"maxspeed_entry",
"vehicle_speed_entry",
"vehicle_speed_exit",
"curvature_exit",
"oneway_exit",
"lane_count_entry",
"has_right_of_way",
"curvature_entry"
]
mse_mean = np.array([])
mse_std = np.array([])
n_est_hist = np.array([])
samples = automatic_test.load_samples('../data/training_data/samples.pickle')
samples = automatic_test.normalize_features(samples)
train_sample_sets, test_sample_sets = automatic_test.get_cross_validation_samples(samples, 0.8, 5)
for n_est in range(1,40, 2):
rf_algo = regressors.RandomForestAlgorithm(feature_list, n_estimators = n_est)
results = automatic_test.test([rf_algo], train_sample_sets, test_sample_sets, cross_validation=True)
result_statistics = automatic_test.get_result_statistics(results)
mse_mean = np.append(mse_mean, result_statistics[rf_algo]['average_mse'])
mse_std = np.append(mse_std, result_statistics[rf_algo]['std_mse'])
n_est_hist = np.append(n_est_hist, n_est)
# Plot the results
plt.hold(True)
plt.plot(n_est_hist, mse_mean)
plt.plot(n_est_hist, mse_mean + mse_std, 'r-')
plt.plot(n_est_hist, mse_mean - mse_std, 'r-')
plt.xlabel('n_estimators')
plt.ylabel('average_mse')
plt.show()
N_tests = 10
training_samples_steps = np.arange(10, N_training_samples+1, 10)
all_training_errors = []
all_cv_errors = []
all_training_samples_sizes = []
for test_i in range(N_tests):
print "====== Test number %d ======" % test_i
random.shuffle(samples)
cv_samples = samples[N_training_samples:]
for training_samples_size in training_samples_steps:
print "Training samples size:", training_samples_size
training_samples = samples[:training_samples_size]
automatic_test.train([rf_algo], training_samples)
rs_train = automatic_test.get_result_statistics(automatic_test.predict([rf_algo], training_samples))
rs_cv = automatic_test.get_result_statistics(automatic_test.predict([rf_algo], cv_samples))
all_training_samples_sizes.append(training_samples_size)
all_training_errors.append(rs_train[rf_algo]['mean_mse'])
all_cv_errors.append(rs_cv[rf_algo]['mean_mse'])
training_errors = []
cv_errors = []
training_samples_sizes = []
# Flatten the results
for training_samples_size in training_samples_steps:
indices = [i for i,x in enumerate(all_training_samples_sizes) if x == training_samples_size]
training_samples_sizes.append(training_samples_size)
