def sentence_prediction(sentence):
sentence = preprocess(sentence)
model_path = config.MODEL_PATH
test_dataset = dataset.BERTDataset(
review=[sentence],
target=[0]
)
test_data_loader = torch.utils.data.DataLoader(
test_dataset,
batch_size=config.VALID_BATCH_SIZE,
num_workers=3
)
device = config.device
model = BERTBaseUncased()
model.load_state_dict(torch.load(
model_path, map_location=torch.device(device)))
model.to(device)
outputs, [] = engine.predict_fn(test_data_loader, model, device)
print(outputs)
return outputs[0]
def main(_):
input = config.EVAL_PROC
output = 'predictions.csv'
model_path = config.MODEL_PATH
if FLAGS.input:
input = FLAGS.input
if FLAGS.output:
output = FLAGS.input
if FLAGS.model_path:
model_path = FLAGS.model_path
df_test = pd.read_fwf(input)
logger.info(f"Bert Model: {config.BERT_PATH}")
logger.info(
f"Current date and time :{datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')} "
)
logger.info(f"Test file: {input}")
logger.info(f"Test size : {len(df_test):.4f}")
trg = []
for i in range(len(df_test.values)):
trg.append(0)
test_dataset = dataset.BERTDataset(text=df_test.values, target=trg)
test_data_loader = torch.utils.data.DataLoader(
test_dataset, batch_size=config.VALID_BATCH_SIZE, num_workers=3)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = BERTBaseUncased(config.DROPOUT)
model.load_state_dict(
torch.load(model_path, map_location=torch.device(device)))
model.to(device)
outputs, extracted_features = engine.predict_fn(
test_data_loader, model, device, extract_features=FLAGS.features)
df_test["predicted"] = outputs
# save file
df_test.to_csv(output, header=None, index=False)
def main(_):
test_file = config.EVAL_PROC
model_path = config.MODEL_PATH
if FLAGS.test_file:
test_file = FLAGS.test_file
if FLAGS.model_path:
model_path = FLAGS.model_path
df_test = pd.read_csv(test_file).fillna("none")
logger.info(f"Bert Model: {config.BERT_PATH}")
logger.info(
f"Current date and time :{datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')} "
)
logger.info(f"Test file: {test_file}")
logger.info(f"Test size : {len(df_test):.4f}")
test_dataset = dataset.BERTDataset(review=df_test.text.values,
target=df_test.label.values)
test_data_loader = torch.utils.data.DataLoader(
test_dataset, batch_size=config.VALID_BATCH_SIZE, num_workers=3)
device = config.device
model = BERTBaseUncased()
model.load_state_dict(
torch.load(model_path, map_location=torch.device(device)))
model.to(device)
outputs, extracted_features = engine.predict_fn(
test_data_loader, model, device, extract_features=FLAGS.features)
df_test["predicted"] = outputs
# save file
df_test.to_csv(model_path.split("/")[-2] + '.csv',
header=None,
index=False)
if FLAGS.features:
pca = PCA(n_components=50, random_state=7)
X1 = pca.fit_transform(extracted_features)
tsne = TSNE(n_components=2,
perplexity=10,
random_state=6,
learning_rate=1000,
n_iter=1500)
X1 = tsne.fit_transform(X1)
# if row == 0: print("Shape after t-SNE: ", X1.shape)
X = pd.DataFrame(np.concatenate([X1], axis=1), columns=["x1", "y1"])
X = X.astype({"x1": float, "y1": float})
# Plot for layer -1
plt.figure(figsize=(20, 15))
p1 = sns.scatterplot(x=X["x1"], y=X["y1"], palette="coolwarm")
# p1.set_title("development-"+str(row+1)+", layer -1")
x_texts = []
for output, value in zip(outputs, df_test.label.values):
if output == value:
x_texts.append("@" + label_decoder(output)[0] +
label_decoder(output))
else:
x_texts.append(
label_decoder(value) + "-" + label_decoder(output))
X["texts"] = x_texts
# X["texts"] = ["@G" + label_decoder(output) if output == value else "@R-" + label_decoder(value) + "-" + label_decoder(output)
# for output, value in zip(outputs, df_test.label.values)]
# df_test.label.astype(str)
#([str(output)+"-" + str(value)] for output, value in zip(outputs, df_test.label.values))
# Label each datapoint with the word it corresponds to
for line in X.index:
text = X.loc[line, "texts"] + "-" + str(line)
if "@U" in text:
p1.text(X.loc[line, "x1"] + 0.2,
X.loc[line, "y1"],
text[2:],
horizontalalignment='left',
size='medium',
color='blue',
weight='semibold')
elif "@P" in text:
p1.text(X.loc[line, "x1"] + 0.2,
X.loc[line, "y1"],
text[2:],
horizontalalignment='left',
size='medium',
color='green',
weight='semibold')
elif "@N" in text:
p1.text(X.loc[line, "x1"] + 0.2,
X.loc[line, "y1"],
text[2:],
horizontalalignment='left',
size='medium',
color='red',
weight='semibold')
else:
p1.text(X.loc[line, "x1"] + 0.2,
X.loc[line, "y1"],
text,
horizontalalignment='left',
size='medium',
color='black',
weight='semibold')
plt.show()
plt.savefig(model_path.split("/")[-2] + '-figure.svg', format="svg")