
  29 V1,1,2-  2,F1.0
  30 V2,1,3-  3,F1.0
  31 V3,1,4-  4,F1.0
  32 V4,1,5-  5,F1.0
  33 V5,1,6-  6,F1.0
  34 V6,1,7-  7,F1.0
  35 V7,1,8-  8,F1.0
  36 V8,1,9-  9,F1.0
  37 V9,1,10- 10,F1.0
  38 V10,1,11- 11,F1.0
  39 V11,1,12- 12,F1.0
  40 V12,1,13- 13,F1.0
  41 V13,1,14- 14,F1.0
  42 V14,1,15- 15,F1.0
  43 V15,1,16- 16,F1.0
  44 V16,1,17- 17,F1.0
  45
  46 Table: Valid cases = 10; cases with missing value(s) = 0.
  47 Variable,Valid N,Missing N,Mean,S.E. Mean,Std Dev,Variance,Kurtosis,S.E. Kurt,Skewness,S.E. Skew,Range,Minimum,Maximum,Sum
  48 V0,10,0,3.80,.84,2.66,7.07,-.03,1.33,.89,.69,8.00,1.00,9.00,38.00
  49 V1,10,0,4.60,.96,3.03,9.16,-1.39,1.33,-.03,.69,9.00,.00,9.00,46.00
  50 V2,10,0,4.10,1.16,3.67,13.43,-2.02,1.33,.48,.69,8.00,1.00,9.00,41.00
  51 V3,10,0,4.10,.87,2.77,7.66,-2.05,1.33,.42,.69,7.00,1.00,8.00,41.00
  52 V4,10,0,7.00,.47,1.49,2.22,7.15,1.33,-2.52,.69,5.00,3.00,8.00,70.00
  53 V5,10,0,4.90,1.03,3.25,10.54,-1.40,1.33,-.20,.69,9.00,.00,9.00,49.00
  54 V6,10,0,5.90,.80,2.51,6.32,-.29,1.33,-.96,.69,7.00,1.00,8.00,59.00
  55 V7,10,0,4.70,1.10,3.47,12.01,-1.99,1.33,-.16,.69,9.00,.00,9.00,47.00
  56 V8,10,0,4.10,1.10,3.48,12.10,-1.93,1.33,.37,.69,9.00,.00,9.00,41.00
  57 V9,10,0,4.30,.87,2.75,7.57,-.87,1.33,.73,.69,8.00,1.00,9.00,43.00
  58 V10,10,0,5.50,.85,2.68,7.17,-1.84,1.33,-.33,.69,7.00,2.00,9.00,55.00
  59 V11,10,0,6.50,.78,2.46,6.06,-1.28,1.33,-.89,.69,6.00,3.00,9.00,65.00
  60 V12,10,0,7.90,.60,1.91,3.66,5.24,1.33,-2.21,.69,6.00,3.00,9.00,79.00
  61 V13,10,0,4.30,.99,3.13,9.79,-1.25,1.33,.33,.69,9.00,.00,9.00,43.00
  62 V14,10,0,3.60,1.01,3.20,10.27,-.96,1.33,.81,.69,9.00,.00,9.00,36.00
  63 V15,10,0,3.70,.92,2.91,8.46,-1.35,1.33,.71,.69,7.00,1.00,8.00,37.00
  64 V16,10,0,6.40,.91,2.88,8.27,-1.14,1.33,-.92,.69,7.00,2.00,9.00,64.00
  65 ])
  66 AT_CLEANUP
  67
  68 m4_define([DESCRIPTIVES_MISSING_DATA],
  69   [data list notable / V1 TO V3 1-3.
  70 mis val v1 to v3 (1).
  71 begin data.
  72 111
  73
  74  1
  75 1 1
  76 112
  77 123
  78 234
  79 end data.
  80 ])
  81
  82 AT_SETUP([DESCRIPTIVES -- excluding missing data])
  83 AT_DATA([descriptives.sps],
  84   [DESCRIPTIVES_MISSING_DATA
  85 descript all/stat=all/format=serial.
  86 ])
  87 AT_CHECK([pspp -O format=csv descriptives.sps], [0],
  88   [Table: Valid cases = 7; cases with missing value(s) = 6.
