Spaces:
Sleeping
Sleeping
File size: 2,789 Bytes
c59cf35 9b3af2e c59cf35 |
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 82 |
# from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
# import torch
# import torch.nn.functional as F
# model_name = "andyqin18/test-finetuned"
# model = AutoModelForSequenceClassification.from_pretrained(model_name)
# tokenizer = AutoTokenizer.from_pretrained(model_name)
# classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
# res = classifier(["Fuck your mom",
# "Hope you don't hate it"])
# for result in res:
# print(result)
import pandas as pd
from sklearn.model_selection import train_test_split
import torch
from torch.utils.data import Dataset
from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer
device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
import numpy as np
df = pd.read_csv("comp/train.csv")
train_texts = df["comment_text"].values
train_labels = df[df.columns[2:]].values
# print(train_labels[0])
# np.random.seed(123)
# small_train_texts = np.random.choice(train_texts, size=1000, replace=False)
# small_train_labels_idx = np.random.choice(train_labels.shape[0], size=1000, replace=False)
# small_train_labels = train_labels[small_train_labels_idx, :]
# train_texts, val_texts, train_labels, val_labels = train_test_split(small_train_texts, small_train_labels, test_size=.2)
train_texts, val_texts, train_labels, val_labels = train_test_split(train_texts, train_labels, test_size=.2)
class TextDataset(Dataset):
def __init__(self,texts,labels):
self.texts = texts
self.labels = labels
def __getitem__(self,idx):
encodings = tokenizer(self.texts[idx], truncation=True, padding="max_length")
item = {key: torch.tensor(val) for key, val in encodings.items()}
item['labels'] = torch.tensor(self.labels[idx],dtype=torch.float32)
del encodings
return item
def __len__(self):
return len(self.labels)
tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
train_dataset = TextDataset(train_texts,train_labels)
val_dataset = TextDataset(val_texts, val_labels)
# small_train_dataset = train_dataset.shuffle(seed=42).select(range(1000))
# small_val_dataset = val_dataset.shuffle(seed=42).select(range(1000))
model = AutoModelForSequenceClassification.from_pretrained("bert-base-uncased", num_labels=6, problem_type="multi_label_classification")
model.to(device)
training_args = TrainingArguments(
output_dir="finetuned-bert-uncased",
per_device_train_batch_size=16,
per_device_eval_batch_size=64,
learning_rate=5e-4,
weight_decay=0.01,
evaluation_strategy="epoch",
push_to_hub=True)
trainer = Trainer(
model=model,
args=training_args,
train_dataset=train_dataset,
eval_dataset=val_dataset,
)
trainer.train() |