Change names of primitive types

VIDA-NYU · Mar 15, 2024 · d71eecc · d71eecc
1 parent b98d41a
commit d71eecc
Show file tree

Hide file tree

Showing 6 changed files with 16 additions and 38 deletions.
diff --git a/alpha_automl/builtin_primitives/semisupervised_classifier.py b/alpha_automl/builtin_primitives/semisupervised_classifier.py
@@ -9,8 +9,7 @@
 from sklearn.preprocessing import FunctionTransformer
 from sklearn.semi_supervised import (
     LabelPropagation,
-    LabelSpreading,
-    SelfTrainingClassifier,
+    LabelSpreading
 )
 
 from alpha_automl.base_primitive import BasePrimitive
@@ -19,19 +18,6 @@
 logger = logging.getLogger(__name__)
 
 
-class SkSelfTrainingClassifier(BasePrimitive):
-    sdg_params = dict(alpha=1e-5, penalty="l2", loss="log_loss")
-    model = SelfTrainingClassifier(SGDClassifier(**sdg_params), verbose=True)
-
-    def fit(self, X, y=None):
-        self.model.fit(X, y)
-
-    def predict(self, X):
-        pred = self.model.predict(X)
-
-        return np.array(pred)
-
-
 def make_label_pipeline(method, X):
     step = None
     if method == "LabelSpreading":

diff --git a/alpha_automl/pipeline_synthesis/pipeline_builder.py b/alpha_automl/pipeline_synthesis/pipeline_builder.py
@@ -32,13 +32,13 @@ def change_default_hyperparams(primitive_object):
 def extract_estimators(pipeline_primitives, all_primitives):
     estimators = []
     classifier_name, classifier_obj = pipeline_primitives.pop()
-    primitive_type_tmp = all_primitives[classifier_name]['type']
+    current_primitive_type = all_primitives[classifier_name]['type']
     counter = 0
 
-    while primitive_type_tmp == 'CLASSIFIER':
+    while current_primitive_type == 'CLASSIFIER':
         estimators.append((f'{classifier_name}-{counter}', classifier_obj))
         classifier_name, classifier_obj = pipeline_primitives.pop()
-        primitive_type_tmp = all_primitives[classifier_name]['type']
+        current_primitive_type = all_primitives[classifier_name]['type']
         counter += 1
 
     return estimators
@@ -88,7 +88,7 @@ def make_primitive_objects(self, primitives):
         for primitive_name in primitives:
             primitive_type = self.all_primitives[primitive_name]['type']
 
-            if primitive_type == 'SEMISUPERVISED_CLASSIFIER':
+            if primitive_type == 'SEMISUPERVISED_SELFTRAINER':
                 classifier_obj = pipeline_primitives.pop()[1]
                 primitive_object = create_object(primitive_name, {'base_estimator': classifier_obj})
             elif primitive_type == 'SINGLE_ENSEMBLER':

