Moved Test_SAM_Classifier to new module test_image_classifier. Added Test_MinimumDistance_Classifier and Test_kNN_Classifier.

Removed classes 'Classifier_Generator' and 'RSImage_Predictor'. Homogenization without clustering is now done with RSImage_ClusterPredictor with n_clusters=1.
Removed corresponding tests.
Updated classifier database.

Added new config parameters 'spechomo_n_clusters', 'spechomo_classif_alg', 'spechomo_kNN_n_neighbors' to control spectral homogenization through cluster learner prediction.
Cluster classifier are now saved with float32 data instead of float64 to save memory.

Added pysptools to dependencies.

Revised image classifiers. Added MinimumDistance_Classifier. Revised RSImage_ClusterPredictor and Cluster_Learner.
Revised Test_SAM_Classifier.

Added first working algorithm for cluster homogenization (must improved (slow, complex code). Added tests.

Added class 'ClusterClassifier_Generator' for generating classifiers with separate transformation parameters for spectral cluster of an image.
Added 'Test_ClusterClassifier_Generator'.

Added more Ridge Regression classifiers for different alpha values.

Updated version info (v0.15.4).

Refactored class process_controller to ProcessController. Merged ProcessController.run_all_processors and ProcessController.run_all_processors_OLD.

Updated version info (v0.15.4).