ANL-CEEESA/MIPLearn
1
0
Fork 0
mirror of https://github.com/ANL-CEEESA/MIPLearn.git synced 2025-12-06 09:28:51 -06:00
Code Issues Packages Projects Releases Wiki Activity

Primal: reactivate before_solve_mip

Browse Source
This commit is contained in:
Alinson S. Xavier
2021-03-31 12:07:58 -05:00
parent fe7bad885c
commit db2f426140
7 changed files with 133 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
miplearn/benchmark.py
View File

@@ -10,7 +10,8 @@ import pandas as pd
from miplearn.instance import Instance from miplearn.instance import Instance
from miplearn.solvers.learning import LearningSolver from miplearn.solvers.learning import LearningSolver
from miplearn.types import LearningSolveStats
logger = logging.getLogger(__name__)
class BenchmarkRunner: class BenchmarkRunner:
@@ -110,6 +111,7 @@ class BenchmarkRunner:
""" """
for (solver_name, solver) in self.solvers.items(): for (solver_name, solver) in self.solvers.items():
logger.debug(f"Fitting {solver_name}...")
solver.fit(instances) solver.fit(instances)
def _silence_miplearn_logger(self) -> None: def _silence_miplearn_logger(self) -> None:

11
miplearn/classifiers/__init__.py
View File

@@ -34,7 +34,11 @@ class Classifier(ABC):
""" """
assert isinstance(x_train, np.ndarray) assert isinstance(x_train, np.ndarray)
assert isinstance(y_train, np.ndarray) assert isinstance(y_train, np.ndarray)
assert x_train.dtype in [np.float16, np.float32, np.float64] assert x_train.dtype in [
np.float16,
np.float32,
np.float64,
], f"x_train.dtype shoule be float. Found {x_train.dtype} instead."
assert y_train.dtype == np.bool8 assert y_train.dtype == np.bool8
assert len(x_train.shape) == 2 assert len(x_train.shape) == 2
assert len(y_train.shape) == 2 assert len(y_train.shape) == 2
@@ -67,7 +71,10 @@ class Classifier(ABC):
assert isinstance(x_test, np.ndarray) assert isinstance(x_test, np.ndarray)
assert len(x_test.shape) == 2 assert len(x_test.shape) == 2
(n_samples, n_features_x) = x_test.shape (n_samples, n_features_x) = x_test.shape
assert n_features_x == self.n_features assert n_features_x == self.n_features, (
f"Test and training data have different number of "
f"features: {n_features_x} != {self.n_features}"
)
return np.ndarray([]) return np.ndarray([])