  89 Variable,Valid N,Missing N,Mean,S.E. Mean,Std Dev,Variance,Kurtosis,S.E. Kurt,Skewness,S.E. Skew,Range,Minimum,Maximum,Sum
  90 V1,1,6,2.00,.  ,.  ,.  ,.  ,.  ,.  ,.  ,.00,2.00,2.00,2.00
  91 V2,2,5,2.50,.50,.71,.50,.  ,.  ,.  ,.  ,1.00,2.00,3.00,5.00
  92 V3,3,4,3.00,.58,1.00,1.00,.  ,.  ,.00,1.22,2.00,2.00,4.00,9.00
  93 ])
  94 AT_CLEANUP
  95
  96 AT_SETUP([DESCRIPTIVES -- including missing data])
  97 AT_DATA([descriptives.sps],
  98   [DESCRIPTIVES_MISSING_DATA
  99 descript all/stat=all/format=serial/missing=include.
 100 ])
 101 AT_CHECK([pspp -O format=csv descriptives.sps], [0],
 102   [Table: Valid cases = 7; cases with missing value(s) = 3.
 103 Variable,Valid N,Missing N,Mean,S.E. Mean,Std Dev,Variance,Kurtosis,S.E. Kurt,Skewness,S.E. Skew,Range,Minimum,Maximum,Sum
 104 V1,5,2,1.20,.20,.45,.20,5.00,2.00,2.24,.91,1.00,1.00,2.00,6.00
 105 V2,5,2,1.60,.40,.89,.80,.31,2.00,1.26,.91,2.00,1.00,3.00,8.00
 106 V3,5,2,2.20,.58,1.30,1.70,-1.49,2.00,.54,.91,3.00,1.00,4.00,11.00
 107 ])
 108 AT_CLEANUP
 109
 110 AT_SETUP([DESCRIPTIVES -- excluding missing data listwise])
 111 AT_DATA([descriptives.sps],
 112   [DESCRIPTIVES_MISSING_DATA
 113 descript all/stat=all/format=serial/missing=listwise.
 114 ])
 115 AT_CHECK([pspp -O format=csv descriptives.sps], [0],
 116   [Table: Valid cases = 1; cases with missing value(s) = 6.
 117 Variable,Valid N,Missing N,Mean,S.E. Mean,Std Dev,Variance,Kurtosis,S.E. Kurt,Skewness,S.E. Skew,Range,Minimum,Maximum,Sum
 118 V1,1,0,2.00,.  ,.  ,.  ,.  ,.  ,.  ,.  ,.00,2.00,2.00,2.00
 119 V2,1,0,3.00,.  ,.  ,.  ,.  ,.  ,.  ,.  ,.00,3.00,3.00,3.00
 120 V3,1,0,4.00,.  ,.  ,.  ,.  ,.  ,.  ,.  ,.00,4.00,4.00,4.00
 121 ])
 122 AT_CLEANUP
 123
 124 AT_SETUP([DESCRIPTIVES -- including missing data listwise])
 125 AT_DATA([descriptives.sps],
 126   [DESCRIPTIVES_MISSING_DATA
 127 descript all/stat=all/format=serial/missing=listwise include.
 128 ])
 129 AT_CHECK([pspp -O format=csv descriptives.sps], [0],
 130   [Table: Valid cases = 4; cases with missing value(s) = 3.
 131 Variable,Valid N,Missing N,Mean,S.E. Mean,Std Dev,Variance,Kurtosis,S.E. Kurt,Skewness,S.E. Skew,Range,Minimum,Maximum,Sum
 132 V1,4,0,1.25,.25,.50,.25,4.00,2.62,2.00,1.01,1.00,1.00,2.00,5.00
 133 V2,4,0,1.75,.48,.96,.92,-1.29,2.62,.85,1.01,2.00,1.00,3.00,7.00
 134 V3,4,0,2.50,.65,1.29,1.67,-1.20,2.62,.00,1.01,3.00,1.00,4.00,10.00
 135 ])
 136 AT_CLEANUP
 137
 138 AT_SETUP([DESCRIPTIVES bug calculating mean only])
 139 AT_DATA([descriptives.sps],
 140   [SET FORMAT F8.3.
 141
 142 data list notable / X 1.
 143 begin data.
 144 0
 145 1
 146 2
 147 3
 148 4
 149 5
 150 end data.
 151
 152 descript all/stat=mean.
 153 ])
 154 AT_CHECK([pspp -O format=csv descriptives.sps], [0],
 155   [Table: Valid cases = 6; cases with missing value(s) = 0.
