8 issues detected
Performance 7
Robustness 1

We found some data slices in your dataset on which your model performance is lower than average. Performance bias may happen for different reasons:

  • Not enough examples in the low-performing data slice in the training set
  • Wrong labels in the training set in the low-performing data slice
  • Drift between your training set and test set

To learn more about causes and solutions, check our guide on performance bias.

Issues

2 major 5 medium
`text` contains "said" Precision = 0.737 (Global = 0.917) -19.67% than global 205 samples affected
(9.1% of dataset)
Show details
`text` contains "period" Precision = 0.821 (Global = 0.917) -10.49% than global 173 samples affected
(7.6% of dataset)
Show details
`text` contains "finland" Balanced Accuracy = 0.810 (Global = 0.886) -8.58% than global 133 samples affected
(5.9% of dataset)
Show details
`text` contains "year" Precision = 0.862 (Global = 0.917) -6.02% than global 217 samples affected
(9.6% of dataset)
Show details
`text` contains "eur" Precision = 0.865 (Global = 0.917) -5.68% than global 444 samples affected
(19.6% of dataset)
Show details
`text` contains "quarter" Precision = 0.866 (Global = 0.917) -5.57% than global 164 samples affected
(7.2% of dataset)
Show details
`text_length(text)` >= 122.500 AND `text_length(text)` < 133.500 Balanced Accuracy = 0.839 (Global = 0.886) -5.28% than global 148 samples affected
(6.5% of dataset)
Show details

Debug your issues in the Giskard hub

Install the Giskard hub app to:

  • Debug and diagnose your scan issues
  • Save your scan result as a re-executable test suite to benchmark your model
  • Extend your test suite with our catalog of ready-to-use tests

You can find installation instructions here.

from giskard import GiskardClient

# Create a test suite from your scan results
test_suite = results.generate_test_suite("My first test suite")

# Upload your test suite to your Giskard hub instance
client = GiskardClient("http://localhost:19000", "GISKARD_API_KEY")
client.create_project("my_project_id", "my_project_name")
test_suite.upload(client, "my_project_id")