from src.bin import statistics
from src.data_manager import cross_val
from src.models.multitask_learning import multitask_autoencoder
from src.utils.read_utils import read_pickle
feature_list = data_manager.FEATURE_LIST
# ##### Pickle #####
data_file_path = os.path.join(
definitions.DATA_DIR, 'training_data/shuffled_splits',
'training_date_normalized_shuffled_splits_select_features_no_prev_stress_2.pkl'
)
data = read_pickle(data_file_path)
############ Stats #############
print(statistics.get_train_test_val_label_counts_from_raw_data(data))
################################## Init ##################################
use_historgram = True
autoencoder_bottle_neck_feature_size = 128
autoencoder_num_layers = 1
alpha, beta = 0.001, 1
decay = 0.0001
first_key = next(iter(data['data'].keys()))
if use_historgram:
num_features = len(data['data'][first_key][4][0])
else:
num_features = len(data['data'][first_key][0][0])
num_covariates = len(data['data'][first_key][definitions.COVARIATE_DATA_IDX])
shared_hidden_layer_size = 256
user_dense_layer_hidden_size = 64
def search_multitask_auto_encoder(hyper_parameters_list, data: dict):
splits = cross_val.get_k_fod_cross_val_splits_stratified_by_students(data)
student_list = conversions.extract_distinct_student_idsfrom_keys(
data['data'].keys())
tensorified_data = tensorify.tensorify_data_gru_d(
copy.deepcopy(data), torch.cuda.is_available())
final_scores_for_each_config = []
print("Label Distribution")
print(statistics.get_train_test_val_label_counts_from_raw_data(data))
for model_params_no, model_params in enumerate(hyper_parameters_list):
print(
"###################### Param Config No: {} ########################"
.format(model_params_no))
print("Params: ", model_params)
(use_histogram, autoencoder_bottle_neck_feature_size,
autoencoder_num_layers, alpha, beta, decay, num_features,
num_covariates, shared_hidden_layer_size,
user_dense_layer_hidden_size, num_classes, learning_rate, n_epochs,
shared_layer_dropout_prob, user_head_dropout_prob, class_weights,
device) = helper.get_params_from_model(model_params, data)
best_val_scores = []
for split_no, split in enumerate(splits):
print("Split {}".format(split_no))
best_split_score = -1
tensorified_data['train_ids'] = split["train_ids"]
tensorified_data['val_ids'] = split["val_ids"]
tensorified_data['test_ids'] = []
model, reconstruction_criterion, classification_criterion, optimizer = helper.init_multitask_autoencoder_learner(
num_features, autoencoder_bottle_neck_feature_size,
autoencoder_num_layers, shared_hidden_layer_size,
user_dense_layer_hidden_size, num_classes, num_covariates,
shared_layer_dropout_prob, user_head_dropout_prob,
learning_rate, decay, class_weights, student_list)
total_loss_over_epochs, scores_over_epochs = plotting.get_empty_stat_over_n_epoch_dictionaries(
)
reconstruction_loss_over_epochs = copy.deepcopy(
total_loss_over_epochs)
classification_loss_over_epochs = copy.deepcopy(
total_loss_over_epochs)
for epoch in tqdm.tqdm(range(n_epochs)):
(train_total_loss, train_total_reconstruction_loss,
train_total_classification_loss, train_labels, train_preds,
train_users), (val_total_loss, val_total_reconstruction_loss,
val_total_classification_loss, val_labels,
val_preds,
val_users) = helper.train_for_one_epoch(
tensorified_data, num_classes, model,
reconstruction_criterion,
classification_criterion, device,
optimizer, alpha, beta, use_histogram)
######## Appending losses ########
total_loss_over_epochs['train_loss'].append(train_total_loss)
total_loss_over_epochs['val_loss'].append(val_total_loss)
reconstruction_loss_over_epochs['train_loss'].append(
train_total_reconstruction_loss)
reconstruction_loss_over_epochs['val_loss'].append(
val_total_reconstruction_loss)
classification_loss_over_epochs['train_loss'].append(
train_total_classification_loss)
classification_loss_over_epochs['val_loss'].append(
val_total_classification_loss)
######## Appending Metrics ########
train_label_list = conversions.tensor_list_to_int_list(
train_labels)
train_pred_list = conversions.tensor_list_to_int_list(
train_preds)
val_label_list = conversions.tensor_list_to_int_list(
val_labels)
val_pred_list = conversions.tensor_list_to_int_list(val_preds)
train_scores = metrics.precision_recall_fscore_support(
train_label_list, train_pred_list,
average='weighted')[F_SCORE_INDEX]
val_scores = metrics.precision_recall_fscore_support(
val_label_list, val_pred_list,
average='weighted')[F_SCORE_INDEX]
scores_over_epochs['train_scores'].append(train_scores)
scores_over_epochs['val_scores'].append(val_scores)
if val_scores > best_split_score:
best_split_score = val_scores
best_val_scores.append(best_split_score)
avg_val_score = list_mean(best_val_scores)
final_scores_for_each_config.append((avg_val_score, model_params))
print("Average score for current configuration: {}".format(
avg_val_score))
grid_search_details_file_path = os.path.join(definitions.DATA_DIR,
"grid_search_details.pkl")
write_utils.data_structure_to_pickle(final_scores_for_each_config,
grid_search_details_file_path)