def test_batch(self):
filepaths = self.filepaths_file_1
gene = iter(get_h5_generator(self.orga, filepaths))
target_xs_batch_1 = {
"input_A": self.train_A_file_1_ctnt[0][:2],
"input_B": self.train_B_file_1_ctnt[0][:2],
}
target_ys_batch_1 = label_modifier(
{"y_values": self.train_A_file_1_ctnt[1][:2]})
target_xs_batch_2 = {
"input_A": self.train_A_file_1_ctnt[0][2:4],
"input_B": self.train_B_file_1_ctnt[0][2:4],
}
target_ys_batch_2 = label_modifier(
{"y_values": self.train_A_file_1_ctnt[1][2:4]})
xs, ys = next(gene)
assert_dict_arrays_equal(xs, target_xs_batch_1)
assert_dict_arrays_equal(ys, target_ys_batch_1)
xs, ys = next(gene)
assert_dict_arrays_equal(xs, target_xs_batch_2)
assert_dict_arrays_equal(ys, target_ys_batch_2)
with self.assertRaises(StopIteration):
next(gene)
def test_batch_sample_modifier(self):
filepaths = self.filepaths_file_1
def sample_modifier(info_blob):
xs_in = info_blob["x_values"]
mod = {name: val * 2 for name, val in xs_in.items()}
return mod
self.orga.cfg.sample_modifier = sample_modifier
gene = iter(get_h5_generator(self.orga, filepaths))
target_xs_batch_1 = {
"input_A": self.train_A_file_1_ctnt[0][:2] * 2,
"input_B": self.train_B_file_1_ctnt[0][:2] * 2,
}
target_ys_batch_1 = label_modifier(
{"y_values": self.train_A_file_1_ctnt[1][:2]})
target_xs_batch_2 = {
"input_A": self.train_A_file_1_ctnt[0][2:4] * 2,
"input_B": self.train_B_file_1_ctnt[0][2:4] * 2,
}
target_ys_batch_2 = label_modifier(
{"y_values": self.train_A_file_1_ctnt[1][2:4]})
xs, ys = next(gene)
assert_dict_arrays_equal(xs, target_xs_batch_1)
assert_dict_arrays_equal(ys, target_ys_batch_1)
xs, ys = next(gene)
assert_dict_arrays_equal(xs, target_xs_batch_2)
assert_dict_arrays_equal(ys, target_ys_batch_2)
def test_batch_mc_infos(self):
filepaths = self.filepaths_file_1
gene = iter(get_h5_generator(self.orga, filepaths, keras_mode=False))
target_xs_batch_1 = {
"input_A": self.train_A_file_1_ctnt[0][:2],
"input_B": self.train_B_file_1_ctnt[0][:2],
}
target_ys_batch_1 = label_modifier(
{"y_values": self.train_A_file_1_ctnt[1][:2]})
target_mc_info_batch_1 = self.train_A_file_1_ctnt[1][:2]
target_xs_batch_2 = {
"input_A": self.train_A_file_1_ctnt[0][2:4],
"input_B": self.train_B_file_1_ctnt[0][2:4],
}
target_ys_batch_2 = label_modifier(
{"y_values": self.train_A_file_1_ctnt[1][2:4]})
target_mc_info_batch_2 = self.train_A_file_1_ctnt[1][2:4]
info_blob = next(gene)
assert_dict_arrays_equal(info_blob["xs"], target_xs_batch_1)
assert_dict_arrays_equal(info_blob["ys"], target_ys_batch_1)
assert_equal_struc_array(info_blob["y_values"], target_mc_info_batch_1)
info_blob = next(gene)
assert_dict_arrays_equal(info_blob["xs"], target_xs_batch_2)
assert_dict_arrays_equal(info_blob["ys"], target_ys_batch_2)
assert_equal_struc_array(info_blob["y_values"], target_mc_info_batch_2)
def test_batch_zero_center(self):
filepaths = self.filepaths_file_1
xs_mean = {name: np.ones(shape) * 0.5 for name, shape in self.n_bins.items()}
self.orga.get_xs_mean = MagicMock(return_value=xs_mean)
gene = iter(get_h5_generator(self.orga, filepaths, zero_center=True))
target_xs_batch_1 = {
"input_A": np.subtract(self.train_A_file_1_ctnt[0][:2], xs_mean["input_A"]),
"input_B": np.subtract(self.train_B_file_1_ctnt[0][:2], xs_mean["input_B"]),
}
target_ys_batch_1 = label_modifier({"y_values": self.train_A_file_1_ctnt[1][:2]})
target_xs_batch_2 = {
"input_A": np.subtract(self.train_A_file_1_ctnt[0][2:], xs_mean["input_A"]),
"input_B": np.subtract(self.train_B_file_1_ctnt[0][2:], xs_mean["input_B"]),
}
target_ys_batch_2 = label_modifier({"y_values": self.train_A_file_1_ctnt[1][2:]})
xs, ys = next(gene)
assert_dict_arrays_equal(xs, target_xs_batch_1)
assert_dict_arrays_equal(ys, target_ys_batch_1)
xs, ys = next(gene)
assert_dict_arrays_equal(xs, target_xs_batch_2)
assert_dict_arrays_equal(ys, target_ys_batch_2)