Pythonで認知バイアスタグ付けのためのミニトランスフォーマーを微調整する

pip install transformers datasets pandas scikit-learn torch

text,all_or_nothing,overgeneralization,mental_filter,disqualifying_the_positive,jumping_to_conclusions,magnification_minimization,emotional_reasoning,should_statements,labeling,personalization
"I completely failed the exam. I'm a total idiot.",1,0,0,0,0,0,0,0,1,0
"She didn't text back, she must be mad at me.",0,0,0,0,1,0,0,0,0,0
"I always ruin everything.",0,1,0,0,0,0,0,0,0,0
"I got a promotion, but it was just luck.",0,0,0,1,0,0,0,0,0,0
"I feel anxious, so something terrible must be about to happen.",0,0,0,0,0,0,1,0,0,0
"He only pointed out one mistake in my presentation, so the whole thing was a disaster.",0,0,1,0,0,1,0,0,0,0
"I should be able to handle this without getting stressed.",0,0,0,0,0,0,0,1,0,0
"It's all my fault that the team project is behind schedule.",0,0,0,0,0,0,0,0,0,1
"I'm just a loser.",0,0,0,0,0,0,0,0,1,0
"This will be a catastrophe.",0,0,0,0,1,1,0,0,0,0
"I never get any recognition for my hard work.",0,1,1,0,0,0,0,0,0,0
"I'm a bad person for feeling this way.",0,0,0,0,0,0,1,0,1,0
"I ought to have known better.",0,0,0,0,0,0,0,1,0,0
"They probably think I'm incompetent.",0,0,0,0,1,0,0,0,0,1
"I made one small mistake, so I'm a complete failure.",1,0,0,0,0,1,0,0,1,0

# src/data_loader.py
import pandas as pd
from datasets import Dataset
from transformers import AutoTokenizer

def load_and_preprocess_data(file_path, model_checkpoint):
    # pandasでデータを読み込む
    df = pd.read_csv(file_path)

    # ラベルをテキストから分離する
    labels = [col for col in df.columns if col != 'text']
    id2label = {idx: label for idx, label in enumerate(labels)}
    label2id = {label: idx for idx, label in enumerate(labels)}
    
    # バイナリ値のリストを持つ新しい'labels'列を作成する
    df['labels'] = df[labels].values.tolist()
    
    # Hugging Face Datasetオブジェクトに変換
    dataset = Dataset.from_pandas(df)
    
    # トークナイザを初期化
    tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)

    # トークン化関数
    def tokenize_data(examples):
        return tokenizer(examples['text'], truncation=True)

    # データセット全体にトークン化を適用
    dataset = dataset.map(tokenize_data, batched=True)
    
    # PyTorch用のデータセットフォーマットを設定
    dataset = dataset.map(lambda x: {'labels': [float(label) for label in x['labels']]})
    dataset.set_format("torch", columns=["input_ids", "attention_mask", "labels"])

    return dataset, id2label, label2id

# 使用例
if __name__ == '__main__':
    MODEL_CHECKPOINT = "distilbert-base-uncased"
    dataset, id2label, label2id = load_and_preprocess_data('cognitive_distortions.csv', MODEL_CHECKPOINT)
    print(dataset[0])
    print(f"id2label: {id2label}")

# src/train.py
import torch
from transformers import AutoModelForSequenceClassification, Trainer, TrainingArguments
from sklearn.metrics import f1_score, roc_auc_score, accuracy_score
from data_loader import load_and_preprocess_data

MODEL_CHECKPOINT = "distilbert-base-uncased"
dataset, id2label, label2id = load_and_preprocess_data('cognitive_distortions.csv', MODEL_CHECKPOINT)

# データセットを分割（実際のシナリオでは別途テストセットをお持ちになります）
train_test_split = dataset.train_test_split(test_size=0.2)
train_dataset = train_test_split['train']
eval_dataset = train_test_split['test']

# モデルを読み込む
model = AutoModelForSequenceClassification.from_pretrained(
    MODEL_CHECKPOINT,
    problem_type="multi_label_classification",
    num_labels=len(id2label),
    id2label=id2label,
    label2id=label2id
)

# 指標を定義
def compute_metrics(p):
    preds = p.predictions[0] if isinstance(p.predictions, tuple) else p.predictions
    # シグモイドを適用して確率を取得し、閾値を設定
    sigmoid = torch.nn.Sigmoid()
    probs = sigmoid(torch.Tensor(preds))
    y_pred = (probs > 0.5).int()
    y_true = p.label_ids

    f1_micro_average = f1_score(y_true=y_true, y_pred=y_pred, average='micro')
    roc_auc = roc_auc_score(y_true, y_pred, average='micro')
    accuracy = accuracy_score(y_true, y_pred)
    
    metrics = {'f1': f1_micro_average, 'roc_auc': roc_auc, 'accuracy': accuracy}
    return metrics

# トレーニング引数を定義
training_args = TrainingArguments(
    output_dir="cognitive-distortion-model",
    learning_rate=2e-5,
    per_device_train_batchサイズ=8,
    per_device_eval_batch_size=8,
    num_train_epochs=10, # 小さなデータセットでは増加
    weight_decay=0.01,
    evaluation_strategy="epoch",
    save_strategy="epoch",
    load_best_model_at_end=True,
)

# Trainerを作成
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=train_dataset,
    eval_dataset=eval_dataset,
    tokenizer=AutoTokenizer.from_pretrained(MODEL_CHECKPOINT),
    compute_metrics=compute_metrics,
)

# トレーニングを開始
trainer.train()

# 最良モデルを保存
trainer.save_model("best_cognitive_distortion_model")

# src/predict.py
from transformers import pipeline

# 微調整済みモデルを読み込む
model_path = "best_cognitive_distortion_model"
classifier = pipeline("text-classification", model=model_path, return_all_scores=True)

# いくつかのサンプルテキストでテスト
text1 = "I can't believe I made such a stupid mistake. I'm a complete failure."
text2 = "I'm sure they are all talking about how bad my presentation was."
text3 = "This is a great achievement, but I was just lucky."

predictions1 = classifier(text1)
predictions2 = classifier(text2)
predictions3 = classifier(text3)

def display_predictions(text, predictions):
    print(f"\
Text: '{text}'")
    print("予測結果:")
    for prediction in predictions[0]:
        if prediction['score'] > 0.5: # 信頼度の高いラベルを表示
            print(f"  - {prediction['label']}: {prediction['score']:.4f}")

display_predictions(text1, predictions1)
display_predictions(text2, predictions2)
display_predictions(text3, predictions3)