def competition_run():
data = GalaxyData()
(training_features, training_solutions) = data.get_training_data()
(test_features, _) = data.get_test_data()
# Predict
(clf, columns) = models.default_model(training_features, training_solutions, 5)
predicted_solutions = models.predict(clf, test_features, columns)
data.save_solution(predicted_solutions)
def run_training_test(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.raw_9, scale_features=False)
(test_features, test_solutions) = data.get_test_data()
(training_features, training_solutions) = data.get_training_data()
# Train and Predict Model
(clf, columns) = model(training_features, training_solutions, verbose)
predicted_solutions = models.predict(clf, test_features, columns)
# Evaluate Predictions
score = evaluate.get_rmse(test_solutions, predicted_solutions)
print(score)
import numpy as np from evaluate import cross_validate from galaxy_data import GalaxyData from sklearn import (ensemble, cross_validation) data = GalaxyData(scale_features=False) (X_train, y_train) = data.get_training_data() (X_test, y_test) = data.get_test_data() clf = ensemble.RandomForestRegressor(n_estimators=1, n_jobs=-1, verbose=5) scores = cross_validate(clf, X_train, y_train, 2) mean_score = sum(scores) / float(scores.shape[0]) print(scores) print(mean_score)