78
miplearn/components/primal.py
View File

@@ -24,11 +24,9 @@ from miplearn.classifiers.adaptive import AdaptiveClassifier
from miplearn.classifiers.threshold import MinPrecisionThreshold, Threshold from miplearn.classifiers.threshold import MinPrecisionThreshold, Threshold
from miplearn.components import classifier_evaluation_dict from miplearn.components import classifier_evaluation_dict
from miplearn.components.component import Component from miplearn.components.component import Component
from miplearn.extractors import InstanceIterator
from miplearn.instance import Instance from miplearn.instance import Instance
from miplearn.types import ( from miplearn.types import (
TrainingSample, TrainingSample,
VarIndex,
Solution, Solution,
LearningSolveStats, LearningSolveStats,
Features, Features,
@@ -70,30 +68,33 @@ class PrimalSolutionComponent(Component):
self._n_one = 0 self._n_one = 0
def before_solve_mip(self, solver, instance, model): def before_solve_mip(self, solver, instance, model):
pass if len(self.thresholds) > 0:
# if len(self.thresholds) > 0: logger.info("Predicting primal solution...")
# logger.info("Predicting primal solution...") solution = self.predict(instance.features, instance.training_data[-1])
# solution = self.predict(instance)
# # Collect prediction statistics
# # Collect prediction statistics self._n_free = 0
# self._n_free = 0 self._n_zero = 0
# self._n_zero = 0 self._n_one = 0
# self._n_one = 0 for (var, var_dict) in solution.items():
# for (var, var_dict) in solution.items(): for (idx, value) in var_dict.items():
# for (idx, value) in var_dict.items(): if value is None:
# if value is None: self._n_free += 1
# self._n_free += 1 else:
# else: if value < 0.5:
# if value < 0.5: self._n_zero += 1
# self._n_zero += 1 else:
# else: self._n_one += 1
# self._n_one += 1 logger.info(
# f"Predicted: {self._n_free} free, {self._n_zero} fix-zero, "
# # Provide solution to the solver f"{self._n_one} fix-one"
# if self.mode == "heuristic": )
# solver.internal_solver.fix(solution)
# else: # Provide solution to the solver
# solver.internal_solver.set_warm_start(solution) if self.mode == "heuristic":
solver.internal_solver.fix(solution)
else:
solver.internal_solver.set_warm_start(solution)
def after_solve_mip( def after_solve_mip(
self, self,
@@ -120,27 +121,29 @@ class PrimalSolutionComponent(Component):
self.classifiers[category] = clf self.classifiers[category] = clf
self.thresholds[category] = thr self.thresholds[category] = thr
def predict(self, instance: Instance) -> Solution: def predict(
assert len(instance.training_data) > 0 self,
sample = instance.training_data[-1] features: Features,
sample: TrainingSample,
) -> Solution:
# Initialize empty solution # Initialize empty solution
solution: Solution = {} solution: Solution = {}
for (var_name, var_dict) in instance.features["Variables"].items(): for (var_name, var_dict) in features["Variables"].items():
solution[var_name] = {} solution[var_name] = {}
for idx in var_dict.keys(): for idx in var_dict.keys():
solution[var_name][idx] = None solution[var_name][idx] = None
# Compute y_pred # Compute y_pred
x = self.x_sample(instance.features, sample) x = self.x_sample(features, sample)
y_pred = {} y_pred = {}
for category in x.keys(): for category in x.keys():
assert category in self.classifiers, ( assert category in self.classifiers, (
f"Classifier for category {category} has not been trained. " f"Classifier for category {category} has not been trained. "
f"Please call component.fit before component.predict." f"Please call component.fit before component.predict."
) )
proba = self.classifiers[category].predict_proba(x[category]) xc = np.array(x[category])
thr = self.thresholds[category].predict(x[category]) proba = self.classifiers[category].predict_proba(xc)
thr = self.thresholds[category].predict(xc)
y_pred[category] = np.vstack( y_pred[category] = np.vstack(
[ [
proba[:, 0] > thr[0], proba[:, 0] > thr[0],
@@ -150,7 +153,7 @@ class PrimalSolutionComponent(Component):
# Convert y_pred into solution # Convert y_pred into solution
category_offset: Dict[Hashable, int] = {cat: 0 for cat in x.keys()} category_offset: Dict[Hashable, int] = {cat: 0 for cat in x.keys()}
for (var_name, var_dict) in instance.features["Variables"].items(): for (var_name, var_dict) in features["Variables"].items():
for (idx, var_features) in var_dict.items(): for (idx, var_features) in var_dict.items():
category = var_features["Category"] category = var_features["Category"]
offset = category_offset[category] offset = category_offset[category]
@@ -250,8 +253,9 @@ class PrimalSolutionComponent(Component):
if category not in x.keys(): if category not in x.keys():
x[category] = [] x[category] = []
y[category] = [] y[category] = []
f = var_features["User features"] f: List[float] = []
assert f is not None assert var_features["User features"] is not None
f += var_features["User features"]
if "LP solution" in sample and sample["LP solution"] is not None: if "LP solution" in sample and sample["LP solution"] is not None:
lp_value = sample["LP solution"][var_name][idx] lp_value = sample["LP solution"][var_name][idx]
if lp_value is not None: if lp_value is not None:

