Replace InstanceIterator by PickleGzInstance

miplearn/components/component.py

@@ -2,10 +2,10 @@
 #  Copyright (C) 2020, UChicago Argonne, LLC. All rights reserved.
 #  Released under the modified BSD license. See COPYING.md for more details.
 
-import numpy as np
-from typing import Any, List, Union, TYPE_CHECKING, Tuple, Dict, Optional, Hashable
+from typing import Any, List, TYPE_CHECKING, Tuple, Dict, Hashable
+
+import numpy as np
 
-from miplearn.extractors import InstanceIterator
 from miplearn.instance import Instance
 from miplearn.types import LearningSolveStats, TrainingSample, Features
 
@@ -120,11 +120,11 @@ class Component:
 
     def xy_instances(
         self,
-        instances: Union[List[str], List[Instance]],
+        instances: List[Instance],
     ) -> Tuple[Dict, Dict]:
         x_combined: Dict = {}
         y_combined: Dict = {}
-        for instance in InstanceIterator(instances):
+        for instance in instances:
             assert isinstance(instance, Instance)
             for sample in instance.training_data:
                 xy = self.sample_xy(instance.features, sample)
@@ -141,7 +141,7 @@ class Component:
 
     def fit(
         self,
-        training_instances: Union[List[str], List[Instance]],
+        training_instances: List[Instance],
     ) -> None:
         x, y = self.xy_instances(training_instances)
         for cat in x.keys():
@@ -198,9 +198,9 @@ class Component:
     ) -> None:
         return
 
-    def evaluate(self, instances: Union[List[str], List[Instance]]) -> List:
+    def evaluate(self, instances: List[Instance]) -> List:
         ev = []
-        for instance in InstanceIterator(instances):
+        for instance in instances:
             for sample in instance.training_data:
                 ev += [self.sample_evaluate(instance.features, sample)]
         return ev

miplearn/components/lazy_dynamic.py

@@ -13,7 +13,7 @@ from miplearn.classifiers import Classifier
 from miplearn.classifiers.counting import CountingClassifier
 from miplearn.components import classifier_evaluation_dict
 from miplearn.components.component import Component
-from miplearn.extractors import InstanceFeaturesExtractor, InstanceIterator
+from miplearn.extractors import InstanceFeaturesExtractor
 
 logger = logging.getLogger(__name__)
 
@@ -68,7 +68,7 @@ class DynamicLazyConstraintsComponent(Component):
 
         self.classifiers = {}
         violation_to_instance_idx = {}
-        for (idx, instance) in enumerate(InstanceIterator(training_instances)):
+        for (idx, instance) in enumerate(training_instances):
             for v in instance.found_violated_lazy_constraints:
                 if isinstance(v, list):
                     v = tuple(v)

miplearn/components/objective.py

@@ -3,22 +3,14 @@
 #  Released under the modified BSD license. See COPYING.md for more details.
 
 import logging
-from typing import List, Dict, Union, Optional, Any, TYPE_CHECKING, Tuple, Hashable
+from typing import List, Dict, Any, TYPE_CHECKING, Tuple, Hashable
 
 import numpy as np
 from sklearn.linear_model import LinearRegression
-from sklearn.metrics import (
-    mean_squared_error,
-    explained_variance_score,
-    max_error,
-    mean_absolute_error,
-    r2_score,
-)
 
 from miplearn.classifiers import Regressor
 from miplearn.classifiers.sklearn import ScikitLearnRegressor
 from miplearn.components.component import Component
-from miplearn.extractors import InstanceIterator
 from miplearn.instance import Instance
 from miplearn.types import TrainingSample, LearningSolveStats, Features
 

miplearn/components/steps/convert_tight.py

@@ -13,7 +13,6 @@ from miplearn.classifiers.counting import CountingClassifier
 from miplearn.components import classifier_evaluation_dict
 from miplearn.components.component import Component
 from miplearn.components.steps.drop_redundant import DropRedundantInequalitiesStep
-from miplearn.extractors import InstanceIterator
 
 logger = logging.getLogger(__name__)
 
@@ -116,7 +115,7 @@ class ConvertTightIneqsIntoEqsStep(Component):
     def _x_train(instances):
         x = {}
         for instance in tqdm(
-            InstanceIterator(instances),
+            instances,
             desc="Extract (drop:x)",
             disable=len(instances) < 5,
         ):
@@ -139,7 +138,7 @@ class ConvertTightIneqsIntoEqsStep(Component):
     def y(self, instances):
         y = {}
         for instance in tqdm(
-            InstanceIterator(instances),
+            instances,
             desc="Extract (rlx:conv_ineqs:y)",
             disable=len(instances) < 5,
         ):

miplearn/components/steps/drop_redundant.py

@@ -6,14 +6,13 @@ import logging
 from copy import deepcopy
 
 import numpy as np
-from tqdm import tqdm
 from p_tqdm import p_umap
+from tqdm import tqdm
 
 from miplearn.classifiers.counting import CountingClassifier
 from miplearn.components import classifier_evaluation_dict
 from miplearn.components.component import Component
 from miplearn.components.lazy_static import LazyConstraint
-from miplearn.extractors import InstanceIterator
 
 logger = logging.getLogger(__name__)
 
@@ -131,31 +130,24 @@ class DropRedundantInequalitiesStep(Component):
         def _extract(instance):
             x = {}
             y = {}
-            for instance in InstanceIterator([instance]):
-                for training_data in instance.training_data:
-                    for (cid, slack) in training_data["slacks"].items():
-                        category = instance.get_constraint_category(cid)
-                        if category is None:
-                            continue
-                        if category not in x:
-                            x[category] = []
-                        if category not in y:
-                            y[category] = []
-                        if slack > self.slack_tolerance:
-                            y[category] += [[False, True]]
-                        else:
-                            y[category] += [[True, False]]
-                        x[category] += [instance.get_constraint_features(cid)]
+            for training_data in instance.training_data:
+                for (cid, slack) in training_data["slacks"].items():
+                    category = instance.get_constraint_category(cid)
+                    if category is None:
+                        continue
+                    if category not in x:
+                        x[category] = []
+                    if category not in y:
+                        y[category] = []
+                    if slack > self.slack_tolerance:
+                        y[category] += [[False, True]]
+                    else:
+                        y[category] += [[True, False]]
+                    x[category] += [instance.get_constraint_features(cid)]
             return x, y
 
         if n_jobs == 1:
-            results = [
-                _extract(i)
-                for i in tqdm(
-                    instances,
-                    desc="Extract (drop 1/3)",
-                )
-            ]
+            results = [_extract(i) for i in tqdm(instances, desc="Extract (drop 1/3)")]
         else:
             results = p_umap(
                 _extract,