Stowage/tutanota
2
0
Fork 0
mirror of https://github.com/tutao/tutanota.git synced 2025-12-08 06:09:50 +00:00
Code Issues Projects Releases Packages Wiki Activity

remove DynamicTfVectorizer

Browse source 
Co-authored-by: map <mpfau@users.noreply.github.com>
This commit is contained in:
abp 2025-10-20 16:03:20 +02:00
parent 6d4a656a69
commit 5124985d4f
No known key found for this signature in database
GPG key ID: 791D4EC38A7AA7C2
4 changed files with 1 additions and 189 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/mail-app/workerUtils/spamClassification/SpamClassifier.ts
View file

@ -1,6 +1,5 @@
import { assertWorkerOrNode } from "../../../common/api/common/Env"
import { assertNotNull, defer, groupByAndMap, isNotNull, Nullable, promiseMap, tokenize } from "@tutao/tutanota-utils"
import { DynamicTfVectorizer } from "./DynamicTfVectorizer"
import { HashingVectorizer } from "./HashingVectorizer"
import {
ML_BITCOIN_REGEX,
@ -110,7 +109,7 @@ export class SpamClassifier {
private readonly initializer: SpamClassificationInitializer,
private readonly deterministic: boolean = false,
private readonly preprocessConfiguration: PreprocessConfiguration = DEFAULT_PREPROCESS_CONFIGURATION,
private readonly vectorizer: DynamicTfVectorizer | HashingVectorizer = new HashingVectorizer(),
private readonly vectorizer: HashingVectorizer = new HashingVectorizer(),
) {
this.classifier = new Map()
}
@ -228,9 +227,6 @@ export class SpamClassifier {
const preprocessingTime = performance.now() - preprocessingStart
const vectorizationStart = performance.now()
if (this.vectorizer instanceof DynamicTfVectorizer) {
this.vectorizer.buildInitialTokenVocabulary(tokenizedMails)
}
const vectors = await this.vectorizer.transform(tokenizedMails)
const labels = mails.map((mail) => (mail.isSpam ? 1 : 0))