 156 Variable,N,Mean
 157 X,6,2.500
 158 ])
 159 AT_CLEANUP
 160
 161 dnl Git history shows that this was probably a bug in the PSPP
 162 dnl core regarding multipass procedures, not anything specific
 163 dnl to DESCRIPTIVES.
 164 AT_SETUP([DESCRIPTIVES bug with TEMPORARY])
 165 AT_DATA([descriptives.sps], [dnl
 166 DATA LIST LIST NOTABLE /id * abc *.
 167 BEGIN DATA.
 168 1 3.5
 169 2 2.0
 170 3 2.0
 171 4 3.5
 172 5 3.0
 173 6 4.0
 174 7 5.0
 175 END DATA.
 176
 177 TEMPORARY.
 178 SELECT IF id < 7 .
 179
 180 DESCRIPTIVES /VAR=abc.
 181 ])
 182 AT_CHECK([pspp -O format=csv descriptives.sps], [0], [dnl
 183 Table: Valid cases = 6; cases with missing value(s) = 0.
 184 Variable,N,Mean,Std Dev,Minimum,Maximum
 185 abc,6,3.00,.84,2.00,4.00
 186 ])
 187 AT_CLEANUP
 188
 189 AT_SETUP([DESCRIPTIVES -- Z scores])
 190 AT_DATA([descriptives.sps], [dnl
 191 DATA LIST LIST NOTABLE /a b.
 192 BEGIN DATA.
 193 1 50
 194 2 60
 195 3 70
 196 END DATA.
 197
 198 DESCRIPTIVES /VAR=a b /SAVE.
 199 LIST.
 200 ])
 201 AT_CHECK([pspp -O format=csv descriptives.sps], [0], [dnl
 202 Table: Mapping of variables to corresponding Z-scores.
 203 Source,Target
 204 a,Za
 205 b,Zb
 206
 207 Table: Valid cases = 3; cases with missing value(s) = 0.
 208 Variable,N,Mean,Std Dev,Minimum,Maximum
 209 a,3,2.00,1.00,1.00,3.00
 210 b,3,60.00,10.00,50.00,70.00
 211
 212 Table: Data List
 213 a,b,Za,Zb
 214 1.00,50.00,-1.00,-1.00
 215 2.00,60.00,.00,.00
 216 3.00,70.00,1.00,1.00
 217 ])
 218 AT_CLEANUP
 219
 220 AT_SETUP([DESCRIPTIVES -- Z scores with SPLIT FILE])
 221 AT_DATA([descriptives.sps], [dnl
 222 DATA LIST LIST NOTABLE /group a b.
 223 BEGIN DATA.
 224 1 1 50
 225 1 2 60
 226 1 3 70
 227 2 100 6000
 228 2 200 7000
 229 2 400 9000
 230 2 500 10000
 231 END DATA.
 232
 233 SPLIT FILE BY group.
 234 DESCRIPTIVES /VAR=a b /SAVE.
 235 LIST.
 236 ])
 237 AT_CHECK([pspp -O format=csv descriptives.sps], [0], [dnl
 238 Table: Mapping of variables to corresponding Z-scores.
 239 Source,Target
 240 a,Za
 241 b,Zb
 242
 243 Variable,Value,Label
 244 group,1.00,
 245
 246 Table: Valid cases = 3; cases with missing value(s) = 0.
 247 Variable,N,Mean,Std Dev,Minimum,Maximum
 248 a,3,2.00,1.00,1.00,3.00
 249 b,3,60.00,10.00,50.00,70.00
 250
 251 Variable,Value,Label
 252 group,2.00,
 253
 254 Table: Valid cases = 4; cases with missing value(s) = 0.
 255 Variable,N,Mean,Std Dev,Minimum,Maximum
 256 a,4,300.00,182.57,100.00,500.00
 257 b,4,8000.00,1825.74,6000.00,10000.00
 258
 259 Variable,Value,Label
 260 group,1.00,
 261
 262 Table: Data List
 263 group,a,b,Za,Zb
 264 1.00,1.00,50.00,-1.00,-1.00
 265 1.00,2.00,60.00,.00,.00
 266 1.00,3.00,70.00,1.00,1.00
 267
 268 Variable,Value,Label
 269 group,2.00,
 270
 271 Table: Data List
 272 group,a,b,Za,Zb
 273 2.00,100.00,6000.00,-1.10,-1.10
 274 2.00,200.00,7000.00,-.55,-.55
 275 2.00,400.00,9000.00,.55,.55
 276 2.00,500.00,10000.00,1.10,1.10
 277 ])
 278 AT_CLEANUP
 279
 280 dnl Ideally DESCRIPTIVES would not make temporary transformations permanent
 281 dnl as it does now (bug #38786), so these results are imperfect.  However,
 282 dnl this test does verify that DESCRIPTIVES does not crash in this situation
 283 dnl (as it once did).
