def run(model, verbose=0):
"""Entry Point to run models
Args:
model: model function to run.
"""
# Load the data and split into training and validation sets
data = GalaxyData(feature_extraction.hog_features, scale_features=False)
(training_features, training_solutions,
validation_features, validation_solutions) = data.split_training_and_validation_data(50)
# Train and Predict Model
(clf, columns) = model(training_features, training_solutions, verbose)
predicted_validation_solutions = models.predict(clf, validation_features, columns)
# Evaluate Predictions
valid_rmse = evaluate.get_errors_clf(clf, validation_features, validation_solutions)
train_rmse = evaluate.get_errors_clf(clf, training_features, training_solutions)
print " Validation RMSE: ", valid_rmse
print " Training RMSE: ", train_rmse
def extract_features(extraction_method, index=None, percent_subset=100, classification=False):
"""Runs the given extraction method on only those galaxys listed in index. Return a subset of
those galaxies.
Attrubutes:
extraction_method: Extraction method to use. See feature_extraction
index: Index of Galaxy for which to process data. If None, process all galaxies.
percent_subset: Returns a subset of the data of this size (percent).
Returns: A Tuple containing (X, y), with X being the features and y the labels.
"""
data = GalaxyData(extraction_method, scale_features=False)
if index is not None:
data.set_restricted_universe(index)
if percent_subset == 100:
(X, y) = data.get_training_data(competition=True)
else:
(X, y, _, _) = data.split_training_and_validation_data(100-percent_subset, competition=True)
y = get_reduced_solutions(y, classification=classification)
return (X, y)