def run_single(train_files_glob, i):
x_train, y_train = gen_vw.read_train_data(train_files_glob, i)
x_test, y_test = gen_vw.read_test_data(train_files_glob, i)
x_valid, y_valid = gen_vw.read_valid_data(train_files_glob, i)
x = T.matrix("x")
y = T.ivector("y")
error = train_batch(x, y, x_train, y_train, x_valid, y_valid, x_test, y_test)
return 1 - error
def run_single(train_files_glob, i):
print '... reading'
sys.stdout.flush()
x_train, y_train = gen_vw.read_train_data(train_files_glob, i)
x_test, y_test = gen_vw.read_test_data(train_files_glob, i)
x_valid, y_valid = gen_vw.read_valid_data(train_files_glob, i)
print '... reading done'
sys.stdout.flush()
x = T.matrix('x')
y = T.ivector('y')
error = train_batch(x, y, x_train, y_train, x_valid, y_valid, x_test, y_test)
return 1 - error
def get_train_files(index):
all_files = glob(train_files_glob)
return all_files[:index] + all_files[index + 1:]
def get_test_files(index):
all_files = glob(train_files_glob)
return [all_files[index]]
def precision(y_test, y_pred):
correct = len(filter(lambda (x, y): x == y, itertools.izip(y_test, y_pred)))
return float(correct) / len(y_test)
if __name__ == '__main__':
X_train, y_train = gen_vw.read_train_data(get_train_files(0))
clf = neighbors.KNeighborsClassifier(5, metric='euclidean')
clf.fit(X_train, y_train)
print 'Fitting done'
X_test, y_test = gen_vw.read_train_data(get_test_files(0))
print 'Testing'
y_pred = clf.predict(X_test)
print precision(y_test, y_pred)
