1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457
|
# -*- tcl -*-
# statistics.test --
# Test cases for the ::math::statistics package
#
# Note:
# The tests assume tcltest 2.1, in order to compare
# floating-point results
# -------------------------------------------------------------------------
source [file join \
[file dirname [file dirname [file join [pwd] [info script]]]] \
devtools testutilities.tcl]
testsNeedTcl 8.4;# statistics,linalg!
testsNeedTcltest 2.1
support {
useLocal math.tcl math
useLocal linalg.tcl math::linearalgebra
}
testing {
useLocal statistics.tcl math::statistics
}
# -------------------------------------------------------------------------
set ::data_uniform [list 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0 1.0]
set ::data_missing [list 1.0 1.0 1.0 {} 1.0 {} {} 1.0 1.0 1.0 1.0 1.0 1.0]
set ::data_linear [list 1.0 2.0 3.0 4.0 5.0 6.0 7.0 8.0 9.0 10.0]
set ::data_empty [list {} {} {}]
set ::data_missing2 [list 1.0 2.0 3.0 {} 4.0 5.0 6.0 7.0 8.0 9.0 10.0]
#
# Create and register (in that order!) custom matching procedures
#
proc matchTolerant { expected actual } {
set match 1
foreach a $actual e $expected {
if { abs($e-$a)>0.0001*abs($e) &&
abs($e-$a)>0.0001*abs($a) } {
set match 0
break
}
}
return $match
}
proc matchTolerant2 { expected actual } {
set match 1
foreach a $actual e $expected {
if { abs($e-$a)>0.025*abs($e) &&
abs($e-$a)>0.025*abs($a) } {
set match 0
break
}
}
return $match
}
proc matchAlmostZero { expected actual } {
set match 1
foreach a $actual {
if { abs($a)>1.0e-6 } {
set match 0
break
}
}
return $match
}
customMatch tolerant matchTolerant
customMatch tolerant2 matchTolerant2
customMatch almostzero matchAlmostZero
#
# Test cases
#
test "BasicStats-1.0" "Basic statistics - uniform data" -match tolerant -body {
set all_data [::math::statistics::BasicStats all $::data_uniform]
} -result [list 1.0 1.0 1.0 [llength $::data_uniform] 0.0 0.0 0.0 0.0]
test "BasicStats-1.1" "Basic statistics - empty data" -match glob -body {
catch {
set all_data [::math::statistics::BasicStats all $::data_empty]
} msg
set msg
} -result "Too*"
#
# Result must be the same as for 1.0! Hence ::data_empty and ::data_uniform
#
test "BasicStats-1.2" "Basic statistics - missing data" -match tolerant -body {
set all_data [::math::statistics::BasicStats all $::data_missing]
} -result [list 1.0 1.0 1.0 [llength $::data_uniform] 0.0 0.0 0.0 0.0]
test "BasicStats-1.3" "Basic statistics - linear data - mean" -match tolerant -body {
set value [::math::statistics::mean $::data_linear]
} -result 5.5
test "BasicStats-1.4" "Basic statistics - linear data - min" -match tolerant -body {
set value [::math::statistics::min $::data_linear]
} -result 1.0
test "BasicStats-1.5" "Basic statistics - linear data - max" -match tolerant -body {
set value [::math::statistics::max $::data_linear]
} -result 10.0
test "BasicStats-1.6" "Basic statistics - linear data - number" -match tolerant -body {
set value [::math::statistics::number $::data_linear]
} -result 10
test "BasicStats-1.7" "Basic statistics - missing data - number" -match tolerant -body {
set value [::math::statistics::number $::data_missing2]
} -result 10
test "BasicStats-1.8" "Basic statistics - missing data - stdev" -match almostzero -body {
set value1 [::math::statistics::stdev $::data_linear]
set value2 [::math::statistics::stdev $::data_missing2]
expr {abs($value1-$value2)}
} -result 0.001 ;# Zero is impossible
test "BasicStats-1.9" "Basic statistics - missing data - var" -match almostzero -body {
set value1 [::math::statistics::stdev $::data_linear]
set value2 [::math::statistics::var $::data_missing2]