 284 AT_SETUP([DESCRIPTIVES -- Z scores bug with TEMPORARY])
 285 AT_DATA([descriptives.sps], [dnl
 286 DATA LIST LIST NOTABLE /id abc.
 287 BEGIN DATA.
 288 1 3.5
 289 2 2.0
 290 3 2.0
 291 4 3.5
 292 5 3.0
 293 6 4.0
 294 7 5.0
 295 END DATA.
 296
 297 TEMPORARY.
 298 SELECT IF id < 7 .
 299
 300 DESCRIPTIVES /VAR=abc/SAVE.
 301 LIST.
 302 ])
 303 AT_CHECK([pspp -O format=csv descriptives.sps], [0], [dnl
 304 descriptives.sps:15: warning: DESCRIPTIVES: DESCRIPTIVES with Z scores ignores TEMPORARY.  Temporary transformations will be made permanent.
 305
 306 Table: Mapping of variables to corresponding Z-scores.
 307 Source,Target
 308 abc,Zabc
 309
 310 Table: Valid cases = 6; cases with missing value(s) = 0.
 311 Variable,N,Mean,Std Dev,Minimum,Maximum
 312 abc,6,3.00,.84,2.00,4.00
 313
 314 Table: Data List
 315 id,abc,Zabc
 316 1.00,3.50,.60
 317 2.00,2.00,-1.20
 318 3.00,2.00,-1.20
 319 4.00,3.50,.60
 320 5.00,3.00,.00
 321 6.00,4.00,1.20
 322 ])
 323 AT_CLEANUP
 324
 325 dnl This test was supplied by Mindaugus as part of the report for bug #42012.
 326 AT_SETUP([DESCRIPTIVES -- Z scores with FILTER])
 327 AT_DATA([descriptives.sps], [dnl
 328 DATA LIST LIST/filter1 filter2 x.
 329 BEGIN DATA.
 330 0,0,300
 331 0,1,200
 332 0,1,100
 333 1,0,5
 334 1,0,4
 335 1,1,3
 336 1,1,2
 337 1,1,1
 338 END DATA.
 339
 340 FILTER OFF.
 341 SPLIT FILE OFF.
 342 DESCRIPTIVES /VARIABLES=X /SAVE.
 343
 344 FILTER BY filter1.
 345 SPLIT FILE OFF.
 346 DESCRIPTIVES /VARIABLES=X /SAVE.
 347
 348 FILTER OFF.
 349 SORT CASES BY filter1.
 350 SPLIT FILE BY filter1.
 351 DESCRIPTIVES /VARIABLES=X /SAVE.
 352
 353 FILTER BY filter2.
 354 SPLIT FILE BY filter1.
 355 DESCRIPTIVES /VARIABLES=X /SAVE.
 356
 357 FILTER OFF.
 358 SORT CASES BY filter1 filter2.
 359 SPLIT FILE BY filter1 filter2.
 360 DESCRIPTIVES /VARIABLES=X /SAVE.
 361 EXECUTE.
 362
 363 SPLIT FILE OFF.
 364 LIST.
 365 ])
 366 AT_CHECK([pspp -o pspp.csv descriptives.sps])
 367 AT_CHECK([sed -n '/Table: Data List/,$p' < pspp.csv], [0], [dnl
 368 Table: Data List
 369 filter1,filter2,x,Zx,ZSC001,ZSC002,ZSC003,ZSC004
 370 .00,.00,300.00,1.94,.  ,1.00,.  ,.  @&t@
 371 .00,1.00,200.00,1.07,.  ,.00,.71,.71
 372 .00,1.00,100.00,.20,.  ,-1.00,-.71,-.71
 373 1.00,.00,5.00,-.62,1.26,1.26,.  ,.71
 374 1.00,.00,4.00,-.63,.63,.63,.  ,-.71
 375 1.00,1.00,3.00,-.64,.00,.00,1.00,1.00
 376 1.00,1.00,2.00,-.65,-.63,-.63,.00,.00
 377 1.00,1.00,1.00,-.66,-1.26,-1.26,-1.00,-1.00
 378 ])
 379 AT_CLEANUP