Returns a Model of e-mail messages. Document type=True => HAM, False => SPAM. Documents are mostly of a technical nature (developer forum posts).
(top=None)
| 16 | PATH = "" |
| 17 | |
| 18 | def model(top=None): |
| 19 | """ Returns a Model of e-mail messages. |
| 20 | Document type=True => HAM, False => SPAM. |
| 21 | Documents are mostly of a technical nature (developer forum posts). |
| 22 | """ |
| 23 | documents = [] |
| 24 | for score, message in Datasheet.load(os.path.join(PATH, "corpora", "spam-apache.csv")): |
| 25 | document = vector.Document(message, stemmer="porter", top=top, type=int(score) > 0) |
| 26 | documents.append(document) |
| 27 | return vector.Model(documents) |
| 28 | |
| 29 | #--------------------------------------------------------------------------------------------------- |
| 30 |