expr {$value1*$value1-$value2}
} -result 0.001 ;# Zero is impossible
test "BasicStats-1.10" "Basic statistics - missing data - pstdev" -match almostzero -body {
set value1 [::math::statistics::pstdev $::data_linear]
set value2 [::math::statistics::pstdev $::data_missing2]
expr {abs($value1-$value2)}
} -result 0.001 ;# Zero is impossible
test "BasicStats-1.11" "Basic statistics - missing data - pvar" -match almostzero -body {
set value1 [::math::statistics::pstdev $::data_linear]
set value2 [::math::statistics::pvar $::data_missing2]
expr {$value1*$value1-$value2}
} -result 0.001 ;# Zero is impossible
#
# This test was added because the calculation of the standard deviation
# could fail with uniform data (the difference of two almost equal
# values became a small negative number)
#
test "BasicStats-2.1" "Basic statistics - uniform data caused sqrt domain error" -body {
set values [list]
set count 0
for { set i 0 } { $i < 20 } { incr i } {
lappend values 0.6
set value2 [::math::statistics::mean $values]
incr count
}
set count
} -result 20 ;# We can finish the loop
#
# Histograms
#
test "Histogram-1.0" "Histogram - uniform data" -match glob -body {
set values [::math::statistics::histogram {0 2} $::data_uniform]
} -result [list 0 [llength $::data_uniform] 0]
test "Histogram-1.1" "Histogram - missing data" -match glob -body {
set values [::math::statistics::histogram {0 2} $::data_missing]
} -result [list 0 [::math::statistics::number $::data_missing] 0]
test "Histogram-1.2" "Histogram - linear data" -match glob -body {
set values [::math::statistics::histogram {1.5 4.5 9.5} $::data_linear]
} -result {1 3 5 1}
test "Histogram-1.3" "Histogram - linear data 2" -match glob -body {
set values [::math::statistics::histogram {1.5 2.5 10.5} $::data_linear]
} -result {1 1 8 0}
#
# Quantiles
# Bug #1272910: related to rounding 0.5 - use different levels instead
# because another bug was fixed, return to the original
# levels again
#
test "Quantiles-1.0" "Quantiles - raw data" -match tolerant -body {
set values [::math::statistics::quantiles $::data_linear {0.25 0.55 0.95}]
} -result {3.0 6.0 10.0}
test "Quantiles-1.1" "Quantiles - histogram" -match tolerant -body {
set limits {1.0 2.0 3.0 4.0}
set data_hist {0 10 20 10 0}
set values [::math::statistics::quantiles $limits $data_hist {0.25 0.5 0.9}]
} -result {2.0 2.5 3.6}
#
# Generate histogram limits
#
test "Limits-1.0" "Limits - based on mean/stdev" -match tolerant -body {
set values [::math::statistics::mean-histogram-limits 1.0 1.0 4]
} -result {0.0 0.75 1.25 2.0}
test "Limits-1.1" "Limits - based on mean/stdev" -match tolerant -body {
set values [::math::statistics::mean-histogram-limits 1.0 1.0 9]
} -result {-2.0 -1.0 0.0 0.75 1.0 1.25 2.0 3.0 4.0}
test "Limits-1.2" "Limits - based on mean/stdev" -match tolerant -body {
set values [::math::statistics::mean-histogram-limits 0.0 1.0 11]
} -result {-3.0 -2.4 -1.8 -1.2 -0.6 0.0 0.6 1.2 1.8 2.4 3.0}
test "Limits-2.0" "Limits - based on min/max" -match tolerant -body {
set values [::math::statistics::minmax-histogram-limits -2.0 2.0 9]
} -result {-2.0 -1.5 -1.0 -0.5 0.0 0.5 1.0 1.5 2.0}
test "Limits-2.1" "Limits - based on min/max" -match tolerant -body {
set values [::math::statistics::minmax-histogram-limits -2.0 2.0 2]
} -result {-2.0 2.0}
#
# To do: design test cases for the following functions:
# - t-test-mean
# - estimate-mean-stdev
# - autocorr
# - crosscorr
# - linear-model
# - linear-residuals
# - pdf-*
# - cdf-*
# - random-*
# - histogram-*
#
# Crude test cases for Student's t test
#
test "Students-t-test-1.0" "Student's t - same sample" -match glob -body {
