File size: 2,115 Bytes
db17981 c7b4b03 6b81bf3 c7b4b03 6b81bf3 c7b4b03 020c9d7 c7b4b03 020c9d7 c7b4b03 253a4f3 c7b4b03 6b81bf3 c7b4b03 db17981 c7b4b03 db17981 c7b4b03 db17981 2425ef6 fcc1aa7 253a4f3 db17981 253a4f3 c7b4b03 db17981 c7b4b03 db17981 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
from transformers import BertTokenizer, BertForSequenceClassification, Trainer, TrainingArguments
import numpy as np
import pandas as pd
from datasets import Dataset
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_recall_fscore_support
# Load dataset
df = pd.read_csv("AI_Human.csv")
train_df, eval_df = train_test_split(df, test_size=0.2)
# Tokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
def tokenize_function(examples):
return tokenizer(examples["text"], padding="max_length", truncation=True, max_length=512)
# Convert DataFrames to Datasets and apply tokenization
train_dataset = Dataset.from_pandas(train_df)
eval_dataset = Dataset.from_pandas(eval_df)
train_dataset = train_dataset.map(tokenize_function, batched=True)
train_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])
eval_dataset = eval_dataset.map(tokenize_function, batched=True)
eval_dataset.set_format(type='torch', columns=['input_ids', 'attention_mask', 'labels'])
# Model
model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2)
# Training Arguments
training_args = TrainingArguments(
output_dir="./results",
num_train_epochs=3,
per_device_train_batch_size=8,
per_device_eval_batch_size=8,
warmup_steps=500,
weight_decay=0.01,
logging_dir='./logs',
evaluation_strategy="steps",
save_steps=500,
logging_steps=100,
)
def compute_metrics(pred):
labels = pred.label_ids
preds = np.argmax(pred.predictions, axis=-1)
precision, recall, f1, _ = precision_recall_fscore_support(labels, preds, average='binary')
acc = accuracy_score(labels, preds)
return {
'accuracy': acc,
'f1': f1,
'precision': precision,
'recall': recall
}
trainer = Trainer(
model=model,
args=training_args,
train_dataset=train_dataset,
eval_dataset=eval_dataset,
compute_metrics=compute_metrics
)
trainer.train()
model.save_pretrained("./trained_model")
tokenizer.save_pretrained("./trained_model")
|