print("a")
np.set_printoptions(suppress=True)
print("b")
xy, y_score = load_data(config["task"])
print("c1")
#y_score, best_score = normalize(y_score)
print("c2")
model, i, modelhistory = best_feedforward_model(xy, y_score, True)
print("d")
print("We take:")
print(i)
print("Best score for normalization scale:")
#print(best_score)
WineData = BaseData('data/winequality-red.csv',
';',
11,
10,
config["nr_base_columns"],
rifs=True)
WineData.load()
_ = evaluation_wrapper(config["task"], model, 'data/winequality-red.csv', True,
WineData)
def evaluation_wrapper(task, model, _path, _print, eval_dataset):
if task == Task.multivariate_time_series:
BirthDeaths3 = BaseData(_path,
';',
3,
1,
base_size=config["nr_base_columns"])
BirthDeaths3.load()
evaluations = evaluation(BirthDeaths3.base_xy, add_eval_columns,
eval_dataset.base_dataset[:, 11], model)
if task == Task.regression:
def get_wine_column():
content = open('data/wineexport.csv').read().split("\n")
values = list(map(lambda line: line.split(";")[1], content))
return np.array(values).astype(float)
wc = get_wine_column()
import pdb
pdb.set_trace()
if config["budget_join"]:
add_eval_columns = [
eval_dataset.base_dataset[:, 0],
eval_dataset.base_dataset[:, 1],
eval_dataset.base_dataset[:, 2],
eval_dataset.base_dataset[:, 3],
eval_dataset.base_dataset[:, 11],
]
for i in np.arange(config["nr_add_columns_budget"] -
len(add_eval_columns)):
add_eval_columns.append(
np.random.normal(0, 1, eval_dataset.base_dataset[:,
0].shape))
#add_eval_columns.append(np.ones(eval_dataset.base_dataset[:, 0].shape))
else:
add_eval_columns = [eval_dataset.base_dataset[:, 0]]
import pdb
pdb.set_trace()
evaluations = evaluation(
eval_dataset.base_xy, #5
add_eval_columns, #1200
eval_dataset.base_dataset[:, 11], #
model #model
)
import pdb
pdb.set_trace()
import pdb
pdb.set_trace()
import pdb
pdb.set_trace()
#plot_performance([evaluations[1]], [evaluations[3]])
regr = linear_model.LinearRegression()
regr.fit(eval_dataset.base_x, eval_dataset.base_y)
regression_score_base_data = regr.score(eval_dataset.base_x,
eval_dataset.base_y)
indices = np.where(evaluations[0] > config["nfs_output_threshold"])
regr = linear_model.LinearRegression()
add_columns = np.array(list(map(lambda c: c[0],
eval_dataset.add_columns)))[indices[0], :]
augmented_x = np.transpose(
np.concatenate((np.transpose(eval_dataset.base_x,
(1, 0)), add_columns),
axis=0), (1, 0))
regr.fit(augmented_x, eval_dataset.base_y)
regression_score_augmented = regr.score(augmented_x, eval_dataset.base_y)
output = ""
output += "Path: " + str(_path)
output += "\nBase DataSet size: " + str(eval_dataset.base_x.shape)
output += "\nScore for Base DataSet: " + str(regression_score_base_data)
output += "\nColumns presented to NFS: " + str(
config["nr_add_columns_budget"])
output += "\nColumns chosen by NFS by threshold: " + str(len(indices[0]))
output += "\nAugmented DataSet size: " + str(augmented_x.shape)
output += "\nScore for Augmented DataSet: " + str(
regression_score_augmented)
output += "\nNFS Time: " + str(evaluations[1])
output += "\nPearson Time: " + str(evaluations[3])
output += "\nConfig: " + str(config)
f = open("output/" + str(time.time()).split(".")[0] + ".txt", "a")
f.write(output)
f.close()
return _path, evaluations, regression_score_base_data, regression_score_augmented