set sample [::math::statistics::random-normal 0.0 1.0 40]
set mean 0.0
set stdev 1.0
set confidence 0.95
set result [::math::statistics::t-test-mean $sample $mean $stdev $confidence]
} -result 1
test "Students-t-test-1.1" "Student's t - different sample" -match glob -body {
set sample [::math::statistics::random-normal 0.0 1.0 40]
set mean 10.0
set stdev 1.0
set confidence 0.95
set result [::math::statistics::t-test-mean $sample $mean $stdev $confidence]
} -result 0
test "Students-t-test-1.2" "Student's t - small sample" -match glob -body {
set sample [::math::statistics::random-normal 0.0 1.0 2]
set mean 2.0
set stdev 1.0
set confidence 0.90
set result [::math::statistics::t-test-mean $sample $mean $stdev $confidence]
} -result 1
#
# Test private procedures
#
test "Cdf-toms322-1.0" "TOMS322 - erf(x)" -match tolerant2 -body {
set result {}
foreach z {4.417 3.891 3.291 2.576 2.241 1.960 1.645 1.150 0.674
0.319 0.126 0.063 0.0125} {
set prob [::math::statistics::Cdf-toms322 1 5000 [expr {$z*$z}]]
lappend result [expr {1.0-$prob}]
}
set result
} -result {1.e-5 1.e-4 1.e-3 1.e-2 0.025 0.050 0.100 0.250 0.500
0.750 0.900 0.950 0.990 }
test "Cdf-toms322-2.0" "TOMS322 - inverse erf(x)" -match tolerant2 -body {
set result {}
foreach p {0.5120 0.5948 0.7019 0.7996 0.8997 0.9505 0.9901 0.9980 } {
set z [::math::statistics::Inverse-cdf-normal 0.0 1.0 $p]
lappend result $z
}
set result
} -result {0.03 0.24 0.53 0.84 1.28 1.65 2.33 2.88 }
#
# Correlation coefficients
#
test "Correlation-1.0" "Correlation - linear data" -match tolerant -body {
set corr [::math::statistics::corr $::data_linear $::data_linear]
} -result 1.0
test "Correlation-1.1" "Correlation - linear/uniform" -match almostzero -body {
set corr [::math::statistics::corr $::data_linear $::data_uniform]
} -result 0.0
#
# Test list procedures
#
proc matchListElements { expected actual } {
if { [llength $expected] != [llength $actual] } {
return 0
} else {
set match 1
foreach a $actual e $expected {
if { $a != $e } {
set match 0
break
}
}
}
return $match
}
customMatch matchList matchListElements
set ::data_list {1 2 3 4 5 6 7 8 9 10}
set ::data_pairs {{1 2} {3 4} {5 6} {7 8} {9 10}}
test "Filter-1.0" "True filter" -match matchList -body {
set data [::math::statistics::filter x $::data_list 1]
} -result $::data_list
test "Filter-1.1" "False filter" -match matchList -body {
set data [::math::statistics::filter x $::data_list 0]
} -result {}
test "Filter-1.2" "Even filter" -match matchList -body {
set data [::math::statistics::filter x $::data_list {$x%2==0}]
} -result {2 4 6 8 10}
test "Filter-2.1" "filter with parameter" -match matchList -body {
set param 3.0
set data [::math::statistics::filter x $::data_list {$x > $param}]
} -result {4 5 6 7 8 9 10}
test "Map-1.0" "Identity map" -match matchList -body {
set data [::math::statistics::map x $::data_list {$x}]
} -result $::data_list
test "Map-1.1" "Is-even map" -match matchList -body {
set data [::math::statistics::map x $::data_list {$x%2==0}]
} -result {0 1 0 1 0 1 0 1 0 1}
test "Map-1.2" "Double map" -match matchList -body {
set data [::math::statistics::map x $::data_list {$x*2}]
} -result {2 4 6 8 10 12 14 16 18 20}
test "Map-2.1" "map with parameter" -match matchList -body {
set param 3.0
set data [::math::statistics::map x $::data_list {$x + $param}]
} -result {4.0 5.0 6.0 7.0 8.0 9.0 10.0 11.0 12.0 13.0}
test "Samplescount-1.0" "Single sublist" -match matchList -body {
set data [::math::statistics::samplescount x [list $::data_list]]
} -result {10}
test "Samplescount-1.1" "List of singleton sublist" -match matchList -body {
