File size: 2,580 Bytes
8b412c5 | 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 69 70 71 72 73 74 75 76 77 78 79 80 81 | import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from transformers import DistilBertTokenizerFast, DistilBertForSequenceClassification, Trainer, TrainingArguments
import torch
from datasets import Dataset
# 1. Load and clean data
df = pd.read_csv("/Users/milanradovanovich/Downloads/twitter_training.csv/twitter_training.csv", header=None)
df.columns = ['tweet_id', 'topic', 'sentiment', 'text']
df.dropna(subset=['text', 'sentiment'], inplace=True)
df['sentiment'] = df['sentiment'].str.strip().str.lower()
# 2. Encode sentiment labels
label_map = {'positive': 0, 'negative': 1, 'neutral': 2, 'irrelevant': 3}
df['label'] = df['sentiment'].map(label_map)
# 3. Split into train and validation
train_texts, val_texts, train_labels, val_labels = train_test_split(
df['text'].tolist(),
df['label'].tolist(),
test_size=0.1,
stratify=df['label'],
random_state=42
)
# 4. Tokenize
tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased')
train_encodings = tokenizer(train_texts, truncation=True, padding=True, max_length=128)
val_encodings = tokenizer(val_texts, truncation=True, padding=True, max_length=128)
# 5. Build Dataset class
class SentimentDataset(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)
train_dataset = SentimentDataset(train_encodings, train_labels)
val_dataset = SentimentDataset(val_encodings, val_labels)
# 6. Load model
model = DistilBertForSequenceClassification.from_pretrained(
"distilbert-base-uncased", num_labels=4
)
# 7. Training config
training_args = TrainingArguments(
output_dir="./model_output",
evaluation_strategy="epoch",
save_strategy="epoch",
learning_rate=2e-5,
per_device_train_batch_size=16,
per_device_eval_batch_size=16,
num_train_epochs=3,
weight_decay=0.01,
logging_dir='./logs',
logging_steps=50,
)
# 8. Train
trainer = Trainer(
model=model,
args=training_args,
train_dataset=train_dataset,
eval_dataset=val_dataset,
)
trainer.train()
# 9. Save model and tokenizer
model.save_pretrained("./sentiment_model")
tokenizer.save_pretrained("./sentiment_model")
print(" Training complete and model saved to ./sentiment_model") |