def main(verbose=False,
beta=0.05,
prior_probability=0.5,
epsilon=0.05,
num_features=8,
feature_cardinality=5,
num_examples=100,
visualization_interval=100,
biased_feature_proportion=0.2,
biased_feature_effect_length=10**100,
directory="/tmp/adpredictor/",
extension="png"):
# Initialize globals
np.random.seed(1)
logging.basicConfig(level=logging.DEBUG if verbose else logging.INFO)
# Construct settings
simulation = SimulationRunner.Simulation(
predictor_config=AdPredictor.Config(
beta=beta,
prior_probability=prior_probability,
epsilon=epsilon,
num_features=num_features),
feature_cardinality=feature_cardinality,
num_examples=num_examples,
directory=directory,
biased_feature_proportion=biased_feature_proportion,
biased_feature_effect_length=biased_feature_effect_length,
visualization_interval=visualization_interval,
extension=extension)
# Train and output graphs
simulation_runner = SimulationRunner(simulation)
simulation_runner.run()
def libsvm_file_process(config):
adpredictor = AdPredictor(AdPredictor.Config(config.beta, config.epsilon),
config.feature_num)
train_pred, train_label = [], []
for train_file in config.train_files:
for features, label in FileSampler(train_file).generate_samples():
prob = adpredictor.train(features, label, True)
train_pred.append(prob)
train_label.append(1 if label > 0 else 0)
adpredictor.save_model(config.model_file)
test_pred, test_label = [], []
for test_file in config.test_files:
for features, label in FileSampler(test_file).generate_samples():
prob = adpredictor.predict(features)
test_pred.append(prob)
test_label.append(1 if label > 0 else 0)
return train_pred, train_label, test_pred, test_label, config
def _create_predictor(beta=0.05, prior=0.3, epsilon=0.01, num_features=10):
config = AdPredictor.Config(beta, prior, epsilon, num_features)
return AdPredictor(config)