search

andosa / treeinterpreter

BSD 3-Clause "New" or "Revised" License
745 stars 140 forks source link

Tests? #32

Closed jimfulton closed 3 years ago

jimfulton commented 4 years ago

How should tests be run?

I get 3 test failures using python setup.py test or pytest using Python 3.6.

======================================================================
FAIL: test_forest_regressor (tests.test_treeinterpreter.TestTreeinterpreter)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/Users/c97346/p/treeinterpreter/tests/test_treeinterpreter.py", line 75, in test_forest_regressor
    self.assertTrue(np.allclose(base_prediction, pred))
AssertionError: False is not true

======================================================================
FAIL: test_forest_regressor_joint (tests.test_treeinterpreter.TestTreeinterpreter)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/Users/c97346/p/treeinterpreter/tests/test_treeinterpreter.py", line 90, in test_forest_regressor_joint
    self.assertTrue(np.allclose(base_prediction, pred))
AssertionError: False is not true

======================================================================
FAIL: test_tree_regressor (tests.test_treeinterpreter.TestTreeinterpreter)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/Users/c97346/p/treeinterpreter/tests/test_treeinterpreter.py", line 40, in test_tree_regressor
    self.assertTrue(np.allclose(base_prediction, pred))
AssertionError: False is not true
jimfulton commented 4 years ago

The tests are failing because the shapes of the predictions from treeinterpeter and scikit-learn are different.

Did this change in one or the other?

juliangilbey commented 3 years ago

I notice that in the test test_forest_regressor with ForestRegressor == RandomForestRegressor, the shape of pred (the result of calling treeinterpreter.predict) is (253, 1) while the shape of bias is (253,). This is surely wrong?