def get_test_examples():
global test_X
global test_y
if not test_X:
print "Loading test examples"
_log_time()
test_examples = music.load_examples("data/test_40k_10k.pkl")
_print_time_diff()
print "Obtaining X and y values"
_log_time()
test_X = [model.represent(example) for example in test_examples]
_print_time_diff()
_log_time()
test_y = [model.label(example) for example in test_examples]
_print_time_diff()
return test_X, test_y
clf.fit(X, y)
def predict(examples):
X = [represent(example) for example in examples]
y = clf.predict(X)
return y
import math
from sklearn.metrics import mean_squared_error
def rmse(y_true, y_pred):
mse = mean_squared_error(y_true, y_pred)
return math.sqrt(mse)
from sklearn.cross_validation import cross_val_score
def validate(examples):
X = [represent(example) for example in examples]
y = [label(example) for example in examples]
scores = cross_val_score(clf, X, y, cv=2, score_func=rmse)
return scores
if __name__ == "__main__":
import music
train_examples = music.load_examples('data/train.pkl')
import sys
if len(sys.argv) > 1:
clf.set_params(n_estimators = int(sys.argv[1]))
scores = validate(train_examples)
print "RMSE: %0.6f (+/- %0.6f)" % (scores.mean(), scores.std()/2)
print "Readying training data"
_log_time()
music.ready_training_data(should_use_full_ds)
_print_time_diff()
_draw_separator()
print "Readying testing data"
_log_time()
music.ready_testing_data()
_print_time_diff()
_draw_separator()
print "Start loading examples"
_log_time()
examples = music.load_examples("data/train.pkl")
_print_time_diff()
_draw_separator()
print "Obtaining all x and y values"
_log_time()
all_X = [model.represent(example) for example in examples]
_print_time_diff()
_log_time()
all_y = [model.label(example) for example in examples]
_print_time_diff()
_draw_separator()
def print_consolidated_scores(scores):
_draw_separator(".", 5)