Hugging Face's logo

A-Funakoshi
/
sample-text-classification-bert

Text Classification
Transformers
PyTorch
bert
Inference Endpoints
Model card Files Community
sample-text-classification-bert
File size: 3,384 Bytes 
5e1810a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
 
# %% [markdown]
# ## Hugging Faceを使って事前学習モデルを日本語の感情分析用にファインチューニングしてみた
# 以下で紹介されているコードを写経したもの 
# https://dev.classmethod.jp/articles/huggingface-jp-text-classification/

# %%
from datasets import load_dataset
from transformers import AutoModelForSequenceClassification, AutoTokenizer
from transformers import TrainingArguments
from transformers import Trainer
from sklearn.metrics import accuracy_score, f1_score
from sklearn.metrics import ConfusionMatrixDisplay, confusion_matrix
import torch
import matplotlib.pyplot as plt
import numpy as np

# %%
print('gpu available:',torch.cuda.is_available())

# %% [markdown]
# ## データセット

# %%
dataset = load_dataset("tyqiangz/multilingual-sentiments", "japanese")

# %%
# データフレームとして扱う
dataset.set_format(type='pandas')
train_df = dataset['train'][:]

# %%
def label_int2str(x):
	return dataset["train"].features["label"].int2str(x)

train_df["label_name"] = train_df["label"].apply(label_int2str)

# %%
dataset.reset_format()

# %%
from transformers import AutoTokenizer

model_ckpt = "cl-tohoku/bert-base-japanese-whole-word-masking"
tokenizer = AutoTokenizer.from_pretrained(model_ckpt)

# %%
def tokenize(batch):
    return tokenizer(batch["text"], padding=True, truncation=True)

# %%
dataset_encoded = dataset.map(tokenize, batched=True, batch_size=None)

# %% [markdown]
# ## モデル

# %%
import torch
from transformers import AutoModelForSequenceClassification

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
num_labels = 3

model = (AutoModelForSequenceClassification
    .from_pretrained(model_ckpt, num_labels=num_labels)
    .to(device))

# %%
from sklearn.metrics import accuracy_score, f1_score

def compute_metrics(pred):
    labels = pred.label_ids
    preds = pred.predictions.argmax(-1)
    f1 = f1_score(labels, preds, average="weighted")
    acc = accuracy_score(labels, preds)
    return {"accuracy": acc, "f1": f1}

# %%
from transformers import TrainingArguments

batch_size = 16
logging_steps = len(dataset_encoded["train"]) // batch_size
model_name = "sample-text-classification-bert"

training_args = TrainingArguments(
    output_dir=model_name,
    num_train_epochs=10,
    learning_rate=2e-5,
    per_device_train_batch_size=batch_size,
    per_device_eval_batch_size=batch_size,
    weight_decay=0.01,
    evaluation_strategy="epoch",
    disable_tqdm=False,
    logging_steps=logging_steps,
    push_to_hub=False,
    log_level="error"
)

# %%
from transformers import Trainer

trainer = Trainer(
    model=model,
    args=training_args,
    compute_metrics=compute_metrics,
    train_dataset=dataset_encoded["train"],
    eval_dataset=dataset_encoded["validation"],
    tokenizer=tokenizer
)
print('start training..')
trainer.train()

# %%
# ラベル情報付与
id2label = {}
for i in range(dataset["train"].features["label"].num_classes):
    id2label[i] = dataset["train"].features["label"].int2str(i)

label2id = {}
for i in range(dataset["train"].features["label"].num_classes):
    label2id[dataset["train"].features["label"].int2str(i)] = i

trainer.model.config.id2label = id2label
trainer.model.config.label2id = label2id

# %%
# 保存
print('save model.')
trainer.save_model('sample-text-classification-bert')