set data [::math::statistics::samplescount x $::data_list]
} -result {1 1 1 1 1 1 1 1 1 1}
test "Samplescount-1.2" "Pairs sublist" -match matchList -body {
set data [::math::statistics::samplescount x $::data_pairs]
} -result {2 2 2 2 2}
test "Samplescount-1.3" "Select uneven sublist" -match matchList -body {
set data [::math::statistics::samplescount x $::data_pairs {$x%2}]
} -result {1 1 1 1 1}
test "Samplescount-2.1" "Count with parameter" -match matchList -body {
set param 3.0
set data [::math::statistics::samplescount x $::data_pairs {$x>$param}]
} -result {0 1 2 2 2}
test "Median-1.1" "Median - odd number of data" -body {
set data {1.0 3.0 2.0}
set median [::math::statistics::median $data]
} -result 2.0
test "Median-1.2" "Median - even number of data" -body {
set data {1.0 3.0 2.0 1.0}
set median [::math::statistics::median $data]
} -result 1.5
test "Median-1.3" "Median - missing data" -body {
set data {1.0 {} 3.0 2.0 1.0 {}}
set median [::math::statistics::median $data]
} -result 1.5
test "test-2x2-1.0" "Test 2x2" -match tolerant -body {
set data [::math::statistics::test-2x2 170 94 30 6]
} -result 5.1136364
test "test-xbar-1.0" "Test xbar procedure" -match exact -body {
set data {}
for { set i 0 } { $i < 500 } { incr i } {
lappend data [expr {rand()}]
}
set limits [::math::statistics::control-xbar $data]
set newdata {1.0 1.0 1.0 1.0 0.5 0.5 0.5 0.5 10.0 10.0 10.0 10.0}
set result [::math::statistics::test-xbar $limits $newdata]
} -result {0 2}
test "test-Rchart-1.0" "Test Rchart procedure" -match exact -body {
set data {}
for { set i 0 } { $i < 500 } { incr i } {
lappend data [expr {rand()}]
}
set limits [::math::statistics::control-Rchart $data]
set newdata {0.0 1.0 2.0 1.0 0.4 0.5 0.6 0.5 10.0 0.0 10.0 10.0}
set result [::math::statistics::test-Rchart $limits $newdata]
} -result {0 2}
#
# Testing for normal distribution
#
test "Testnormal-1.0" "Determine normality statistic for birth weight data" -match tolerant -body {
::math::statistics::lillieforsFit {72 112 111 107 119 92 126 80 81 84 115
118 128 128 123 116 125 126 122 126 127 86
142 132 87 123 133 106 103 118 114 94}
} -result 0.82827415657
test "Testnormal-1.0" "Test birthweight data for normality - 80%" -match tolerant -body {
::math::statistics::test-normal {72 112 111 107 119 92 126 80 81 84 115
118 128 128 123 116 125 126 122 126 127 86
142 132 87 123 133 106 103 118 114 94} 0.80
} -result 1
test "Testnormal-1.0" "Test birthweight data for normality - 95%" -match tolerant -body {
::math::statistics::test-normal {72 112 111 107 119 92 126 80 81 84 115
118 128 128 123 116 125 126 122 126 127 86
142 132 87 123 133 106 103 118 114 94} 0.95
} -result 0
#
# Testing multivariate linear regression
#
# Provide some data
test "Testmultivar-1.0" "Ordinary multivariate regression - three independent variables" \
-match tolerant -body {
set data {
{ -.67 14.18 60.03 -7.5}
{ 36.97 15.52 34.24 14.61}
{-29.57 21.85 83.36 -7.}
{-16.9 11.79 51.67 -6.56}
{ 14.09 16.24 36.97 -12.84}
{ 31.52 20.93 45.99 -25.4}
{ 24.05 20.69 50.27 17.27}
{ 22.23 16.91 45.07 -4.3}
{ 40.79 20.49 38.92 -.73}
{-10.35 17.24 58.77 18.78}}
# Call the ols routine
set results [::math::statistics::mv-ols $data]
# Flatten the result (so that we can use the tolerant comparison method)
eval concat [eval concat $results]
} -result {0.887239767929 0.830859651893
3.33854942057 -1.58346976987 0.0362328113288 32.571621244
1.03305463908 0.237943867401 0.234143883673 19.4700016828
0.810755783819 5.86634305732
-2.16569743834 -1.00124210139 -0.536696631937 0.609162254594
-15.0697565684 80.2129990564}
# End of test cases
testsuiteCleanup
|