added fine tunning

fine_tuning.py

@@ -0,0 +1,59 @@
+import random
+import torch
+from transformers import (
+    AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer
+)
+
+class DataWrapper(torch.utils.data.Dataset):
+    def __init__(self, encodings, labels):
+        self.encodings = encodings
+        self.labels = labels
+
+    def __getitem__(self, idx):
+        item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()}
+        item['labels'] = torch.tensor(self.labels[idx])
+        return item
+
+    def __len__(self):
+        return len(self.labels)
+
+def read_data(file_path):
+    with open(file_path) as f:
+        return f.readlines()
+
+def wirte_output(file_path, data):
+    with open(file_path,  'w') as writer:
+        for result in trainer.predict(data):
+            writer.write(f"{str(result)}\n")
+
+print("STEP 1 - READ DATA")
+X_train = read_data('train/in.tsv')
+y_train = read_data('train/expected.tsv')
+X_dev = read_data('dev-0/in.tsv')
+X_test = read_data('test-A/in.tsv')
+
+print("STEP 2 - SHUFFLE")
+data_train = list(zip(X_train, y_train))
+data_train = random.sample(data_train, 15000)
+
+
+print("STEP 3 - FINE TUNING")
+tokenizer = AutoTokenizer.from_pretrained("roberta-base")
+
+train_encodings = tokenizer([text[0] for text in data_train], truncation=True, padding=True)
+train_dataset = DataWrapper(train_encodings, [int(text[1]) for text in data_train])
+
+model = AutoModelForSequenceClassification.from_pretrained("roberta-base", num_labels=2)
+args = TrainingArguments("model")
+
+device = torch.device("cpu")
+# device = torch.device("cuda")
+model.to(device)
+
+trainer = Trainer(model=model, args=args, train_dataset=train_dataset)
+trainer.train()
+
+print("STEP 4 - WRITE OUTPUT")
+wirte_output('train/out.tsv', X_train)
+wirte_output('dev-0/out.tsv', X_dev)
+wirte_output('test-A/out.tsv', X_test)

geval_results.txt

@@ -0,0 +1,5 @@
+Likelihood	0.0000
+Accuracy	0.7517
+F1.0	0.6119
+Precision	0.6848
+Recall	0.5531

log_reg.py

@@ -0,0 +1,94 @@
+import numpy as np
+import pandas as pd
+import torch
+import csv
+import gensim.downloader
+import torch
+from nltk import word_tokenize
+
+class NeuralNetwork(torch.nn.Module):
+    def __init__(self, input_size, hidden_size, num_classes):
+        super(NeuralNetwork, self).__init__()
+        self.l1 = torch.nn.Linear(input_size, hidden_size)
+        self.l2 = torch.nn.Linear(hidden_size, num_classes)
+
+    def forward(self, x):
+        x = self.l1(x)
+        x = torch.relu(x)
+        x = self.l2(x)
+        x = torch.sigmoid(x)
+        return x
+
+print('STEP 1 - LOAD DATA')
+names = ['content', 'id', 'label']
+train_data_content = pd.read_table('train/in.tsv', error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, names=names[:2])
+train_data_labels = pd.read_table('train/expected.tsv', error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, names=names[2:])
+dev_data = pd.read_table('dev-0/in.tsv', error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, names=names[:2])
+test_data = pd.read_table('test-A/in.tsv', error_bad_lines=False, header=None, quoting=csv.QUOTE_NONE, names=names[:2])
+
+print('STEP 2 - SET PARAMS')
+hidden_size = int(input('Hidden units size: ') or '600')
+epochs = int(input("Epochs: ") or '5')
+batch_size = int(input("Batch size: ") or '15')
+
+print('STEP 3 - PREPROCESSING')
+# lowercase all content
+X_train = train_data_content['content'].str.lower()
+y_train = train_data_labels['label']
+X_dev = dev_data['content'].str.lower()
+X_test = test_data['content'].str.lower()
+
+# tokenize datasets
+X_train = [word_tokenize(content) for content in X_train]
+X_dev = [word_tokenize(content) for content in X_dev]
+X_test = [word_tokenize(content) for content in X_test]
+
+# use Google word2vec algorithm
+word2vec = gensim.downloader.load('word2vec-google-news-300')
+X_train = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in X_train]
+X_dev = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in X_dev]
+X_test = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in X_test]
+
+print('STEP 4 - MODEL TRAINING')
+#prepare neural model
+
+model = NeuralNetwork(300, hidden_size, 1)
+criterion = torch.nn.BCELoss()
+optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
+
+for epoch in range(epochs):
+    model.train()
+    for i in range(0, y_train.shape[0], batch_size):
+        X = X_train[i:i+batch_size]
+        X = torch.tensor(X)
+        y = y_train[i:i+batch_size]
+        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
+        outputs = model(X.float())
+        loss = criterion(outputs, y)
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+print('STEP 5 - PREDICTION')
+y_dev, y_test = [], []
+model.eval()
+with torch.no_grad():
+    for i in range(0, len(X_dev), batch_size):
+        X = X_dev[i:i+batch_size]
+        X = torch.tensor(X)
+        outputs = model(X.float())
+        prediction = (outputs > 0.5)
+        y_dev += prediction.tolist()
+    for i in range(0, len(X_test), batch_size):
+        X = X_test[i:i+batch_size]
+        X = torch.tensor(X)
+        outputs = model(X.float())
+        y = (outputs > 0.5)
+        y_test += prediction.tolist()
+
+print('STEP 6 - EXPORT RESULTS')
+# export results to tsv
+y_dev = np.asarray(y_dev, dtype=np.int32)
+y_test = np.asarray(y_test, dtype=np.int32)
+y_dev.tofile('./dev-0/out.tsv', sep='\n')
+y_test.tofile('./test-A/out.tsv', sep='\n')

output_geval_fine.txt

@@ -0,0 +1,5 @@
+Likelihood	0.0000
+Accuracy	0.8253
+F1.0	0.7472
+Precision	0.7659
+Recall	0.7294