Renew Phishing Classifier

[jlevypaloalto]

Status

• In Progress
• Ready
• In Hold - (Reason for hold)

Related Issues

fixes: link to the issue

Description

A few sentences describing the overall goals of the pull request's commits.

Must have

• Tests
• Documentation

[github-actions]

Coverage Report

File	Stmts	Miss	Cover	Missing
Packs/Base/Scripts/DBotFindSimilarIncidents
DBotFindSimilarIncidents.py	463	37	92%	137, 180, 201, 215, 219, 221, 238, 264–265, 267, 332, 351, 480, 484, 563, 593–594, 605–606, 610, 662–663, 665, 669, 712–716, 720, 743, 845, 878, 886, 947, 980–981
Packs/Base/Scripts/DBotFindSimilarIncidentsByIndicators
DBotFindSimilarIncidentsByIndicators.py	219	1	99%	202
Packs/Base/Scripts/DBotPredictPhishingWords
DBotPredictPhishingWords.py	171	48	71%	23, 31–32, 39–40, 48–49, 65–66, 76–79, 86–88, 106, 108, 121, 139–140, 167, 171–180, 182–189, 250, 282–286, 296, 298
Packs/Base/Scripts/DBotPreprocessTextData
DBotPreprocessTextData.py	358	41	88%	121, 160, 173, 187, 245, 255, 267–268, 389, 391, 394–395, 401–403, 407–413, 446–450, 453–454, 465, 483–487, 490–491, 493–494, 502, 506
Packs/Base/Scripts/DBotTrainTextClassifierV2
DBotTrainTextClassifierV2.py	303	198	34%	49–50, 58, 68, 74, 77–78, 80–81, 88, 90, 109, 139–142, 153–154, 156–157, 167–168, 172–178, 197, 199, 211–218, 240–242, 245, 249, 259–261, 265–286, 293–302, 309–313, 315–318, 320–326, 330–331, 333–352, 356–361, 365–369, 373–376, 379–384, 386, 390–395, 399–411, 414, 416–417, 419, 421–422, 428–430, 432–449, 451, 458–463, 467–470, 483, 485
Packs/Base/Scripts/GetMLModelEvaluation
GetMLModelEvaluation.py	213	33	84%	180, 247–248, 293–294, 299, 320, 350–354, 358–365, 367–368, 370, 378–380, 384–390
Packs/ML/Scripts/DBotPredictIncidentsBatch
DBotPredictIncidentsBatch.py	74	74	0%	1, 3–5, 7, 9, 12–21, 23–24, 27–37, 39–40, 43–44, 46–56, 59–65, 67–69, 71, 73, 79–81, 83–97
TOTAL	1801	432	76%

Tests	Skipped	Failures	Errors	Time
29	0 💤	0 ❌	0 🔥	27.657s ⏱️

[CLAassistant]

All committers have signed the CLA.

[content-bot]

The following errors were thrown as a part of this pr: RN106.
The following errors cannot be ignored: RN106.
The following errors don't run as part of the nightly flow and therefore can be force merged: RN106.
##############################################################
Please note that the PR can be force merged from the validation perspective.
##############################################################

[AradCarmi]

Great Job!
Please see my notes.

[AradCarmi]

Why do we need to update this script as well? it doesn't use the updated demisto/ml image.

[jlevypaloalto]

[content-bot]

This PR was automatically updated by a GitHub Action

• Base pack version was bumped to 1.39.25.

To stop automatic version bumps, add the ignore-auto-bump-version label to the github PR.

[content-bot]

This PR was automatically updated by a GitHub Action

• Base pack version was bumped to 1.39.26.

To stop automatic version bumps, add the ignore-auto-bump-version label to the github PR.

[content-bot]

Validate summary
The following errors were thrown as a part of this pr: GR107, DO101.
The following errors can be ignored: GR107.
The following errors cannot be ignored: DO101.

nVerdict: PR can be force merged from validate perspective? ❌