Giskard Scan Results

2 issues detected

Performance 2

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

`text_length(text)` >= 151.500 AND `text_length(text)` < 165.500 Precision = 0.407 (Global = 0.509) -20.03% than global 59 samples affected
(6.8% of dataset) Show details Hide details

Description

For records in the dataset where `text_length(text)` >= 151.500 AND `text_length(text)` < 165.500, the Precision is 20.03% lower than the global Precision.

Examples

	text	text_length(text)	label	Predicted `label`
9	in exactly 89 minutes , most of which passed as slowly as if i 'd been sitting naked on an igloo , formula 51 sank from quirky to jerky to utter turkey .	154	negative	positive (p = 1.00)
11	it takes a strange kind of laziness to waste the talents of robert forster , anne meara , eugene levy , and reginald veljohnson all in the same movie .	152	negative	positive (p = 1.00)
26	the action switches between past and present , but the material link is too tenuous to anchor the emotional connections that purport to span a 125-year divide .	161	negative	positive (p = 1.00)

Taxonomy

avid-effect:performance:P0204

`text` contains "movie" Precision = 0.421 (Global = 0.509) -17.22% than global 95 samples affected
(10.9% of dataset) Show details Hide details

Description

For records in the dataset where `text` contains "movie", the Precision is 17.22% lower than the global Precision.

Examples

	text	label	Predicted `label`
11	it takes a strange kind of laziness to waste the talents of robert forster , anne meara , eugene levy , and reginald veljohnson all in the same movie .	negative	positive (p = 1.00)
14	even horror fans will most likely not find what they 're seeking with trouble every day ; the movie lacks both thrills and humor .	negative	positive (p = 1.00)
18	... the movie is just a plain old monster .	negative	positive (p = 1.00)

Taxonomy

avid-effect:performance:P0204

What's next?

1. Generate a test suite from your scan results

test_suite = results.generate_test_suite("My first test suite")

2. Run your test suite

test_suite.run()