4
miplearn/problems/tsp.py
View File

@@ -157,10 +157,10 @@ class TravelingSalesmanInstance(Instance):
return model return model
def get_instance_features(self): def get_instance_features(self):
return [1] return [0.0]
def get_variable_features(self, var_name, index): def get_variable_features(self, var_name, index):
return [1] return [0.0]
def get_variable_category(self, var_name, index): def get_variable_category(self, var_name, index):
return index return index

41
miplearn/solvers/learning.py
View File

@@ -373,25 +373,28 @@ class LearningSolver:
The list is the same you would obtain by calling The list is the same you would obtain by calling
`[solver.solve(p) for p in instances]` `[solver.solve(p) for p in instances]`
""" """
self.internal_solver = None if n_jobs == 1:
self._silence_miplearn_logger() return [self.solve(p) for p in instances]
_GLOBAL[0].solver = self else:
_GLOBAL[0].output_filenames = output_filenames self.internal_solver = None
_GLOBAL[0].instances = instances self._silence_miplearn_logger()
_GLOBAL[0].discard_outputs = discard_outputs _GLOBAL[0].solver = self
results = p_map( _GLOBAL[0].output_filenames = output_filenames
_parallel_solve, _GLOBAL[0].instances = instances
list(range(len(instances))), _GLOBAL[0].discard_outputs = discard_outputs
num_cpus=n_jobs, results = p_map(
desc=label, _parallel_solve,
) list(range(len(instances))),
results = [r for r in results if r[0]] num_cpus=n_jobs,
stats = [] desc=label,
for (idx, (s, instance)) in enumerate(results): )
stats.append(s) results = [r for r in results if r[0]]
instances[idx] = instance stats = []
self._restore_miplearn_logger() for (idx, (s, instance)) in enumerate(results):
return stats stats.append(s)
instances[idx] = instance
self._restore_miplearn_logger()
return stats
def fit(self, training_instances: Union[List[str], List[Instance]]) -> None: def fit(self, training_instances: Union[List[str], List[Instance]]) -> None:
if len(training_instances) == 0: if len(training_instances) == 0:

