def acc(net: NeuralNet, ds: Dataset, y: torch.Tensor) -> float:
predict_values = net.predict(ds)
return acc_as_metric(predict_values, y)
def run():
parser = get_arg_parser()
cmd_args = parser.parse_args()
if cmd_args.gpu is not None:
os.environ['CUDA_VISIBLE_DEVICES'] = str(cmd_args.gpu)
gpunum = os.getenv('CUDA_VISIBLE_DEVICES')
logging.info("GPU has been set to {}".format(gpunum))
logging.info("Model used for the regression network: {}"
.format(cmd_args.model_name))
# 1. Dataset retrieval
# --------------------
tab_printer(constants.Dataset)
dataset = Dataset(nrows=constants.Dataset.nrows,
augment_labels=constants.Dataset.augment_labels,
top_n=constants.Dataset.top_n)
logging.info("Going to create vocabulary and fit a preprocessing pipeline"
"using {} samples. Settings will be listed below"
.format(len(dataset.X_train)))
# 2. Preprocessing
# -----------------
tab_printer(constants.NLP)
preprocessor = Preprocessing(dataset.X_train)
# Preprocess documents
X_train = preprocessor.transform_documents(dataset.X_train)
X_test = preprocessor.transform_documents(dataset.X_test)
# 3. Word embeddings with word2vec
# --------------------------------
# Train word2vec embeddings if train_word2vec option is selected
if cmd_args.train_word2vec: utils.embeddings.main()
weights = get_embedding_tensor(preprocessor)
# 4. Node embeddings with AttentionWalk
# -------------------------------------
args = _generate_deepwalk_parameters(dataset.y_train_graph)
if cmd_args.train_attentionwalk: train_attention_walk(args)
graph_embeddings = pd.read_csv(args.embedding_path).iloc[:, 1:].values
# Get document representations using node embeddings
y_embedded = _get_label_embeddings(dataset.y_train, graph_embeddings)
y_test_embedded = _get_label_embeddings(dataset.y_test, graph_embeddings)
# 5. Regressor Training
# ---------------------
device = 'cuda:' + str(os.getenv("CUDA_VISIBLE_DEVICES")) \
if torch.cuda.is_available() else 'cpu'
regressor_nn = NeuralNet(
get_network_class(cmd_args.model_name),
max_epochs=constants.NeuralNetworkTraining.epochs,
lr=constants.NeuralNetworkTraining.learning_rate,
batch_size=constants.NeuralNetworkTraining.batch_size,
optimizer=torch.optim.Adam,
criterion=torch.nn.MSELoss,
module__output_dim=args.dimensions,
module__embedding=weights,
module__embedding_dim=constants.NLP.embedding_size,
device=device,
train_split=None,
)
# Train the regressor neural network
regressor_nn.fit(X_train, y_embedded.astype(np.float32))
# 6. Train Multi-label KNN algorithm
# ----------------------------------
tab_printer(constants.MLKNN)
# Train multi-label KNN to turn label embeddings into label predictions
classifier = MLkNN(k=constants.MLKNN.k, s=constants.MLKNN.s)
classifier.fit(y_embedded, dataset.y_train)
# 7. Evaluation
# -------------
# Label prediction with documents
y_test_pred = regressor_nn.predict(X_test)
preds = classifier.predict(y_test_pred)
preds_raw = classifier.predict_proba(y_test_pred)
# Label prediction with label embeddings
preds_w_labels = classifier.predict(y_test_embedded)
preds_w_labels_raw = classifier.predict_proba(y_test_embedded)
# Log evaluation result with label embeddings
eval_metrics_w_labels = evaluation \
.all_metrics(preds_w_labels.toarray(),
dataset.y_test,
yhat_raw=preds_w_labels_raw.toarray())
logging.info(str(eval_metrics_w_labels))
# Log evaluation result with documents
report_evaluation(preds.toarray(),
dataset.y_test,
yhat_raw=preds_raw.toarray())
#%% Fit the model
io = net.fit(WD)
# Save model
net.save_params(f_params='models/baselineNN.pkl')
#%% Or load it from disk
net.initialize()
net.load_params(f_params="models/baselineNN.pkl")
#%% Predict on train
# Out
yhat = net.predict(WD)
# Classes
yhatc = yhat.argmax(axis=1)
# True labels
ytrue = WD.y
(ytrue == yhatc).sum() / yhatc.size
# Classification report
from sklearn import metrics
print(
metrics.classification_report(ytrue,
yhatc,
target_names=list(category_map.values())))
metrics.confusion_matrix(ytrue, yhatc)
#%% Predict on test