easeml / datascope Goto Github PK

ValueError                                Traceback (most recent call last)
[<ipython-input-49-2e03ddd68d36>](https://localhost:8080/#) in <module>()
----> 1 importances.score(test_data, test_labels)

3 frames
[/usr/local/lib/python3.7/dist-packages/datascope-0.0.3-py3.7-linux-x86_64.egg/datascope/importance/importance.py](https://localhost:8080/#) in score(self, X, y, **kwargs)
     38         if isinstance(y, DataFrame):
     39             y = y.values
---> 40         return self._score(X, y, **kwargs)

[/usr/local/lib/python3.7/dist-packages/datascope-0.0.3-py3.7-linux-x86_64.egg/datascope/importance/shapley.py](https://localhost:8080/#) in _score(self, X, y, **kwargs)
    285         units = np.delete(units, np.where(units == -1))
    286         world = kwargs.get("world", np.zeros_like(units, dtype=int))
--> 287         return self._shapley(self.X, self.y, X, y, self.provenance, units, world)
    288 
    289     def _shapley(

[/usr/local/lib/python3.7/dist-packages/datascope-0.0.3-py3.7-linux-x86_64.egg/datascope/importance/shapley.py](https://localhost:8080/#) in _shapley(self, X, y, X_test, y_test, provenance, units, world)

    314             )
    315         elif self.method == ImportanceMethod.NEIGHBOR:
--> 316             return self._shapley_neighbor(X, y, X_test, y_test, provenance, units, world, self.nn_k, self.nn_distance)
    317         else:
    318             raise ValueError("Unknown method '%s'." % self.method)

[/usr/local/lib/python3.7/dist-packages/datascope-0.0.3-py3.7-linux-x86_64.egg/datascope/importance/shapley.py](https://localhost:8080/#) in _shapley_neighbor(self, X, y, X_test, y_test, provenance, units, world, k, distance)
    507             assert isinstance(X_test, spmatrix)
    508             X_test = X_test.todense()
--> 509         distances = distance(X, X_test)
    510 
    511         # Compute the utilitiy values between training and test labels.

sklearn/metrics/_dist_metrics.pyx in sklearn.metrics._dist_metrics.DistanceMetric.pairwise()

ValueError: Buffer has wrong number of dimensions (expected 2, got 4)

from sklearn.pipeline import Pipeline
from sklearn.metrics import accuracy_score

net = reset_model(seed = 0) # gives scikit-learn compatible skorch model

pipeline = Pipeline([("model", net)])

pipeline.fit(train_dataset, train_labels)
y_pred = pipeline.predict(test_dataset)

plot_loss(net)
accuracy_dirty = accuracy_score(y_pred, test_labels)
print("Pipeline accuracy in the beginning:", accuracy_dirty)

from datascope.importance.common import SklearnModelAccuracy
from datascope.importance.shapley import ShapleyImportance

net = reset_model(seed = 0)
pipeline = Pipeline([("model", net)])

utility = SklearnModelAccuracy(pipeline)
importance = ShapleyImportance(method="neighbor", utility=utility)
importances = importance.fit(train_data, train_labels)
importances.score(test_data, test_labels)

train_data.shape, train_labels.shape
((2067, 3, 224, 224), (2067,))

test_data.shape, test_labels.shape
((813, 3, 224, 224), (813,))

...\datascope\importance\shapley.py in compute_shapley_1nn_mapfork(distances, utilities, provenance, units, world, null_scores, simple_provenance)
    219     n_test = distances.shape[1]
    220     null_scores = null_scores if null_scores is not None else np.zeros((1, n_test))
--> 221     all_importances = compute_all_importances_cy(unit_distances, unit_utilities, null_scores)
    222 
    223     # Aggregate results.

datascope/importance/shapley_cy.pyx in datascope.importance.shapley_cy.compute_all_importances_cy()

ValueError: Buffer dtype mismatch, expected 'int_t' but got 'long long'