| 388 | print "pattern.vector.Model.load()" |
| 389 | |
| 390 | def test_model_export(self): |
| 391 | # Assert Orange and Weka ARFF export formats. |
| 392 | for format, src in ( |
| 393 | (vector.ORANGE, |
| 394 | u"bark\tcats\tdogs\thowl\tmeow\tpurr\tm#name\tc#type\n" |
| 395 | u"0\t0.3466\t0\t0\t0\t0.6931\tcat1\tcåt\n" |
| 396 | u"0\t0.3466\t0\t0\t0.6931\t0\tcat2\tcåt\n" |
| 397 | u"0\t0\t0.3466\t0.6931\t0\t0\tdog1\tdøg\n" |
| 398 | u"0.6931\t0\t0.3466\t0\t0\t0\tdog2\tdøg"), |
| 399 | (vector.WEKA, |
| 400 | u"@RELATION 5885744\n" |
| 401 | u"@ATTRIBUTE bark NUMERIC\n" |
| 402 | u"@ATTRIBUTE cats NUMERIC\n" |
| 403 | u"@ATTRIBUTE dogs NUMERIC\n" |
| 404 | u"@ATTRIBUTE howl NUMERIC\n" |
| 405 | u"@ATTRIBUTE meow NUMERIC\n" |
| 406 | u"@ATTRIBUTE purr NUMERIC\n" |
| 407 | u"@ATTRIBUTE class {døg,cåt}\n" |
| 408 | u"@DATA\n0,0.3466,0,0,0,0.6931,cåt\n" |
| 409 | u"0,0.3466,0,0,0.6931,0,cåt\n" |
| 410 | u"0,0,0.3466,0.6931,0,0,døg\n" |
| 411 | u"0.6931,0,0.3466,0,0,0,døg")): |
| 412 | self.model.export("test_%s.txt" % format, format=format) |
| 413 | v = codecs.open("test_%s.txt" % format, encoding="utf-8").read() |
| 414 | v = v.replace("\r\n", "\n") |
| 415 | for line in src.split("\n"): |
| 416 | self.assertTrue(line in src) |
| 417 | os.remove("test_%s.txt" % format) |
| 418 | print "pattern.vector.Model.export()" |
| 419 | |
| 420 | def test_df(self): |
| 421 | # Assert document frequency: "cats" appears in 1/2 documents,"purr" in 1/4. |