Resolve #108 - training data transformations should not be reused

modAL/batch.py

@@ -8,7 +8,7 @@
 import scipy.sparse as sp
 from sklearn.metrics.pairwise import pairwise_distances, pairwise_distances_argmin_min
 
-from modAL.utils.data import data_vstack, modALinput
+from modAL.utils.data import data_vstack, modALinput, data_shape
 from modAL.models.base import BaseCommittee, BaseLearner
 from modAL.uncertainty import classifier_uncertainty
 
@@ -150,8 +150,10 @@ def ranked_batch(classifier: Union[BaseLearner, BaseCommittee],
     if classifier.X_training is None:
         best_coldstart_instance_index, labeled = select_cold_start_instance(X=unlabeled, metric=metric, n_jobs=n_jobs)
         instance_index_ranking = [best_coldstart_instance_index]
-    elif classifier.X_training.shape[0] > 0:
-        labeled = classifier.Xt_training[:] if classifier.on_transformed else classifier.X_training[:]
+    elif data_shape(classifier.X_training)[0] > 0:
+        labeled = classifier.transform_without_estimating(
+            classifier.X_training
+        ) if classifier.on_transformed else classifier.X_training[:]
         instance_index_ranking = []
 
     # The maximum number of records to sample.

modAL/models/base.py

@@ -66,11 +66,9 @@ def __init__(self,
         self.on_transformed = on_transformed
 
         self.X_training = X_training
-        self.Xt_training = None
         self.y_training = y_training
         if X_training is not None:
             self._fit_to_known(bootstrap=bootstrap_init, **fit_kwargs)
-            self.Xt_training = self.transform_without_estimating(self.X_training) if self.on_transformed else None
 
         assert isinstance(force_all_finite, bool), 'force_all_finite must be a bool'
         self.force_all_finite = force_all_finite
@@ -92,15 +90,10 @@ def _add_training_data(self, X: modALinput, y: modALinput) -> None:
 
         if self.X_training is None:
             self.X_training = X
-            self.Xt_training = self.transform_without_estimating(self.X_training) if self.on_transformed else None
             self.y_training = y
         else:
             try:
                 self.X_training = data_vstack((self.X_training, X))
-                self.Xt_training = data_vstack((
-                    self.Xt_training,
-                    self.transform_without_estimating(X)
-                )) if self.on_transformed else None
                 self.y_training = data_vstack((self.y_training, y))
             except ValueError:
                 raise ValueError('the dimensions of the new training data and label must'
@@ -213,7 +206,6 @@ def fit(self, X: modALinput, y: modALinput, bootstrap: bool = False, **fit_kwarg
         check_X_y(X, y, accept_sparse=True, ensure_2d=False, allow_nd=True, multi_output=True, dtype=None,
                   force_all_finite=self.force_all_finite)
         self.X_training, self.y_training = X, y
-        self.Xt_training = self.transform_without_estimating(self.X_training) if self.on_transformed else None
         return self._fit_to_known(bootstrap=bootstrap, **fit_kwargs)
 
     def predict(self, X: modALinput, **predict_kwargs) -> Any:

tests/core_tests.py

@@ -29,6 +29,7 @@
 from sklearn.multiclass import OneVsRestClassifier
 from sklearn.pipeline import make_pipeline
 from sklearn.preprocessing import FunctionTransformer
+from sklearn.feature_extraction.text import CountVectorizer
 from scipy.stats import entropy, norm
 from scipy.special import ndtr
 from scipy import sparse as sp
@@ -824,6 +825,45 @@ def test_on_transformed(self):
             query_idx, query_inst = learner.query(X_pool)
             learner.teach(X_pool.iloc[query_idx], y_pool[query_idx])
 
+    def test_on_transformed_with_variable_transformation(self):
+        """
+        Learnable transformations naturally change after a model is retrained. Make sure this is handled
+        properly for on_transformed=True query strategies.
+        """
+        query_strategies = [
+            modAL.batch.uncertainty_batch_sampling
+            # add further strategies which work with instance representations
+            # no further ones as of 09.12.2020
+        ]
+
+        X_labeled = ['Dog', 'Cat', 'Tree']
+
+        # contains unseen in labeled words, training model on those
+        # will alter CountVectorizer transformations
+        X_pool = ['Airplane', 'House']
+
+        y = [0, 1, 1, 0, 1]  # irrelevant for test
+
+        for query_strategy in query_strategies:
+            learner = modAL.models.learners.ActiveLearner(
+                estimator=make_pipeline(
+                    CountVectorizer(),
+                    RandomForestClassifier(n_estimators=10)
+                ),
+                query_strategy=query_strategy,
+                X_training=X_labeled, y_training=y[:len(X_labeled)],
+                on_transformed=True,
+            )
+
+            for _ in range(len(X_pool)):
+                query_idx, query_instance = learner.query(X_pool, n_instances=1)
+                i = query_idx[0]
+
+                learner.teach(
+                    X=[X_pool[i]],
+                    y=[y[i]]
+                )
+
     def test_old_query_strategy_interface(self):
         n_samples = 10
         n_features = 5