60
tests/components/test_primal.py
View File

@@ -2,7 +2,6 @@
# Copyright (C) 2020, UChicago Argonne, LLC. All rights reserved. # Copyright (C) 2020, UChicago Argonne, LLC. All rights reserved.
# Released under the modified BSD license. See COPYING.md for more details. # Released under the modified BSD license. See COPYING.md for more details.
from typing import cast
from unittest.mock import Mock from unittest.mock import Mock
import numpy as np import numpy as np
@@ -11,7 +10,6 @@ from numpy.testing import assert_array_equal
from miplearn import Classifier from miplearn import Classifier
from miplearn.classifiers.threshold import Threshold from miplearn.classifiers.threshold import Threshold
from miplearn.components.primal import PrimalSolutionComponent from miplearn.components.primal import PrimalSolutionComponent
from miplearn.instance import Instance
from miplearn.types import TrainingSample, Features from miplearn.types import TrainingSample, Features
@@ -142,8 +140,7 @@ def test_predict() -> None:
) )
thr = Mock(spec=Threshold) thr = Mock(spec=Threshold)
thr.predict = Mock(return_value=[0.75, 0.75]) thr.predict = Mock(return_value=[0.75, 0.75])
instance = cast(Instance, Mock(spec=Instance)) features: Features = {
instance.features = {
"Variables": { "Variables": {
"x": { "x": {
0: { 0: {
@@ -161,33 +158,23 @@ def test_predict() -> None:
} }
} }
} }
instance.training_data = [ sample: TrainingSample = {
{ "LP solution": {
"LP solution": { "x": {
"x": { 0: 0.1,
0: 0.1, 1: 0.5,
1: 0.5, 2: 0.9,
2: 0.9,
}
} }
} }
]
x = {
"default": np.array(
[
[0.0, 0.0, 0.1],
[0.0, 2.0, 0.5],
[2.0, 0.0, 0.9],
]
)
} }
x = PrimalSolutionComponent.x_sample(features, sample)
comp = PrimalSolutionComponent() comp = PrimalSolutionComponent()
comp.classifiers = {"default": clf} comp.classifiers = {"default": clf}
comp.thresholds = {"default": thr} comp.thresholds = {"default": thr}
solution_actual = comp.predict(instance) solution_actual = comp.predict(features, sample)
clf.predict_proba.assert_called_once() clf.predict_proba.assert_called_once()
thr.predict.assert_called_once()
assert_array_equal(x["default"], clf.predict_proba.call_args[0][0]) assert_array_equal(x["default"], clf.predict_proba.call_args[0][0])
thr.predict.assert_called_once()
assert_array_equal(x["default"], thr.predict.call_args[0][0]) assert_array_equal(x["default"], thr.predict.call_args[0][0])
assert solution_actual == { assert solution_actual == {
"x": { "x": {
@@ -196,3 +183,30 @@ def test_predict() -> None:
2: 1.0, 2: 1.0,
} }
} }
def test_fit_xy():
comp = PrimalSolutionComponent(
classifier=lambda: Mock(spec=Classifier),
threshold=lambda: Mock(spec=Threshold),
)
x = {
"type-a": np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]]),
"type-b": np.array([[7.0, 8.0, 9.0]]),
}
y = {
"type-a": np.array([[True, False], [False, True]]),
"type-b": np.array([[True, False]]),
}
comp.fit_xy(x, y)
for category in ["type-a", "type-b"]:
assert category in comp.classifiers
assert category in comp.thresholds
clf = comp.classifiers[category]
clf.fit.assert_called_once()
assert_array_equal(x[category], clf.fit.call_args[0][0])
assert_array_equal(y[category], clf.fit.call_args[0][1])
thr = comp.thresholds[category]
thr.fit.assert_called_once()
assert_array_equal(x[category], thr.fit.call_args[0][1])
assert_array_equal(y[category], thr.fit.call_args[0][2])

37
tests/test_benchmark.py
View File

@@ -12,24 +12,25 @@ from miplearn.solvers.learning import LearningSolver
def test_benchmark(): def test_benchmark():
# Generate training and test instances for n_jobs in [1, 4]:
generator = MaxWeightStableSetGenerator(n=randint(low=25, high=26)) # Generate training and test instances
train_instances = generator.generate(5) generator = MaxWeightStableSetGenerator(n=randint(low=25, high=26))
test_instances = generator.generate(3) train_instances = generator.generate(5)
test_instances = generator.generate(3)
# Training phase... # Solve training instances
training_solver = LearningSolver() training_solver = LearningSolver()
training_solver.parallel_solve(train_instances, n_jobs=10) training_solver.parallel_solve(train_instances, n_jobs=n_jobs)
# Test phase... # Benchmark
test_solvers = { test_solvers = {
"Strategy A": LearningSolver(), "Strategy A": LearningSolver(),
"Strategy B": LearningSolver(), "Strategy B": LearningSolver(),
} }
benchmark = BenchmarkRunner(test_solvers) benchmark = BenchmarkRunner(test_solvers)
benchmark.fit(train_instances) benchmark.fit(train_instances)
benchmark.parallel_solve(test_instances, n_jobs=2, n_trials=2) benchmark.parallel_solve(test_instances, n_jobs=n_jobs, n_trials=2)
assert benchmark.results.values.shape == (12, 18) assert benchmark.results.values.shape == (12, 18)
benchmark.write_csv("/tmp/benchmark.csv") benchmark.write_csv("/tmp/benchmark.csv")
assert os.path.isfile("/tmp/benchmark.csv") assert os.path.isfile("/tmp/benchmark.csv")