diff --git a/alpha_automl/resource/base_grammar.bnf b/alpha_automl/resource/base_grammar.bnf
@@ -2,11 +2,12 @@ S -> CLASSIFICATION_TASK | REGRESSION_TASK | CLUSTERING_TASK | TIME_SERIES_FOREC
 CLASSIFICATION_TASK -> IMPUTER ENCODERS FEATURE_SCALER FEATURE_SELECTOR CLASSIFIER ENSEMBLER
 REGRESSION_TASK -> IMPUTER ENCODERS FEATURE_SCALER FEATURE_SELECTOR REGRESSOR
 CLUSTERING_TASK -> IMPUTER ENCODERS FEATURE_SCALER FEATURE_SELECTOR CLUSTERER
-TIME_SERIES_FORECAST_TASK -> REGRESSION_TASK | IMPUTER TIME_SERIES_FORECAST
-SEMISUPERVISED_TASK -> IMPUTER ENCODERS FEATURE_SCALER CLASSIFIER SEMISUPERVISED_CLASSIFIER | IMPUTER ENCODERS FEATURE_SCALER LABELPROPAGATION_CLASSIFIER
+TIME_SERIES_FORECAST_TASK -> IMPUTER TIME_SERIES_FORECASTER | REGRESSION_TASK
+SEMISUPERVISED_TASK -> IMPUTER ENCODERS FEATURE_SCALER SEMISUPERVISED_CLASSIFIER
 NA_TASK -> CLASSIFICATION_TASK | REGRESSION_TASK | SEMISUPERVISED_TASK
 ENCODERS -> TEXT_ENCODER DATETIME_ENCODER CATEGORICAL_ENCODER IMAGE_ENCODER
 ENSEMBLER -> SINGLE_ENSEMBLER | CLASSIFIER CLASSIFIER MULTI_ENSEMBLER | E
+SEMISUPERVISED_CLASSIFIER -> CLASSIFIER SEMISUPERVISED_SELFTRAINER| SEMISUPERVISED_LABELPROPAGATOR
 IMPUTER -> 'primitive_terminal'
 FEATURE_SCALER -> 'primitive_terminal' | 'E'
 FEATURE_SELECTOR -> 'primitive_terminal' | 'E'
@@ -19,6 +20,6 @@ MULTI_ENSEMBLER -> 'primitive_terminal'
 CLASSIFIER -> 'primitive_terminal'
 REGRESSOR -> 'primitive_terminal'
 CLUSTERER -> 'primitive_terminal'
-TIME_SERIES_FORECAST -> 'primitive_terminal'
-SEMISUPERVISED_CLASSIFIER -> 'primitive_terminal'
-LABELPROPAGATION_CLASSIFIER -> 'primitive_terminal'
+TIME_SERIES_FORECASTER -> 'primitive_terminal'
+SEMISUPERVISED_SELFTRAINER -> 'primitive_terminal'
+SEMISUPERVISED_LABELPROPAGATOR -> 'primitive_terminal'
diff --git a/alpha_automl/resource/primitives_hierarchy.json b/alpha_automl/resource/primitives_hierarchy.json
@@ -81,17 +81,17 @@
     "COLUMN_TRANSFORMER": [
         "sklearn.compose.ColumnTransformer"
     ],
-    "TIME_SERIES_FORECAST": [
+    "TIME_SERIES_FORECASTER": [
         "alpha_automl.builtin_primitives.time_series_forecasting.ArimaEstimator",
         "alpha_automl.builtin_primitives.time_series_forecasting.DeeparEstimator",
         "alpha_automl.builtin_primitives.time_series_forecasting.NBEATSEstimator",
         "alpha_automl.builtin_primitives.time_series_forecasting.NHITSEstimator"
     ],
-    "SEMISUPERVISED_CLASSIFIER": [
+    "SEMISUPERVISED_SELFTRAINER": [
         "alpha_automl.builtin_primitives.semisupervised_classifier.AutonBox",
         "sklearn.semi_supervised.SelfTrainingClassifier"
     ],
-    "LABELPROPAGATION_CLASSIFIER": [
+    "SEMISUPERVISED_LABELPROPAGATOR": [
         "alpha_automl.builtin_primitives.semisupervised_classifier.SkLabelSpreading",
         "alpha_automl.builtin_primitives.semisupervised_classifier.SkLabelPropagation"
     ],

diff --git a/alpha_automl/utils.py b/alpha_automl/utils.py
@@ -130,7 +130,7 @@ def make_d3m_pipelines(pipelines, new_primitives, metric, ordering_sign, source_
                 cur_step_idx = add_d3m_step(steps_in_type, cur_step_idx, prev_list, new_prev_list, new_pipeline)
                 prev_list = new_prev_list
 
-            if all_primitive_types[step_id] == 'SEMISUPERVISED_CLASSIFIER':
+            if all_primitive_types[step_id] == 'SEMISUPERVISED_SELFTRAINER':
                 classifier_object = step_object.base_estimator
                 classifier_path = f'classifier.{classifier_object.__class__.__name__}'
                 for primitive_name, primitive_type in all_primitive_types.items():

diff --git a/tests/test_semisupervised.py b/tests/test_semisupervised.py
@@ -8,8 +8,7 @@
 from alpha_automl.builtin_primitives.semisupervised_classifier import (
     AutonBox,
     SkLabelPropagation,
-    SkLabelSpreading,
-    SkSelfTrainingClassifier,
+    SkLabelSpreading
 )
 
 
@@ -50,14 +49,6 @@ class TestSemiSupervisedClassifier:
     )
     X = st_pipeline.fit_transform(X)
 
-    def test_self_training_classifier(self):
-        encoder = SkSelfTrainingClassifier()
-
-        encoder.fit(self.X, self.y)
-        pred = encoder.predict(self.X)
-        print(pred, self.y)
-        assert pred[0] == 0
-
     def test_label_spreading(self):
         encoder = SkLabelSpreading()
         encoder.fit(self.X, self.y)